diff --git "a/profile_trace/iteration_1024/rank1_trace.json" "b/profile_trace/iteration_1024/rank1_trace.json" new file mode 100644--- /dev/null +++ "b/profile_trace/iteration_1024/rank1_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": 1, "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": "42F59018CEF34C8E98EFAD3F44F530BE", + "traceEvents": [ + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: DivBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196718752.159, "dur": 138.062, + "args": { + "External id": 27137,"Record function id": 0, "Sequence number": 479992, "Fwd thread id": 1, "Ev Idx": 0 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "DivBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196718776.057, "dur": 103.336, + "args": { + "External id": 27138,"Sequence number": 479992, "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": 2338707, "tid": 2379456, "ts": 6197196718776.057, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::div", "pid": 2338707, "tid": 2379456, + "ts": 6197196718785.542, "dur": 91.449, + "args": { + "External id": 27139,"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": 2338707, "tid": 2379456, + "ts": 6197196718905.080, "dur": 310.207, + "args": { + "External id": 27140,"Record function id": 0, "Ev Idx": 3 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward", "pid": 2338707, "tid": 2379456, + "ts": 6197196718973.913, "dur": 155.759, + "args": { + "External id": 27141,"Record function id": 0, "Ev Idx": 4 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.25", "pid": 2338707, "tid": 2379456, + "ts": 6197196719009.074, "dur": 107.859, + "args": { + "External id": 27142,"Record function id": 0, "Ev Idx": 5 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196719135.395, "dur": 2.024, + "args": { + "External id": 27143,"Sequence number": 479991, "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": 2338707, "tid": 2379456, "ts": 6197196719135.395, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338707, "tid": 2379456, + "ts": 6197196719142.941, "dur": 65.397, + "args": { + "External id": 27144,"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": 2338707, "tid": 2379456, + "ts": 6197196719153.261, "dur": 54.459, + "args": { + "External id": 27145,"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": 2338707, "tid": 2379456, + "ts": 6197196719165.481, "dur": 3.598, + "args": { + "External id": 27146,"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": 2338707, "tid": 2379456, + "ts": 6197196719226.892, "dur": 38215.929, + "args": { + "External id": 27147,"Record function id": 0, "Sequence number": 479989, "Fwd thread id": 1, "Ev Idx": 10 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197196719228.634, "dur": 38196.854, + "args": { + "External id": 27148,"Sequence number": 479989, "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": 2338707, "tid": 2379456, "ts": 6197196719228.634, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197196719277.329, "dur": 4.458, + "args": { + "External id": 27149,"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": 2338707, "tid": 2379456, + "ts": 6197196719287.865, "dur": 37825.989, + "args": { + "External id": 27150,"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": 2338707, "tid": 2379456, + "ts": 6197196719290.269, "dur": 37823.135, + "args": { + "External id": 27151,"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": 2338707, "tid": 2379456, + "ts": 6197196719294.999, "dur": 7.409, + "args": { + "External id": 27152,"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": 2338707, "tid": 2379456, + "ts": 6197196719304.743, "dur": 37806.656, + "args": { + "External id": 27153,"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": 2338707, "tid": 2379456, + "ts": 6197196757119.911, "dur": 0.786, + "args": { + "External id": 27154,"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": 2338707, "tid": 2379456, + "ts": 6197196757123.027, "dur": 3.561, + "args": { + "External id": 27155,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 18 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach_", "pid": 2338707, "tid": 2379456, + "ts": 6197196757125.111, "dur": 1.199, + "args": { + "External id": 27156,"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": 2338707, "tid": 2379456, + "ts": 6197196757133.279, "dur": 34.549, + "args": { + "External id": 27157,"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": 2338707, "tid": 2379456, + "ts": 6197196757177.165, "dur": 49.144, + "args": { + "External id": 27158,"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": 2338707, "tid": 2379456, + "ts": 6197196757179.107, "dur": 47.002, + "args": { + "External id": 27159,"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": 2338707, "tid": 2379456, + "ts": 6197196757180.849, "dur": 44.870, + "args": { + "External id": 27160,"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": 2338707, "tid": 2379456, + "ts": 6197196757456.548, "dur": 21.028, + "args": { + "External id": 27161,"Record function id": 0, "Sequence number": 479988, "Fwd thread id": 1, "Ev Idx": 24 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196757458.724, "dur": 15.212, + "args": { + "External id": 27162,"Sequence number": 479988, "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": 2338707, "tid": 2379456, "ts": 6197196757458.724, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196757464.318, "dur": 9.313, + "args": { + "External id": 27163,"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": 2338707, "tid": 2379456, + "ts": 6197196757468.052, "dur": 5.344, + "args": { + "External id": 27164,"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": 2338707, "tid": 2379456, + "ts": 6197196757482.073, "dur": 118.107, + "args": { + "External id": 27165,"Record function id": 0, "Sequence number": 479987, "Fwd thread id": 1, "Ev Idx": 28 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196757483.181, "dur": 107.078, + "args": { + "External id": 27166,"Sequence number": 479987, "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": 2338707, "tid": 2379456, "ts": 6197196757483.181, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338707, "tid": 2379456, + "ts": 6197196757487.569, "dur": 102.106, + "args": { + "External id": 27167,"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": 2338707, "tid": 2379456, + "ts": 6197196757493.139, "dur": 40.304, + "args": { + "External id": 27168,"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": 2338707, "tid": 2379456, + "ts": 6197196757497.565, "dur": 6.764, + "args": { + "External id": 27169,"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": 2338707, "tid": 2379456, + "ts": 6197196757506.370, "dur": 26.795, + "args": { + "External id": 27170,"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": 2338707, "tid": 2379456, + "ts": 6197196757511.912, "dur": 20.787, + "args": { + "External id": 27171,"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": 2338707, "tid": 2379456, + "ts": 6197196757536.139, "dur": 7.401, + "args": { + "External id": 27172,"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": 2338707, "tid": 2379456, + "ts": 6197196757539.125, "dur": 4.030, + "args": { + "External id": 27173,"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": 2338707, "tid": 2379456, + "ts": 6197196757544.796, "dur": 44.019, + "args": { + "External id": 27174,"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": 2338707, "tid": 2379456, + "ts": 6197196757604.976, "dur": 66.227, + "args": { + "External id": 27175,"Record function id": 0, "Sequence number": 479986, "Fwd thread id": 1, "Ev Idx": 38 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SelectBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196757606.100, "dur": 60.767, + "args": { + "External id": 27176,"Sequence number": 479986, "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": 2338707, "tid": 2379456, "ts": 6197196757606.100, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select_backward", "pid": 2338707, "tid": 2379456, + "ts": 6197196757609.679, "dur": 56.953, + "args": { + "External id": 27177,"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": 2338707, "tid": 2379456, + "ts": 6197196757613.550, "dur": 21.813, + "args": { + "External id": 27178,"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": 2338707, "tid": 2379456, + "ts": 6197196757614.595, "dur": 3.028, + "args": { + "External id": 27179,"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": 2338707, "tid": 2379456, + "ts": 6197196757618.637, "dur": 16.425, + "args": { + "External id": 27180,"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": 2338707, "tid": 2379456, + "ts": 6197196757621.657, "dur": 12.990, + "args": { + "External id": 27181,"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": 2338707, "tid": 2379456, + "ts": 6197196757637.270, "dur": 8.155, + "args": { + "External id": 27182,"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": 2338707, "tid": 2379456, + "ts": 6197196757643.750, "dur": 1.019, + "args": { + "External id": 27183,"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": 2338707, "tid": 2379456, + "ts": 6197196757646.323, "dur": 19.703, + "args": { + "External id": 27184,"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": 2338707, "tid": 2379456, + "ts": 6197196757675.301, "dur": 239.048, + "args": { + "External id": 27185,"Record function id": 0, "Sequence number": 479985, "Fwd thread id": 1, "Ev Idx": 48 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196757676.388, "dur": 231.430, + "args": { + "External id": 27186,"Sequence number": 479985, "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": 2338707, "tid": 2379456, "ts": 6197196757676.388, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338707, "tid": 2379456, + "ts": 6197196757679.179, "dur": 227.989, + "args": { + "External id": 27187,"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": 2338707, "tid": 2379456, + "ts": 6197196757682.731, "dur": 33.466, + "args": { + "External id": 27188,"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": 2338707, "tid": 2379456, + "ts": 6197196757683.617, "dur": 2.891, + "args": { + "External id": 27189,"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": 2338707, "tid": 2379456, + "ts": 6197196757687.288, "dur": 28.607, + "args": { + "External id": 27190,"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": 2338707, "tid": 2379456, + "ts": 6197196757688.287, "dur": 26.838, + "args": { + "External id": 27191,"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": 2338707, "tid": 2379456, + "ts": 6197196757718.043, "dur": 3.081, + "args": { + "External id": 27192,"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": 2338707, "tid": 2379456, + "ts": 6197196757719.864, "dur": 1.023, + "args": { + "External id": 27193,"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": 2338707, "tid": 2379456, + "ts": 6197196757724.088, "dur": 181.931, + "args": { + "External id": 27194,"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": 2338707, "tid": 2379456, + "ts": 6197196757922.759, "dur": 83.861, + "args": { + "External id": 27195,"Record function id": 0, "Sequence number": 479984, "Fwd thread id": 1, "Ev Idx": 58 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196757924.157, "dur": 78.044, + "args": { + "External id": 27196,"Sequence number": 479984, "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": 2338707, "tid": 2379456, "ts": 6197196757924.157, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338707, "tid": 2379456, + "ts": 6197196757925.837, "dur": 75.923, + "args": { + "External id": 27197,"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": 2338707, "tid": 2379456, + "ts": 6197196757928.140, "dur": 17.615, + "args": { + "External id": 27198,"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": 2338707, "tid": 2379456, + "ts": 6197196757929.110, "dur": 2.607, + "args": { + "External id": 27199,"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": 2338707, "tid": 2379456, + "ts": 6197196757932.635, "dur": 12.873, + "args": { + "External id": 27200,"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": 2338707, "tid": 2379456, + "ts": 6197196757933.633, "dur": 11.575, + "args": { + "External id": 27201,"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": 2338707, "tid": 2379456, + "ts": 6197196757946.799, "dur": 4.110, + "args": { + "External id": 27202,"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": 2338707, "tid": 2379456, + "ts": 6197196757950.048, "dur": 0.684, + "args": { + "External id": 27203,"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": 2338707, "tid": 2379456, + "ts": 6197196757951.732, "dur": 49.048, + "args": { + "External id": 27204,"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": 2338707, "tid": 2379456, + "ts": 6197196758013.826, "dur": 72.298, + "args": { + "External id": 27205,"Record function id": 0, "Sequence number": 479983, "Fwd thread id": 1, "Ev Idx": 68 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196758015.271, "dur": 1.386, + "args": { + "External id": 27206,"Sequence number": 479983, "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": 2338707, "tid": 2379456, "ts": 6197196758015.271, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338707, "tid": 2379456, + "ts": 6197196758020.227, "dur": 29.073, + "args": { + "External id": 27207,"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": 2338707, "tid": 2379456, + "ts": 6197196758022.504, "dur": 26.260, + "args": { + "External id": 27208,"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": 2338707, "tid": 2379456, + "ts": 6197196758030.741, "dur": 0.507, + "args": { + "External id": 27209,"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": 2338707, "tid": 2379456, + "ts": 6197196758094.957, "dur": 2425.322, + "args": { + "External id": 27210,"Record function id": 0, "Sequence number": 479981, "Fwd thread id": 1, "Ev Idx": 73 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197196758097.050, "dur": 2380.557, + "args": { + "External id": 27211,"Sequence number": 479981, "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": 2338707, "tid": 2379456, "ts": 6197196758097.050, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197196758138.733, "dur": 4.260, + "args": { + "External id": 27212,"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": 2338707, "tid": 2379456, + "ts": 6197196758145.743, "dur": 2096.135, + "args": { + "External id": 27213,"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": 2338707, "tid": 2379456, + "ts": 6197196758147.555, "dur": 2093.991, + "args": { + "External id": 27214,"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": 2338707, "tid": 2379456, + "ts": 6197196758150.444, "dur": 6.611, + "args": { + "External id": 27215,"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": 2338707, "tid": 2379456, + "ts": 6197196758158.196, "dur": 2081.828, + "args": { + "External id": 27216,"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": 2338707, "tid": 2379456, + "ts": 6197196760246.353, "dur": 0.528, + "args": { + "External id": 27217,"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": 2338707, "tid": 2379456, + "ts": 6197196760248.337, "dur": 5.100, + "args": { + "External id": 27218,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 81 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach_", "pid": 2338707, "tid": 2379456, + "ts": 6197196760252.214, "dur": 1.103, + "args": { + "External id": 27219,"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": 2338707, "tid": 2379456, + "ts": 6197196760258.390, "dur": 23.319, + "args": { + "External id": 27220,"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": 2338707, "tid": 2379456, + "ts": 6197196760288.280, "dur": 44.065, + "args": { + "External id": 27221,"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": 2338707, "tid": 2379456, + "ts": 6197196760289.583, "dur": 42.569, + "args": { + "External id": 27222,"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": 2338707, "tid": 2379456, + "ts": 6197196760291.066, "dur": 40.746, + "args": { + "External id": 27223,"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": 2338707, "tid": 2379456, + "ts": 6197196760492.038, "dur": 20.662, + "args": { + "External id": 27224,"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": 2338707, "tid": 2379456, + "ts": 6197196760530.932, "dur": 15.013, + "args": { + "External id": 27225,"Record function id": 0, "Sequence number": 479980, "Fwd thread id": 1, "Ev Idx": 88 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196760532.623, "dur": 9.877, + "args": { + "External id": 27226,"Sequence number": 479980, "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": 2338707, "tid": 2379456, "ts": 6197196760532.623, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196760536.133, "dur": 6.111, + "args": { + "External id": 27227,"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": 2338707, "tid": 2379456, + "ts": 6197196760537.778, "dur": 4.292, + "args": { + "External id": 27228,"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": 2338707, "tid": 2379456, + "ts": 6197196760549.709, "dur": 84.034, + "args": { + "External id": 27229,"Record function id": 0, "Sequence number": 479979, "Fwd thread id": 1, "Ev Idx": 92 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196760550.790, "dur": 77.357, + "args": { + "External id": 27230,"Sequence number": 479979, "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": 2338707, "tid": 2379456, "ts": 6197196760550.790, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338707, "tid": 2379456, + "ts": 6197196760553.691, "dur": 73.987, + "args": { + "External id": 27231,"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": 2338707, "tid": 2379456, + "ts": 6197196760559.386, "dur": 22.343, + "args": { + "External id": 27232,"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": 2338707, "tid": 2379456, + "ts": 6197196760561.827, "dur": 3.672, + "args": { + "External id": 27233,"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": 2338707, "tid": 2379456, + "ts": 6197196760566.440, "dur": 14.993, + "args": { + "External id": 27234,"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": 2338707, "tid": 2379456, + "ts": 6197196760568.431, "dur": 12.590, + "args": { + "External id": 27235,"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": 2338707, "tid": 2379456, + "ts": 6197196760583.612, "dur": 5.535, + "args": { + "External id": 27236,"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": 2338707, "tid": 2379456, + "ts": 6197196760587.217, "dur": 1.563, + "args": { + "External id": 27237,"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": 2338707, "tid": 2379456, + "ts": 6197196760590.245, "dur": 36.375, + "args": { + "External id": 27238,"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": 2338707, "tid": 2379456, + "ts": 6197196760638.066, "dur": 60.001, + "args": { + "External id": 27239,"Record function id": 0, "Sequence number": 479978, "Fwd thread id": 1, "Ev Idx": 102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SelectBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196760639.389, "dur": 54.872, + "args": { + "External id": 27240,"Sequence number": 479978, "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": 2338707, "tid": 2379456, "ts": 6197196760639.389, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select_backward", "pid": 2338707, "tid": 2379456, + "ts": 6197196760642.712, "dur": 51.168, + "args": { + "External id": 27241,"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": 2338707, "tid": 2379456, + "ts": 6197196760644.740, "dur": 22.876, + "args": { + "External id": 27242,"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": 2338707, "tid": 2379456, + "ts": 6197196760646.054, "dur": 2.241, + "args": { + "External id": 27243,"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": 2338707, "tid": 2379456, + "ts": 6197196760651.554, "dur": 15.820, + "args": { + "External id": 27244,"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": 2338707, "tid": 2379456, + "ts": 6197196760652.559, "dur": 14.385, + "args": { + "External id": 27245,"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": 2338707, "tid": 2379456, + "ts": 6197196760669.102, "dur": 6.245, + "args": { + "External id": 27246,"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": 2338707, "tid": 2379456, + "ts": 6197196760673.637, "dur": 1.161, + "args": { + "External id": 27247,"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": 2338707, "tid": 2379456, + "ts": 6197196760676.165, "dur": 16.999, + "args": { + "External id": 27248,"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": 2338707, "tid": 2379456, + "ts": 6197196760717.838, "dur": 142.776, + "args": { + "External id": 27249,"Record function id": 0, "Sequence number": 479977, "Fwd thread id": 1, "Ev Idx": 112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196760719.637, "dur": 136.491, + "args": { + "External id": 27250,"Sequence number": 479977, "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": 2338707, "tid": 2379456, "ts": 6197196760719.637, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338707, "tid": 2379456, + "ts": 6197196760721.871, "dur": 133.802, + "args": { + "External id": 27251,"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": 2338707, "tid": 2379456, + "ts": 6197196760723.668, "dur": 23.264, + "args": { + "External id": 27252,"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": 2338707, "tid": 2379456, + "ts": 6197196760724.717, "dur": 3.135, + "args": { + "External id": 27253,"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": 2338707, "tid": 2379456, + "ts": 6197196760730.668, "dur": 15.966, + "args": { + "External id": 27254,"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": 2338707, "tid": 2379456, + "ts": 6197196760731.672, "dur": 14.541, + "args": { + "External id": 27255,"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": 2338707, "tid": 2379456, + "ts": 6197196760748.467, "dur": 5.260, + "args": { + "External id": 27256,"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": 2338707, "tid": 2379456, + "ts": 6197196760752.714, "dur": 0.712, + "args": { + "External id": 27257,"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": 2338707, "tid": 2379456, + "ts": 6197196760754.764, "dur": 99.928, + "args": { + "External id": 27258,"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": 2338707, "tid": 2379456, + "ts": 6197196760865.399, "dur": 105.022, + "args": { + "External id": 27259,"Record function id": 0, "Sequence number": 479976, "Fwd thread id": 1, "Ev Idx": 122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196760866.417, "dur": 83.358, + "args": { + "External id": 27260,"Sequence number": 479976, "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": 2338707, "tid": 2379456, "ts": 6197196760866.417, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338707, "tid": 2379456, + "ts": 6197196760868.931, "dur": 80.430, + "args": { + "External id": 27261,"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": 2338707, "tid": 2379456, + "ts": 6197196760870.478, "dur": 19.886, + "args": { + "External id": 27262,"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": 2338707, "tid": 2379456, + "ts": 6197196760871.573, "dur": 2.684, + "args": { + "External id": 27263,"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": 2338707, "tid": 2379456, + "ts": 6197196760875.189, "dur": 14.879, + "args": { + "External id": 27264,"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": 2338707, "tid": 2379456, + "ts": 6197196760878.183, "dur": 11.512, + "args": { + "External id": 27265,"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": 2338707, "tid": 2379456, + "ts": 6197196760891.331, "dur": 2.712, + "args": { + "External id": 27266,"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": 2338707, "tid": 2379456, + "ts": 6197196760893.257, "dur": 0.534, + "args": { + "External id": 27267,"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": 2338707, "tid": 2379456, + "ts": 6197196760894.813, "dur": 53.914, + "args": { + "External id": 27268,"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": 2338707, "tid": 2379456, + "ts": 6197196760954.332, "dur": 14.654, + "args": { + "External id": 27269,"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": 2338707, "tid": 2379456, + "ts": 6197196760975.690, "dur": 39.047, + "args": { + "External id": 27270,"Record function id": 0, "Sequence number": 479975, "Fwd thread id": 1, "Ev Idx": 133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196760977.076, "dur": 1.124, + "args": { + "External id": 27271,"Sequence number": 479975, "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": 2338707, "tid": 2379456, "ts": 6197196760977.076, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338707, "tid": 2379456, + "ts": 6197196760981.177, "dur": 30.093, + "args": { + "External id": 27272,"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": 2338707, "tid": 2379456, + "ts": 6197196760983.403, "dur": 27.424, + "args": { + "External id": 27273,"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": 2338707, "tid": 2379456, + "ts": 6197196760991.731, "dur": 0.741, + "args": { + "External id": 27274,"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": 2338707, "tid": 2379456, + "ts": 6197196761019.719, "dur": 3463.542, + "args": { + "External id": 27275,"Record function id": 0, "Sequence number": 479973, "Fwd thread id": 1, "Ev Idx": 138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197196761023.214, "dur": 3425.654, + "args": { + "External id": 27276,"Sequence number": 479973, "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": 2338707, "tid": 2379456, "ts": 6197196761023.214, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197196761100.808, "dur": 3.487, + "args": { + "External id": 27277,"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": 2338707, "tid": 2379456, + "ts": 6197196761107.390, "dur": 3121.904, + "args": { + "External id": 27278,"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": 2338707, "tid": 2379456, + "ts": 6197196761109.111, "dur": 3119.834, + "args": { + "External id": 27279,"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": 2338707, "tid": 2379456, + "ts": 6197196761112.294, "dur": 4.702, + "args": { + "External id": 27280,"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": 2338707, "tid": 2379456, + "ts": 6197196761120.832, "dur": 3107.123, + "args": { + "External id": 27281,"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": 2338707, "tid": 2379456, + "ts": 6197196764233.070, "dur": 0.454, + "args": { + "External id": 27282,"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": 2338707, "tid": 2379456, + "ts": 6197196764234.791, "dur": 2.459, + "args": { + "External id": 27283,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach_", "pid": 2338707, "tid": 2379456, + "ts": 6197196764236.133, "dur": 0.971, + "args": { + "External id": 27284,"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": 2338707, "tid": 2379456, + "ts": 6197196764241.817, "dur": 24.117, + "args": { + "External id": 27285,"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": 2338707, "tid": 2379456, + "ts": 6197196764271.445, "dur": 44.256, + "args": { + "External id": 27286,"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": 2338707, "tid": 2379456, + "ts": 6197196764272.613, "dur": 42.885, + "args": { + "External id": 27287,"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": 2338707, "tid": 2379456, + "ts": 6197196764274.551, "dur": 40.598, + "args": { + "External id": 27288,"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": 2338707, "tid": 2379456, + "ts": 6197196764461.472, "dur": 16.593, + "args": { + "External id": 27289,"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": 2338707, "tid": 2379456, + "ts": 6197196764497.450, "dur": 15.980, + "args": { + "External id": 27290,"Record function id": 0, "Sequence number": 479972, "Fwd thread id": 1, "Ev Idx": 153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196764501.418, "dur": 9.078, + "args": { + "External id": 27291,"Sequence number": 479972, "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": 2338707, "tid": 2379456, "ts": 6197196764501.418, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196764504.603, "dur": 5.634, + "args": { + "External id": 27292,"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": 2338707, "tid": 2379456, + "ts": 6197196764506.199, "dur": 3.858, + "args": { + "External id": 27293,"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": 2338707, "tid": 2379456, + "ts": 6197196764517.047, "dur": 77.855, + "args": { + "External id": 27294,"Record function id": 0, "Sequence number": 479971, "Fwd thread id": 1, "Ev Idx": 157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196764518.282, "dur": 70.104, + "args": { + "External id": 27295,"Sequence number": 479971, "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": 2338707, "tid": 2379456, "ts": 6197196764518.282, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338707, "tid": 2379456, + "ts": 6197196764520.966, "dur": 67.049, + "args": { + "External id": 27296,"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": 2338707, "tid": 2379456, + "ts": 6197196764523.982, "dur": 22.661, + "args": { + "External id": 27297,"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": 2338707, "tid": 2379456, + "ts": 6197196764526.220, "dur": 3.439, + "args": { + "External id": 27298,"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": 2338707, "tid": 2379456, + "ts": 6197196764530.518, "dur": 15.771, + "args": { + "External id": 27299,"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": 2338707, "tid": 2379456, + "ts": 6197196764532.333, "dur": 13.389, + "args": { + "External id": 27300,"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": 2338707, "tid": 2379456, + "ts": 6197196764548.474, "dur": 4.883, + "args": { + "External id": 27301,"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": 2338707, "tid": 2379456, + "ts": 6197196764551.791, "dur": 1.246, + "args": { + "External id": 27302,"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": 2338707, "tid": 2379456, + "ts": 6197196764556.758, "dur": 30.302, + "args": { + "External id": 27303,"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": 2338707, "tid": 2379456, + "ts": 6197196764599.030, "dur": 52.343, + "args": { + "External id": 27304,"Record function id": 0, "Sequence number": 479970, "Fwd thread id": 1, "Ev Idx": 167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SelectBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196764600.109, "dur": 47.991, + "args": { + "External id": 27305,"Sequence number": 479970, "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": 2338707, "tid": 2379456, "ts": 6197196764600.109, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select_backward", "pid": 2338707, "tid": 2379456, + "ts": 6197196764602.422, "dur": 45.367, + "args": { + "External id": 27306,"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": 2338707, "tid": 2379456, + "ts": 6197196764604.334, "dur": 17.529, + "args": { + "External id": 27307,"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": 2338707, "tid": 2379456, + "ts": 6197196764605.164, "dur": 2.697, + "args": { + "External id": 27308,"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": 2338707, "tid": 2379456, + "ts": 6197196764608.522, "dur": 13.089, + "args": { + "External id": 27309,"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": 2338707, "tid": 2379456, + "ts": 6197196764609.590, "dur": 11.715, + "args": { + "External id": 27310,"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": 2338707, "tid": 2379456, + "ts": 6197196764622.965, "dur": 7.584, + "args": { + "External id": 27311,"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": 2338707, "tid": 2379456, + "ts": 6197196764629.052, "dur": 0.935, + "args": { + "External id": 27312,"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": 2338707, "tid": 2379456, + "ts": 6197196764631.451, "dur": 15.791, + "args": { + "External id": 27313,"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": 2338707, "tid": 2379456, + "ts": 6197196764655.224, "dur": 135.493, + "args": { + "External id": 27314,"Record function id": 0, "Sequence number": 479969, "Fwd thread id": 1, "Ev Idx": 177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196764656.293, "dur": 128.329, + "args": { + "External id": 27315,"Sequence number": 479969, "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": 2338707, "tid": 2379456, "ts": 6197196764656.293, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338707, "tid": 2379456, + "ts": 6197196764658.509, "dur": 125.583, + "args": { + "External id": 27316,"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": 2338707, "tid": 2379456, + "ts": 6197196764659.827, "dur": 18.217, + "args": { + "External id": 27317,"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": 2338707, "tid": 2379456, + "ts": 6197196764661.048, "dur": 4.022, + "args": { + "External id": 27318,"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": 2338707, "tid": 2379456, + "ts": 6197196764665.677, "dur": 12.115, + "args": { + "External id": 27319,"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": 2338707, "tid": 2379456, + "ts": 6197196764666.467, "dur": 10.969, + "args": { + "External id": 27320,"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": 2338707, "tid": 2379456, + "ts": 6197196764678.941, "dur": 2.867, + "args": { + "External id": 27321,"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": 2338707, "tid": 2379456, + "ts": 6197196764681.135, "dur": 0.465, + "args": { + "External id": 27322,"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": 2338707, "tid": 2379456, + "ts": 6197196764684.919, "dur": 97.727, + "args": { + "External id": 27323,"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": 2338707, "tid": 2379456, + "ts": 6197196764797.677, "dur": 110.336, + "args": { + "External id": 27324,"Record function id": 0, "Sequence number": 479968, "Fwd thread id": 1, "Ev Idx": 187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196764798.885, "dur": 88.648, + "args": { + "External id": 27325,"Sequence number": 479968, "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": 2338707, "tid": 2379456, "ts": 6197196764798.885, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338707, "tid": 2379456, + "ts": 6197196764804.043, "dur": 83.032, + "args": { + "External id": 27326,"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": 2338707, "tid": 2379456, + "ts": 6197196764805.692, "dur": 22.461, + "args": { + "External id": 27327,"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": 2338707, "tid": 2379456, + "ts": 6197196764807.549, "dur": 2.866, + "args": { + "External id": 27328,"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": 2338707, "tid": 2379456, + "ts": 6197196764811.297, "dur": 16.503, + "args": { + "External id": 27329,"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": 2338707, "tid": 2379456, + "ts": 6197196764812.267, "dur": 15.137, + "args": { + "External id": 27330,"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": 2338707, "tid": 2379456, + "ts": 6197196764829.220, "dur": 3.240, + "args": { + "External id": 27331,"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": 2338707, "tid": 2379456, + "ts": 6197196764831.276, "dur": 0.965, + "args": { + "External id": 27332,"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": 2338707, "tid": 2379456, + "ts": 6197196764835.784, "dur": 50.442, + "args": { + "External id": 27333,"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": 2338707, "tid": 2379456, + "ts": 6197196764891.660, "dur": 14.952, + "args": { + "External id": 27334,"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": 2338707, "tid": 2379456, + "ts": 6197196764912.771, "dur": 38.593, + "args": { + "External id": 27335,"Record function id": 0, "Sequence number": 479967, "Fwd thread id": 1, "Ev Idx": 198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196764914.103, "dur": 0.974, + "args": { + "External id": 27336,"Sequence number": 479967, "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": 2338707, "tid": 2379456, "ts": 6197196764914.103, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338707, "tid": 2379456, + "ts": 6197196764917.317, "dur": 28.041, + "args": { + "External id": 27337,"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": 2338707, "tid": 2379456, + "ts": 6197196764919.450, "dur": 25.461, + "args": { + "External id": 27338,"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": 2338707, "tid": 2379456, + "ts": 6197196764925.277, "dur": 0.603, + "args": { + "External id": 27339,"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": 2338707, "tid": 2379456, + "ts": 6197196764956.122, "dur": 3494.268, + "args": { + "External id": 27340,"Record function id": 0, "Sequence number": 479966, "Fwd thread id": 1, "Ev Idx": 203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197196764968.349, "dur": 3447.912, + "args": { + "External id": 27341,"Sequence number": 479966, "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": 2338707, "tid": 2379456, "ts": 6197196764968.349, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197196764996.851, "dur": 2.733, + "args": { + "External id": 27342,"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": 2338707, "tid": 2379456, + "ts": 6197196765001.937, "dur": 3203.651, + "args": { + "External id": 27343,"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": 2338707, "tid": 2379456, + "ts": 6197196765003.750, "dur": 3201.581, + "args": { + "External id": 27344,"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": 2338707, "tid": 2379456, + "ts": 6197196765006.737, "dur": 3.469, + "args": { + "External id": 27345,"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": 2338707, "tid": 2379456, + "ts": 6197196765011.001, "dur": 3193.159, + "args": { + "External id": 27346,"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": 2338707, "tid": 2379456, + "ts": 6197196768209.580, "dur": 0.366, + "args": { + "External id": 27347,"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": 2338707, "tid": 2379456, + "ts": 6197196768213.400, "dur": 2.677, + "args": { + "External id": 27348,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach_", "pid": 2338707, "tid": 2379456, + "ts": 6197196768214.904, "dur": 1.049, + "args": { + "External id": 27349,"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": 2338707, "tid": 2379456, + "ts": 6197196768220.994, "dur": 21.987, + "args": { + "External id": 27350,"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": 2338707, "tid": 2379456, + "ts": 6197196768251.336, "dur": 42.401, + "args": { + "External id": 27351,"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": 2338707, "tid": 2379456, + "ts": 6197196768252.764, "dur": 40.763, + "args": { + "External id": 27352,"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": 2338707, "tid": 2379456, + "ts": 6197196768254.189, "dur": 38.848, + "args": { + "External id": 27353,"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": 2338707, "tid": 2379456, + "ts": 6197196768428.770, "dur": 15.211, + "args": { + "External id": 27354,"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": 2338707, "tid": 2379456, + "ts": 6197196768467.083, "dur": 13.967, + "args": { + "External id": 27355,"Record function id": 0, "Ev Idx": 218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197196768470.073, "dur": 9.125, + "args": { + "External id": 27356,"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": 2338707, "tid": 2379456, + "ts": 6197196768473.264, "dur": 4.694, + "args": { + "External id": 27357,"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": 2338707, "tid": 2379456, + "ts": 6197196768474.596, "dur": 3.287, + "args": { + "External id": 27358,"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": 2338707, "tid": 2379456, + "ts": 6197196768484.659, "dur": 14.184, + "args": { + "External id": 27359,"Record function id": 0, "Sequence number": 479965, "Fwd thread id": 1, "Ev Idx": 222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196768487.821, "dur": 8.872, + "args": { + "External id": 27360,"Sequence number": 479965, "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": 2338707, "tid": 2379456, "ts": 6197196768487.821, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196768491.041, "dur": 5.390, + "args": { + "External id": 27361,"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": 2338707, "tid": 2379456, + "ts": 6197196768492.820, "dur": 3.381, + "args": { + "External id": 27362,"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": 2338707, "tid": 2379456, + "ts": 6197196768502.318, "dur": 71.393, + "args": { + "External id": 27363,"Record function id": 0, "Sequence number": 479964, "Fwd thread id": 1, "Ev Idx": 226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196768503.423, "dur": 64.479, + "args": { + "External id": 27364,"Sequence number": 479964, "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": 2338707, "tid": 2379456, "ts": 6197196768503.423, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338707, "tid": 2379456, + "ts": 6197196768506.110, "dur": 61.446, + "args": { + "External id": 27365,"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": 2338707, "tid": 2379456, + "ts": 6197196768509.504, "dur": 21.145, + "args": { + "External id": 27366,"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": 2338707, "tid": 2379456, + "ts": 6197196768511.473, "dur": 3.450, + "args": { + "External id": 27367,"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": 2338707, "tid": 2379456, + "ts": 6197196768515.940, "dur": 14.405, + "args": { + "External id": 27368,"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": 2338707, "tid": 2379456, + "ts": 6197196768517.353, "dur": 12.550, + "args": { + "External id": 27369,"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": 2338707, "tid": 2379456, + "ts": 6197196768531.900, "dur": 4.678, + "args": { + "External id": 27370,"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": 2338707, "tid": 2379456, + "ts": 6197196768535.247, "dur": 1.087, + "args": { + "External id": 27371,"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": 2338707, "tid": 2379456, + "ts": 6197196768540.522, "dur": 26.122, + "args": { + "External id": 27372,"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": 2338707, "tid": 2379456, + "ts": 6197196768580.049, "dur": 54.698, + "args": { + "External id": 27373,"Record function id": 0, "Sequence number": 479963, "Fwd thread id": 1, "Ev Idx": 236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SelectBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196768581.031, "dur": 49.068, + "args": { + "External id": 27374,"Sequence number": 479963, "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": 2338707, "tid": 2379456, "ts": 6197196768581.031, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select_backward", "pid": 2338707, "tid": 2379456, + "ts": 6197196768584.359, "dur": 45.521, + "args": { + "External id": 27375,"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": 2338707, "tid": 2379456, + "ts": 6197196768586.591, "dur": 18.120, + "args": { + "External id": 27376,"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": 2338707, "tid": 2379456, + "ts": 6197196768588.067, "dur": 2.920, + "args": { + "External id": 27377,"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": 2338707, "tid": 2379456, + "ts": 6197196768591.748, "dur": 12.708, + "args": { + "External id": 27378,"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": 2338707, "tid": 2379456, + "ts": 6197196768592.552, "dur": 11.559, + "args": { + "External id": 27379,"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": 2338707, "tid": 2379456, + "ts": 6197196768605.840, "dur": 8.769, + "args": { + "External id": 27380,"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": 2338707, "tid": 2379456, + "ts": 6197196768612.896, "dur": 1.095, + "args": { + "External id": 27381,"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": 2338707, "tid": 2379456, + "ts": 6197196768615.361, "dur": 14.027, + "args": { + "External id": 27382,"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": 2338707, "tid": 2379456, + "ts": 6197196768638.705, "dur": 139.370, + "args": { + "External id": 27383,"Record function id": 0, "Sequence number": 479962, "Fwd thread id": 1, "Ev Idx": 246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196768639.926, "dur": 132.117, + "args": { + "External id": 27384,"Sequence number": 479962, "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": 2338707, "tid": 2379456, "ts": 6197196768639.926, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338707, "tid": 2379456, + "ts": 6197196768642.211, "dur": 129.396, + "args": { + "External id": 27385,"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": 2338707, "tid": 2379456, + "ts": 6197196768646.092, "dur": 15.533, + "args": { + "External id": 27386,"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": 2338707, "tid": 2379456, + "ts": 6197196768646.798, "dur": 2.374, + "args": { + "External id": 27387,"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": 2338707, "tid": 2379456, + "ts": 6197196768649.893, "dur": 11.431, + "args": { + "External id": 27388,"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": 2338707, "tid": 2379456, + "ts": 6197196768650.771, "dur": 10.179, + "args": { + "External id": 27389,"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": 2338707, "tid": 2379456, + "ts": 6197196768662.852, "dur": 5.251, + "args": { + "External id": 27390,"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": 2338707, "tid": 2379456, + "ts": 6197196768664.795, "dur": 3.116, + "args": { + "External id": 27391,"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": 2338707, "tid": 2379456, + "ts": 6197196768670.812, "dur": 99.594, + "args": { + "External id": 27392,"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": 2338707, "tid": 2379456, + "ts": 6197196768784.969, "dur": 111.937, + "args": { + "External id": 27393,"Record function id": 0, "Sequence number": 479961, "Fwd thread id": 1, "Ev Idx": 256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196768786.205, "dur": 90.438, + "args": { + "External id": 27394,"Sequence number": 479961, "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": 2338707, "tid": 2379456, "ts": 6197196768786.205, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338707, "tid": 2379456, + "ts": 6197196768788.420, "dur": 87.854, + "args": { + "External id": 27395,"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": 2338707, "tid": 2379456, + "ts": 6197196768790.263, "dur": 24.036, + "args": { + "External id": 27396,"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": 2338707, "tid": 2379456, + "ts": 6197196768791.852, "dur": 2.815, + "args": { + "External id": 27397,"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": 2338707, "tid": 2379456, + "ts": 6197196768799.311, "dur": 14.622, + "args": { + "External id": 27398,"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": 2338707, "tid": 2379456, + "ts": 6197196768801.978, "dur": 11.642, + "args": { + "External id": 27399,"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": 2338707, "tid": 2379456, + "ts": 6197196768817.785, "dur": 5.118, + "args": { + "External id": 27400,"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": 2338707, "tid": 2379456, + "ts": 6197196768821.839, "dur": 0.833, + "args": { + "External id": 27401,"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": 2338707, "tid": 2379456, + "ts": 6197196768823.652, "dur": 51.815, + "args": { + "External id": 27402,"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": 2338707, "tid": 2379456, + "ts": 6197196768881.526, "dur": 13.451, + "args": { + "External id": 27403,"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": 2338707, "tid": 2379456, + "ts": 6197196768903.780, "dur": 396.395, + "args": { + "External id": 27404,"Record function id": 0, "Sequence number": 479960, "Fwd thread id": 1, "Ev Idx": 267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197196768905.618, "dur": 384.170, + "args": { + "External id": 27405,"Sequence number": 479960, "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": 2338707, "tid": 2379456, "ts": 6197196768905.618, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338707, "tid": 2379456, + "ts": 6197196769115.514, "dur": 46.040, + "args": { + "External id": 27406,"kernel_hash": "cze4nwoznzp5ccj3536wygl2i2ykkdyt3hdmkvx2y6tl7tevwkdm", "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/ze/cze4nwoznzp5ccj3536wygl2i2ykkdyt3hdmkvx2y6tl7tevwkdm.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": 2338707, "tid": 2379456, + "ts": 6197196769198.372, "dur": 27.931, + "args": { + "External id": 27407,"kernel_hash": "ccswrdngzi6jo4g2p2v6rs3fdbvr7wkgz5izdhrj3lqu7uzzy4ad", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/cs/ccswrdngzi6jo4g2p2v6rs3fdbvr7wkgz5izdhrj3lqu7uzzy4ad.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": 2338707, "tid": 2379456, + "ts": 6197196769245.253, "dur": 21.194, + "args": { + "External id": 27408,"kernel_hash": "cddm6binnqpaq4idvznth7jqun5cvp5pc6dr7dh3ezznaxoowmjo", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/dd/cddm6binnqpaq4idvznth7jqun5cvp5pc6dr7dh3ezznaxoowmjo.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": 2338707, "tid": 2379456, + "ts": 6197196769311.368, "dur": 16.807, + "args": { + "External id": 27409,"Record function id": 0, "Ev Idx": 272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197196769314.578, "dur": 12.641, + "args": { + "External id": 27410,"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": 2338707, "tid": 2379456, + "ts": 6197196769317.678, "dur": 8.567, + "args": { + "External id": 27411,"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": 2338707, "tid": 2379456, + "ts": 6197196769320.708, "dur": 5.406, + "args": { + "External id": 27412,"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": 2338707, "tid": 2379456, + "ts": 6197196769334.749, "dur": 38.339, + "args": { + "External id": 27413,"Record function id": 0, "Sequence number": 479959, "Fwd thread id": 1, "Ev Idx": 276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "StackBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196769335.648, "dur": 26.957, + "args": { + "External id": 27414,"Sequence number": 479959, "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": 2338707, "tid": 2379456, "ts": 6197196769335.648, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 2338707, "tid": 2379456, + "ts": 6197196769337.708, "dur": 10.374, + "args": { + "External id": 27415,"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": 2338707, "tid": 2379456, + "ts": 6197196769344.712, "dur": 1.482, + "args": { + "External id": 27416,"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": 2338707, "tid": 2379456, + "ts": 6197196769348.840, "dur": 3.219, + "args": { + "External id": 27417,"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": 2338707, "tid": 2379456, + "ts": 6197196769351.088, "dur": 0.436, + "args": { + "External id": 27418,"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": 2338707, "tid": 2379456, + "ts": 6197196769352.435, "dur": 5.657, + "args": { + "External id": 27419,"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": 2338707, "tid": 2379456, + "ts": 6197196769356.956, "dur": 0.460, + "args": { + "External id": 27420,"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": 2338707, "tid": 2379456, + "ts": 6197196769358.589, "dur": 3.332, + "args": { + "External id": 27421,"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": 2338707, "tid": 2379456, + "ts": 6197196769360.901, "dur": 0.410, + "args": { + "External id": 27422,"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": 2338707, "tid": 2379456, + "ts": 6197196769376.980, "dur": 7.168, + "args": { + "External id": 27423,"Record function id": 0, "Sequence number": 479958, "Fwd thread id": 1, "Ev Idx": 286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196769378.082, "dur": 1.434, + "args": { + "External id": 27424,"Sequence number": 479958, "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": 2338707, "tid": 2379456, "ts": 6197196769378.082, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SwiGLULinearFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197196769388.962, "dur": 549.804, + "args": { + "External id": 27425,"Record function id": 0, "Sequence number": 479957, "Fwd thread id": 1, "Ev Idx": 288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197196769390.763, "dur": 527.607, + "args": { + "External id": 27426,"Sequence number": 479957, "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": 2338707, "tid": 2379456, "ts": 6197196769390.763, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196769429.208, "dur": 11.028, + "args": { + "External id": 27427,"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": 2338707, "tid": 2379456, + "ts": 6197196769436.183, "dur": 3.684, + "args": { + "External id": 27428,"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": 2338707, "tid": 2379456, + "ts": 6197196769446.059, "dur": 7.710, + "args": { + "External id": 27429,"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": 2338707, "tid": 2379456, + "ts": 6197196769449.300, "dur": 3.221, + "args": { + "External id": 27430,"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": 2338707, "tid": 2379456, + "ts": 6197196769451.501, "dur": 0.774, + "args": { + "External id": 27431,"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": 2338707, "tid": 2379456, + "ts": 6197196769458.297, "dur": 128.694, + "args": { + "External id": 27432,"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": 2338707, "tid": 2379456, + "ts": 6197196769461.972, "dur": 3.206, + "args": { + "External id": 27433,"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": 2338707, "tid": 2379456, + "ts": 6197196769462.705, "dur": 1.803, + "args": { + "External id": 27434,"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": 2338707, "tid": 2379456, + "ts": 6197196769463.952, "dur": 0.457, + "args": { + "External id": 27435,"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": 2338707, "tid": 2379456, + "ts": 6197196769467.373, "dur": 118.883, + "args": { + "External id": 27436,"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": 2338707, "tid": 2379456, + "ts": 6197196769469.559, "dur": 115.539, + "args": { + "External id": 27437,"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": 2338707, "tid": 2379456, + "ts": 6197196769593.022, "dur": 4.342, + "args": { + "External id": 27438,"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": 2338707, "tid": 2379456, + "ts": 6197196769594.852, "dur": 2.362, + "args": { + "External id": 27439,"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": 2338707, "tid": 2379456, + "ts": 6197196769639.752, "dur": 6.026, + "args": { + "External id": 27440,"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": 2338707, "tid": 2379456, + "ts": 6197196769647.384, "dur": 3.233, + "args": { + "External id": 27441,"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": 2338707, "tid": 2379456, + "ts": 6197196769651.881, "dur": 2.029, + "args": { + "External id": 27442,"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": 2338707, "tid": 2379456, + "ts": 6197196769689.270, "dur": 2.520, + "args": { + "External id": 27443,"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": 2338707, "tid": 2379456, + "ts": 6197196769690.108, "dur": 1.530, + "args": { + "External id": 27444,"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": 2338707, "tid": 2379456, + "ts": 6197196769742.398, "dur": 152.587, + "args": { + "External id": 27445,"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": 2338707, "tid": 2379456, + "ts": 6197196769748.934, "dur": 8.838, + "args": { + "External id": 27446,"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": 2338707, "tid": 2379456, + "ts": 6197196769754.071, "dur": 1.068, + "args": { + "External id": 27447,"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": 2338707, "tid": 2379456, + "ts": 6197196769760.311, "dur": 6.518, + "args": { + "External id": 27448,"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": 2338707, "tid": 2379456, + "ts": 6197196769765.512, "dur": 0.589, + "args": { + "External id": 27449,"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": 2338707, "tid": 2379456, + "ts": 6197196769768.550, "dur": 5.104, + "args": { + "External id": 27450,"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": 2338707, "tid": 2379456, + "ts": 6197196769770.837, "dur": 2.421, + "args": { + "External id": 27451,"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": 2338707, "tid": 2379456, + "ts": 6197196769774.732, "dur": 2.878, + "args": { + "External id": 27452,"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": 2338707, "tid": 2379456, + "ts": 6197196769776.878, "dur": 0.387, + "args": { + "External id": 27453,"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": 2338707, "tid": 2379456, + "ts": 6197196769782.331, "dur": 3.445, + "args": { + "External id": 27454,"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": 2338707, "tid": 2379456, + "ts": 6197196769784.817, "dur": 0.633, + "args": { + "External id": 27455,"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": 2338707, "tid": 2379456, + "ts": 6197196769787.148, "dur": 7.621, + "args": { + "External id": 27456,"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": 2338707, "tid": 2379456, + "ts": 6197196769792.424, "dur": 2.173, + "args": { + "External id": 27457,"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": 2338707, "tid": 2379456, + "ts": 6197196769797.906, "dur": 3.108, + "args": { + "External id": 27458,"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": 2338707, "tid": 2379456, + "ts": 6197196769800.271, "dur": 0.447, + "args": { + "External id": 27459,"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": 2338707, "tid": 2379456, + "ts": 6197196769802.271, "dur": 2.946, + "args": { + "External id": 27460,"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": 2338707, "tid": 2379456, + "ts": 6197196769803.777, "dur": 1.315, + "args": { + "External id": 27461,"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": 2338707, "tid": 2379456, + "ts": 6197196769807.225, "dur": 73.727, + "args": { + "External id": 27462,"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": 2338707, "tid": 2379456, + "ts": 6197196769882.831, "dur": 1.214, + "args": { + "External id": 27463,"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": 2338707, "tid": 2379456, + "ts": 6197196769885.225, "dur": 5.375, + "args": { + "External id": 27464,"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": 2338707, "tid": 2379456, + "ts": 6197196769887.511, "dur": 2.686, + "args": { + "External id": 27465,"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": 2338707, "tid": 2379456, + "ts": 6197196769892.948, "dur": 0.757, + "args": { + "External id": 27466,"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": 2338707, "tid": 2379456, + "ts": 6197196769952.898, "dur": 11.120, + "args": { + "External id": 27467,"Record function id": 0, "Ev Idx": 330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197196769955.391, "dur": 7.786, + "args": { + "External id": 27468,"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": 2338707, "tid": 2379456, + "ts": 6197196769958.029, "dur": 4.244, + "args": { + "External id": 27469,"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": 2338707, "tid": 2379456, + "ts": 6197196769959.497, "dur": 2.587, + "args": { + "External id": 27470,"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": 2338707, "tid": 2379456, + "ts": 6197196769968.788, "dur": 10.131, + "args": { + "External id": 27471,"Record function id": 0, "Sequence number": 479956, "Fwd thread id": 1, "Ev Idx": 334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196769970.724, "dur": 5.223, + "args": { + "External id": 27472,"Sequence number": 479956, "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": 2338707, "tid": 2379456, "ts": 6197196769970.724, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196769973.046, "dur": 2.684, + "args": { + "External id": 27473,"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": 2338707, "tid": 2379456, + "ts": 6197196769974.561, "dur": 1.009, + "args": { + "External id": 27474,"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": 2338707, "tid": 2379456, + "ts": 6197196769983.040, "dur": 187.127, + "args": { + "External id": 27475,"Record function id": 0, "Sequence number": 479955, "Fwd thread id": 1, "Ev Idx": 338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196769984.247, "dur": 175.568, + "args": { + "External id": 27476,"Sequence number": 479955, "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": 2338707, "tid": 2379456, "ts": 6197196769984.247, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197196769989.506, "dur": 7.738, + "args": { + "External id": 27477,"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": 2338707, "tid": 2379456, + "ts": 6197196769993.638, "dur": 2.969, + "args": { + "External id": 27478,"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": 2338707, "tid": 2379456, + "ts": 6197196769995.699, "dur": 0.730, + "args": { + "External id": 27479,"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": 2338707, "tid": 2379456, + "ts": 6197196769998.821, "dur": 48.612, + "args": { + "External id": 27480,"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": 2338707, "tid": 2379456, + "ts": 6197196770049.012, "dur": 42.367, + "args": { + "External id": 27481,"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": 2338707, "tid": 2379456, + "ts": 6197196770049.621, "dur": 40.523, + "args": { + "External id": 27482,"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": 2338707, "tid": 2379456, + "ts": 6197196770051.477, "dur": 37.962, + "args": { + "External id": 27483,"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": 2338707, "tid": 2379456, + "ts": 6197196770096.506, "dur": 4.815, + "args": { + "External id": 27484,"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": 2338707, "tid": 2379456, + "ts": 6197196770097.895, "dur": 2.735, + "args": { + "External id": 27485,"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": 2338707, "tid": 2379456, + "ts": 6197196770099.748, "dur": 0.802, + "args": { + "External id": 27486,"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": 2338707, "tid": 2379456, + "ts": 6197196770102.280, "dur": 56.838, + "args": { + "External id": 27487,"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": 2338707, "tid": 2379456, + "ts": 6197196770177.470, "dur": 10.377, + "args": { + "External id": 27488,"Record function id": 0, "Sequence number": 479954, "Fwd thread id": 1, "Ev Idx": 351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196770178.899, "dur": 6.903, + "args": { + "External id": 27489,"Sequence number": 479954, "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": 2338707, "tid": 2379456, "ts": 6197196770178.899, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196770180.840, "dur": 4.810, + "args": { + "External id": 27490,"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": 2338707, "tid": 2379456, + "ts": 6197196770182.167, "dur": 3.358, + "args": { + "External id": 27491,"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": 2338707, "tid": 2379456, + "ts": 6197196770191.797, "dur": 11.440, + "args": { + "External id": 27492,"Record function id": 0, "Sequence number": 479953, "Fwd thread id": 1, "Ev Idx": 355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196770193.056, "dur": 7.261, + "args": { + "External id": 27493,"Sequence number": 479953, "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": 2338707, "tid": 2379456, "ts": 6197196770193.056, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197196770196.155, "dur": 3.964, + "args": { + "External id": 27494,"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": 2338707, "tid": 2379456, + "ts": 6197196770197.130, "dur": 2.484, + "args": { + "External id": 27495,"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": 2338707, "tid": 2379456, + "ts": 6197196770199.005, "dur": 0.529, + "args": { + "External id": 27496,"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": 2338707, "tid": 2379456, + "ts": 6197196770207.466, "dur": 7.368, + "args": { + "External id": 27497,"Record function id": 0, "Ev Idx": 360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197196770209.624, "dur": 4.679, + "args": { + "External id": 27498,"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": 2338707, "tid": 2379456, + "ts": 6197196770211.353, "dur": 2.571, + "args": { + "External id": 27499,"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": 2338707, "tid": 2379456, + "ts": 6197196770212.121, "dur": 1.723, + "args": { + "External id": 27500,"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": 2338707, "tid": 2379456, + "ts": 6197196770218.464, "dur": 11.144, + "args": { + "External id": 27501,"Record function id": 0, "Sequence number": 479952, "Fwd thread id": 1, "Ev Idx": 364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196770220.660, "dur": 6.031, + "args": { + "External id": 27502,"Sequence number": 479952, "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": 2338707, "tid": 2379456, "ts": 6197196770220.660, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196770222.158, "dur": 4.372, + "args": { + "External id": 27503,"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": 2338707, "tid": 2379456, + "ts": 6197196770225.421, "dur": 0.993, + "args": { + "External id": 27504,"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": 2338707, "tid": 2379456, + "ts": 6197196770232.755, "dur": 124.198, + "args": { + "External id": 27505,"Record function id": 0, "Sequence number": 479951, "Fwd thread id": 1, "Ev Idx": 368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196770234.024, "dur": 113.026, + "args": { + "External id": 27506,"Sequence number": 479951, "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": 2338707, "tid": 2379456, "ts": 6197196770234.024, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197196770236.908, "dur": 2.872, + "args": { + "External id": 27507,"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": 2338707, "tid": 2379456, + "ts": 6197196770237.490, "dur": 1.860, + "args": { + "External id": 27508,"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": 2338707, "tid": 2379456, + "ts": 6197196770238.874, "dur": 0.387, + "args": { + "External id": 27509,"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": 2338707, "tid": 2379456, + "ts": 6197196770240.823, "dur": 46.252, + "args": { + "External id": 27510,"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": 2338707, "tid": 2379456, + "ts": 6197196770290.376, "dur": 4.008, + "args": { + "External id": 27511,"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": 2338707, "tid": 2379456, + "ts": 6197196770290.981, "dur": 2.838, + "args": { + "External id": 27512,"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": 2338707, "tid": 2379456, + "ts": 6197196770292.610, "dur": 1.086, + "args": { + "External id": 27513,"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": 2338707, "tid": 2379456, + "ts": 6197196770295.783, "dur": 3.563, + "args": { + "External id": 27514,"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": 2338707, "tid": 2379456, + "ts": 6197196770296.764, "dur": 1.815, + "args": { + "External id": 27515,"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": 2338707, "tid": 2379456, + "ts": 6197196770298.074, "dur": 0.405, + "args": { + "External id": 27516,"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": 2338707, "tid": 2379456, + "ts": 6197196770302.128, "dur": 44.061, + "args": { + "External id": 27517,"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": 2338707, "tid": 2379456, + "ts": 6197196770364.641, "dur": 36.947, + "args": { + "External id": 27518,"Record function id": 0, "Sequence number": 479950, "Fwd thread id": 1, "Ev Idx": 381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196770365.557, "dur": 5.104, + "args": { + "External id": 27519,"Sequence number": 479950, "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": 2338707, "tid": 2379456, "ts": 6197196770365.557, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196770367.895, "dur": 2.626, + "args": { + "External id": 27520,"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": 2338707, "tid": 2379456, + "ts": 6197196770369.437, "dur": 0.942, + "args": { + "External id": 27521,"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": 2338707, "tid": 2379456, + "ts": 6197196770374.639, "dur": 23.979, + "args": { + "External id": 27522,"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": 2338707, "tid": 2379456, + "ts": 6197196770405.368, "dur": 11.588, + "args": { + "External id": 27523,"Record function id": 0, "Sequence number": 479949, "Fwd thread id": 1, "Ev Idx": 386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196770406.417, "dur": 7.420, + "args": { + "External id": 27524,"Sequence number": 479949, "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": 2338707, "tid": 2379456, "ts": 6197196770406.417, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197196770407.493, "dur": 6.133, + "args": { + "External id": 27525,"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": 2338707, "tid": 2379456, + "ts": 6197196770408.402, "dur": 4.658, + "args": { + "External id": 27526,"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": 2338707, "tid": 2379456, + "ts": 6197196770412.102, "dur": 0.855, + "args": { + "External id": 27527,"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": 2338707, "tid": 2379456, + "ts": 6197196770420.979, "dur": 6.254, + "args": { + "External id": 27528,"Record function id": 0, "Ev Idx": 391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197196770422.676, "dur": 4.061, + "args": { + "External id": 27529,"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": 2338707, "tid": 2379456, + "ts": 6197196770424.068, "dur": 2.306, + "args": { + "External id": 27530,"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": 2338707, "tid": 2379456, + "ts": 6197196770425.189, "dur": 1.111, + "args": { + "External id": 27531,"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": 2338707, "tid": 2379456, + "ts": 6197196770431.964, "dur": 468.593, + "args": { + "External id": 27532,"Record function id": 0, "Sequence number": 479948, "Fwd thread id": 1, "Ev Idx": 395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197196770434.148, "dur": 449.220, + "args": { + "External id": 27533,"Sequence number": 479948, "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": 2338707, "tid": 2379456, "ts": 6197196770434.148, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338707, "tid": 2379456, + "ts": 6197196770463.031, "dur": 35.044, + "args": { + "External id": 27534,"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": 2338707, "tid": 2379456, + "ts": 6197196770465.022, "dur": 32.842, + "args": { + "External id": 27535,"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": 2338707, "tid": 2379456, + "ts": 6197196770468.638, "dur": 6.599, + "args": { + "External id": 27536,"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": 2338707, "tid": 2379456, + "ts": 6197196770471.482, "dur": 3.264, + "args": { + "External id": 27537,"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": 2338707, "tid": 2379456, + "ts": 6197196770476.715, "dur": 20.727, + "args": { + "External id": 27538,"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": 2338707, "tid": 2379456, + "ts": 6197196770511.821, "dur": 4.343, + "args": { + "External id": 27539,"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": 2338707, "tid": 2379456, + "ts": 6197196770514.806, "dur": 1.216, + "args": { + "External id": 27540,"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": 2338707, "tid": 2379456, + "ts": 6197196770520.197, "dur": 1.996, + "args": { + "External id": 27541,"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": 2338707, "tid": 2379456, + "ts": 6197196770521.142, "dur": 0.955, + "args": { + "External id": 27542,"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": 2338707, "tid": 2379456, + "ts": 6197196770537.818, "dur": 4.384, + "args": { + "External id": 27543,"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": 2338707, "tid": 2379456, + "ts": 6197196770554.355, "dur": 2.829, + "args": { + "External id": 27544,"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": 2338707, "tid": 2379456, + "ts": 6197196770768.059, "dur": 3.580, + "args": { + "External id": 27545,"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": 2338707, "tid": 2379456, + "ts": 6197196770776.844, "dur": 37.073, + "args": { + "External id": 27546,"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": 2338707, "tid": 2379456, + "ts": 6197196770790.026, "dur": 0.909, + "args": { + "External id": 27547,"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": 2338707, "tid": 2379456, + "ts": 6197196770819.947, "dur": 29.638, + "args": { + "External id": 27548,"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": 2338707, "tid": 2379456, + "ts": 6197196770821.809, "dur": 27.543, + "args": { + "External id": 27549,"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": 2338707, "tid": 2379456, + "ts": 6197196770826.641, "dur": 4.629, + "args": { + "External id": 27550,"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": 2338707, "tid": 2379456, + "ts": 6197196770832.870, "dur": 15.823, + "args": { + "External id": 27551,"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": 2338707, "tid": 2379456, + "ts": 6197196770856.441, "dur": 2.851, + "args": { + "External id": 27552,"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": 2338707, "tid": 2379456, + "ts": 6197196770858.142, "dur": 1.024, + "args": { + "External id": 27553,"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": 2338707, "tid": 2379456, + "ts": 6197196770867.422, "dur": 2.779, + "args": { + "External id": 27554,"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": 2338707, "tid": 2379456, + "ts": 6197196770868.906, "dur": 1.204, + "args": { + "External id": 27555,"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": 2338707, "tid": 2379456, + "ts": 6197196770872.691, "dur": 2.440, + "args": { + "External id": 27556,"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": 2338707, "tid": 2379456, + "ts": 6197196770874.004, "dur": 1.047, + "args": { + "External id": 27557,"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": 2338707, "tid": 2379456, + "ts": 6197196770916.089, "dur": 10.184, + "args": { + "External id": 27558,"Record function id": 0, "Ev Idx": 421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197196770919.266, "dur": 6.292, + "args": { + "External id": 27559,"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": 2338707, "tid": 2379456, + "ts": 6197196770921.668, "dur": 2.975, + "args": { + "External id": 27560,"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": 2338707, "tid": 2379456, + "ts": 6197196770922.633, "dur": 1.893, + "args": { + "External id": 27561,"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": 2338707, "tid": 2379456, + "ts": 6197196770930.262, "dur": 9.521, + "args": { + "External id": 27562,"Record function id": 0, "Sequence number": 479947, "Fwd thread id": 1, "Ev Idx": 425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196770931.862, "dur": 4.160, + "args": { + "External id": 27563,"Sequence number": 479947, "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": 2338707, "tid": 2379456, "ts": 6197196770931.862, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196770933.532, "dur": 2.244, + "args": { + "External id": 27564,"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": 2338707, "tid": 2379456, + "ts": 6197196770934.419, "dur": 1.234, + "args": { + "External id": 27565,"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": 2338707, "tid": 2379456, + "ts": 6197196770943.180, "dur": 232.295, + "args": { + "External id": 27566,"Record function id": 0, "Sequence number": 479946, "Fwd thread id": 1, "Ev Idx": 429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196770944.318, "dur": 224.273, + "args": { + "External id": 27567,"Sequence number": 479946, "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": 2338707, "tid": 2379456, "ts": 6197196770944.318, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197196770951.224, "dur": 5.420, + "args": { + "External id": 27568,"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": 2338707, "tid": 2379456, + "ts": 6197196770953.000, "dur": 2.978, + "args": { + "External id": 27569,"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": 2338707, "tid": 2379456, + "ts": 6197196770955.175, "dur": 0.636, + "args": { + "External id": 27570,"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": 2338707, "tid": 2379456, + "ts": 6197196770957.850, "dur": 80.408, + "args": { + "External id": 27571,"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": 2338707, "tid": 2379456, + "ts": 6197196771039.753, "dur": 6.308, + "args": { + "External id": 27572,"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": 2338707, "tid": 2379456, + "ts": 6197196771040.455, "dur": 4.951, + "args": { + "External id": 27573,"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": 2338707, "tid": 2379456, + "ts": 6197196771042.502, "dur": 2.711, + "args": { + "External id": 27574,"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": 2338707, "tid": 2379456, + "ts": 6197196771049.998, "dur": 57.082, + "args": { + "External id": 27575,"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": 2338707, "tid": 2379456, + "ts": 6197196771051.179, "dur": 54.853, + "args": { + "External id": 27576,"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": 2338707, "tid": 2379456, + "ts": 6197196771102.299, "dur": 3.191, + "args": { + "External id": 27577,"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": 2338707, "tid": 2379456, + "ts": 6197196771108.027, "dur": 59.294, + "args": { + "External id": 27578,"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": 2338707, "tid": 2379456, + "ts": 6197196771182.685, "dur": 9.090, + "args": { + "External id": 27579,"Record function id": 0, "Sequence number": 479945, "Fwd thread id": 1, "Ev Idx": 442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196771184.051, "dur": 5.441, + "args": { + "External id": 27580,"Sequence number": 479945, "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": 2338707, "tid": 2379456, "ts": 6197196771184.051, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196771186.180, "dur": 3.149, + "args": { + "External id": 27581,"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": 2338707, "tid": 2379456, + "ts": 6197196771187.814, "dur": 1.372, + "args": { + "External id": 27582,"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": 2338707, "tid": 2379456, + "ts": 6197196771195.167, "dur": 12.715, + "args": { + "External id": 27583,"Record function id": 0, "Sequence number": 479944, "Fwd thread id": 1, "Ev Idx": 446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196771196.243, "dur": 8.435, + "args": { + "External id": 27584,"Sequence number": 479944, "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": 2338707, "tid": 2379456, "ts": 6197196771196.243, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197196771200.216, "dur": 4.254, + "args": { + "External id": 27585,"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": 2338707, "tid": 2379456, + "ts": 6197196771201.415, "dur": 2.578, + "args": { + "External id": 27586,"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": 2338707, "tid": 2379456, + "ts": 6197196771203.435, "dur": 0.442, + "args": { + "External id": 27587,"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": 2338707, "tid": 2379456, + "ts": 6197196771212.070, "dur": 7.219, + "args": { + "External id": 27588,"Record function id": 0, "Ev Idx": 451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197196771213.920, "dur": 4.766, + "args": { + "External id": 27589,"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": 2338707, "tid": 2379456, + "ts": 6197196771215.586, "dur": 2.813, + "args": { + "External id": 27590,"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": 2338707, "tid": 2379456, + "ts": 6197196771216.724, "dur": 1.574, + "args": { + "External id": 27591,"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": 2338707, "tid": 2379456, + "ts": 6197196771222.778, "dur": 9.338, + "args": { + "External id": 27592,"Record function id": 0, "Sequence number": 479943, "Fwd thread id": 1, "Ev Idx": 455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196771223.806, "dur": 5.864, + "args": { + "External id": 27593,"Sequence number": 479943, "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": 2338707, "tid": 2379456, "ts": 6197196771223.806, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196771225.299, "dur": 4.206, + "args": { + "External id": 27594,"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": 2338707, "tid": 2379456, + "ts": 6197196771228.222, "dur": 1.145, + "args": { + "External id": 27595,"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": 2338707, "tid": 2379456, + "ts": 6197196771237.354, "dur": 405.367, + "args": { + "External id": 27596,"Record function id": 0, "Sequence number": 479942, "Fwd thread id": 1, "Ev Idx": 459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFuncBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197196771239.197, "dur": 380.666, + "args": { + "External id": 27597,"Sequence number": 479942, "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": 2338707, "tid": 2379456, "ts": 6197196771239.197, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338707, "tid": 2379456, + "ts": 6197196771260.129, "dur": 8.396, + "args": { + "External id": 27598,"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": 2338707, "tid": 2379456, + "ts": 6197196771263.115, "dur": 4.918, + "args": { + "External id": 27599,"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": 2338707, "tid": 2379456, + "ts": 6197196771270.828, "dur": 4.296, + "args": { + "External id": 27600,"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": 2338707, "tid": 2379456, + "ts": 6197196771272.388, "dur": 2.557, + "args": { + "External id": 27601,"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": 2338707, "tid": 2379456, + "ts": 6197196771276.966, "dur": 7.869, + "args": { + "External id": 27602,"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": 2338707, "tid": 2379456, + "ts": 6197196771278.951, "dur": 5.645, + "args": { + "External id": 27603,"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": 2338707, "tid": 2379456, + "ts": 6197196771318.678, "dur": 276.077, + "args": { + "External id": 27604,"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": 2338707, "tid": 2379456, + "ts": 6197196771410.522, "dur": 3.338, + "args": { + "External id": 27605,"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": 2338707, "tid": 2379456, + "ts": 6197196771417.932, "dur": 2.572, + "args": { + "External id": 27606,"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": 2338707, "tid": 2379456, + "ts": 6197196771421.622, "dur": 1.496, + "args": { + "External id": 27607,"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": 2338707, "tid": 2379456, + "ts": 6197196771424.114, "dur": 4.493, + "args": { + "External id": 27608,"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": 2338707, "tid": 2379456, + "ts": 6197196771487.655, "dur": 3.080, + "args": { + "External id": 27609,"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": 2338707, "tid": 2379456, + "ts": 6197196771488.938, "dur": 1.670, + "args": { + "External id": 27610,"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": 2338707, "tid": 2379456, + "ts": 6197196771492.234, "dur": 31.986, + "args": { + "External id": 27611,"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": 2338707, "tid": 2379456, + "ts": 6197196771498.178, "dur": 2.830, + "args": { + "External id": 27612,"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": 2338707, "tid": 2379456, + "ts": 6197196771525.494, "dur": 1.714, + "args": { + "External id": 27613,"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": 2338707, "tid": 2379456, + "ts": 6197196771526.501, "dur": 0.633, + "args": { + "External id": 27614,"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": 2338707, "tid": 2379456, + "ts": 6197196771530.918, "dur": 16.295, + "args": { + "External id": 27615,"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": 2338707, "tid": 2379456, + "ts": 6197196771533.188, "dur": 0.599, + "args": { + "External id": 27616,"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": 2338707, "tid": 2379456, + "ts": 6197196771607.442, "dur": 3.626, + "args": { + "External id": 27617,"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": 2338707, "tid": 2379456, + "ts": 6197196771614.099, "dur": 0.612, + "args": { + "External id": 27618,"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": 2338707, "tid": 2379456, + "ts": 6197196771616.670, "dur": 0.509, + "args": { + "External id": 27619,"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": 2338707, "tid": 2379456, + "ts": 6197196771651.182, "dur": 265.372, + "args": { + "External id": 27620,"Record function id": 0, "Sequence number": 479941, "Fwd thread id": 1, "Ev Idx": 483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197196771653.181, "dur": 254.717, + "args": { + "External id": 27621,"Sequence number": 479941, "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": 2338707, "tid": 2379456, "ts": 6197196771653.181, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338707, "tid": 2379456, + "ts": 6197196771676.453, "dur": 66.802, + "args": { + "External id": 27622,"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": 2338707, "tid": 2379456, + "ts": 6197196771679.831, "dur": 3.184, + "args": { + "External id": 27623,"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": 2338707, "tid": 2379456, + "ts": 6197196771684.894, "dur": 57.624, + "args": { + "External id": 27624,"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": 2338707, "tid": 2379456, + "ts": 6197196771756.179, "dur": 6.090, + "args": { + "External id": 27625,"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": 2338707, "tid": 2379456, + "ts": 6197196771758.552, "dur": 3.410, + "args": { + "External id": 27626,"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": 2338707, "tid": 2379456, + "ts": 6197196771925.684, "dur": 238.707, + "args": { + "External id": 27627,"Record function id": 0, "Sequence number": 479940, "Fwd thread id": 1, "Ev Idx": 490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197196771927.940, "dur": 227.136, + "args": { + "External id": 27628,"Sequence number": 479940, "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": 2338707, "tid": 2379456, "ts": 6197196771927.940, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338707, "tid": 2379456, + "ts": 6197196771940.478, "dur": 53.225, + "args": { + "External id": 27629,"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": 2338707, "tid": 2379456, + "ts": 6197196771946.917, "dur": 2.774, + "args": { + "External id": 27630,"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": 2338707, "tid": 2379456, + "ts": 6197196771951.081, "dur": 42.177, + "args": { + "External id": 27631,"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": 2338707, "tid": 2379456, + "ts": 6197196772004.138, "dur": 6.076, + "args": { + "External id": 27632,"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": 2338707, "tid": 2379456, + "ts": 6197196772006.096, "dur": 3.851, + "args": { + "External id": 27633,"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": 2338707, "tid": 2379456, + "ts": 6197196772173.750, "dur": 17.432, + "args": { + "External id": 27634,"Record function id": 0, "Sequence number": 479939, "Fwd thread id": 1, "Ev Idx": 497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196772177.380, "dur": 10.154, + "args": { + "External id": 27635,"Sequence number": 479939, "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": 2338707, "tid": 2379456, "ts": 6197196772177.380, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196772180.503, "dur": 6.696, + "args": { + "External id": 27636,"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": 2338707, "tid": 2379456, + "ts": 6197196772181.878, "dur": 5.128, + "args": { + "External id": 27637,"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": 2338707, "tid": 2379456, + "ts": 6197196772194.606, "dur": 8.597, + "args": { + "External id": 27638,"Record function id": 0, "Sequence number": 479938, "Fwd thread id": 1, "Ev Idx": 501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196772195.760, "dur": 4.145, + "args": { + "External id": 27639,"Sequence number": 479938, "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": 2338707, "tid": 2379456, "ts": 6197196772195.760, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196772197.651, "dur": 2.104, + "args": { + "External id": 27640,"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": 2338707, "tid": 2379456, + "ts": 6197196772198.771, "dur": 0.885, + "args": { + "External id": 27641,"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": 2338707, "tid": 2379456, + "ts": 6197196772206.468, "dur": 9.428, + "args": { + "External id": 27642,"Record function id": 0, "Sequence number": 479937, "Fwd thread id": 1, "Ev Idx": 505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196772207.538, "dur": 5.978, + "args": { + "External id": 27643,"Sequence number": 479937, "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": 2338707, "tid": 2379456, "ts": 6197196772207.538, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196772208.942, "dur": 4.424, + "args": { + "External id": 27644,"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": 2338707, "tid": 2379456, + "ts": 6197196772212.376, "dur": 0.900, + "args": { + "External id": 27645,"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": 2338707, "tid": 2379456, + "ts": 6197196772219.493, "dur": 36.806, + "args": { + "External id": 27646,"Record function id": 0, "Sequence number": 479936, "Fwd thread id": 1, "Ev Idx": 509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196772221.198, "dur": 31.782, + "args": { + "External id": 27647,"Sequence number": 479936, "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": 2338707, "tid": 2379456, "ts": 6197196772221.198, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196772222.566, "dur": 30.239, + "args": { + "External id": 27648,"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": 2338707, "tid": 2379456, + "ts": 6197196772249.416, "dur": 3.222, + "args": { + "External id": 27649,"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": 2338707, "tid": 2379456, + "ts": 6197196772259.703, "dur": 166.869, + "args": { + "External id": 27650,"Record function id": 0, "Sequence number": 479935, "Fwd thread id": 1, "Ev Idx": 513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196772260.749, "dur": 158.223, + "args": { + "External id": 27651,"Sequence number": 479935, "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": 2338707, "tid": 2379456, "ts": 6197196772260.749, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197196772266.998, "dur": 8.733, + "args": { + "External id": 27652,"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": 2338707, "tid": 2379456, + "ts": 6197196772269.067, "dur": 5.972, + "args": { + "External id": 27653,"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": 2338707, "tid": 2379456, + "ts": 6197196772273.106, "dur": 1.681, + "args": { + "External id": 27654,"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": 2338707, "tid": 2379456, + "ts": 6197196772277.566, "dur": 77.877, + "args": { + "External id": 27655,"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": 2338707, "tid": 2379456, + "ts": 6197196772356.656, "dur": 8.065, + "args": { + "External id": 27656,"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": 2338707, "tid": 2379456, + "ts": 6197196772357.500, "dur": 6.507, + "args": { + "External id": 27657,"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": 2338707, "tid": 2379456, + "ts": 6197196772361.467, "dur": 2.359, + "args": { + "External id": 27658,"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": 2338707, "tid": 2379456, + "ts": 6197196772366.759, "dur": 3.853, + "args": { + "External id": 27659,"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": 2338707, "tid": 2379456, + "ts": 6197196772368.050, "dur": 1.990, + "args": { + "External id": 27660,"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": 2338707, "tid": 2379456, + "ts": 6197196772369.465, "dur": 0.511, + "args": { + "External id": 27661,"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": 2338707, "tid": 2379456, + "ts": 6197196772371.194, "dur": 46.855, + "args": { + "External id": 27662,"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": 2338707, "tid": 2379456, + "ts": 6197196772431.929, "dur": 10.369, + "args": { + "External id": 27663,"Record function id": 0, "Sequence number": 479934, "Fwd thread id": 1, "Ev Idx": 526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196772432.851, "dur": 6.541, + "args": { + "External id": 27664,"Sequence number": 479934, "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": 2338707, "tid": 2379456, "ts": 6197196772432.851, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196772434.759, "dur": 4.476, + "args": { + "External id": 27665,"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": 2338707, "tid": 2379456, + "ts": 6197196772438.065, "dur": 1.032, + "args": { + "External id": 27666,"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": 2338707, "tid": 2379456, + "ts": 6197196772445.904, "dur": 8.562, + "args": { + "External id": 27667,"Record function id": 0, "Sequence number": 479933, "Fwd thread id": 1, "Ev Idx": 530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196772446.737, "dur": 4.420, + "args": { + "External id": 27668,"Sequence number": 479933, "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": 2338707, "tid": 2379456, "ts": 6197196772446.737, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197196772447.453, "dur": 3.500, + "args": { + "External id": 27669,"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": 2338707, "tid": 2379456, + "ts": 6197196772448.043, "dur": 2.388, + "args": { + "External id": 27670,"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": 2338707, "tid": 2379456, + "ts": 6197196772449.794, "dur": 0.471, + "args": { + "External id": 27671,"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": 2338707, "tid": 2379456, + "ts": 6197196772460.352, "dur": 13.811, + "args": { + "External id": 27672,"Record function id": 0, "Ev Idx": 535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197196772462.416, "dur": 10.945, + "args": { + "External id": 27673,"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": 2338707, "tid": 2379456, + "ts": 6197196772464.811, "dur": 8.141, + "args": { + "External id": 27674,"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": 2338707, "tid": 2379456, + "ts": 6197196772468.546, "dur": 4.298, + "args": { + "External id": 27675,"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": 2338707, "tid": 2379456, + "ts": 6197196772480.469, "dur": 7.286, + "args": { + "External id": 27676,"Record function id": 0, "Sequence number": 479932, "Fwd thread id": 1, "Ev Idx": 539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196772482.123, "dur": 3.157, + "args": { + "External id": 27677,"Sequence number": 479932, "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": 2338707, "tid": 2379456, "ts": 6197196772482.123, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196772483.303, "dur": 1.820, + "args": { + "External id": 27678,"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": 2338707, "tid": 2379456, + "ts": 6197196772484.169, "dur": 0.827, + "args": { + "External id": 27679,"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": 2338707, "tid": 2379456, + "ts": 6197196772490.895, "dur": 97.909, + "args": { + "External id": 27680,"Record function id": 0, "Sequence number": 479931, "Fwd thread id": 1, "Ev Idx": 543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196772491.876, "dur": 89.288, + "args": { + "External id": 27681,"Sequence number": 479931, "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": 2338707, "tid": 2379456, "ts": 6197196772491.876, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197196772494.751, "dur": 5.696, + "args": { + "External id": 27682,"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": 2338707, "tid": 2379456, + "ts": 6197196772495.192, "dur": 4.811, + "args": { + "External id": 27683,"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": 2338707, "tid": 2379456, + "ts": 6197196772499.327, "dur": 0.536, + "args": { + "External id": 27684,"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": 2338707, "tid": 2379456, + "ts": 6197196772501.049, "dur": 28.291, + "args": { + "External id": 27685,"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": 2338707, "tid": 2379456, + "ts": 6197196772530.303, "dur": 4.096, + "args": { + "External id": 27686,"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": 2338707, "tid": 2379456, + "ts": 6197196772530.779, "dur": 3.009, + "args": { + "External id": 27687,"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": 2338707, "tid": 2379456, + "ts": 6197196772532.740, "dur": 0.934, + "args": { + "External id": 27688,"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": 2338707, "tid": 2379456, + "ts": 6197196772535.650, "dur": 6.286, + "args": { + "External id": 27689,"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": 2338707, "tid": 2379456, + "ts": 6197196772539.016, "dur": 2.155, + "args": { + "External id": 27690,"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": 2338707, "tid": 2379456, + "ts": 6197196772540.749, "dur": 0.358, + "args": { + "External id": 27691,"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": 2338707, "tid": 2379456, + "ts": 6197196772542.334, "dur": 37.986, + "args": { + "External id": 27692,"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": 2338707, "tid": 2379456, + "ts": 6197196772593.507, "dur": 34.086, + "args": { + "External id": 27693,"Record function id": 0, "Sequence number": 479930, "Fwd thread id": 1, "Ev Idx": 556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196772594.403, "dur": 3.686, + "args": { + "External id": 27694,"Sequence number": 479930, "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": 2338707, "tid": 2379456, "ts": 6197196772594.403, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196772596.099, "dur": 1.832, + "args": { + "External id": 27695,"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": 2338707, "tid": 2379456, + "ts": 6197196772596.875, "dur": 0.937, + "args": { + "External id": 27696,"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": 2338707, "tid": 2379456, + "ts": 6197196772601.074, "dur": 24.147, + "args": { + "External id": 27697,"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": 2338707, "tid": 2379456, + "ts": 6197196772631.121, "dur": 9.942, + "args": { + "External id": 27698,"Record function id": 0, "Sequence number": 479929, "Fwd thread id": 1, "Ev Idx": 561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196772633.420, "dur": 5.060, + "args": { + "External id": 27699,"Sequence number": 479929, "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": 2338707, "tid": 2379456, "ts": 6197196772633.420, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197196772634.262, "dur": 4.023, + "args": { + "External id": 27700,"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": 2338707, "tid": 2379456, + "ts": 6197196772635.143, "dur": 2.571, + "args": { + "External id": 27701,"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": 2338707, "tid": 2379456, + "ts": 6197196772637.063, "dur": 0.567, + "args": { + "External id": 27702,"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": 2338707, "tid": 2379456, + "ts": 6197196772644.924, "dur": 5.549, + "args": { + "External id": 27703,"Record function id": 0, "Ev Idx": 566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197196772646.503, "dur": 3.442, + "args": { + "External id": 27704,"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": 2338707, "tid": 2379456, + "ts": 6197196772647.645, "dur": 1.876, + "args": { + "External id": 27705,"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": 2338707, "tid": 2379456, + "ts": 6197196772648.447, "dur": 0.966, + "args": { + "External id": 27706,"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": 2338707, "tid": 2379456, + "ts": 6197196772653.961, "dur": 9.300, + "args": { + "External id": 27707,"Record function id": 0, "Sequence number": 479928, "Fwd thread id": 1, "Ev Idx": 570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196772655.585, "dur": 5.438, + "args": { + "External id": 27708,"Sequence number": 479928, "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": 2338707, "tid": 2379456, "ts": 6197196772655.585, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196772657.041, "dur": 3.817, + "args": { + "External id": 27709,"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": 2338707, "tid": 2379456, + "ts": 6197196772659.923, "dur": 0.806, + "args": { + "External id": 27710,"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": 2338707, "tid": 2379456, + "ts": 6197196772666.404, "dur": 131.342, + "args": { + "External id": 27711,"Record function id": 0, "Sequence number": 479927, "Fwd thread id": 1, "Ev Idx": 574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196772667.212, "dur": 119.638, + "args": { + "External id": 27712,"Sequence number": 479927, "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": 2338707, "tid": 2379456, "ts": 6197196772667.212, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197196772669.634, "dur": 2.747, + "args": { + "External id": 27713,"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": 2338707, "tid": 2379456, + "ts": 6197196772670.106, "dur": 1.817, + "args": { + "External id": 27714,"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": 2338707, "tid": 2379456, + "ts": 6197196772671.347, "dur": 0.455, + "args": { + "External id": 27715,"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": 2338707, "tid": 2379456, + "ts": 6197196772678.481, "dur": 52.192, + "args": { + "External id": 27716,"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": 2338707, "tid": 2379456, + "ts": 6197196772732.803, "dur": 6.601, + "args": { + "External id": 27717,"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": 2338707, "tid": 2379456, + "ts": 6197196772733.528, "dur": 5.004, + "args": { + "External id": 27718,"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": 2338707, "tid": 2379456, + "ts": 6197196772735.723, "dur": 2.651, + "args": { + "External id": 27719,"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": 2338707, "tid": 2379456, + "ts": 6197196772741.094, "dur": 3.349, + "args": { + "External id": 27720,"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": 2338707, "tid": 2379456, + "ts": 6197196772741.977, "dur": 1.933, + "args": { + "External id": 27721,"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": 2338707, "tid": 2379456, + "ts": 6197196772743.296, "dur": 0.520, + "args": { + "External id": 27722,"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": 2338707, "tid": 2379456, + "ts": 6197196772747.323, "dur": 38.779, + "args": { + "External id": 27723,"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": 2338707, "tid": 2379456, + "ts": 6197196772804.189, "dur": 28.428, + "args": { + "External id": 27724,"Record function id": 0, "Sequence number": 479926, "Fwd thread id": 1, "Ev Idx": 587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196772805.245, "dur": 4.664, + "args": { + "External id": 27725,"Sequence number": 479926, "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": 2338707, "tid": 2379456, "ts": 6197196772805.245, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196772807.360, "dur": 2.408, + "args": { + "External id": 27726,"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": 2338707, "tid": 2379456, + "ts": 6197196772808.287, "dur": 1.379, + "args": { + "External id": 27727,"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": 2338707, "tid": 2379456, + "ts": 6197196772812.636, "dur": 17.757, + "args": { + "External id": 27728,"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": 2338707, "tid": 2379456, + "ts": 6197196772836.202, "dur": 9.736, + "args": { + "External id": 27729,"Record function id": 0, "Sequence number": 479925, "Fwd thread id": 1, "Ev Idx": 592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196772837.332, "dur": 6.270, + "args": { + "External id": 27730,"Sequence number": 479925, "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": 2338707, "tid": 2379456, "ts": 6197196772837.332, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197196772838.340, "dur": 5.079, + "args": { + "External id": 27731,"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": 2338707, "tid": 2379456, + "ts": 6197196772838.888, "dur": 3.962, + "args": { + "External id": 27732,"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": 2338707, "tid": 2379456, + "ts": 6197196772842.301, "dur": 0.440, + "args": { + "External id": 27733,"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": 2338707, "tid": 2379456, + "ts": 6197196772850.317, "dur": 6.337, + "args": { + "External id": 27734,"Record function id": 0, "Ev Idx": 597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197196772852.295, "dur": 3.829, + "args": { + "External id": 27735,"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": 2338707, "tid": 2379456, + "ts": 6197196772853.492, "dur": 2.318, + "args": { + "External id": 27736,"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": 2338707, "tid": 2379456, + "ts": 6197196772854.221, "dur": 1.485, + "args": { + "External id": 27737,"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": 2338707, "tid": 2379456, + "ts": 6197196772861.773, "dur": 450.682, + "args": { + "External id": 27738,"Record function id": 0, "Sequence number": 479924, "Fwd thread id": 1, "Ev Idx": 601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197196772863.239, "dur": 407.541, + "args": { + "External id": 27739,"Sequence number": 479924, "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": 2338707, "tid": 2379456, "ts": 6197196772863.239, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196772899.762, "dur": 2.401, + "args": { + "External id": 27740,"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": 2338707, "tid": 2379456, + "ts": 6197196772900.747, "dur": 1.274, + "args": { + "External id": 27741,"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": 2338707, "tid": 2379456, + "ts": 6197196772920.178, "dur": 4.117, + "args": { + "External id": 27742,"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": 2338707, "tid": 2379456, + "ts": 6197196772933.643, "dur": 2.187, + "args": { + "External id": 27743,"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": 2338707, "tid": 2379456, + "ts": 6197196773149.080, "dur": 3.150, + "args": { + "External id": 27744,"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": 2338707, "tid": 2379456, + "ts": 6197196773156.781, "dur": 42.134, + "args": { + "External id": 27745,"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": 2338707, "tid": 2379456, + "ts": 6197196773171.790, "dur": 1.245, + "args": { + "External id": 27746,"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": 2338707, "tid": 2379456, + "ts": 6197196773205.130, "dur": 39.099, + "args": { + "External id": 27747,"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": 2338707, "tid": 2379456, + "ts": 6197196773206.971, "dur": 37.053, + "args": { + "External id": 27748,"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": 2338707, "tid": 2379456, + "ts": 6197196773211.584, "dur": 4.330, + "args": { + "External id": 27749,"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": 2338707, "tid": 2379456, + "ts": 6197196773217.666, "dur": 25.715, + "args": { + "External id": 27750,"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": 2338707, "tid": 2379456, + "ts": 6197196773251.457, "dur": 2.397, + "args": { + "External id": 27751,"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": 2338707, "tid": 2379456, + "ts": 6197196773252.791, "dur": 0.940, + "args": { + "External id": 27752,"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": 2338707, "tid": 2379456, + "ts": 6197196773260.941, "dur": 2.643, + "args": { + "External id": 27753,"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": 2338707, "tid": 2379456, + "ts": 6197196773262.182, "dur": 1.297, + "args": { + "External id": 27754,"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": 2338707, "tid": 2379456, + "ts": 6197196773285.395, "dur": 19.209, + "args": { + "External id": 27755,"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": 2338707, "tid": 2379456, + "ts": 6197196773325.970, "dur": 9.911, + "args": { + "External id": 27756,"Record function id": 0, "Ev Idx": 619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197196773328.548, "dur": 6.635, + "args": { + "External id": 27757,"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": 2338707, "tid": 2379456, + "ts": 6197196773330.938, "dur": 3.082, + "args": { + "External id": 27758,"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": 2338707, "tid": 2379456, + "ts": 6197196773332.044, "dur": 1.835, + "args": { + "External id": 27759,"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": 2338707, "tid": 2379456, + "ts": 6197196773342.412, "dur": 7.563, + "args": { + "External id": 27760,"Record function id": 0, "Sequence number": 479923, "Fwd thread id": 1, "Ev Idx": 623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196773344.287, "dur": 1.232, + "args": { + "External id": 27761,"Sequence number": 479923, "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": 2338707, "tid": 2379456, "ts": 6197196773344.287, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SwiGLULinearFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197196773354.429, "dur": 455.872, + "args": { + "External id": 27762,"Record function id": 0, "Sequence number": 479922, "Fwd thread id": 1, "Ev Idx": 625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197196773356.322, "dur": 441.132, + "args": { + "External id": 27763,"Sequence number": 479922, "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": 2338707, "tid": 2379456, "ts": 6197196773356.322, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196773390.366, "dur": 8.948, + "args": { + "External id": 27764,"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": 2338707, "tid": 2379456, + "ts": 6197196773395.848, "dur": 3.186, + "args": { + "External id": 27765,"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": 2338707, "tid": 2379456, + "ts": 6197196773402.485, "dur": 5.341, + "args": { + "External id": 27766,"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": 2338707, "tid": 2379456, + "ts": 6197196773403.935, "dur": 3.247, + "args": { + "External id": 27767,"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": 2338707, "tid": 2379456, + "ts": 6197196773406.104, "dur": 0.837, + "args": { + "External id": 27768,"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": 2338707, "tid": 2379456, + "ts": 6197196773413.259, "dur": 94.553, + "args": { + "External id": 27769,"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": 2338707, "tid": 2379456, + "ts": 6197196773414.178, "dur": 3.179, + "args": { + "External id": 27770,"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": 2338707, "tid": 2379456, + "ts": 6197196773414.812, "dur": 2.034, + "args": { + "External id": 27771,"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": 2338707, "tid": 2379456, + "ts": 6197196773416.202, "dur": 0.538, + "args": { + "External id": 27772,"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": 2338707, "tid": 2379456, + "ts": 6197196773418.641, "dur": 88.658, + "args": { + "External id": 27773,"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": 2338707, "tid": 2379456, + "ts": 6197196773420.277, "dur": 86.170, + "args": { + "External id": 27774,"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": 2338707, "tid": 2379456, + "ts": 6197196773511.492, "dur": 5.611, + "args": { + "External id": 27775,"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": 2338707, "tid": 2379456, + "ts": 6197196773515.435, "dur": 1.561, + "args": { + "External id": 27776,"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": 2338707, "tid": 2379456, + "ts": 6197196773549.958, "dur": 7.491, + "args": { + "External id": 27777,"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": 2338707, "tid": 2379456, + "ts": 6197196773558.964, "dur": 1.488, + "args": { + "External id": 27778,"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": 2338707, "tid": 2379456, + "ts": 6197196773561.739, "dur": 1.540, + "args": { + "External id": 27779,"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": 2338707, "tid": 2379456, + "ts": 6197196773602.193, "dur": 2.751, + "args": { + "External id": 27780,"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": 2338707, "tid": 2379456, + "ts": 6197196773603.520, "dur": 1.291, + "args": { + "External id": 27781,"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": 2338707, "tid": 2379456, + "ts": 6197196773628.600, "dur": 147.842, + "args": { + "External id": 27782,"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": 2338707, "tid": 2379456, + "ts": 6197196773633.646, "dur": 7.247, + "args": { + "External id": 27783,"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": 2338707, "tid": 2379456, + "ts": 6197196773637.577, "dur": 2.449, + "args": { + "External id": 27784,"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": 2338707, "tid": 2379456, + "ts": 6197196773642.725, "dur": 4.773, + "args": { + "External id": 27785,"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": 2338707, "tid": 2379456, + "ts": 6197196773646.339, "dur": 0.538, + "args": { + "External id": 27786,"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": 2338707, "tid": 2379456, + "ts": 6197196773648.721, "dur": 3.197, + "args": { + "External id": 27787,"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": 2338707, "tid": 2379456, + "ts": 6197196773651.161, "dur": 0.421, + "args": { + "External id": 27788,"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": 2338707, "tid": 2379456, + "ts": 6197196773653.109, "dur": 3.156, + "args": { + "External id": 27789,"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": 2338707, "tid": 2379456, + "ts": 6197196773655.443, "dur": 0.372, + "args": { + "External id": 27790,"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": 2338707, "tid": 2379456, + "ts": 6197196773659.956, "dur": 4.899, + "args": { + "External id": 27791,"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": 2338707, "tid": 2379456, + "ts": 6197196773662.118, "dur": 2.417, + "args": { + "External id": 27792,"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": 2338707, "tid": 2379456, + "ts": 6197196773668.143, "dur": 5.730, + "args": { + "External id": 27793,"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": 2338707, "tid": 2379456, + "ts": 6197196773671.932, "dur": 1.737, + "args": { + "External id": 27794,"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": 2338707, "tid": 2379456, + "ts": 6197196773675.117, "dur": 2.836, + "args": { + "External id": 27795,"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": 2338707, "tid": 2379456, + "ts": 6197196773677.217, "dur": 0.401, + "args": { + "External id": 27796,"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": 2338707, "tid": 2379456, + "ts": 6197196773679.064, "dur": 3.531, + "args": { + "External id": 27797,"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": 2338707, "tid": 2379456, + "ts": 6197196773680.188, "dur": 2.305, + "args": { + "External id": 27798,"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": 2338707, "tid": 2379456, + "ts": 6197196773683.801, "dur": 77.890, + "args": { + "External id": 27799,"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": 2338707, "tid": 2379456, + "ts": 6197196773764.687, "dur": 1.787, + "args": { + "External id": 27800,"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": 2338707, "tid": 2379456, + "ts": 6197196773767.981, "dur": 3.768, + "args": { + "External id": 27801,"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": 2338707, "tid": 2379456, + "ts": 6197196773770.700, "dur": 0.603, + "args": { + "External id": 27802,"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": 2338707, "tid": 2379456, + "ts": 6197196773774.431, "dur": 0.862, + "args": { + "External id": 27803,"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": 2338707, "tid": 2379456, + "ts": 6197196773822.334, "dur": 10.146, + "args": { + "External id": 27804,"Record function id": 0, "Ev Idx": 667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197196773825.198, "dur": 6.469, + "args": { + "External id": 27805,"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": 2338707, "tid": 2379456, + "ts": 6197196773827.535, "dur": 3.306, + "args": { + "External id": 27806,"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": 2338707, "tid": 2379456, + "ts": 6197196773828.602, "dur": 2.115, + "args": { + "External id": 27807,"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": 2338707, "tid": 2379456, + "ts": 6197196773836.941, "dur": 9.008, + "args": { + "External id": 27808,"Record function id": 0, "Sequence number": 479921, "Fwd thread id": 1, "Ev Idx": 671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196773838.652, "dur": 4.376, + "args": { + "External id": 27809,"Sequence number": 479921, "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": 2338707, "tid": 2379456, "ts": 6197196773838.652, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196773840.627, "dur": 2.162, + "args": { + "External id": 27810,"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": 2338707, "tid": 2379456, + "ts": 6197196773841.420, "dur": 1.219, + "args": { + "External id": 27811,"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": 2338707, "tid": 2379456, + "ts": 6197196773849.437, "dur": 119.843, + "args": { + "External id": 27812,"Record function id": 0, "Sequence number": 479920, "Fwd thread id": 1, "Ev Idx": 675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196773852.579, "dur": 109.715, + "args": { + "External id": 27813,"Sequence number": 479920, "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": 2338707, "tid": 2379456, "ts": 6197196773852.579, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197196773856.508, "dur": 4.819, + "args": { + "External id": 27814,"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": 2338707, "tid": 2379456, + "ts": 6197196773857.944, "dur": 2.797, + "args": { + "External id": 27815,"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": 2338707, "tid": 2379456, + "ts": 6197196773860.114, "dur": 0.437, + "args": { + "External id": 27816,"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": 2338707, "tid": 2379456, + "ts": 6197196773862.537, "dur": 43.597, + "args": { + "External id": 27817,"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": 2338707, "tid": 2379456, + "ts": 6197196773907.300, "dur": 8.748, + "args": { + "External id": 27818,"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": 2338707, "tid": 2379456, + "ts": 6197196773908.063, "dur": 7.330, + "args": { + "External id": 27819,"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": 2338707, "tid": 2379456, + "ts": 6197196773911.721, "dur": 3.487, + "args": { + "External id": 27820,"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": 2338707, "tid": 2379456, + "ts": 6197196773917.997, "dur": 7.578, + "args": { + "External id": 27821,"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": 2338707, "tid": 2379456, + "ts": 6197196773922.821, "dur": 2.243, + "args": { + "External id": 27822,"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": 2338707, "tid": 2379456, + "ts": 6197196773924.428, "dur": 0.532, + "args": { + "External id": 27823,"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": 2338707, "tid": 2379456, + "ts": 6197196773926.328, "dur": 34.980, + "args": { + "External id": 27824,"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": 2338707, "tid": 2379456, + "ts": 6197196773974.488, "dur": 10.236, + "args": { + "External id": 27825,"Record function id": 0, "Sequence number": 479919, "Fwd thread id": 1, "Ev Idx": 688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196773975.644, "dur": 7.411, + "args": { + "External id": 27826,"Sequence number": 479919, "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": 2338707, "tid": 2379456, "ts": 6197196773975.644, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196773980.624, "dur": 2.263, + "args": { + "External id": 27827,"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": 2338707, "tid": 2379456, + "ts": 6197196773981.737, "dur": 1.058, + "args": { + "External id": 27828,"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": 2338707, "tid": 2379456, + "ts": 6197196773988.967, "dur": 8.901, + "args": { + "External id": 27829,"Record function id": 0, "Sequence number": 479918, "Fwd thread id": 1, "Ev Idx": 692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196773989.951, "dur": 5.029, + "args": { + "External id": 27830,"Sequence number": 479918, "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": 2338707, "tid": 2379456, "ts": 6197196773989.951, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197196773991.032, "dur": 3.719, + "args": { + "External id": 27831,"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": 2338707, "tid": 2379456, + "ts": 6197196773991.835, "dur": 2.386, + "args": { + "External id": 27832,"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": 2338707, "tid": 2379456, + "ts": 6197196773993.613, "dur": 0.522, + "args": { + "External id": 27833,"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": 2338707, "tid": 2379456, + "ts": 6197196774001.884, "dur": 7.940, + "args": { + "External id": 27834,"Record function id": 0, "Ev Idx": 697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197196774003.836, "dur": 5.509, + "args": { + "External id": 27835,"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": 2338707, "tid": 2379456, + "ts": 6197196774005.102, "dur": 3.992, + "args": { + "External id": 27836,"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": 2338707, "tid": 2379456, + "ts": 6197196774007.833, "dur": 1.145, + "args": { + "External id": 27837,"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": 2338707, "tid": 2379456, + "ts": 6197196774013.427, "dur": 6.663, + "args": { + "External id": 27838,"Record function id": 0, "Sequence number": 479917, "Fwd thread id": 1, "Ev Idx": 701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196774015.297, "dur": 2.838, + "args": { + "External id": 27839,"Sequence number": 479917, "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": 2338707, "tid": 2379456, "ts": 6197196774015.297, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196774016.438, "dur": 1.540, + "args": { + "External id": 27840,"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": 2338707, "tid": 2379456, + "ts": 6197196774017.177, "dur": 0.674, + "args": { + "External id": 27841,"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": 2338707, "tid": 2379456, + "ts": 6197196774023.277, "dur": 163.352, + "args": { + "External id": 27842,"Record function id": 0, "Sequence number": 479916, "Fwd thread id": 1, "Ev Idx": 705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196774024.224, "dur": 150.689, + "args": { + "External id": 27843,"Sequence number": 479916, "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": 2338707, "tid": 2379456, "ts": 6197196774024.224, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197196774027.446, "dur": 6.080, + "args": { + "External id": 27844,"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": 2338707, "tid": 2379456, + "ts": 6197196774028.201, "dur": 4.894, + "args": { + "External id": 27845,"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": 2338707, "tid": 2379456, + "ts": 6197196774032.448, "dur": 0.554, + "args": { + "External id": 27846,"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": 2338707, "tid": 2379456, + "ts": 6197196774034.246, "dur": 84.314, + "args": { + "External id": 27847,"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": 2338707, "tid": 2379456, + "ts": 6197196774121.287, "dur": 5.503, + "args": { + "External id": 27848,"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": 2338707, "tid": 2379456, + "ts": 6197196774122.335, "dur": 3.627, + "args": { + "External id": 27849,"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": 2338707, "tid": 2379456, + "ts": 6197196774124.627, "dur": 1.218, + "args": { + "External id": 27850,"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": 2338707, "tid": 2379456, + "ts": 6197196774128.391, "dur": 6.631, + "args": { + "External id": 27851,"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": 2338707, "tid": 2379456, + "ts": 6197196774132.325, "dur": 2.020, + "args": { + "External id": 27852,"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": 2338707, "tid": 2379456, + "ts": 6197196774133.782, "dur": 0.452, + "args": { + "External id": 27853,"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": 2338707, "tid": 2379456, + "ts": 6197196774135.642, "dur": 38.623, + "args": { + "External id": 27854,"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": 2338707, "tid": 2379456, + "ts": 6197196774193.784, "dur": 31.392, + "args": { + "External id": 27855,"Record function id": 0, "Sequence number": 479915, "Fwd thread id": 1, "Ev Idx": 718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196774194.984, "dur": 4.746, + "args": { + "External id": 27856,"Sequence number": 479915, "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": 2338707, "tid": 2379456, "ts": 6197196774194.984, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196774196.721, "dur": 2.882, + "args": { + "External id": 27857,"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": 2338707, "tid": 2379456, + "ts": 6197196774198.013, "dur": 1.472, + "args": { + "External id": 27858,"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": 2338707, "tid": 2379456, + "ts": 6197196774202.796, "dur": 19.606, + "args": { + "External id": 27859,"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": 2338707, "tid": 2379456, + "ts": 6197196774228.857, "dur": 10.507, + "args": { + "External id": 27860,"Record function id": 0, "Sequence number": 479914, "Fwd thread id": 1, "Ev Idx": 723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196774229.865, "dur": 7.233, + "args": { + "External id": 27861,"Sequence number": 479914, "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": 2338707, "tid": 2379456, "ts": 6197196774229.865, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197196774233.000, "dur": 3.889, + "args": { + "External id": 27862,"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": 2338707, "tid": 2379456, + "ts": 6197196774233.896, "dur": 2.435, + "args": { + "External id": 27863,"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": 2338707, "tid": 2379456, + "ts": 6197196774235.442, "dur": 0.761, + "args": { + "External id": 27864,"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": 2338707, "tid": 2379456, + "ts": 6197196774243.669, "dur": 8.919, + "args": { + "External id": 27865,"Record function id": 0, "Ev Idx": 728 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197196774245.587, "dur": 6.504, + "args": { + "External id": 27866,"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": 2338707, "tid": 2379456, + "ts": 6197196774247.256, "dur": 4.397, + "args": { + "External id": 27867,"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": 2338707, "tid": 2379456, + "ts": 6197196774247.977, "dur": 3.583, + "args": { + "External id": 27868,"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": 2338707, "tid": 2379456, + "ts": 6197196774259.426, "dur": 419.815, + "args": { + "External id": 27869,"Record function id": 0, "Sequence number": 479913, "Fwd thread id": 1, "Ev Idx": 732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197196774261.604, "dur": 383.463, + "args": { + "External id": 27870,"Sequence number": 479913, "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": 2338707, "tid": 2379456, "ts": 6197196774261.604, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338707, "tid": 2379456, + "ts": 6197196774286.033, "dur": 34.019, + "args": { + "External id": 27871,"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": 2338707, "tid": 2379456, + "ts": 6197196774287.709, "dur": 32.059, + "args": { + "External id": 27872,"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": 2338707, "tid": 2379456, + "ts": 6197196774290.797, "dur": 6.435, + "args": { + "External id": 27873,"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": 2338707, "tid": 2379456, + "ts": 6197196774293.539, "dur": 3.208, + "args": { + "External id": 27874,"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": 2338707, "tid": 2379456, + "ts": 6197196774298.466, "dur": 20.801, + "args": { + "External id": 27875,"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": 2338707, "tid": 2379456, + "ts": 6197196774334.729, "dur": 2.397, + "args": { + "External id": 27876,"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": 2338707, "tid": 2379456, + "ts": 6197196774335.806, "dur": 1.176, + "args": { + "External id": 27877,"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": 2338707, "tid": 2379456, + "ts": 6197196774341.423, "dur": 1.853, + "args": { + "External id": 27878,"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": 2338707, "tid": 2379456, + "ts": 6197196774342.316, "dur": 0.877, + "args": { + "External id": 27879,"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": 2338707, "tid": 2379456, + "ts": 6197196774358.320, "dur": 2.459, + "args": { + "External id": 27880,"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": 2338707, "tid": 2379456, + "ts": 6197196774371.844, "dur": 2.477, + "args": { + "External id": 27881,"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": 2338707, "tid": 2379456, + "ts": 6197196774536.350, "dur": 2.042, + "args": { + "External id": 27882,"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": 2338707, "tid": 2379456, + "ts": 6197196774542.325, "dur": 36.265, + "args": { + "External id": 27883,"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": 2338707, "tid": 2379456, + "ts": 6197196774553.184, "dur": 2.721, + "args": { + "External id": 27884,"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": 2338707, "tid": 2379456, + "ts": 6197196774583.741, "dur": 29.617, + "args": { + "External id": 27885,"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": 2338707, "tid": 2379456, + "ts": 6197196774585.460, "dur": 27.675, + "args": { + "External id": 27886,"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": 2338707, "tid": 2379456, + "ts": 6197196774589.882, "dur": 3.758, + "args": { + "External id": 27887,"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": 2338707, "tid": 2379456, + "ts": 6197196774597.185, "dur": 15.392, + "args": { + "External id": 27888,"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": 2338707, "tid": 2379456, + "ts": 6197196774618.007, "dur": 2.353, + "args": { + "External id": 27889,"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": 2338707, "tid": 2379456, + "ts": 6197196774619.208, "dur": 1.023, + "args": { + "External id": 27890,"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": 2338707, "tid": 2379456, + "ts": 6197196774627.750, "dur": 2.462, + "args": { + "External id": 27891,"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": 2338707, "tid": 2379456, + "ts": 6197196774628.965, "dur": 1.156, + "args": { + "External id": 27892,"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": 2338707, "tid": 2379456, + "ts": 6197196774632.561, "dur": 2.299, + "args": { + "External id": 27893,"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": 2338707, "tid": 2379456, + "ts": 6197196774633.958, "dur": 0.803, + "args": { + "External id": 27894,"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": 2338707, "tid": 2379456, + "ts": 6197196774660.412, "dur": 17.238, + "args": { + "External id": 27895,"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": 2338707, "tid": 2379456, + "ts": 6197196774688.647, "dur": 7.917, + "args": { + "External id": 27896,"Record function id": 0, "Ev Idx": 759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197196774691.360, "dur": 4.558, + "args": { + "External id": 27897,"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": 2338707, "tid": 2379456, + "ts": 6197196774692.834, "dur": 2.195, + "args": { + "External id": 27898,"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": 2338707, "tid": 2379456, + "ts": 6197196774693.512, "dur": 1.410, + "args": { + "External id": 27899,"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": 2338707, "tid": 2379456, + "ts": 6197196774719.268, "dur": 13.517, + "args": { + "External id": 27900,"Record function id": 0, "Sequence number": 479912, "Fwd thread id": 1, "Ev Idx": 763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196774721.777, "dur": 7.728, + "args": { + "External id": 27901,"Sequence number": 479912, "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": 2338707, "tid": 2379456, "ts": 6197196774721.777, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196774723.917, "dur": 5.392, + "args": { + "External id": 27902,"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": 2338707, "tid": 2379456, + "ts": 6197196774727.162, "dur": 1.915, + "args": { + "External id": 27903,"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": 2338707, "tid": 2379456, + "ts": 6197196774737.341, "dur": 147.539, + "args": { + "External id": 27904,"Record function id": 0, "Sequence number": 479911, "Fwd thread id": 1, "Ev Idx": 767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196774738.486, "dur": 138.317, + "args": { + "External id": 27905,"Sequence number": 479911, "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": 2338707, "tid": 2379456, "ts": 6197196774738.486, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197196774743.034, "dur": 5.536, + "args": { + "External id": 27906,"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": 2338707, "tid": 2379456, + "ts": 6197196774744.820, "dur": 3.146, + "args": { + "External id": 27907,"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": 2338707, "tid": 2379456, + "ts": 6197196774746.828, "dur": 0.968, + "args": { + "External id": 27908,"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": 2338707, "tid": 2379456, + "ts": 6197196774749.825, "dur": 72.061, + "args": { + "External id": 27909,"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": 2338707, "tid": 2379456, + "ts": 6197196774823.213, "dur": 6.374, + "args": { + "External id": 27910,"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": 2338707, "tid": 2379456, + "ts": 6197196774826.372, "dur": 2.561, + "args": { + "External id": 27911,"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": 2338707, "tid": 2379456, + "ts": 6197196774828.110, "dur": 0.708, + "args": { + "External id": 27912,"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": 2338707, "tid": 2379456, + "ts": 6197196774831.272, "dur": 4.090, + "args": { + "External id": 27913,"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": 2338707, "tid": 2379456, + "ts": 6197196774832.760, "dur": 2.109, + "args": { + "External id": 27914,"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": 2338707, "tid": 2379456, + "ts": 6197196774834.505, "dur": 0.297, + "args": { + "External id": 27915,"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": 2338707, "tid": 2379456, + "ts": 6197196774836.119, "dur": 39.786, + "args": { + "External id": 27916,"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": 2338707, "tid": 2379456, + "ts": 6197196774889.767, "dur": 11.473, + "args": { + "External id": 27917,"Record function id": 0, "Sequence number": 479910, "Fwd thread id": 1, "Ev Idx": 780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196774891.125, "dur": 6.971, + "args": { + "External id": 27918,"Sequence number": 479910, "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": 2338707, "tid": 2379456, "ts": 6197196774891.125, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196774892.909, "dur": 5.023, + "args": { + "External id": 27919,"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": 2338707, "tid": 2379456, + "ts": 6197196774896.654, "dur": 1.177, + "args": { + "External id": 27920,"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": 2338707, "tid": 2379456, + "ts": 6197196774904.773, "dur": 7.327, + "args": { + "External id": 27921,"Record function id": 0, "Sequence number": 479909, "Fwd thread id": 1, "Ev Idx": 784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196774905.578, "dur": 4.621, + "args": { + "External id": 27922,"Sequence number": 479909, "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": 2338707, "tid": 2379456, "ts": 6197196774905.578, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197196774906.535, "dur": 3.423, + "args": { + "External id": 27923,"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": 2338707, "tid": 2379456, + "ts": 6197196774907.223, "dur": 2.270, + "args": { + "External id": 27924,"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": 2338707, "tid": 2379456, + "ts": 6197196774908.869, "dur": 0.494, + "args": { + "External id": 27925,"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": 2338707, "tid": 2379456, + "ts": 6197196774916.439, "dur": 6.789, + "args": { + "External id": 27926,"Record function id": 0, "Ev Idx": 789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197196774918.540, "dur": 4.117, + "args": { + "External id": 27927,"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": 2338707, "tid": 2379456, + "ts": 6197196774920.033, "dur": 2.293, + "args": { + "External id": 27928,"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": 2338707, "tid": 2379456, + "ts": 6197196774920.716, "dur": 1.518, + "args": { + "External id": 27929,"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": 2338707, "tid": 2379456, + "ts": 6197196774926.317, "dur": 10.713, + "args": { + "External id": 27930,"Record function id": 0, "Sequence number": 479908, "Fwd thread id": 1, "Ev Idx": 793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196774929.779, "dur": 3.911, + "args": { + "External id": 27931,"Sequence number": 479908, "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": 2338707, "tid": 2379456, "ts": 6197196774929.779, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196774931.256, "dur": 2.275, + "args": { + "External id": 27932,"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": 2338707, "tid": 2379456, + "ts": 6197196774932.027, "dur": 1.366, + "args": { + "External id": 27933,"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": 2338707, "tid": 2379456, + "ts": 6197196774941.567, "dur": 421.704, + "args": { + "External id": 27934,"Record function id": 0, "Sequence number": 479907, "Fwd thread id": 1, "Ev Idx": 797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFuncBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197196774943.346, "dur": 396.420, + "args": { + "External id": 27935,"Sequence number": 479907, "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": 2338707, "tid": 2379456, "ts": 6197196774943.346, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338707, "tid": 2379456, + "ts": 6197196774961.668, "dur": 6.990, + "args": { + "External id": 27936,"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": 2338707, "tid": 2379456, + "ts": 6197196774964.613, "dur": 3.601, + "args": { + "External id": 27937,"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": 2338707, "tid": 2379456, + "ts": 6197196774970.881, "dur": 4.079, + "args": { + "External id": 27938,"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": 2338707, "tid": 2379456, + "ts": 6197196774972.999, "dur": 1.778, + "args": { + "External id": 27939,"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": 2338707, "tid": 2379456, + "ts": 6197196774976.629, "dur": 4.518, + "args": { + "External id": 27940,"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": 2338707, "tid": 2379456, + "ts": 6197196774978.873, "dur": 2.101, + "args": { + "External id": 27941,"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": 2338707, "tid": 2379456, + "ts": 6197196775007.565, "dur": 306.356, + "args": { + "External id": 27942,"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": 2338707, "tid": 2379456, + "ts": 6197196775141.162, "dur": 7.621, + "args": { + "External id": 27943,"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": 2338707, "tid": 2379456, + "ts": 6197196775151.130, "dur": 3.705, + "args": { + "External id": 27944,"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": 2338707, "tid": 2379456, + "ts": 6197196775158.304, "dur": 1.737, + "args": { + "External id": 27945,"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": 2338707, "tid": 2379456, + "ts": 6197196775161.275, "dur": 2.191, + "args": { + "External id": 27946,"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": 2338707, "tid": 2379456, + "ts": 6197196775211.088, "dur": 3.194, + "args": { + "External id": 27947,"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": 2338707, "tid": 2379456, + "ts": 6197196775212.462, "dur": 1.690, + "args": { + "External id": 27948,"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": 2338707, "tid": 2379456, + "ts": 6197196775216.122, "dur": 31.163, + "args": { + "External id": 27949,"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": 2338707, "tid": 2379456, + "ts": 6197196775224.145, "dur": 1.116, + "args": { + "External id": 27950,"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": 2338707, "tid": 2379456, + "ts": 6197196775248.705, "dur": 1.347, + "args": { + "External id": 27951,"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": 2338707, "tid": 2379456, + "ts": 6197196775249.511, "dur": 0.471, + "args": { + "External id": 27952,"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": 2338707, "tid": 2379456, + "ts": 6197196775251.148, "dur": 16.021, + "args": { + "External id": 27953,"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": 2338707, "tid": 2379456, + "ts": 6197196775253.312, "dur": 2.468, + "args": { + "External id": 27954,"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": 2338707, "tid": 2379456, + "ts": 6197196775326.816, "dur": 3.955, + "args": { + "External id": 27955,"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": 2338707, "tid": 2379456, + "ts": 6197196775333.504, "dur": 0.889, + "args": { + "External id": 27956,"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": 2338707, "tid": 2379456, + "ts": 6197196775336.358, "dur": 0.699, + "args": { + "External id": 27957,"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": 2338707, "tid": 2379456, + "ts": 6197196775373.589, "dur": 219.143, + "args": { + "External id": 27958,"Record function id": 0, "Sequence number": 479906, "Fwd thread id": 1, "Ev Idx": 821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197196775375.922, "dur": 209.193, + "args": { + "External id": 27959,"Sequence number": 479906, "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": 2338707, "tid": 2379456, "ts": 6197196775375.922, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338707, "tid": 2379456, + "ts": 6197196775396.496, "dur": 41.342, + "args": { + "External id": 27960,"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": 2338707, "tid": 2379456, + "ts": 6197196775400.028, "dur": 3.595, + "args": { + "External id": 27961,"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": 2338707, "tid": 2379456, + "ts": 6197196775405.143, "dur": 32.210, + "args": { + "External id": 27962,"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": 2338707, "tid": 2379456, + "ts": 6197196775448.278, "dur": 4.822, + "args": { + "External id": 27963,"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": 2338707, "tid": 2379456, + "ts": 6197196775450.488, "dur": 2.291, + "args": { + "External id": 27964,"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": 2338707, "tid": 2379456, + "ts": 6197196775599.937, "dur": 195.681, + "args": { + "External id": 27965,"Record function id": 0, "Sequence number": 479905, "Fwd thread id": 1, "Ev Idx": 828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197196775602.247, "dur": 184.748, + "args": { + "External id": 27966,"Sequence number": 479905, "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": 2338707, "tid": 2379456, "ts": 6197196775602.247, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338707, "tid": 2379456, + "ts": 6197196775613.972, "dur": 47.699, + "args": { + "External id": 27967,"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": 2338707, "tid": 2379456, + "ts": 6197196775616.400, "dur": 3.197, + "args": { + "External id": 27968,"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": 2338707, "tid": 2379456, + "ts": 6197196775620.784, "dur": 40.279, + "args": { + "External id": 27969,"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": 2338707, "tid": 2379456, + "ts": 6197196775668.612, "dur": 6.799, + "args": { + "External id": 27970,"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": 2338707, "tid": 2379456, + "ts": 6197196775670.694, "dur": 4.429, + "args": { + "External id": 27971,"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": 2338707, "tid": 2379456, + "ts": 6197196775804.672, "dur": 14.071, + "args": { + "External id": 27972,"Record function id": 0, "Sequence number": 479904, "Fwd thread id": 1, "Ev Idx": 835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196775806.410, "dur": 9.559, + "args": { + "External id": 27973,"Sequence number": 479904, "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": 2338707, "tid": 2379456, "ts": 6197196775806.410, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196775809.770, "dur": 5.865, + "args": { + "External id": 27974,"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": 2338707, "tid": 2379456, + "ts": 6197196775811.354, "dur": 4.081, + "args": { + "External id": 27975,"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": 2338707, "tid": 2379456, + "ts": 6197196775822.899, "dur": 6.556, + "args": { + "External id": 27976,"Record function id": 0, "Sequence number": 479903, "Fwd thread id": 1, "Ev Idx": 839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196775823.677, "dur": 3.661, + "args": { + "External id": 27977,"Sequence number": 479903, "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": 2338707, "tid": 2379456, "ts": 6197196775823.677, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196775825.350, "dur": 1.858, + "args": { + "External id": 27978,"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": 2338707, "tid": 2379456, + "ts": 6197196775826.306, "dur": 0.796, + "args": { + "External id": 27979,"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": 2338707, "tid": 2379456, + "ts": 6197196775835.205, "dur": 8.531, + "args": { + "External id": 27980,"Record function id": 0, "Sequence number": 479902, "Fwd thread id": 1, "Ev Idx": 843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196775838.128, "dur": 3.735, + "args": { + "External id": 27981,"Sequence number": 479902, "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": 2338707, "tid": 2379456, "ts": 6197196775838.128, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196775839.410, "dur": 2.296, + "args": { + "External id": 27982,"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": 2338707, "tid": 2379456, + "ts": 6197196775840.444, "dur": 1.178, + "args": { + "External id": 27983,"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": 2338707, "tid": 2379456, + "ts": 6197196775847.652, "dur": 6.933, + "args": { + "External id": 27984,"Record function id": 0, "Sequence number": 479901, "Fwd thread id": 1, "Ev Idx": 847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196775849.354, "dur": 3.096, + "args": { + "External id": 27985,"Sequence number": 479901, "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": 2338707, "tid": 2379456, "ts": 6197196775849.354, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196775850.583, "dur": 1.713, + "args": { + "External id": 27986,"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": 2338707, "tid": 2379456, + "ts": 6197196775851.165, "dur": 1.042, + "args": { + "External id": 27987,"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": 2338707, "tid": 2379456, + "ts": 6197196775858.089, "dur": 153.788, + "args": { + "External id": 27988,"Record function id": 0, "Sequence number": 479900, "Fwd thread id": 1, "Ev Idx": 851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196775858.859, "dur": 146.924, + "args": { + "External id": 27989,"Sequence number": 479900, "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": 2338707, "tid": 2379456, "ts": 6197196775858.859, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197196775865.352, "dur": 6.639, + "args": { + "External id": 27990,"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": 2338707, "tid": 2379456, + "ts": 6197196775867.265, "dur": 4.060, + "args": { + "External id": 27991,"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": 2338707, "tid": 2379456, + "ts": 6197196775869.443, "dur": 1.630, + "args": { + "External id": 27992,"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": 2338707, "tid": 2379456, + "ts": 6197196775873.909, "dur": 69.815, + "args": { + "External id": 27993,"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": 2338707, "tid": 2379456, + "ts": 6197196775945.219, "dur": 7.252, + "args": { + "External id": 27994,"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": 2338707, "tid": 2379456, + "ts": 6197196775945.868, "dur": 5.822, + "args": { + "External id": 27995,"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": 2338707, "tid": 2379456, + "ts": 6197196775950.386, "dur": 1.107, + "args": { + "External id": 27996,"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": 2338707, "tid": 2379456, + "ts": 6197196775954.547, "dur": 6.314, + "args": { + "External id": 27997,"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": 2338707, "tid": 2379456, + "ts": 6197196775955.880, "dur": 4.376, + "args": { + "External id": 27998,"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": 2338707, "tid": 2379456, + "ts": 6197196775957.543, "dur": 2.647, + "args": { + "External id": 27999,"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": 2338707, "tid": 2379456, + "ts": 6197196775961.416, "dur": 43.194, + "args": { + "External id": 28000,"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": 2338707, "tid": 2379456, + "ts": 6197196776016.733, "dur": 10.296, + "args": { + "External id": 28001,"Record function id": 0, "Sequence number": 479899, "Fwd thread id": 1, "Ev Idx": 864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196776017.739, "dur": 7.248, + "args": { + "External id": 28002,"Sequence number": 479899, "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": 2338707, "tid": 2379456, "ts": 6197196776017.739, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196776019.946, "dur": 4.885, + "args": { + "External id": 28003,"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": 2338707, "tid": 2379456, + "ts": 6197196776023.757, "dur": 0.936, + "args": { + "External id": 28004,"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": 2338707, "tid": 2379456, + "ts": 6197196776030.283, "dur": 9.690, + "args": { + "External id": 28005,"Record function id": 0, "Sequence number": 479898, "Fwd thread id": 1, "Ev Idx": 868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196776031.443, "dur": 5.469, + "args": { + "External id": 28006,"Sequence number": 479898, "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": 2338707, "tid": 2379456, "ts": 6197196776031.443, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197196776032.573, "dur": 4.103, + "args": { + "External id": 28007,"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": 2338707, "tid": 2379456, + "ts": 6197196776033.299, "dur": 2.862, + "args": { + "External id": 28008,"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": 2338707, "tid": 2379456, + "ts": 6197196776035.617, "dur": 0.426, + "args": { + "External id": 28009,"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": 2338707, "tid": 2379456, + "ts": 6197196776045.666, "dur": 48.756, + "args": { + "External id": 28010,"Record function id": 0, "Ev Idx": 873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197196776047.873, "dur": 44.926, + "args": { + "External id": 28011,"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": 2338707, "tid": 2379456, + "ts": 6197196776050.288, "dur": 41.919, + "args": { + "External id": 28012,"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": 2338707, "tid": 2379456, + "ts": 6197196776053.765, "dur": 37.941, + "args": { + "External id": 28013,"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": 2338707, "tid": 2379456, + "ts": 6197196776100.483, "dur": 9.144, + "args": { + "External id": 28014,"Record function id": 0, "Sequence number": 479897, "Fwd thread id": 1, "Ev Idx": 877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196776102.497, "dur": 4.309, + "args": { + "External id": 28015,"Sequence number": 479897, "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": 2338707, "tid": 2379456, "ts": 6197196776102.497, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196776104.180, "dur": 2.458, + "args": { + "External id": 28016,"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": 2338707, "tid": 2379456, + "ts": 6197196776105.164, "dur": 1.336, + "args": { + "External id": 28017,"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": 2338707, "tid": 2379456, + "ts": 6197196776112.713, "dur": 113.634, + "args": { + "External id": 28018,"Record function id": 0, "Sequence number": 479896, "Fwd thread id": 1, "Ev Idx": 881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196776113.981, "dur": 105.193, + "args": { + "External id": 28019,"Sequence number": 479896, "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": 2338707, "tid": 2379456, "ts": 6197196776113.981, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197196776117.256, "dur": 5.501, + "args": { + "External id": 28020,"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": 2338707, "tid": 2379456, + "ts": 6197196776117.875, "dur": 4.438, + "args": { + "External id": 28021,"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": 2338707, "tid": 2379456, + "ts": 6197196776121.549, "dur": 0.644, + "args": { + "External id": 28022,"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": 2338707, "tid": 2379456, + "ts": 6197196776123.593, "dur": 36.790, + "args": { + "External id": 28023,"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": 2338707, "tid": 2379456, + "ts": 6197196776161.708, "dur": 12.219, + "args": { + "External id": 28024,"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": 2338707, "tid": 2379456, + "ts": 6197196776167.146, "dur": 6.251, + "args": { + "External id": 28025,"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": 2338707, "tid": 2379456, + "ts": 6197196776168.891, "dur": 4.360, + "args": { + "External id": 28026,"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": 2338707, "tid": 2379456, + "ts": 6197196776175.225, "dur": 6.654, + "args": { + "External id": 28027,"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": 2338707, "tid": 2379456, + "ts": 6197196776179.032, "dur": 2.090, + "args": { + "External id": 28028,"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": 2338707, "tid": 2379456, + "ts": 6197196776180.464, "dur": 0.542, + "args": { + "External id": 28029,"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": 2338707, "tid": 2379456, + "ts": 6197196776182.291, "dur": 35.999, + "args": { + "External id": 28030,"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": 2338707, "tid": 2379456, + "ts": 6197196776231.040, "dur": 35.583, + "args": { + "External id": 28031,"Record function id": 0, "Sequence number": 479895, "Fwd thread id": 1, "Ev Idx": 894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196776232.028, "dur": 4.453, + "args": { + "External id": 28032,"Sequence number": 479895, "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": 2338707, "tid": 2379456, "ts": 6197196776232.028, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196776234.187, "dur": 2.156, + "args": { + "External id": 28033,"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": 2338707, "tid": 2379456, + "ts": 6197196776235.274, "dur": 0.945, + "args": { + "External id": 28034,"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": 2338707, "tid": 2379456, + "ts": 6197196776242.589, "dur": 21.551, + "args": { + "External id": 28035,"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": 2338707, "tid": 2379456, + "ts": 6197196776270.566, "dur": 15.241, + "args": { + "External id": 28036,"Record function id": 0, "Sequence number": 479894, "Fwd thread id": 1, "Ev Idx": 899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196776271.653, "dur": 11.120, + "args": { + "External id": 28037,"Sequence number": 479894, "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": 2338707, "tid": 2379456, "ts": 6197196776271.653, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197196776274.614, "dur": 7.960, + "args": { + "External id": 28038,"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": 2338707, "tid": 2379456, + "ts": 6197196776275.388, "dur": 6.679, + "args": { + "External id": 28039,"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": 2338707, "tid": 2379456, + "ts": 6197196776281.489, "dur": 0.432, + "args": { + "External id": 28040,"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": 2338707, "tid": 2379456, + "ts": 6197196776290.196, "dur": 6.979, + "args": { + "External id": 28041,"Record function id": 0, "Ev Idx": 904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197196776292.114, "dur": 4.512, + "args": { + "External id": 28042,"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": 2338707, "tid": 2379456, + "ts": 6197196776293.657, "dur": 2.387, + "args": { + "External id": 28043,"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": 2338707, "tid": 2379456, + "ts": 6197196776294.413, "dur": 1.486, + "args": { + "External id": 28044,"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": 2338707, "tid": 2379456, + "ts": 6197196776302.800, "dur": 10.618, + "args": { + "External id": 28045,"Record function id": 0, "Sequence number": 479893, "Fwd thread id": 1, "Ev Idx": 908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196776304.574, "dur": 5.345, + "args": { + "External id": 28046,"Sequence number": 479893, "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": 2338707, "tid": 2379456, "ts": 6197196776304.574, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196776305.880, "dur": 3.887, + "args": { + "External id": 28047,"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": 2338707, "tid": 2379456, + "ts": 6197196776308.739, "dur": 0.919, + "args": { + "External id": 28048,"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": 2338707, "tid": 2379456, + "ts": 6197196776316.649, "dur": 102.258, + "args": { + "External id": 28049,"Record function id": 0, "Sequence number": 479892, "Fwd thread id": 1, "Ev Idx": 912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196776317.369, "dur": 90.870, + "args": { + "External id": 28050,"Sequence number": 479892, "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": 2338707, "tid": 2379456, "ts": 6197196776317.369, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197196776320.070, "dur": 2.895, + "args": { + "External id": 28051,"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": 2338707, "tid": 2379456, + "ts": 6197196776320.619, "dur": 1.881, + "args": { + "External id": 28052,"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": 2338707, "tid": 2379456, + "ts": 6197196776321.908, "dur": 0.474, + "args": { + "External id": 28053,"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": 2338707, "tid": 2379456, + "ts": 6197196776323.548, "dur": 37.197, + "args": { + "External id": 28054,"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": 2338707, "tid": 2379456, + "ts": 6197196776363.684, "dur": 3.670, + "args": { + "External id": 28055,"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": 2338707, "tid": 2379456, + "ts": 6197196776364.201, "dur": 2.586, + "args": { + "External id": 28056,"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": 2338707, "tid": 2379456, + "ts": 6197196776366.087, "dur": 0.583, + "args": { + "External id": 28057,"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": 2338707, "tid": 2379456, + "ts": 6197196776368.823, "dur": 3.833, + "args": { + "External id": 28058,"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": 2338707, "tid": 2379456, + "ts": 6197196776369.927, "dur": 2.008, + "args": { + "External id": 28059,"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": 2338707, "tid": 2379456, + "ts": 6197196776371.343, "dur": 0.522, + "args": { + "External id": 28060,"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": 2338707, "tid": 2379456, + "ts": 6197196776375.079, "dur": 32.397, + "args": { + "External id": 28061,"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": 2338707, "tid": 2379456, + "ts": 6197196776423.368, "dur": 26.087, + "args": { + "External id": 28062,"Record function id": 0, "Sequence number": 479891, "Fwd thread id": 1, "Ev Idx": 925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196776424.293, "dur": 4.345, + "args": { + "External id": 28063,"Sequence number": 479891, "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": 2338707, "tid": 2379456, "ts": 6197196776424.293, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196776426.336, "dur": 2.123, + "args": { + "External id": 28064,"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": 2338707, "tid": 2379456, + "ts": 6197196776427.462, "dur": 0.877, + "args": { + "External id": 28065,"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": 2338707, "tid": 2379456, + "ts": 6197196776431.308, "dur": 15.985, + "args": { + "External id": 28066,"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": 2338707, "tid": 2379456, + "ts": 6197196776453.425, "dur": 11.807, + "args": { + "External id": 28067,"Record function id": 0, "Sequence number": 479890, "Fwd thread id": 1, "Ev Idx": 930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196776454.569, "dur": 8.126, + "args": { + "External id": 28068,"Sequence number": 479890, "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": 2338707, "tid": 2379456, "ts": 6197196776454.569, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197196776455.633, "dur": 6.818, + "args": { + "External id": 28069,"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": 2338707, "tid": 2379456, + "ts": 6197196776456.402, "dur": 5.520, + "args": { + "External id": 28070,"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": 2338707, "tid": 2379456, + "ts": 6197196776461.371, "dur": 0.396, + "args": { + "External id": 28071,"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": 2338707, "tid": 2379456, + "ts": 6197196776469.442, "dur": 5.167, + "args": { + "External id": 28072,"Record function id": 0, "Ev Idx": 935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197196776471.226, "dur": 2.896, + "args": { + "External id": 28073,"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": 2338707, "tid": 2379456, + "ts": 6197196776472.142, "dur": 1.720, + "args": { + "External id": 28074,"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": 2338707, "tid": 2379456, + "ts": 6197196776472.732, "dur": 1.005, + "args": { + "External id": 28075,"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": 2338707, "tid": 2379456, + "ts": 6197196776479.481, "dur": 387.658, + "args": { + "External id": 28076,"Record function id": 0, "Sequence number": 479889, "Fwd thread id": 1, "Ev Idx": 939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197196776481.443, "dur": 353.049, + "args": { + "External id": 28077,"Sequence number": 479889, "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": 2338707, "tid": 2379456, "ts": 6197196776481.443, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196776514.957, "dur": 1.936, + "args": { + "External id": 28078,"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": 2338707, "tid": 2379456, + "ts": 6197196776515.754, "dur": 0.995, + "args": { + "External id": 28079,"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": 2338707, "tid": 2379456, + "ts": 6197196776532.656, "dur": 5.854, + "args": { + "External id": 28080,"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": 2338707, "tid": 2379456, + "ts": 6197196776550.782, "dur": 2.413, + "args": { + "External id": 28081,"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": 2338707, "tid": 2379456, + "ts": 6197196776719.733, "dur": 3.009, + "args": { + "External id": 28082,"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": 2338707, "tid": 2379456, + "ts": 6197196776727.930, "dur": 41.300, + "args": { + "External id": 28083,"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": 2338707, "tid": 2379456, + "ts": 6197196776740.397, "dur": 1.039, + "args": { + "External id": 28084,"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": 2338707, "tid": 2379456, + "ts": 6197196776775.306, "dur": 32.200, + "args": { + "External id": 28085,"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": 2338707, "tid": 2379456, + "ts": 6197196776777.138, "dur": 30.161, + "args": { + "External id": 28086,"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": 2338707, "tid": 2379456, + "ts": 6197196776782.220, "dur": 4.267, + "args": { + "External id": 28087,"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": 2338707, "tid": 2379456, + "ts": 6197196776788.439, "dur": 18.293, + "args": { + "External id": 28088,"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": 2338707, "tid": 2379456, + "ts": 6197196776814.622, "dur": 2.948, + "args": { + "External id": 28089,"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": 2338707, "tid": 2379456, + "ts": 6197196776816.229, "dur": 1.197, + "args": { + "External id": 28090,"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": 2338707, "tid": 2379456, + "ts": 6197196776825.337, "dur": 2.354, + "args": { + "External id": 28091,"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": 2338707, "tid": 2379456, + "ts": 6197196776826.562, "dur": 1.005, + "args": { + "External id": 28092,"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": 2338707, "tid": 2379456, + "ts": 6197196776845.642, "dur": 17.029, + "args": { + "External id": 28093,"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": 2338707, "tid": 2379456, + "ts": 6197196776879.558, "dur": 11.495, + "args": { + "External id": 28094,"Record function id": 0, "Ev Idx": 957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197196776882.258, "dur": 7.996, + "args": { + "External id": 28095,"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": 2338707, "tid": 2379456, + "ts": 6197196776884.404, "dur": 4.695, + "args": { + "External id": 28096,"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": 2338707, "tid": 2379456, + "ts": 6197196776887.362, "dur": 1.635, + "args": { + "External id": 28097,"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": 2338707, "tid": 2379456, + "ts": 6197196776894.735, "dur": 6.506, + "args": { + "External id": 28098,"Record function id": 0, "Sequence number": 479888, "Fwd thread id": 1, "Ev Idx": 961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196776896.253, "dur": 1.498, + "args": { + "External id": 28099,"Sequence number": 479888, "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": 2338707, "tid": 2379456, "ts": 6197196776896.253, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SwiGLULinearFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197196776905.516, "dur": 485.678, + "args": { + "External id": 28100,"Record function id": 0, "Sequence number": 479887, "Fwd thread id": 1, "Ev Idx": 963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197196776907.523, "dur": 468.637, + "args": { + "External id": 28101,"Sequence number": 479887, "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": 2338707, "tid": 2379456, "ts": 6197196776907.523, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196776938.031, "dur": 8.391, + "args": { + "External id": 28102,"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": 2338707, "tid": 2379456, + "ts": 6197196776943.076, "dur": 3.052, + "args": { + "External id": 28103,"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": 2338707, "tid": 2379456, + "ts": 6197196776949.751, "dur": 7.788, + "args": { + "External id": 28104,"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": 2338707, "tid": 2379456, + "ts": 6197196776953.564, "dur": 3.227, + "args": { + "External id": 28105,"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": 2338707, "tid": 2379456, + "ts": 6197196776955.852, "dur": 0.751, + "args": { + "External id": 28106,"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": 2338707, "tid": 2379456, + "ts": 6197196776960.964, "dur": 130.822, + "args": { + "External id": 28107,"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": 2338707, "tid": 2379456, + "ts": 6197196776961.898, "dur": 6.048, + "args": { + "External id": 28108,"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": 2338707, "tid": 2379456, + "ts": 6197196776962.556, "dur": 4.902, + "args": { + "External id": 28109,"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": 2338707, "tid": 2379456, + "ts": 6197196776964.475, "dur": 2.863, + "args": { + "External id": 28110,"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": 2338707, "tid": 2379456, + "ts": 6197196776971.047, "dur": 84.079, + "args": { + "External id": 28111,"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": 2338707, "tid": 2379456, + "ts": 6197196776972.571, "dur": 81.563, + "args": { + "External id": 28112,"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": 2338707, "tid": 2379456, + "ts": 6197196777098.785, "dur": 3.810, + "args": { + "External id": 28113,"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": 2338707, "tid": 2379456, + "ts": 6197196777100.453, "dur": 2.036, + "args": { + "External id": 28114,"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": 2338707, "tid": 2379456, + "ts": 6197196777137.155, "dur": 7.928, + "args": { + "External id": 28115,"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": 2338707, "tid": 2379456, + "ts": 6197196777146.393, "dur": 2.386, + "args": { + "External id": 28116,"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": 2338707, "tid": 2379456, + "ts": 6197196777150.355, "dur": 1.992, + "args": { + "External id": 28117,"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": 2338707, "tid": 2379456, + "ts": 6197196777193.144, "dur": 2.636, + "args": { + "External id": 28118,"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": 2338707, "tid": 2379456, + "ts": 6197196777194.533, "dur": 1.115, + "args": { + "External id": 28119,"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": 2338707, "tid": 2379456, + "ts": 6197196777217.518, "dur": 140.403, + "args": { + "External id": 28120,"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": 2338707, "tid": 2379456, + "ts": 6197196777222.606, "dur": 6.481, + "args": { + "External id": 28121,"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": 2338707, "tid": 2379456, + "ts": 6197196777227.408, "dur": 0.862, + "args": { + "External id": 28122,"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": 2338707, "tid": 2379456, + "ts": 6197196777230.824, "dur": 11.856, + "args": { + "External id": 28123,"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": 2338707, "tid": 2379456, + "ts": 6197196777236.315, "dur": 5.645, + "args": { + "External id": 28124,"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": 2338707, "tid": 2379456, + "ts": 6197196777244.420, "dur": 2.814, + "args": { + "External id": 28125,"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": 2338707, "tid": 2379456, + "ts": 6197196777246.194, "dur": 0.666, + "args": { + "External id": 28126,"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": 2338707, "tid": 2379456, + "ts": 6197196777248.232, "dur": 3.647, + "args": { + "External id": 28127,"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": 2338707, "tid": 2379456, + "ts": 6197196777250.755, "dur": 0.691, + "args": { + "External id": 28128,"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": 2338707, "tid": 2379456, + "ts": 6197196777258.316, "dur": 2.989, + "args": { + "External id": 28129,"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": 2338707, "tid": 2379456, + "ts": 6197196777260.425, "dur": 0.585, + "args": { + "External id": 28130,"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": 2338707, "tid": 2379456, + "ts": 6197196777262.733, "dur": 6.424, + "args": { + "External id": 28131,"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": 2338707, "tid": 2379456, + "ts": 6197196777267.147, "dur": 1.765, + "args": { + "External id": 28132,"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": 2338707, "tid": 2379456, + "ts": 6197196777270.262, "dur": 2.889, + "args": { + "External id": 28133,"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": 2338707, "tid": 2379456, + "ts": 6197196777272.324, "dur": 0.551, + "args": { + "External id": 28134,"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": 2338707, "tid": 2379456, + "ts": 6197196777274.466, "dur": 3.434, + "args": { + "External id": 28135,"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": 2338707, "tid": 2379456, + "ts": 6197196777275.592, "dur": 2.226, + "args": { + "External id": 28136,"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": 2338707, "tid": 2379456, + "ts": 6197196777278.935, "dur": 62.160, + "args": { + "External id": 28137,"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": 2338707, "tid": 2379456, + "ts": 6197196777345.789, "dur": 2.967, + "args": { + "External id": 28138,"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": 2338707, "tid": 2379456, + "ts": 6197196777349.817, "dur": 3.455, + "args": { + "External id": 28139,"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": 2338707, "tid": 2379456, + "ts": 6197196777352.218, "dur": 0.516, + "args": { + "External id": 28140,"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": 2338707, "tid": 2379456, + "ts": 6197196777355.620, "dur": 1.058, + "args": { + "External id": 28141,"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": 2338707, "tid": 2379456, + "ts": 6197196777403.187, "dur": 8.930, + "args": { + "External id": 28142,"Record function id": 0, "Ev Idx": 1005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197196777405.607, "dur": 5.832, + "args": { + "External id": 28143,"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": 2338707, "tid": 2379456, + "ts": 6197196777407.586, "dur": 3.101, + "args": { + "External id": 28144,"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": 2338707, "tid": 2379456, + "ts": 6197196777408.537, "dur": 2.015, + "args": { + "External id": 28145,"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": 2338707, "tid": 2379456, + "ts": 6197196777416.301, "dur": 10.442, + "args": { + "External id": 28146,"Record function id": 0, "Sequence number": 479886, "Fwd thread id": 1, "Ev Idx": 1009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196777418.139, "dur": 5.848, + "args": { + "External id": 28147,"Sequence number": 479886, "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": 2338707, "tid": 2379456, "ts": 6197196777418.139, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196777420.065, "dur": 3.684, + "args": { + "External id": 28148,"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": 2338707, "tid": 2379456, + "ts": 6197196777422.877, "dur": 0.747, + "args": { + "External id": 28149,"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": 2338707, "tid": 2379456, + "ts": 6197196777430.408, "dur": 140.965, + "args": { + "External id": 28150,"Record function id": 0, "Sequence number": 479885, "Fwd thread id": 1, "Ev Idx": 1013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196777431.520, "dur": 132.751, + "args": { + "External id": 28151,"Sequence number": 479885, "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": 2338707, "tid": 2379456, "ts": 6197196777431.520, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197196777434.941, "dur": 4.414, + "args": { + "External id": 28152,"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": 2338707, "tid": 2379456, + "ts": 6197196777436.335, "dur": 2.492, + "args": { + "External id": 28153,"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": 2338707, "tid": 2379456, + "ts": 6197196777438.055, "dur": 0.592, + "args": { + "External id": 28154,"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": 2338707, "tid": 2379456, + "ts": 6197196777442.563, "dur": 44.361, + "args": { + "External id": 28155,"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": 2338707, "tid": 2379456, + "ts": 6197196777487.974, "dur": 4.948, + "args": { + "External id": 28156,"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": 2338707, "tid": 2379456, + "ts": 6197196777488.774, "dur": 3.477, + "args": { + "External id": 28157,"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": 2338707, "tid": 2379456, + "ts": 6197196777490.804, "dur": 1.276, + "args": { + "External id": 28158,"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": 2338707, "tid": 2379456, + "ts": 6197196777494.740, "dur": 31.567, + "args": { + "External id": 28159,"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": 2338707, "tid": 2379456, + "ts": 6197196777495.860, "dur": 29.723, + "args": { + "External id": 28160,"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": 2338707, "tid": 2379456, + "ts": 6197196777525.106, "dur": 0.406, + "args": { + "External id": 28161,"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": 2338707, "tid": 2379456, + "ts": 6197196777526.862, "dur": 36.368, + "args": { + "External id": 28162,"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": 2338707, "tid": 2379456, + "ts": 6197196777578.781, "dur": 10.735, + "args": { + "External id": 28163,"Record function id": 0, "Sequence number": 479884, "Fwd thread id": 1, "Ev Idx": 1026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196777579.845, "dur": 8.026, + "args": { + "External id": 28164,"Sequence number": 479884, "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": 2338707, "tid": 2379456, "ts": 6197196777579.845, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196777582.662, "dur": 5.033, + "args": { + "External id": 28165,"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": 2338707, "tid": 2379456, + "ts": 6197196777583.879, "dur": 3.664, + "args": { + "External id": 28166,"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": 2338707, "tid": 2379456, + "ts": 6197196777593.218, "dur": 9.730, + "args": { + "External id": 28167,"Record function id": 0, "Sequence number": 479883, "Fwd thread id": 1, "Ev Idx": 1030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196777594.205, "dur": 6.146, + "args": { + "External id": 28168,"Sequence number": 479883, "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": 2338707, "tid": 2379456, "ts": 6197196777594.205, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197196777594.973, "dur": 5.181, + "args": { + "External id": 28169,"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": 2338707, "tid": 2379456, + "ts": 6197196777595.600, "dur": 4.010, + "args": { + "External id": 28170,"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": 2338707, "tid": 2379456, + "ts": 6197196777598.998, "dur": 0.462, + "args": { + "External id": 28171,"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": 2338707, "tid": 2379456, + "ts": 6197196777606.959, "dur": 5.699, + "args": { + "External id": 28172,"Record function id": 0, "Ev Idx": 1035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197196777608.514, "dur": 3.593, + "args": { + "External id": 28173,"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": 2338707, "tid": 2379456, + "ts": 6197196777609.849, "dur": 1.923, + "args": { + "External id": 28174,"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": 2338707, "tid": 2379456, + "ts": 6197196777610.409, "dur": 1.278, + "args": { + "External id": 28175,"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": 2338707, "tid": 2379456, + "ts": 6197196777615.944, "dur": 7.405, + "args": { + "External id": 28176,"Record function id": 0, "Sequence number": 479882, "Fwd thread id": 1, "Ev Idx": 1039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196777617.643, "dur": 2.948, + "args": { + "External id": 28177,"Sequence number": 479882, "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": 2338707, "tid": 2379456, "ts": 6197196777617.643, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196777618.795, "dur": 1.634, + "args": { + "External id": 28178,"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": 2338707, "tid": 2379456, + "ts": 6197196777619.652, "dur": 0.645, + "args": { + "External id": 28179,"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": 2338707, "tid": 2379456, + "ts": 6197196777626.382, "dur": 120.269, + "args": { + "External id": 28180,"Record function id": 0, "Sequence number": 479881, "Fwd thread id": 1, "Ev Idx": 1043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196777627.229, "dur": 108.725, + "args": { + "External id": 28181,"Sequence number": 479881, "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": 2338707, "tid": 2379456, "ts": 6197196777627.229, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197196777631.916, "dur": 2.946, + "args": { + "External id": 28182,"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": 2338707, "tid": 2379456, + "ts": 6197196777632.359, "dur": 2.075, + "args": { + "External id": 28183,"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": 2338707, "tid": 2379456, + "ts": 6197196777633.831, "dur": 0.468, + "args": { + "External id": 28184,"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": 2338707, "tid": 2379456, + "ts": 6197196777635.402, "dur": 33.233, + "args": { + "External id": 28185,"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": 2338707, "tid": 2379456, + "ts": 6197196777669.577, "dur": 5.497, + "args": { + "External id": 28186,"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": 2338707, "tid": 2379456, + "ts": 6197196777670.000, "dur": 4.546, + "args": { + "External id": 28187,"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": 2338707, "tid": 2379456, + "ts": 6197196777673.742, "dur": 0.690, + "args": { + "External id": 28188,"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": 2338707, "tid": 2379456, + "ts": 6197196777676.585, "dur": 3.967, + "args": { + "External id": 28189,"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": 2338707, "tid": 2379456, + "ts": 6197196777678.031, "dur": 1.934, + "args": { + "External id": 28190,"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": 2338707, "tid": 2379456, + "ts": 6197196777679.351, "dur": 0.543, + "args": { + "External id": 28191,"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": 2338707, "tid": 2379456, + "ts": 6197196777681.035, "dur": 53.754, + "args": { + "External id": 28192,"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": 2338707, "tid": 2379456, + "ts": 6197196777753.800, "dur": 36.184, + "args": { + "External id": 28193,"Record function id": 0, "Sequence number": 479880, "Fwd thread id": 1, "Ev Idx": 1056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196777754.840, "dur": 7.179, + "args": { + "External id": 28194,"Sequence number": 479880, "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": 2338707, "tid": 2379456, "ts": 6197196777754.840, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196777756.910, "dur": 4.971, + "args": { + "External id": 28195,"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": 2338707, "tid": 2379456, + "ts": 6197196777760.188, "dur": 1.576, + "args": { + "External id": 28196,"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": 2338707, "tid": 2379456, + "ts": 6197196777764.933, "dur": 21.803, + "args": { + "External id": 28197,"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": 2338707, "tid": 2379456, + "ts": 6197196777793.904, "dur": 9.746, + "args": { + "External id": 28198,"Record function id": 0, "Sequence number": 479879, "Fwd thread id": 1, "Ev Idx": 1061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196777794.956, "dur": 5.187, + "args": { + "External id": 28199,"Sequence number": 479879, "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": 2338707, "tid": 2379456, "ts": 6197196777794.956, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197196777795.894, "dur": 4.060, + "args": { + "External id": 28200,"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": 2338707, "tid": 2379456, + "ts": 6197196777796.780, "dur": 2.656, + "args": { + "External id": 28201,"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": 2338707, "tid": 2379456, + "ts": 6197196777798.813, "dur": 0.510, + "args": { + "External id": 28202,"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": 2338707, "tid": 2379456, + "ts": 6197196777807.909, "dur": 9.072, + "args": { + "External id": 28203,"Record function id": 0, "Ev Idx": 1066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197196777809.848, "dur": 6.620, + "args": { + "External id": 28204,"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": 2338707, "tid": 2379456, + "ts": 6197196777810.935, "dur": 5.024, + "args": { + "External id": 28205,"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": 2338707, "tid": 2379456, + "ts": 6197196777814.484, "dur": 1.356, + "args": { + "External id": 28206,"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": 2338707, "tid": 2379456, + "ts": 6197196777821.786, "dur": 475.953, + "args": { + "External id": 28207,"Record function id": 0, "Sequence number": 479878, "Fwd thread id": 1, "Ev Idx": 1070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197196777823.796, "dur": 434.466, + "args": { + "External id": 28208,"Sequence number": 479878, "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": 2338707, "tid": 2379456, "ts": 6197196777823.796, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338707, "tid": 2379456, + "ts": 6197196777848.287, "dur": 34.627, + "args": { + "External id": 28209,"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": 2338707, "tid": 2379456, + "ts": 6197196777849.798, "dur": 32.912, + "args": { + "External id": 28210,"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": 2338707, "tid": 2379456, + "ts": 6197196777852.672, "dur": 6.333, + "args": { + "External id": 28211,"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": 2338707, "tid": 2379456, + "ts": 6197196777855.354, "dur": 3.089, + "args": { + "External id": 28212,"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": 2338707, "tid": 2379456, + "ts": 6197196777860.537, "dur": 21.578, + "args": { + "External id": 28213,"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": 2338707, "tid": 2379456, + "ts": 6197196777894.090, "dur": 2.365, + "args": { + "External id": 28214,"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": 2338707, "tid": 2379456, + "ts": 6197196777895.215, "dur": 1.082, + "args": { + "External id": 28215,"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": 2338707, "tid": 2379456, + "ts": 6197196777900.414, "dur": 3.229, + "args": { + "External id": 28216,"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": 2338707, "tid": 2379456, + "ts": 6197196777902.743, "dur": 0.798, + "args": { + "External id": 28217,"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": 2338707, "tid": 2379456, + "ts": 6197196777916.274, "dur": 4.676, + "args": { + "External id": 28218,"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": 2338707, "tid": 2379456, + "ts": 6197196777931.780, "dur": 2.137, + "args": { + "External id": 28219,"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": 2338707, "tid": 2379456, + "ts": 6197196778144.200, "dur": 3.025, + "args": { + "External id": 28220,"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": 2338707, "tid": 2379456, + "ts": 6197196778151.849, "dur": 35.501, + "args": { + "External id": 28221,"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": 2338707, "tid": 2379456, + "ts": 6197196778165.234, "dur": 1.017, + "args": { + "External id": 28222,"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": 2338707, "tid": 2379456, + "ts": 6197196778192.865, "dur": 31.632, + "args": { + "External id": 28223,"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": 2338707, "tid": 2379456, + "ts": 6197196778196.712, "dur": 27.575, + "args": { + "External id": 28224,"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": 2338707, "tid": 2379456, + "ts": 6197196778201.201, "dur": 5.855, + "args": { + "External id": 28225,"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": 2338707, "tid": 2379456, + "ts": 6197196778208.832, "dur": 14.900, + "args": { + "External id": 28226,"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": 2338707, "tid": 2379456, + "ts": 6197196778229.196, "dur": 2.571, + "args": { + "External id": 28227,"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": 2338707, "tid": 2379456, + "ts": 6197196778230.720, "dur": 0.912, + "args": { + "External id": 28228,"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": 2338707, "tid": 2379456, + "ts": 6197196778239.426, "dur": 4.736, + "args": { + "External id": 28229,"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": 2338707, "tid": 2379456, + "ts": 6197196778242.939, "dur": 1.062, + "args": { + "External id": 28230,"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": 2338707, "tid": 2379456, + "ts": 6197196778246.648, "dur": 2.448, + "args": { + "External id": 28231,"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": 2338707, "tid": 2379456, + "ts": 6197196778248.107, "dur": 0.892, + "args": { + "External id": 28232,"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": 2338707, "tid": 2379456, + "ts": 6197196778278.044, "dur": 18.062, + "args": { + "External id": 28233,"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": 2338707, "tid": 2379456, + "ts": 6197196778311.110, "dur": 11.229, + "args": { + "External id": 28234,"Record function id": 0, "Ev Idx": 1097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197196778313.972, "dur": 7.599, + "args": { + "External id": 28235,"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": 2338707, "tid": 2379456, + "ts": 6197196778317.229, "dur": 3.465, + "args": { + "External id": 28236,"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": 2338707, "tid": 2379456, + "ts": 6197196778318.894, "dur": 1.685, + "args": { + "External id": 28237,"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": 2338707, "tid": 2379456, + "ts": 6197196778326.592, "dur": 11.507, + "args": { + "External id": 28238,"Record function id": 0, "Sequence number": 479877, "Fwd thread id": 1, "Ev Idx": 1101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196778328.595, "dur": 6.235, + "args": { + "External id": 28239,"Sequence number": 479877, "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": 2338707, "tid": 2379456, "ts": 6197196778328.595, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196778330.536, "dur": 4.088, + "args": { + "External id": 28240,"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": 2338707, "tid": 2379456, + "ts": 6197196778333.225, "dur": 1.268, + "args": { + "External id": 28241,"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": 2338707, "tid": 2379456, + "ts": 6197196778341.420, "dur": 167.976, + "args": { + "External id": 28242,"Record function id": 0, "Sequence number": 479876, "Fwd thread id": 1, "Ev Idx": 1105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196778342.467, "dur": 159.356, + "args": { + "External id": 28243,"Sequence number": 479876, "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": 2338707, "tid": 2379456, "ts": 6197196778342.467, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197196778346.050, "dur": 5.845, + "args": { + "External id": 28244,"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": 2338707, "tid": 2379456, + "ts": 6197196778347.570, "dur": 3.709, + "args": { + "External id": 28245,"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": 2338707, "tid": 2379456, + "ts": 6197196778350.003, "dur": 1.036, + "args": { + "External id": 28246,"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": 2338707, "tid": 2379456, + "ts": 6197196778355.596, "dur": 79.456, + "args": { + "External id": 28247,"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": 2338707, "tid": 2379456, + "ts": 6197196778436.326, "dur": 4.883, + "args": { + "External id": 28248,"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": 2338707, "tid": 2379456, + "ts": 6197196778437.140, "dur": 3.390, + "args": { + "External id": 28249,"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": 2338707, "tid": 2379456, + "ts": 6197196778439.527, "dur": 0.878, + "args": { + "External id": 28250,"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": 2338707, "tid": 2379456, + "ts": 6197196778442.814, "dur": 16.644, + "args": { + "External id": 28251,"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": 2338707, "tid": 2379456, + "ts": 6197196778452.630, "dur": 5.842, + "args": { + "External id": 28252,"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": 2338707, "tid": 2379456, + "ts": 6197196778456.840, "dur": 0.874, + "args": { + "External id": 28253,"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": 2338707, "tid": 2379456, + "ts": 6197196778459.948, "dur": 40.938, + "args": { + "External id": 28254,"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": 2338707, "tid": 2379456, + "ts": 6197196778518.220, "dur": 8.668, + "args": { + "External id": 28255,"Record function id": 0, "Sequence number": 479875, "Fwd thread id": 1, "Ev Idx": 1118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196778519.307, "dur": 5.132, + "args": { + "External id": 28256,"Sequence number": 479875, "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": 2338707, "tid": 2379456, "ts": 6197196778519.307, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196778521.794, "dur": 2.481, + "args": { + "External id": 28257,"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": 2338707, "tid": 2379456, + "ts": 6197196778522.857, "dur": 1.301, + "args": { + "External id": 28258,"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": 2338707, "tid": 2379456, + "ts": 6197196778530.614, "dur": 9.369, + "args": { + "External id": 28259,"Record function id": 0, "Sequence number": 479874, "Fwd thread id": 1, "Ev Idx": 1122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196778531.849, "dur": 6.368, + "args": { + "External id": 28260,"Sequence number": 479874, "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": 2338707, "tid": 2379456, "ts": 6197196778531.849, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197196778532.623, "dur": 5.316, + "args": { + "External id": 28261,"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": 2338707, "tid": 2379456, + "ts": 6197196778533.355, "dur": 4.021, + "args": { + "External id": 28262,"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": 2338707, "tid": 2379456, + "ts": 6197196778536.756, "dur": 0.479, + "args": { + "External id": 28263,"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": 2338707, "tid": 2379456, + "ts": 6197196778543.927, "dur": 5.596, + "args": { + "External id": 28264,"Record function id": 0, "Ev Idx": 1127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197196778545.614, "dur": 3.378, + "args": { + "External id": 28265,"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": 2338707, "tid": 2379456, + "ts": 6197196778546.711, "dur": 1.971, + "args": { + "External id": 28266,"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": 2338707, "tid": 2379456, + "ts": 6197196778547.198, "dur": 1.382, + "args": { + "External id": 28267,"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": 2338707, "tid": 2379456, + "ts": 6197196778552.723, "dur": 7.691, + "args": { + "External id": 28268,"Record function id": 0, "Sequence number": 479873, "Fwd thread id": 1, "Ev Idx": 1131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196778553.540, "dur": 4.829, + "args": { + "External id": 28269,"Sequence number": 479873, "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": 2338707, "tid": 2379456, "ts": 6197196778553.540, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196778555.678, "dur": 2.529, + "args": { + "External id": 28270,"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": 2338707, "tid": 2379456, + "ts": 6197196778556.912, "dur": 1.153, + "args": { + "External id": 28271,"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": 2338707, "tid": 2379456, + "ts": 6197196778564.899, "dur": 416.219, + "args": { + "External id": 28272,"Record function id": 0, "Sequence number": 479872, "Fwd thread id": 1, "Ev Idx": 1135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFuncBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197196778566.607, "dur": 389.969, + "args": { + "External id": 28273,"Sequence number": 479872, "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": 2338707, "tid": 2379456, "ts": 6197196778566.607, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338707, "tid": 2379456, + "ts": 6197196778582.518, "dur": 9.765, + "args": { + "External id": 28274,"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": 2338707, "tid": 2379456, + "ts": 6197196778586.330, "dur": 5.419, + "args": { + "External id": 28275,"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": 2338707, "tid": 2379456, + "ts": 6197196778594.774, "dur": 3.492, + "args": { + "External id": 28276,"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": 2338707, "tid": 2379456, + "ts": 6197196778596.254, "dur": 1.829, + "args": { + "External id": 28277,"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": 2338707, "tid": 2379456, + "ts": 6197196778603.204, "dur": 7.141, + "args": { + "External id": 28278,"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": 2338707, "tid": 2379456, + "ts": 6197196778606.690, "dur": 3.479, + "args": { + "External id": 28279,"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": 2338707, "tid": 2379456, + "ts": 6197196778637.180, "dur": 292.463, + "args": { + "External id": 28280,"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": 2338707, "tid": 2379456, + "ts": 6197196778737.615, "dur": 6.880, + "args": { + "External id": 28281,"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": 2338707, "tid": 2379456, + "ts": 6197196778746.890, "dur": 2.639, + "args": { + "External id": 28282,"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": 2338707, "tid": 2379456, + "ts": 6197196778750.715, "dur": 1.890, + "args": { + "External id": 28283,"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": 2338707, "tid": 2379456, + "ts": 6197196778753.625, "dur": 3.381, + "args": { + "External id": 28284,"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": 2338707, "tid": 2379456, + "ts": 6197196778816.667, "dur": 2.958, + "args": { + "External id": 28285,"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": 2338707, "tid": 2379456, + "ts": 6197196778818.015, "dur": 1.510, + "args": { + "External id": 28286,"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": 2338707, "tid": 2379456, + "ts": 6197196778823.528, "dur": 33.841, + "args": { + "External id": 28287,"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": 2338707, "tid": 2379456, + "ts": 6197196778828.721, "dur": 3.409, + "args": { + "External id": 28288,"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": 2338707, "tid": 2379456, + "ts": 6197196778860.763, "dur": 2.010, + "args": { + "External id": 28289,"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": 2338707, "tid": 2379456, + "ts": 6197196778861.862, "dur": 0.828, + "args": { + "External id": 28290,"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": 2338707, "tid": 2379456, + "ts": 6197196778863.732, "dur": 18.213, + "args": { + "External id": 28291,"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": 2338707, "tid": 2379456, + "ts": 6197196778867.942, "dur": 0.426, + "args": { + "External id": 28292,"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": 2338707, "tid": 2379456, + "ts": 6197196778942.317, "dur": 4.753, + "args": { + "External id": 28293,"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": 2338707, "tid": 2379456, + "ts": 6197196778950.253, "dur": 0.463, + "args": { + "External id": 28294,"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": 2338707, "tid": 2379456, + "ts": 6197196778952.549, "dur": 1.134, + "args": { + "External id": 28295,"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": 2338707, "tid": 2379456, + "ts": 6197196778991.763, "dur": 299.538, + "args": { + "External id": 28296,"Record function id": 0, "Sequence number": 479871, "Fwd thread id": 1, "Ev Idx": 1159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197196778994.096, "dur": 289.263, + "args": { + "External id": 28297,"Sequence number": 479871, "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": 2338707, "tid": 2379456, "ts": 6197196778994.096, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338707, "tid": 2379456, + "ts": 6197196779014.837, "dur": 100.670, + "args": { + "External id": 28298,"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": 2338707, "tid": 2379456, + "ts": 6197196779018.761, "dur": 3.520, + "args": { + "External id": 28299,"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": 2338707, "tid": 2379456, + "ts": 6197196779023.988, "dur": 90.229, + "args": { + "External id": 28300,"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": 2338707, "tid": 2379456, + "ts": 6197196779129.561, "dur": 6.531, + "args": { + "External id": 28301,"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": 2338707, "tid": 2379456, + "ts": 6197196779132.040, "dur": 3.681, + "args": { + "External id": 28302,"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": 2338707, "tid": 2379456, + "ts": 6197196779301.766, "dur": 179.195, + "args": { + "External id": 28303,"Record function id": 0, "Sequence number": 479870, "Fwd thread id": 1, "Ev Idx": 1166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197196779304.345, "dur": 168.544, + "args": { + "External id": 28304,"Sequence number": 479870, "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": 2338707, "tid": 2379456, "ts": 6197196779304.345, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338707, "tid": 2379456, + "ts": 6197196779317.781, "dur": 49.145, + "args": { + "External id": 28305,"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": 2338707, "tid": 2379456, + "ts": 6197196779321.818, "dur": 3.206, + "args": { + "External id": 28306,"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": 2338707, "tid": 2379456, + "ts": 6197196779326.088, "dur": 40.329, + "args": { + "External id": 28307,"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": 2338707, "tid": 2379456, + "ts": 6197196779375.379, "dur": 5.813, + "args": { + "External id": 28308,"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": 2338707, "tid": 2379456, + "ts": 6197196779377.578, "dur": 3.307, + "args": { + "External id": 28309,"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": 2338707, "tid": 2379456, + "ts": 6197196779488.172, "dur": 18.019, + "args": { + "External id": 28310,"Record function id": 0, "Sequence number": 479869, "Fwd thread id": 1, "Ev Idx": 1173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196779490.282, "dur": 12.557, + "args": { + "External id": 28311,"Sequence number": 479869, "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": 2338707, "tid": 2379456, "ts": 6197196779490.282, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196779493.283, "dur": 9.228, + "args": { + "External id": 28312,"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": 2338707, "tid": 2379456, + "ts": 6197196779495.175, "dur": 7.143, + "args": { + "External id": 28313,"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": 2338707, "tid": 2379456, + "ts": 6197196779509.691, "dur": 10.144, + "args": { + "External id": 28314,"Record function id": 0, "Sequence number": 479868, "Fwd thread id": 1, "Ev Idx": 1177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196779513.138, "dur": 3.876, + "args": { + "External id": 28315,"Sequence number": 479868, "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": 2338707, "tid": 2379456, "ts": 6197196779513.138, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196779514.857, "dur": 2.002, + "args": { + "External id": 28316,"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": 2338707, "tid": 2379456, + "ts": 6197196779515.883, "dur": 0.841, + "args": { + "External id": 28317,"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": 2338707, "tid": 2379456, + "ts": 6197196779523.333, "dur": 7.133, + "args": { + "External id": 28318,"Record function id": 0, "Sequence number": 479867, "Fwd thread id": 1, "Ev Idx": 1181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196779524.402, "dur": 3.983, + "args": { + "External id": 28319,"Sequence number": 479867, "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": 2338707, "tid": 2379456, "ts": 6197196779524.402, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196779525.666, "dur": 2.569, + "args": { + "External id": 28320,"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": 2338707, "tid": 2379456, + "ts": 6197196779526.841, "dur": 1.274, + "args": { + "External id": 28321,"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": 2338707, "tid": 2379456, + "ts": 6197196779533.957, "dur": 9.269, + "args": { + "External id": 28322,"Record function id": 0, "Sequence number": 479866, "Fwd thread id": 1, "Ev Idx": 1185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196779535.966, "dur": 5.078, + "args": { + "External id": 28323,"Sequence number": 479866, "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": 2338707, "tid": 2379456, "ts": 6197196779535.966, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196779537.231, "dur": 3.653, + "args": { + "External id": 28324,"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": 2338707, "tid": 2379456, + "ts": 6197196779539.875, "dur": 0.868, + "args": { + "External id": 28325,"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": 2338707, "tid": 2379456, + "ts": 6197196779549.401, "dur": 213.642, + "args": { + "External id": 28326,"Record function id": 0, "Sequence number": 479865, "Fwd thread id": 1, "Ev Idx": 1189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196779550.211, "dur": 202.444, + "args": { + "External id": 28327,"Sequence number": 479865, "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": 2338707, "tid": 2379456, "ts": 6197196779550.211, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197196779555.793, "dur": 7.073, + "args": { + "External id": 28328,"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": 2338707, "tid": 2379456, + "ts": 6197196779557.959, "dur": 4.250, + "args": { + "External id": 28329,"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": 2338707, "tid": 2379456, + "ts": 6197196779560.324, "dur": 1.599, + "args": { + "External id": 28330,"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": 2338707, "tid": 2379456, + "ts": 6197196779565.292, "dur": 78.317, + "args": { + "External id": 28331,"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": 2338707, "tid": 2379456, + "ts": 6197196779645.013, "dur": 13.942, + "args": { + "External id": 28332,"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": 2338707, "tid": 2379456, + "ts": 6197196779652.946, "dur": 5.187, + "args": { + "External id": 28333,"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": 2338707, "tid": 2379456, + "ts": 6197196779655.535, "dur": 2.413, + "args": { + "External id": 28334,"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": 2338707, "tid": 2379456, + "ts": 6197196779660.647, "dur": 4.278, + "args": { + "External id": 28335,"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": 2338707, "tid": 2379456, + "ts": 6197196779662.168, "dur": 2.167, + "args": { + "External id": 28336,"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": 2338707, "tid": 2379456, + "ts": 6197196779663.751, "dur": 0.508, + "args": { + "External id": 28337,"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": 2338707, "tid": 2379456, + "ts": 6197196779665.780, "dur": 85.380, + "args": { + "External id": 28338,"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": 2338707, "tid": 2379456, + "ts": 6197196779771.855, "dur": 12.170, + "args": { + "External id": 28339,"Record function id": 0, "Sequence number": 479864, "Fwd thread id": 1, "Ev Idx": 1202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196779773.411, "dur": 7.901, + "args": { + "External id": 28340,"Sequence number": 479864, "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": 2338707, "tid": 2379456, "ts": 6197196779773.411, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196779775.663, "dur": 5.487, + "args": { + "External id": 28341,"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": 2338707, "tid": 2379456, + "ts": 6197196779779.158, "dur": 1.840, + "args": { + "External id": 28342,"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": 2338707, "tid": 2379456, + "ts": 6197196779787.393, "dur": 9.553, + "args": { + "External id": 28343,"Record function id": 0, "Sequence number": 479863, "Fwd thread id": 1, "Ev Idx": 1206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196779788.618, "dur": 5.122, + "args": { + "External id": 28344,"Sequence number": 479863, "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": 2338707, "tid": 2379456, "ts": 6197196779788.618, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197196779789.637, "dur": 3.878, + "args": { + "External id": 28345,"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": 2338707, "tid": 2379456, + "ts": 6197196779790.362, "dur": 2.664, + "args": { + "External id": 28346,"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": 2338707, "tid": 2379456, + "ts": 6197196779792.173, "dur": 0.686, + "args": { + "External id": 28347,"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": 2338707, "tid": 2379456, + "ts": 6197196779803.277, "dur": 13.714, + "args": { + "External id": 28348,"Record function id": 0, "Ev Idx": 1211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197196779805.340, "dur": 10.700, + "args": { + "External id": 28349,"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": 2338707, "tid": 2379456, + "ts": 6197196779808.475, "dur": 6.974, + "args": { + "External id": 28350,"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": 2338707, "tid": 2379456, + "ts": 6197196779812.100, "dur": 3.197, + "args": { + "External id": 28351,"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": 2338707, "tid": 2379456, + "ts": 6197196779821.274, "dur": 7.338, + "args": { + "External id": 28352,"Record function id": 0, "Sequence number": 479862, "Fwd thread id": 1, "Ev Idx": 1215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196779822.946, "dur": 3.567, + "args": { + "External id": 28353,"Sequence number": 479862, "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": 2338707, "tid": 2379456, "ts": 6197196779822.946, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196779824.633, "dur": 1.727, + "args": { + "External id": 28354,"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": 2338707, "tid": 2379456, + "ts": 6197196779825.384, "dur": 0.850, + "args": { + "External id": 28355,"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": 2338707, "tid": 2379456, + "ts": 6197196779832.331, "dur": 125.606, + "args": { + "External id": 28356,"Record function id": 0, "Sequence number": 479861, "Fwd thread id": 1, "Ev Idx": 1219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196779833.445, "dur": 116.606, + "args": { + "External id": 28357,"Sequence number": 479861, "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": 2338707, "tid": 2379456, "ts": 6197196779833.445, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197196779837.062, "dur": 5.626, + "args": { + "External id": 28358,"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": 2338707, "tid": 2379456, + "ts": 6197196779837.862, "dur": 4.318, + "args": { + "External id": 28359,"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": 2338707, "tid": 2379456, + "ts": 6197196779841.480, "dur": 0.605, + "args": { + "External id": 28360,"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": 2338707, "tid": 2379456, + "ts": 6197196779843.695, "dur": 33.756, + "args": { + "External id": 28361,"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": 2338707, "tid": 2379456, + "ts": 6197196779878.354, "dur": 4.781, + "args": { + "External id": 28362,"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": 2338707, "tid": 2379456, + "ts": 6197196779878.966, "dur": 3.671, + "args": { + "External id": 28363,"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": 2338707, "tid": 2379456, + "ts": 6197196779881.134, "dur": 1.390, + "args": { + "External id": 28364,"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": 2338707, "tid": 2379456, + "ts": 6197196779884.501, "dur": 8.606, + "args": { + "External id": 28365,"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": 2338707, "tid": 2379456, + "ts": 6197196779887.943, "dur": 4.401, + "args": { + "External id": 28366,"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": 2338707, "tid": 2379456, + "ts": 6197196779889.604, "dur": 2.619, + "args": { + "External id": 28367,"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": 2338707, "tid": 2379456, + "ts": 6197196779893.612, "dur": 55.626, + "args": { + "External id": 28368,"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": 2338707, "tid": 2379456, + "ts": 6197196779962.355, "dur": 34.856, + "args": { + "External id": 28369,"Record function id": 0, "Sequence number": 479860, "Fwd thread id": 1, "Ev Idx": 1232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196779963.628, "dur": 4.520, + "args": { + "External id": 28370,"Sequence number": 479860, "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": 2338707, "tid": 2379456, "ts": 6197196779963.628, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196779965.831, "dur": 2.157, + "args": { + "External id": 28371,"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": 2338707, "tid": 2379456, + "ts": 6197196779966.780, "dur": 1.082, + "args": { + "External id": 28372,"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": 2338707, "tid": 2379456, + "ts": 6197196779971.113, "dur": 23.780, + "args": { + "External id": 28373,"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": 2338707, "tid": 2379456, + "ts": 6197196780000.868, "dur": 10.568, + "args": { + "External id": 28374,"Record function id": 0, "Sequence number": 479859, "Fwd thread id": 1, "Ev Idx": 1237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196780004.339, "dur": 4.987, + "args": { + "External id": 28375,"Sequence number": 479859, "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": 2338707, "tid": 2379456, "ts": 6197196780004.339, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197196780005.419, "dur": 3.707, + "args": { + "External id": 28376,"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": 2338707, "tid": 2379456, + "ts": 6197196780006.076, "dur": 2.492, + "args": { + "External id": 28377,"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": 2338707, "tid": 2379456, + "ts": 6197196780007.790, "dur": 0.678, + "args": { + "External id": 28378,"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": 2338707, "tid": 2379456, + "ts": 6197196780015.477, "dur": 6.118, + "args": { + "External id": 28379,"Record function id": 0, "Ev Idx": 1242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197196780017.310, "dur": 3.758, + "args": { + "External id": 28380,"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": 2338707, "tid": 2379456, + "ts": 6197196780018.528, "dur": 2.119, + "args": { + "External id": 28381,"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": 2338707, "tid": 2379456, + "ts": 6197196780018.993, "dur": 1.540, + "args": { + "External id": 28382,"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": 2338707, "tid": 2379456, + "ts": 6197196780024.848, "dur": 8.965, + "args": { + "External id": 28383,"Record function id": 0, "Sequence number": 479858, "Fwd thread id": 1, "Ev Idx": 1246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196780026.333, "dur": 5.072, + "args": { + "External id": 28384,"Sequence number": 479858, "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": 2338707, "tid": 2379456, "ts": 6197196780026.333, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196780027.759, "dur": 3.492, + "args": { + "External id": 28385,"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": 2338707, "tid": 2379456, + "ts": 6197196780030.395, "dur": 0.726, + "args": { + "External id": 28386,"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": 2338707, "tid": 2379456, + "ts": 6197196780036.963, "dur": 183.033, + "args": { + "External id": 28387,"Record function id": 0, "Sequence number": 479857, "Fwd thread id": 1, "Ev Idx": 1250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196780038.289, "dur": 171.335, + "args": { + "External id": 28388,"Sequence number": 479857, "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": 2338707, "tid": 2379456, "ts": 6197196780038.289, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197196780041.071, "dur": 3.020, + "args": { + "External id": 28389,"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": 2338707, "tid": 2379456, + "ts": 6197196780041.584, "dur": 2.007, + "args": { + "External id": 28390,"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": 2338707, "tid": 2379456, + "ts": 6197196780043.078, "dur": 0.422, + "args": { + "External id": 28391,"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": 2338707, "tid": 2379456, + "ts": 6197196780046.935, "dur": 96.007, + "args": { + "External id": 28392,"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": 2338707, "tid": 2379456, + "ts": 6197196780145.522, "dur": 5.188, + "args": { + "External id": 28393,"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": 2338707, "tid": 2379456, + "ts": 6197196780146.524, "dur": 3.272, + "args": { + "External id": 28394,"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": 2338707, "tid": 2379456, + "ts": 6197196780148.362, "dur": 1.323, + "args": { + "External id": 28395,"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": 2338707, "tid": 2379456, + "ts": 6197196780152.056, "dur": 5.827, + "args": { + "External id": 28396,"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": 2338707, "tid": 2379456, + "ts": 6197196780153.164, "dur": 4.229, + "args": { + "External id": 28397,"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": 2338707, "tid": 2379456, + "ts": 6197196780156.949, "dur": 0.369, + "args": { + "External id": 28398,"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": 2338707, "tid": 2379456, + "ts": 6197196780158.382, "dur": 50.561, + "args": { + "External id": 28399,"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": 2338707, "tid": 2379456, + "ts": 6197196780226.705, "dur": 29.579, + "args": { + "External id": 28400,"Record function id": 0, "Sequence number": 479856, "Fwd thread id": 1, "Ev Idx": 1263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196780227.637, "dur": 5.333, + "args": { + "External id": 28401,"Sequence number": 479856, "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": 2338707, "tid": 2379456, "ts": 6197196780227.637, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196780230.207, "dur": 2.618, + "args": { + "External id": 28402,"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": 2338707, "tid": 2379456, + "ts": 6197196780231.576, "dur": 1.118, + "args": { + "External id": 28403,"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": 2338707, "tid": 2379456, + "ts": 6197196780235.889, "dur": 17.914, + "args": { + "External id": 28404,"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": 2338707, "tid": 2379456, + "ts": 6197196780260.175, "dur": 9.403, + "args": { + "External id": 28405,"Record function id": 0, "Sequence number": 479855, "Fwd thread id": 1, "Ev Idx": 1268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196780261.506, "dur": 6.195, + "args": { + "External id": 28406,"Sequence number": 479855, "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": 2338707, "tid": 2379456, "ts": 6197196780261.506, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197196780262.392, "dur": 5.104, + "args": { + "External id": 28407,"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": 2338707, "tid": 2379456, + "ts": 6197196780263.130, "dur": 3.797, + "args": { + "External id": 28408,"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": 2338707, "tid": 2379456, + "ts": 6197196780266.153, "dur": 0.665, + "args": { + "External id": 28409,"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": 2338707, "tid": 2379456, + "ts": 6197196780273.966, "dur": 6.754, + "args": { + "External id": 28410,"Record function id": 0, "Ev Idx": 1273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197196780276.232, "dur": 3.911, + "args": { + "External id": 28411,"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": 2338707, "tid": 2379456, + "ts": 6197196780277.440, "dur": 2.330, + "args": { + "External id": 28412,"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": 2338707, "tid": 2379456, + "ts": 6197196780278.170, "dur": 1.484, + "args": { + "External id": 28413,"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": 2338707, "tid": 2379456, + "ts": 6197196780288.264, "dur": 358.004, + "args": { + "External id": 28414,"Record function id": 0, "Sequence number": 479854, "Fwd thread id": 1, "Ev Idx": 1277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197196780289.837, "dur": 326.913, + "args": { + "External id": 28415,"Sequence number": 479854, "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": 2338707, "tid": 2379456, "ts": 6197196780289.837, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196780326.366, "dur": 2.716, + "args": { + "External id": 28416,"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": 2338707, "tid": 2379456, + "ts": 6197196780327.458, "dur": 1.485, + "args": { + "External id": 28417,"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": 2338707, "tid": 2379456, + "ts": 6197196780346.503, "dur": 5.787, + "args": { + "External id": 28418,"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": 2338707, "tid": 2379456, + "ts": 6197196780362.499, "dur": 2.414, + "args": { + "External id": 28419,"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": 2338707, "tid": 2379456, + "ts": 6197196780512.852, "dur": 1.770, + "args": { + "External id": 28420,"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": 2338707, "tid": 2379456, + "ts": 6197196780519.012, "dur": 37.110, + "args": { + "External id": 28421,"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": 2338707, "tid": 2379456, + "ts": 6197196780530.951, "dur": 0.753, + "args": { + "External id": 28422,"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": 2338707, "tid": 2379456, + "ts": 6197196780561.618, "dur": 30.776, + "args": { + "External id": 28423,"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": 2338707, "tid": 2379456, + "ts": 6197196780563.599, "dur": 28.542, + "args": { + "External id": 28424,"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": 2338707, "tid": 2379456, + "ts": 6197196780568.180, "dur": 3.751, + "args": { + "External id": 28425,"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": 2338707, "tid": 2379456, + "ts": 6197196780573.460, "dur": 18.132, + "args": { + "External id": 28426,"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": 2338707, "tid": 2379456, + "ts": 6197196780598.936, "dur": 2.685, + "args": { + "External id": 28427,"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": 2338707, "tid": 2379456, + "ts": 6197196780600.418, "dur": 1.063, + "args": { + "External id": 28428,"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": 2338707, "tid": 2379456, + "ts": 6197196780607.739, "dur": 2.470, + "args": { + "External id": 28429,"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": 2338707, "tid": 2379456, + "ts": 6197196780609.129, "dur": 0.959, + "args": { + "External id": 28430,"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": 2338707, "tid": 2379456, + "ts": 6197196780626.461, "dur": 16.051, + "args": { + "External id": 28431,"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": 2338707, "tid": 2379456, + "ts": 6197196780655.453, "dur": 10.202, + "args": { + "External id": 28432,"Record function id": 0, "Ev Idx": 1295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197196780657.482, "dur": 7.506, + "args": { + "External id": 28433,"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": 2338707, "tid": 2379456, + "ts": 6197196780659.113, "dur": 4.844, + "args": { + "External id": 28434,"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": 2338707, "tid": 2379456, + "ts": 6197196780662.201, "dur": 1.652, + "args": { + "External id": 28435,"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": 2338707, "tid": 2379456, + "ts": 6197196780669.658, "dur": 7.978, + "args": { + "External id": 28436,"Record function id": 0, "Sequence number": 479853, "Fwd thread id": 1, "Ev Idx": 1299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196780671.560, "dur": 1.062, + "args": { + "External id": 28437,"Sequence number": 479853, "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": 2338707, "tid": 2379456, "ts": 6197196780671.560, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SwiGLULinearFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197196780682.080, "dur": 506.830, + "args": { + "External id": 28438,"Record function id": 0, "Sequence number": 479852, "Fwd thread id": 1, "Ev Idx": 1301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197196780684.136, "dur": 489.811, + "args": { + "External id": 28439,"Sequence number": 479852, "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": 2338707, "tid": 2379456, "ts": 6197196780684.136, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196780738.336, "dur": 9.917, + "args": { + "External id": 28440,"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": 2338707, "tid": 2379456, + "ts": 6197196780743.811, "dur": 4.071, + "args": { + "External id": 28441,"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": 2338707, "tid": 2379456, + "ts": 6197196780751.676, "dur": 7.851, + "args": { + "External id": 28442,"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": 2338707, "tid": 2379456, + "ts": 6197196780755.521, "dur": 3.308, + "args": { + "External id": 28443,"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": 2338707, "tid": 2379456, + "ts": 6197196780757.826, "dur": 0.810, + "args": { + "External id": 28444,"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": 2338707, "tid": 2379456, + "ts": 6197196780762.869, "dur": 96.768, + "args": { + "External id": 28445,"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": 2338707, "tid": 2379456, + "ts": 6197196780763.680, "dur": 5.559, + "args": { + "External id": 28446,"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": 2338707, "tid": 2379456, + "ts": 6197196780764.305, "dur": 4.388, + "args": { + "External id": 28447,"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": 2338707, "tid": 2379456, + "ts": 6197196780765.831, "dur": 2.755, + "args": { + "External id": 28448,"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": 2338707, "tid": 2379456, + "ts": 6197196780772.547, "dur": 86.575, + "args": { + "External id": 28449,"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": 2338707, "tid": 2379456, + "ts": 6197196780774.391, "dur": 83.916, + "args": { + "External id": 28450,"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": 2338707, "tid": 2379456, + "ts": 6197196780863.516, "dur": 3.548, + "args": { + "External id": 28451,"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": 2338707, "tid": 2379456, + "ts": 6197196780865.549, "dur": 1.411, + "args": { + "External id": 28452,"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": 2338707, "tid": 2379456, + "ts": 6197196780901.193, "dur": 3.714, + "args": { + "External id": 28453,"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": 2338707, "tid": 2379456, + "ts": 6197196780906.500, "dur": 4.938, + "args": { + "External id": 28454,"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": 2338707, "tid": 2379456, + "ts": 6197196780912.584, "dur": 2.145, + "args": { + "External id": 28455,"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": 2338707, "tid": 2379456, + "ts": 6197196780951.363, "dur": 2.587, + "args": { + "External id": 28456,"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": 2338707, "tid": 2379456, + "ts": 6197196780952.579, "dur": 1.228, + "args": { + "External id": 28457,"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": 2338707, "tid": 2379456, + "ts": 6197196780974.829, "dur": 178.336, + "args": { + "External id": 28458,"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": 2338707, "tid": 2379456, + "ts": 6197196780980.109, "dur": 5.868, + "args": { + "External id": 28459,"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": 2338707, "tid": 2379456, + "ts": 6197196780984.436, "dur": 0.821, + "args": { + "External id": 28460,"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": 2338707, "tid": 2379456, + "ts": 6197196780987.407, "dur": 8.747, + "args": { + "External id": 28461,"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": 2338707, "tid": 2379456, + "ts": 6197196780992.801, "dur": 2.633, + "args": { + "External id": 28462,"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": 2338707, "tid": 2379456, + "ts": 6197196780997.541, "dur": 3.014, + "args": { + "External id": 28463,"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": 2338707, "tid": 2379456, + "ts": 6197196780999.592, "dur": 0.609, + "args": { + "External id": 28464,"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": 2338707, "tid": 2379456, + "ts": 6197196781001.872, "dur": 3.764, + "args": { + "External id": 28465,"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": 2338707, "tid": 2379456, + "ts": 6197196781004.478, "dur": 0.609, + "args": { + "External id": 28466,"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": 2338707, "tid": 2379456, + "ts": 6197196781011.575, "dur": 3.466, + "args": { + "External id": 28467,"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": 2338707, "tid": 2379456, + "ts": 6197196781014.228, "dur": 0.501, + "args": { + "External id": 28468,"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": 2338707, "tid": 2379456, + "ts": 6197196781016.212, "dur": 6.042, + "args": { + "External id": 28469,"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": 2338707, "tid": 2379456, + "ts": 6197196781020.218, "dur": 1.859, + "args": { + "External id": 28470,"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": 2338707, "tid": 2379456, + "ts": 6197196781023.513, "dur": 2.739, + "args": { + "External id": 28471,"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": 2338707, "tid": 2379456, + "ts": 6197196781025.631, "dur": 0.316, + "args": { + "External id": 28472,"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": 2338707, "tid": 2379456, + "ts": 6197196781027.299, "dur": 4.896, + "args": { + "External id": 28473,"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": 2338707, "tid": 2379456, + "ts": 6197196781028.693, "dur": 3.419, + "args": { + "External id": 28474,"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": 2338707, "tid": 2379456, + "ts": 6197196781033.422, "dur": 99.393, + "args": { + "External id": 28475,"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": 2338707, "tid": 2379456, + "ts": 6197196781136.757, "dur": 4.192, + "args": { + "External id": 28476,"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": 2338707, "tid": 2379456, + "ts": 6197196781144.288, "dur": 3.887, + "args": { + "External id": 28477,"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": 2338707, "tid": 2379456, + "ts": 6197196781146.468, "dur": 1.069, + "args": { + "External id": 28478,"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": 2338707, "tid": 2379456, + "ts": 6197196781150.953, "dur": 0.929, + "args": { + "External id": 28479,"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": 2338707, "tid": 2379456, + "ts": 6197196781202.376, "dur": 13.838, + "args": { + "External id": 28480,"Record function id": 0, "Ev Idx": 1343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197196781204.782, "dur": 10.492, + "args": { + "External id": 28481,"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": 2338707, "tid": 2379456, + "ts": 6197196781207.362, "dur": 6.783, + "args": { + "External id": 28482,"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": 2338707, "tid": 2379456, + "ts": 6197196781211.550, "dur": 2.463, + "args": { + "External id": 28483,"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": 2338707, "tid": 2379456, + "ts": 6197196781220.621, "dur": 9.593, + "args": { + "External id": 28484,"Record function id": 0, "Sequence number": 479851, "Fwd thread id": 1, "Ev Idx": 1347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196781222.010, "dur": 5.892, + "args": { + "External id": 28485,"Sequence number": 479851, "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": 2338707, "tid": 2379456, "ts": 6197196781222.010, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196781226.109, "dur": 1.563, + "args": { + "External id": 28486,"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": 2338707, "tid": 2379456, + "ts": 6197196781226.754, "dur": 0.800, + "args": { + "External id": 28487,"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": 2338707, "tid": 2379456, + "ts": 6197196781234.069, "dur": 116.465, + "args": { + "External id": 28488,"Record function id": 0, "Sequence number": 479850, "Fwd thread id": 1, "Ev Idx": 1351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196781234.957, "dur": 108.564, + "args": { + "External id": 28489,"Sequence number": 479850, "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": 2338707, "tid": 2379456, "ts": 6197196781234.957, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197196781238.616, "dur": 5.781, + "args": { + "External id": 28490,"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": 2338707, "tid": 2379456, + "ts": 6197196781239.993, "dur": 3.808, + "args": { + "External id": 28491,"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": 2338707, "tid": 2379456, + "ts": 6197196781243.082, "dur": 0.585, + "args": { + "External id": 28492,"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": 2338707, "tid": 2379456, + "ts": 6197196781245.779, "dur": 47.459, + "args": { + "External id": 28493,"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": 2338707, "tid": 2379456, + "ts": 6197196781294.212, "dur": 3.273, + "args": { + "External id": 28494,"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": 2338707, "tid": 2379456, + "ts": 6197196781295.113, "dur": 1.838, + "args": { + "External id": 28495,"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": 2338707, "tid": 2379456, + "ts": 6197196781296.231, "dur": 0.578, + "args": { + "External id": 28496,"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": 2338707, "tid": 2379456, + "ts": 6197196781299.161, "dur": 5.891, + "args": { + "External id": 28497,"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": 2338707, "tid": 2379456, + "ts": 6197196781300.436, "dur": 4.026, + "args": { + "External id": 28498,"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": 2338707, "tid": 2379456, + "ts": 6197196781303.789, "dur": 0.603, + "args": { + "External id": 28499,"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": 2338707, "tid": 2379456, + "ts": 6197196781305.565, "dur": 37.161, + "args": { + "External id": 28500,"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": 2338707, "tid": 2379456, + "ts": 6197196781355.463, "dur": 6.696, + "args": { + "External id": 28501,"Record function id": 0, "Sequence number": 479849, "Fwd thread id": 1, "Ev Idx": 1364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196781356.462, "dur": 3.837, + "args": { + "External id": 28502,"Sequence number": 479849, "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": 2338707, "tid": 2379456, "ts": 6197196781356.462, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196781357.936, "dur": 2.215, + "args": { + "External id": 28503,"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": 2338707, "tid": 2379456, + "ts": 6197196781359.036, "dur": 0.973, + "args": { + "External id": 28504,"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": 2338707, "tid": 2379456, + "ts": 6197196781365.513, "dur": 10.159, + "args": { + "External id": 28505,"Record function id": 0, "Sequence number": 479848, "Fwd thread id": 1, "Ev Idx": 1368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196781366.847, "dur": 6.223, + "args": { + "External id": 28506,"Sequence number": 479848, "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": 2338707, "tid": 2379456, "ts": 6197196781366.847, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197196781367.682, "dur": 5.187, + "args": { + "External id": 28507,"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": 2338707, "tid": 2379456, + "ts": 6197196781368.340, "dur": 4.040, + "args": { + "External id": 28508,"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": 2338707, "tid": 2379456, + "ts": 6197196781371.716, "dur": 0.572, + "args": { + "External id": 28509,"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": 2338707, "tid": 2379456, + "ts": 6197196781379.669, "dur": 5.429, + "args": { + "External id": 28510,"Record function id": 0, "Ev Idx": 1373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197196781381.154, "dur": 3.411, + "args": { + "External id": 28511,"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": 2338707, "tid": 2379456, + "ts": 6197196781382.345, "dur": 1.904, + "args": { + "External id": 28512,"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": 2338707, "tid": 2379456, + "ts": 6197196781382.956, "dur": 1.179, + "args": { + "External id": 28513,"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": 2338707, "tid": 2379456, + "ts": 6197196781388.563, "dur": 6.986, + "args": { + "External id": 28514,"Record function id": 0, "Sequence number": 479847, "Fwd thread id": 1, "Ev Idx": 1377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196781389.796, "dur": 3.274, + "args": { + "External id": 28515,"Sequence number": 479847, "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": 2338707, "tid": 2379456, "ts": 6197196781389.796, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196781391.226, "dur": 1.683, + "args": { + "External id": 28516,"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": 2338707, "tid": 2379456, + "ts": 6197196781391.984, "dur": 0.792, + "args": { + "External id": 28517,"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": 2338707, "tid": 2379456, + "ts": 6197196781398.941, "dur": 99.336, + "args": { + "External id": 28518,"Record function id": 0, "Sequence number": 479846, "Fwd thread id": 1, "Ev Idx": 1381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196781402.002, "dur": 87.279, + "args": { + "External id": 28519,"Sequence number": 479846, "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": 2338707, "tid": 2379456, "ts": 6197196781402.002, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197196781404.465, "dur": 2.675, + "args": { + "External id": 28520,"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": 2338707, "tid": 2379456, + "ts": 6197196781405.147, "dur": 1.553, + "args": { + "External id": 28521,"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": 2338707, "tid": 2379456, + "ts": 6197196781406.043, "dur": 0.518, + "args": { + "External id": 28522,"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": 2338707, "tid": 2379456, + "ts": 6197196781407.716, "dur": 33.264, + "args": { + "External id": 28523,"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": 2338707, "tid": 2379456, + "ts": 6197196781442.133, "dur": 5.205, + "args": { + "External id": 28524,"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": 2338707, "tid": 2379456, + "ts": 6197196781442.663, "dur": 4.174, + "args": { + "External id": 28525,"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": 2338707, "tid": 2379456, + "ts": 6197196781446.090, "dur": 0.627, + "args": { + "External id": 28526,"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": 2338707, "tid": 2379456, + "ts": 6197196781448.730, "dur": 5.797, + "args": { + "External id": 28527,"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": 2338707, "tid": 2379456, + "ts": 6197196781449.857, "dur": 4.006, + "args": { + "External id": 28528,"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": 2338707, "tid": 2379456, + "ts": 6197196781450.717, "dur": 3.052, + "args": { + "External id": 28529,"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": 2338707, "tid": 2379456, + "ts": 6197196781455.041, "dur": 33.572, + "args": { + "External id": 28530,"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": 2338707, "tid": 2379456, + "ts": 6197196781505.325, "dur": 35.899, + "args": { + "External id": 28531,"Record function id": 0, "Sequence number": 479845, "Fwd thread id": 1, "Ev Idx": 1394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196781506.143, "dur": 6.371, + "args": { + "External id": 28532,"Sequence number": 479845, "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": 2338707, "tid": 2379456, "ts": 6197196781506.143, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196781510.129, "dur": 2.221, + "args": { + "External id": 28533,"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": 2338707, "tid": 2379456, + "ts": 6197196781511.079, "dur": 1.155, + "args": { + "External id": 28534,"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": 2338707, "tid": 2379456, + "ts": 6197196781515.268, "dur": 22.709, + "args": { + "External id": 28535,"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": 2338707, "tid": 2379456, + "ts": 6197196781544.982, "dur": 7.526, + "args": { + "External id": 28536,"Record function id": 0, "Sequence number": 479844, "Fwd thread id": 1, "Ev Idx": 1399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196781545.803, "dur": 4.718, + "args": { + "External id": 28537,"Sequence number": 479844, "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": 2338707, "tid": 2379456, "ts": 6197196781545.803, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197196781546.913, "dur": 3.373, + "args": { + "External id": 28538,"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": 2338707, "tid": 2379456, + "ts": 6197196781547.698, "dur": 2.085, + "args": { + "External id": 28539,"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": 2338707, "tid": 2379456, + "ts": 6197196781549.078, "dur": 0.600, + "args": { + "External id": 28540,"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": 2338707, "tid": 2379456, + "ts": 6197196781556.227, "dur": 8.270, + "args": { + "External id": 28541,"Record function id": 0, "Ev Idx": 1404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197196781557.919, "dur": 6.079, + "args": { + "External id": 28542,"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": 2338707, "tid": 2379456, + "ts": 6197196781558.995, "dur": 4.531, + "args": { + "External id": 28543,"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": 2338707, "tid": 2379456, + "ts": 6197196781562.143, "dur": 1.260, + "args": { + "External id": 28544,"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": 2338707, "tid": 2379456, + "ts": 6197196781568.571, "dur": 436.788, + "args": { + "External id": 28545,"Record function id": 0, "Sequence number": 479843, "Fwd thread id": 1, "Ev Idx": 1408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197196781570.384, "dur": 400.385, + "args": { + "External id": 28546,"Sequence number": 479843, "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": 2338707, "tid": 2379456, "ts": 6197196781570.384, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338707, "tid": 2379456, + "ts": 6197196781593.005, "dur": 35.475, + "args": { + "External id": 28547,"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": 2338707, "tid": 2379456, + "ts": 6197196781594.466, "dur": 33.801, + "args": { + "External id": 28548,"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": 2338707, "tid": 2379456, + "ts": 6197196781597.516, "dur": 6.901, + "args": { + "External id": 28549,"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": 2338707, "tid": 2379456, + "ts": 6197196781600.596, "dur": 3.408, + "args": { + "External id": 28550,"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": 2338707, "tid": 2379456, + "ts": 6197196781605.725, "dur": 21.928, + "args": { + "External id": 28551,"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": 2338707, "tid": 2379456, + "ts": 6197196781639.691, "dur": 2.416, + "args": { + "External id": 28552,"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": 2338707, "tid": 2379456, + "ts": 6197196781640.520, "dur": 1.407, + "args": { + "External id": 28553,"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": 2338707, "tid": 2379456, + "ts": 6197196781648.298, "dur": 3.787, + "args": { + "External id": 28554,"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": 2338707, "tid": 2379456, + "ts": 6197196781648.977, "dur": 3.022, + "args": { + "External id": 28555,"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": 2338707, "tid": 2379456, + "ts": 6197196781665.057, "dur": 2.678, + "args": { + "External id": 28556,"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": 2338707, "tid": 2379456, + "ts": 6197196781679.598, "dur": 2.207, + "args": { + "External id": 28557,"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": 2338707, "tid": 2379456, + "ts": 6197196781864.605, "dur": 2.655, + "args": { + "External id": 28558,"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": 2338707, "tid": 2379456, + "ts": 6197196781871.307, "dur": 34.116, + "args": { + "External id": 28559,"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": 2338707, "tid": 2379456, + "ts": 6197196781882.874, "dur": 0.890, + "args": { + "External id": 28560,"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": 2338707, "tid": 2379456, + "ts": 6197196781911.031, "dur": 26.442, + "args": { + "External id": 28561,"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": 2338707, "tid": 2379456, + "ts": 6197196781912.932, "dur": 24.347, + "args": { + "External id": 28562,"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": 2338707, "tid": 2379456, + "ts": 6197196781917.026, "dur": 3.866, + "args": { + "External id": 28563,"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": 2338707, "tid": 2379456, + "ts": 6197196781922.123, "dur": 14.537, + "args": { + "External id": 28564,"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": 2338707, "tid": 2379456, + "ts": 6197196781941.929, "dur": 2.442, + "args": { + "External id": 28565,"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": 2338707, "tid": 2379456, + "ts": 6197196781943.066, "dur": 1.171, + "args": { + "External id": 28566,"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": 2338707, "tid": 2379456, + "ts": 6197196781953.973, "dur": 2.325, + "args": { + "External id": 28567,"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": 2338707, "tid": 2379456, + "ts": 6197196781955.169, "dur": 1.029, + "args": { + "External id": 28568,"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": 2338707, "tid": 2379456, + "ts": 6197196781958.533, "dur": 3.766, + "args": { + "External id": 28569,"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": 2338707, "tid": 2379456, + "ts": 6197196781959.283, "dur": 2.911, + "args": { + "External id": 28570,"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": 2338707, "tid": 2379456, + "ts": 6197196781987.590, "dur": 16.395, + "args": { + "External id": 28571,"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": 2338707, "tid": 2379456, + "ts": 6197196782018.330, "dur": 9.223, + "args": { + "External id": 28572,"Record function id": 0, "Ev Idx": 1435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197196782020.742, "dur": 6.087, + "args": { + "External id": 28573,"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": 2338707, "tid": 2379456, + "ts": 6197196782022.934, "dur": 2.911, + "args": { + "External id": 28574,"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": 2338707, "tid": 2379456, + "ts": 6197196782023.849, "dur": 1.873, + "args": { + "External id": 28575,"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": 2338707, "tid": 2379456, + "ts": 6197196782031.187, "dur": 11.200, + "args": { + "External id": 28576,"Record function id": 0, "Sequence number": 479842, "Fwd thread id": 1, "Ev Idx": 1439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196782032.793, "dur": 6.508, + "args": { + "External id": 28577,"Sequence number": 479842, "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": 2338707, "tid": 2379456, "ts": 6197196782032.793, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196782037.281, "dur": 1.807, + "args": { + "External id": 28578,"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": 2338707, "tid": 2379456, + "ts": 6197196782037.831, "dur": 1.096, + "args": { + "External id": 28579,"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": 2338707, "tid": 2379456, + "ts": 6197196782045.928, "dur": 187.042, + "args": { + "External id": 28580,"Record function id": 0, "Sequence number": 479841, "Fwd thread id": 1, "Ev Idx": 1443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196782050.268, "dur": 174.921, + "args": { + "External id": 28581,"Sequence number": 479841, "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": 2338707, "tid": 2379456, "ts": 6197196782050.268, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197196782053.708, "dur": 45.933, + "args": { + "External id": 28582,"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": 2338707, "tid": 2379456, + "ts": 6197196782091.627, "dur": 6.931, + "args": { + "External id": 28583,"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": 2338707, "tid": 2379456, + "ts": 6197196782096.859, "dur": 1.314, + "args": { + "External id": 28584,"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": 2338707, "tid": 2379456, + "ts": 6197196782101.111, "dur": 72.023, + "args": { + "External id": 28585,"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": 2338707, "tid": 2379456, + "ts": 6197196782174.461, "dur": 4.158, + "args": { + "External id": 28586,"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": 2338707, "tid": 2379456, + "ts": 6197196782175.325, "dur": 2.673, + "args": { + "External id": 28587,"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": 2338707, "tid": 2379456, + "ts": 6197196782177.193, "dur": 0.690, + "args": { + "External id": 28588,"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": 2338707, "tid": 2379456, + "ts": 6197196782180.516, "dur": 5.876, + "args": { + "External id": 28589,"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": 2338707, "tid": 2379456, + "ts": 6197196782181.514, "dur": 4.296, + "args": { + "External id": 28590,"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": 2338707, "tid": 2379456, + "ts": 6197196782185.273, "dur": 0.468, + "args": { + "External id": 28591,"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": 2338707, "tid": 2379456, + "ts": 6197196782187.013, "dur": 37.280, + "args": { + "External id": 28592,"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": 2338707, "tid": 2379456, + "ts": 6197196782239.891, "dur": 11.524, + "args": { + "External id": 28593,"Record function id": 0, "Sequence number": 479840, "Fwd thread id": 1, "Ev Idx": 1456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196782241.459, "dur": 7.222, + "args": { + "External id": 28594,"Sequence number": 479840, "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": 2338707, "tid": 2379456, "ts": 6197196782241.459, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196782243.514, "dur": 5.008, + "args": { + "External id": 28595,"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": 2338707, "tid": 2379456, + "ts": 6197196782244.803, "dur": 3.588, + "args": { + "External id": 28596,"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": 2338707, "tid": 2379456, + "ts": 6197196782254.845, "dur": 10.409, + "args": { + "External id": 28597,"Record function id": 0, "Sequence number": 479839, "Fwd thread id": 1, "Ev Idx": 1460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196782255.749, "dur": 7.254, + "args": { + "External id": 28598,"Sequence number": 479839, "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": 2338707, "tid": 2379456, "ts": 6197196782255.749, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197196782256.711, "dur": 6.069, + "args": { + "External id": 28599,"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": 2338707, "tid": 2379456, + "ts": 6197196782259.720, "dur": 2.488, + "args": { + "External id": 28600,"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": 2338707, "tid": 2379456, + "ts": 6197196782261.553, "dur": 0.475, + "args": { + "External id": 28601,"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": 2338707, "tid": 2379456, + "ts": 6197196782269.585, "dur": 6.856, + "args": { + "External id": 28602,"Record function id": 0, "Ev Idx": 1465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197196782271.014, "dur": 4.853, + "args": { + "External id": 28603,"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": 2338707, "tid": 2379456, + "ts": 6197196782272.768, "dur": 2.618, + "args": { + "External id": 28604,"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": 2338707, "tid": 2379456, + "ts": 6197196782273.524, "dur": 1.759, + "args": { + "External id": 28605,"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": 2338707, "tid": 2379456, + "ts": 6197196782279.552, "dur": 7.511, + "args": { + "External id": 28606,"Record function id": 0, "Sequence number": 479838, "Fwd thread id": 1, "Ev Idx": 1469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196782280.535, "dur": 3.422, + "args": { + "External id": 28607,"Sequence number": 479838, "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": 2338707, "tid": 2379456, "ts": 6197196782280.535, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196782281.764, "dur": 2.040, + "args": { + "External id": 28608,"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": 2338707, "tid": 2379456, + "ts": 6197196782282.521, "dur": 1.134, + "args": { + "External id": 28609,"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": 2338707, "tid": 2379456, + "ts": 6197196782291.783, "dur": 350.363, + "args": { + "External id": 28610,"Record function id": 0, "Sequence number": 479837, "Fwd thread id": 1, "Ev Idx": 1473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFuncBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197196782293.428, "dur": 326.146, + "args": { + "External id": 28611,"Sequence number": 479837, "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": 2338707, "tid": 2379456, "ts": 6197196782293.428, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338707, "tid": 2379456, + "ts": 6197196782312.019, "dur": 7.279, + "args": { + "External id": 28612,"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": 2338707, "tid": 2379456, + "ts": 6197196782315.303, "dur": 3.423, + "args": { + "External id": 28613,"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": 2338707, "tid": 2379456, + "ts": 6197196782321.256, "dur": 4.323, + "args": { + "External id": 28614,"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": 2338707, "tid": 2379456, + "ts": 6197196782323.388, "dur": 2.002, + "args": { + "External id": 28615,"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": 2338707, "tid": 2379456, + "ts": 6197196782327.380, "dur": 3.457, + "args": { + "External id": 28616,"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": 2338707, "tid": 2379456, + "ts": 6197196782328.966, "dur": 1.682, + "args": { + "External id": 28617,"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": 2338707, "tid": 2379456, + "ts": 6197196782357.733, "dur": 238.239, + "args": { + "External id": 28618,"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": 2338707, "tid": 2379456, + "ts": 6197196782436.065, "dur": 4.940, + "args": { + "External id": 28619,"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": 2338707, "tid": 2379456, + "ts": 6197196782443.117, "dur": 5.386, + "args": { + "External id": 28620,"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": 2338707, "tid": 2379456, + "ts": 6197196782449.605, "dur": 2.035, + "args": { + "External id": 28621,"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": 2338707, "tid": 2379456, + "ts": 6197196782452.623, "dur": 1.646, + "args": { + "External id": 28622,"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": 2338707, "tid": 2379456, + "ts": 6197196782499.238, "dur": 4.701, + "args": { + "External id": 28623,"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": 2338707, "tid": 2379456, + "ts": 6197196782502.276, "dur": 1.519, + "args": { + "External id": 28624,"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": 2338707, "tid": 2379456, + "ts": 6197196782508.086, "dur": 26.244, + "args": { + "External id": 28625,"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": 2338707, "tid": 2379456, + "ts": 6197196782513.376, "dur": 0.973, + "args": { + "External id": 28626,"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": 2338707, "tid": 2379456, + "ts": 6197196782535.603, "dur": 1.532, + "args": { + "External id": 28627,"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": 2338707, "tid": 2379456, + "ts": 6197196782536.484, "dur": 0.539, + "args": { + "External id": 28628,"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": 2338707, "tid": 2379456, + "ts": 6197196782537.993, "dur": 15.503, + "args": { + "External id": 28629,"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": 2338707, "tid": 2379456, + "ts": 6197196782539.976, "dur": 1.516, + "args": { + "External id": 28630,"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": 2338707, "tid": 2379456, + "ts": 6197196782608.106, "dur": 3.078, + "args": { + "External id": 28631,"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": 2338707, "tid": 2379456, + "ts": 6197196782613.910, "dur": 0.674, + "args": { + "External id": 28632,"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": 2338707, "tid": 2379456, + "ts": 6197196782616.368, "dur": 0.441, + "args": { + "External id": 28633,"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": 2338707, "tid": 2379456, + "ts": 6197196782649.734, "dur": 254.974, + "args": { + "External id": 28634,"Record function id": 0, "Sequence number": 479836, "Fwd thread id": 1, "Ev Idx": 1497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197196782651.226, "dur": 244.880, + "args": { + "External id": 28635,"Sequence number": 479836, "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": 2338707, "tid": 2379456, "ts": 6197196782651.226, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338707, "tid": 2379456, + "ts": 6197196782670.517, "dur": 64.693, + "args": { + "External id": 28636,"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": 2338707, "tid": 2379456, + "ts": 6197196782674.968, "dur": 3.299, + "args": { + "External id": 28637,"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": 2338707, "tid": 2379456, + "ts": 6197196782679.702, "dur": 54.655, + "args": { + "External id": 28638,"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": 2338707, "tid": 2379456, + "ts": 6197196782747.302, "dur": 5.945, + "args": { + "External id": 28639,"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": 2338707, "tid": 2379456, + "ts": 6197196782749.665, "dur": 3.214, + "args": { + "External id": 28640,"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": 2338707, "tid": 2379456, + "ts": 6197196782914.659, "dur": 219.194, + "args": { + "External id": 28641,"Record function id": 0, "Sequence number": 479835, "Fwd thread id": 1, "Ev Idx": 1504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197196782916.513, "dur": 207.728, + "args": { + "External id": 28642,"Sequence number": 479835, "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": 2338707, "tid": 2379456, "ts": 6197196782916.513, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338707, "tid": 2379456, + "ts": 6197196782934.815, "dur": 45.951, + "args": { + "External id": 28643,"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": 2338707, "tid": 2379456, + "ts": 6197196782938.189, "dur": 5.122, + "args": { + "External id": 28644,"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": 2338707, "tid": 2379456, + "ts": 6197196782944.292, "dur": 35.731, + "args": { + "External id": 28645,"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": 2338707, "tid": 2379456, + "ts": 6197196782988.162, "dur": 7.364, + "args": { + "External id": 28646,"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": 2338707, "tid": 2379456, + "ts": 6197196782990.988, "dur": 4.174, + "args": { + "External id": 28647,"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": 2338707, "tid": 2379456, + "ts": 6197196783143.842, "dur": 17.713, + "args": { + "External id": 28648,"Record function id": 0, "Sequence number": 479834, "Fwd thread id": 1, "Ev Idx": 1511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196783145.602, "dur": 13.114, + "args": { + "External id": 28649,"Sequence number": 479834, "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": 2338707, "tid": 2379456, "ts": 6197196783145.602, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196783148.644, "dur": 9.761, + "args": { + "External id": 28650,"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": 2338707, "tid": 2379456, + "ts": 6197196783152.519, "dur": 5.702, + "args": { + "External id": 28651,"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": 2338707, "tid": 2379456, + "ts": 6197196783165.159, "dur": 7.413, + "args": { + "External id": 28652,"Record function id": 0, "Sequence number": 479833, "Fwd thread id": 1, "Ev Idx": 1515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196783166.013, "dur": 3.966, + "args": { + "External id": 28653,"Sequence number": 479833, "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": 2338707, "tid": 2379456, "ts": 6197196783166.013, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196783167.766, "dur": 2.085, + "args": { + "External id": 28654,"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": 2338707, "tid": 2379456, + "ts": 6197196783168.878, "dur": 0.830, + "args": { + "External id": 28655,"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": 2338707, "tid": 2379456, + "ts": 6197196783178.379, "dur": 7.242, + "args": { + "External id": 28656,"Record function id": 0, "Sequence number": 479832, "Fwd thread id": 1, "Ev Idx": 1519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196783179.365, "dur": 4.263, + "args": { + "External id": 28657,"Sequence number": 479832, "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": 2338707, "tid": 2379456, "ts": 6197196783179.365, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196783180.844, "dur": 2.641, + "args": { + "External id": 28658,"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": 2338707, "tid": 2379456, + "ts": 6197196783182.086, "dur": 1.278, + "args": { + "External id": 28659,"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": 2338707, "tid": 2379456, + "ts": 6197196783189.387, "dur": 9.566, + "args": { + "External id": 28660,"Record function id": 0, "Sequence number": 479831, "Fwd thread id": 1, "Ev Idx": 1523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196783190.804, "dur": 5.265, + "args": { + "External id": 28661,"Sequence number": 479831, "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": 2338707, "tid": 2379456, "ts": 6197196783190.804, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196783191.899, "dur": 4.018, + "args": { + "External id": 28662,"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": 2338707, "tid": 2379456, + "ts": 6197196783195.009, "dur": 0.821, + "args": { + "External id": 28663,"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": 2338707, "tid": 2379456, + "ts": 6197196783202.188, "dur": 202.523, + "args": { + "External id": 28664,"Record function id": 0, "Sequence number": 479830, "Fwd thread id": 1, "Ev Idx": 1527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196783202.946, "dur": 193.218, + "args": { + "External id": 28665,"Sequence number": 479830, "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": 2338707, "tid": 2379456, "ts": 6197196783202.946, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197196783208.113, "dur": 6.928, + "args": { + "External id": 28666,"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": 2338707, "tid": 2379456, + "ts": 6197196783209.967, "dur": 4.373, + "args": { + "External id": 28667,"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": 2338707, "tid": 2379456, + "ts": 6197196783212.382, "dur": 1.654, + "args": { + "External id": 28668,"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": 2338707, "tid": 2379456, + "ts": 6197196783219.193, "dur": 74.594, + "args": { + "External id": 28669,"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": 2338707, "tid": 2379456, + "ts": 6197196783295.454, "dur": 7.017, + "args": { + "External id": 28670,"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": 2338707, "tid": 2379456, + "ts": 6197196783296.124, "dur": 5.396, + "args": { + "External id": 28671,"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": 2338707, "tid": 2379456, + "ts": 6197196783298.027, "dur": 3.327, + "args": { + "External id": 28672,"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": 2338707, "tid": 2379456, + "ts": 6197196783330.781, "dur": 13.934, + "args": { + "External id": 28673,"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": 2338707, "tid": 2379456, + "ts": 6197196783332.226, "dur": 11.913, + "args": { + "External id": 28674,"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": 2338707, "tid": 2379456, + "ts": 6197196783343.554, "dur": 0.476, + "args": { + "External id": 28675,"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": 2338707, "tid": 2379456, + "ts": 6197196783345.460, "dur": 49.968, + "args": { + "External id": 28676,"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": 2338707, "tid": 2379456, + "ts": 6197196783409.920, "dur": 7.626, + "args": { + "External id": 28677,"Record function id": 0, "Sequence number": 479829, "Fwd thread id": 1, "Ev Idx": 1540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196783410.893, "dur": 4.800, + "args": { + "External id": 28678,"Sequence number": 479829, "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": 2338707, "tid": 2379456, "ts": 6197196783410.893, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196783412.926, "dur": 2.622, + "args": { + "External id": 28679,"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": 2338707, "tid": 2379456, + "ts": 6197196783414.121, "dur": 1.293, + "args": { + "External id": 28680,"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": 2338707, "tid": 2379456, + "ts": 6197196783421.544, "dur": 10.745, + "args": { + "External id": 28681,"Record function id": 0, "Sequence number": 479828, "Fwd thread id": 1, "Ev Idx": 1544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196783422.289, "dur": 7.037, + "args": { + "External id": 28682,"Sequence number": 479828, "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": 2338707, "tid": 2379456, "ts": 6197196783422.289, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197196783423.254, "dur": 5.867, + "args": { + "External id": 28683,"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": 2338707, "tid": 2379456, + "ts": 6197196783426.334, "dur": 2.203, + "args": { + "External id": 28684,"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": 2338707, "tid": 2379456, + "ts": 6197196783427.884, "dur": 0.534, + "args": { + "External id": 28685,"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": 2338707, "tid": 2379456, + "ts": 6197196783438.454, "dur": 10.109, + "args": { + "External id": 28686,"Record function id": 0, "Ev Idx": 1549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197196783440.345, "dur": 7.309, + "args": { + "External id": 28687,"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": 2338707, "tid": 2379456, + "ts": 6197196783442.861, "dur": 4.280, + "args": { + "External id": 28688,"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": 2338707, "tid": 2379456, + "ts": 6197196783444.072, "dur": 2.966, + "args": { + "External id": 28689,"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": 2338707, "tid": 2379456, + "ts": 6197196783451.744, "dur": 7.132, + "args": { + "External id": 28690,"Record function id": 0, "Sequence number": 479827, "Fwd thread id": 1, "Ev Idx": 1553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196783452.810, "dur": 3.830, + "args": { + "External id": 28691,"Sequence number": 479827, "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": 2338707, "tid": 2379456, "ts": 6197196783452.810, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196783454.389, "dur": 2.092, + "args": { + "External id": 28692,"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": 2338707, "tid": 2379456, + "ts": 6197196783455.479, "dur": 0.881, + "args": { + "External id": 28693,"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": 2338707, "tid": 2379456, + "ts": 6197196783464.408, "dur": 100.759, + "args": { + "External id": 28694,"Record function id": 0, "Sequence number": 479826, "Fwd thread id": 1, "Ev Idx": 1557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196783465.382, "dur": 91.449, + "args": { + "External id": 28695,"Sequence number": 479826, "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": 2338707, "tid": 2379456, "ts": 6197196783465.382, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197196783468.588, "dur": 5.637, + "args": { + "External id": 28696,"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": 2338707, "tid": 2379456, + "ts": 6197196783469.134, "dur": 4.579, + "args": { + "External id": 28697,"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": 2338707, "tid": 2379456, + "ts": 6197196783473.132, "dur": 0.469, + "args": { + "External id": 28698,"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": 2338707, "tid": 2379456, + "ts": 6197196783474.880, "dur": 30.976, + "args": { + "External id": 28699,"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": 2338707, "tid": 2379456, + "ts": 6197196783508.961, "dur": 4.109, + "args": { + "External id": 28700,"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": 2338707, "tid": 2379456, + "ts": 6197196783509.567, "dur": 2.957, + "args": { + "External id": 28701,"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": 2338707, "tid": 2379456, + "ts": 6197196783511.082, "dur": 1.270, + "args": { + "External id": 28702,"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": 2338707, "tid": 2379456, + "ts": 6197196783514.395, "dur": 3.789, + "args": { + "External id": 28703,"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": 2338707, "tid": 2379456, + "ts": 6197196783515.368, "dur": 2.294, + "args": { + "External id": 28704,"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": 2338707, "tid": 2379456, + "ts": 6197196783517.129, "dur": 0.467, + "args": { + "External id": 28705,"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": 2338707, "tid": 2379456, + "ts": 6197196783520.782, "dur": 35.306, + "args": { + "External id": 28706,"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": 2338707, "tid": 2379456, + "ts": 6197196783570.042, "dur": 33.575, + "args": { + "External id": 28707,"Record function id": 0, "Sequence number": 479825, "Fwd thread id": 1, "Ev Idx": 1570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196783571.013, "dur": 4.029, + "args": { + "External id": 28708,"Sequence number": 479825, "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": 2338707, "tid": 2379456, "ts": 6197196783571.013, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196783572.770, "dur": 2.129, + "args": { + "External id": 28709,"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": 2338707, "tid": 2379456, + "ts": 6197196783573.838, "dur": 0.953, + "args": { + "External id": 28710,"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": 2338707, "tid": 2379456, + "ts": 6197196783578.031, "dur": 22.689, + "args": { + "External id": 28711,"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": 2338707, "tid": 2379456, + "ts": 6197196783608.176, "dur": 8.364, + "args": { + "External id": 28712,"Record function id": 0, "Sequence number": 479824, "Fwd thread id": 1, "Ev Idx": 1575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196783609.171, "dur": 4.777, + "args": { + "External id": 28713,"Sequence number": 479824, "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": 2338707, "tid": 2379456, "ts": 6197196783609.171, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197196783610.065, "dur": 3.698, + "args": { + "External id": 28714,"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": 2338707, "tid": 2379456, + "ts": 6197196783610.717, "dur": 2.489, + "args": { + "External id": 28715,"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": 2338707, "tid": 2379456, + "ts": 6197196783612.464, "dur": 0.627, + "args": { + "External id": 28716,"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": 2338707, "tid": 2379456, + "ts": 6197196783620.625, "dur": 9.075, + "args": { + "External id": 28717,"Record function id": 0, "Ev Idx": 1580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197196783622.229, "dur": 6.917, + "args": { + "External id": 28718,"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": 2338707, "tid": 2379456, + "ts": 6197196783623.146, "dur": 5.503, + "args": { + "External id": 28719,"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": 2338707, "tid": 2379456, + "ts": 6197196783625.549, "dur": 2.993, + "args": { + "External id": 28720,"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": 2338707, "tid": 2379456, + "ts": 6197196783632.960, "dur": 6.538, + "args": { + "External id": 28721,"Record function id": 0, "Sequence number": 479823, "Fwd thread id": 1, "Ev Idx": 1584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196783634.627, "dur": 2.744, + "args": { + "External id": 28722,"Sequence number": 479823, "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": 2338707, "tid": 2379456, "ts": 6197196783634.627, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196783635.599, "dur": 1.615, + "args": { + "External id": 28723,"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": 2338707, "tid": 2379456, + "ts": 6197196783636.295, "dur": 0.838, + "args": { + "External id": 28724,"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": 2338707, "tid": 2379456, + "ts": 6197196783642.893, "dur": 128.114, + "args": { + "External id": 28725,"Record function id": 0, "Sequence number": 479822, "Fwd thread id": 1, "Ev Idx": 1588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196783643.820, "dur": 116.887, + "args": { + "External id": 28726,"Sequence number": 479822, "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": 2338707, "tid": 2379456, "ts": 6197196783643.820, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197196783646.707, "dur": 4.686, + "args": { + "External id": 28727,"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": 2338707, "tid": 2379456, + "ts": 6197196783649.206, "dur": 1.730, + "args": { + "External id": 28728,"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": 2338707, "tid": 2379456, + "ts": 6197196783650.180, "dur": 0.649, + "args": { + "External id": 28729,"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": 2338707, "tid": 2379456, + "ts": 6197196783652.031, "dur": 34.901, + "args": { + "External id": 28730,"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": 2338707, "tid": 2379456, + "ts": 6197196783688.000, "dur": 3.649, + "args": { + "External id": 28731,"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": 2338707, "tid": 2379456, + "ts": 6197196783688.514, "dur": 2.548, + "args": { + "External id": 28732,"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": 2338707, "tid": 2379456, + "ts": 6197196783690.084, "dur": 0.853, + "args": { + "External id": 28733,"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": 2338707, "tid": 2379456, + "ts": 6197196783695.217, "dur": 24.979, + "args": { + "External id": 28734,"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": 2338707, "tid": 2379456, + "ts": 6197196783696.342, "dur": 22.856, + "args": { + "External id": 28735,"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": 2338707, "tid": 2379456, + "ts": 6197196783718.276, "dur": 0.592, + "args": { + "External id": 28736,"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": 2338707, "tid": 2379456, + "ts": 6197196783720.814, "dur": 38.942, + "args": { + "External id": 28737,"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": 2338707, "tid": 2379456, + "ts": 6197196783778.800, "dur": 30.573, + "args": { + "External id": 28738,"Record function id": 0, "Sequence number": 479821, "Fwd thread id": 1, "Ev Idx": 1601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196783779.883, "dur": 6.525, + "args": { + "External id": 28739,"Sequence number": 479821, "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": 2338707, "tid": 2379456, "ts": 6197196783779.883, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196783783.764, "dur": 2.493, + "args": { + "External id": 28740,"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": 2338707, "tid": 2379456, + "ts": 6197196783784.843, "dur": 1.281, + "args": { + "External id": 28741,"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": 2338707, "tid": 2379456, + "ts": 6197196783788.998, "dur": 17.485, + "args": { + "External id": 28742,"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": 2338707, "tid": 2379456, + "ts": 6197196783813.524, "dur": 9.567, + "args": { + "External id": 28743,"Record function id": 0, "Sequence number": 479820, "Fwd thread id": 1, "Ev Idx": 1606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197196783814.533, "dur": 6.846, + "args": { + "External id": 28744,"Sequence number": 479820, "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": 2338707, "tid": 2379456, "ts": 6197196783814.533, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197196783815.458, "dur": 5.680, + "args": { + "External id": 28745,"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": 2338707, "tid": 2379456, + "ts": 6197196783816.139, "dur": 4.449, + "args": { + "External id": 28746,"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": 2338707, "tid": 2379456, + "ts": 6197196783817.784, "dur": 2.693, + "args": { + "External id": 28747,"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": 2338707, "tid": 2379456, + "ts": 6197196783827.382, "dur": 5.735, + "args": { + "External id": 28748,"Record function id": 0, "Ev Idx": 1611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197196783828.799, "dur": 3.811, + "args": { + "External id": 28749,"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": 2338707, "tid": 2379456, + "ts": 6197196783830.203, "dur": 2.019, + "args": { + "External id": 28750,"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": 2338707, "tid": 2379456, + "ts": 6197196783830.817, "dur": 1.277, + "args": { + "External id": 28751,"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": 2338707, "tid": 2379456, + "ts": 6197196783837.143, "dur": 415.136, + "args": { + "External id": 28752,"Record function id": 0, "Sequence number": 479819, "Fwd thread id": 1, "Ev Idx": 1615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197196783838.665, "dur": 375.481, + "args": { + "External id": 28753,"Sequence number": 479819, "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": 2338707, "tid": 2379456, "ts": 6197196783838.665, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197196783875.907, "dur": 2.477, + "args": { + "External id": 28754,"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": 2338707, "tid": 2379456, + "ts": 6197196783877.176, "dur": 1.087, + "args": { + "External id": 28755,"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": 2338707, "tid": 2379456, + "ts": 6197196783893.744, "dur": 4.067, + "args": { + "External id": 28756,"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": 2338707, "tid": 2379456, + "ts": 6197196783907.207, "dur": 2.242, + "args": { + "External id": 28757,"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": 2338707, "tid": 2379456, + "ts": 6197196784093.301, "dur": 3.017, + "args": { + "External id": 28758,"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": 2338707, "tid": 2379456, + "ts": 6197196784102.016, "dur": 41.854, + "args": { + "External id": 28759,"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": 2338707, "tid": 2379456, + "ts": 6197196784115.134, "dur": 1.174, + "args": { + "External id": 28760,"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": 2338707, "tid": 2379456, + "ts": 6197196784149.798, "dur": 34.094, + "args": { + "External id": 28761,"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": 2338707, "tid": 2379456, + "ts": 6197196784153.568, "dur": 30.118, + "args": { + "External id": 28762,"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": 2338707, "tid": 2379456, + "ts": 6197196784158.152, "dur": 5.304, + "args": { + "External id": 28763,"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": 2338707, "tid": 2379456, + "ts": 6197196784165.009, "dur": 17.935, + "args": { + "External id": 28764,"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": 2338707, "tid": 2379456, + "ts": 6197196784188.625, "dur": 5.094, + "args": { + "External id": 28765,"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": 2338707, "tid": 2379456, + "ts": 6197196784189.909, "dur": 3.713, + "args": { + "External id": 28766,"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": 2338707, "tid": 2379456, + "ts": 6197196784202.172, "dur": 4.835, + "args": { + "External id": 28767,"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": 2338707, "tid": 2379456, + "ts": 6197196784205.754, "dur": 1.139, + "args": { + "External id": 28768,"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": 2338707, "tid": 2379456, + "ts": 6197196784230.096, "dur": 16.153, + "args": { + "External id": 28769,"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": 2338707, "tid": 2379456, + "ts": 6197196784264.050, "dur": 8.515, + "args": { + "External id": 28770,"Record function id": 0, "Ev Idx": 1633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197196784266.170, "dur": 5.699, + "args": { + "External id": 28771,"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": 2338707, "tid": 2379456, + "ts": 6197196784268.182, "dur": 2.849, + "args": { + "External id": 28772,"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": 2338707, "tid": 2379456, + "ts": 6197196784269.014, "dur": 1.915, + "args": { + "External id": 28773,"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": 2338707, "tid": 2379456, + "ts": 6197196784277.121, "dur": 2845.281, + "args": { + "External id": 28774,"Record function id": 0, "Ev Idx": 1637 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.25)", "pid": 2338707, "tid": 2379456, + "ts": 6197196784310.603, "dur": 971.195, + "args": { + "External id": 28775,"Record function id": 0, "Ev Idx": 1638 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.24", "pid": 2338707, "tid": 2379456, + "ts": 6197196784335.199, "dur": 938.579, + "args": { + "External id": 28776,"Record function id": 0, "Ev Idx": 1639 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.24)", "pid": 2338707, "tid": 2379456, + "ts": 6197196784351.674, "dur": 906.388, + "args": { + "External id": 28777,"Record function id": 0, "Ev Idx": 1640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197196784440.509, "dur": 5.387, + "args": { + "External id": 28778,"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": 2338707, "tid": 2379456, + "ts": 6197196784462.614, "dur": 33.413, + "args": { + "External id": 28779,"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": 2338707, "tid": 2379456, + "ts": 6197196784467.339, "dur": 1.393, + "args": { + "External id": 28780,"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": 2338707, "tid": 2379456, + "ts": 6197196784471.865, "dur": 0.386, + "args": { + "External id": 28781,"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": 2338707, "tid": 2379456, + "ts": 6197196784473.960, "dur": 0.393, + "args": { + "External id": 28782,"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": 2338707, "tid": 2379456, + "ts": 6197196784475.922, "dur": 1.812, + "args": { + "External id": 28783,"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": 2338707, "tid": 2379456, + "ts": 6197196784479.219, "dur": 0.252, + "args": { + "External id": 28784,"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": 2338707, "tid": 2379456, + "ts": 6197196784480.947, "dur": 2.265, + "args": { + "External id": 28785,"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": 2338707, "tid": 2379456, + "ts": 6197196784486.664, "dur": 0.376, + "args": { + "External id": 28786,"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": 2338707, "tid": 2379456, + "ts": 6197196784488.409, "dur": 0.349, + "args": { + "External id": 28787,"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": 2338707, "tid": 2379456, + "ts": 6197196784490.041, "dur": 0.395, + "args": { + "External id": 28788,"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": 2338707, "tid": 2379456, + "ts": 6197196784509.714, "dur": 46.229, + "args": { + "External id": 28789,"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": 2338707, "tid": 2379456, + "ts": 6197196784600.473, "dur": 148.898, + "args": { + "External id": 28790,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2379456, + "ts": 6197196784612.343, "dur": 4.142, + "args": { + "External id": 28791,"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": 2338707, "tid": 2379456, + "ts": 6197196784622.471, "dur": 11.376, + "args": { + "External id": 28792,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2379456, + "ts": 6197196784626.301, "dur": 7.148, + "args": { + "External id": 28793,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2379456, + "ts": 6197196784629.879, "dur": 2.195, + "args": { + "External id": 28794,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197196784640.788, "dur": 30.630, + "args": { + "External id": 28795,"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": 2338707, "tid": 2379456, + "ts": 6197196784642.839, "dur": 0.574, + "args": { + "External id": 28796,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197196784644.944, "dur": 0.428, + "args": { + "External id": 28797,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2379456, + "ts": 6197196784646.778, "dur": 2.723, + "args": { + "External id": 28798,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2379456, + "ts": 6197196784651.790, "dur": 0.345, + "args": { + "External id": 28799,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2379456, + "ts": 6197196784654.114, "dur": 0.399, + "args": { + "External id": 28800,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2379456, + "ts": 6197196784655.923, "dur": 1.614, + "args": { + "External id": 28801,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2379456, + "ts": 6197196784659.112, "dur": 0.369, + "args": { + "External id": 28802,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2379456, + "ts": 6197196784660.928, "dur": 0.282, + "args": { + "External id": 28803,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2379456, + "ts": 6197196784664.342, "dur": 0.426, + "args": { + "External id": 28804,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2379456, + "ts": 6197196784682.823, "dur": 56.312, + "args": { + "External id": 28805,"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": 2338707, "tid": 2379456, + "ts": 6197196784812.501, "dur": 336.132, + "args": { + "External id": 28806,"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": 2338707, "tid": 2379456, + "ts": 6197196784845.641, "dur": 297.588, + "args": { + "External id": 28807,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197196784856.543, "dur": 280.608, + "args": { + "External id": 28808,"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": 2338707, "tid": 2379456, + "ts": 6197196785174.100, "dur": 2.549, + "args": { + "External id": 28809,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197196785289.878, "dur": 1804.974, + "args": { + "External id": 28810,"Sequence number": 479818, "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": 2338707, "tid": 2379456, "ts": 6197196785289.878, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6197196785415.387, "dur": 110.579, + "args": { + "External id": 28811,"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": 2338707, "tid": 2379456, + "ts": 6197196785570.740, "dur": 43.626, + "args": { + "External id": 28812,"kernel_hash": "cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/u7/cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs.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": 2338707, "tid": 2379456, + "ts": 6197196785633.680, "dur": 50.099, + "args": { + "External id": 28813,"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": 2338707, "tid": 2379456, + "ts": 6197196785696.176, "dur": 54.535, + "args": { + "External id": 28814,"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": 2338707, "tid": 2379456, + "ts": 6197196785759.787, "dur": 36.954, + "args": { + "External id": 28815,"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": 2338707, "tid": 2379456, + "ts": 6197196785803.687, "dur": 31.878, + "args": { + "External id": 28816,"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": 2338707, "tid": 2379456, + "ts": 6197196785843.461, "dur": 28.748, + "args": { + "External id": 28817,"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": 2338707, "tid": 2379456, + "ts": 6197196785902.693, "dur": 25.971, + "args": { + "External id": 28818,"kernel_hash": "cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/wm/cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s.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": 2338707, "tid": 2379456, + "ts": 6197196785953.159, "dur": 29.053, + "args": { + "External id": 28819,"kernel_hash": "cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql", "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/qt/cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql.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": 2338707, "tid": 2379456, + "ts": 6197196786004.444, "dur": 19.925, + "args": { + "External id": 28820,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197196786044.610, "dur": 50.492, + "args": { + "External id": 28821,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197196786107.119, "dur": 43.607, + "args": { + "External id": 28822,"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": 2338707, "tid": 2379456, + "ts": 6197196786154.448, "dur": 33.425, + "args": { + "External id": 28823,"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": 2338707, "tid": 2379456, + "ts": 6197196786222.610, "dur": 252.286, + "args": { + "External id": 28824,"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": 2338707, "tid": 2379456, + "ts": 6197196786304.515, "dur": 6.419, + "args": { + "External id": 28825,"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": 2338707, "tid": 2379456, + "ts": 6197196786313.102, "dur": 2.201, + "args": { + "External id": 28826,"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": 2338707, "tid": 2379456, + "ts": 6197196786316.737, "dur": 3.683, + "args": { + "External id": 28827,"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": 2338707, "tid": 2379456, + "ts": 6197196786321.628, "dur": 1.949, + "args": { + "External id": 28828,"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": 2338707, "tid": 2379456, + "ts": 6197196786365.726, "dur": 6.387, + "args": { + "External id": 28829,"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": 2338707, "tid": 2379456, + "ts": 6197196786367.962, "dur": 3.932, + "args": { + "External id": 28830,"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": 2338707, "tid": 2379456, + "ts": 6197196786374.149, "dur": 34.522, + "args": { + "External id": 28831,"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": 2338707, "tid": 2379456, + "ts": 6197196786380.158, "dur": 3.278, + "args": { + "External id": 28832,"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": 2338707, "tid": 2379456, + "ts": 6197196786410.281, "dur": 2.397, + "args": { + "External id": 28833,"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": 2338707, "tid": 2379456, + "ts": 6197196786411.752, "dur": 0.846, + "args": { + "External id": 28834,"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": 2338707, "tid": 2379456, + "ts": 6197196786413.789, "dur": 16.720, + "args": { + "External id": 28835,"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": 2338707, "tid": 2379456, + "ts": 6197196786417.196, "dur": 0.454, + "args": { + "External id": 28836,"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": 2338707, "tid": 2379456, + "ts": 6197196786515.200, "dur": 29.443, + "args": { + "External id": 28837,"kernel_hash": "cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4", "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/yk/cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4.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": 2338707, "tid": 2379456, + "ts": 6197196786564.093, "dur": 17.514, + "args": { + "External id": 28838,"kernel_hash": "ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg", "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/eu/ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg.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": 2338707, "tid": 2379456, + "ts": 6197196786588.959, "dur": 42.192, + "args": { + "External id": 28839,"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": 2338707, "tid": 2379456, + "ts": 6197196786637.426, "dur": 36.206, + "args": { + "External id": 28840,"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": 2338707, "tid": 2379456, + "ts": 6197196786684.560, "dur": 39.131, + "args": { + "External id": 28841,"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": 2338707, "tid": 2379456, + "ts": 6197196786732.186, "dur": 34.923, + "args": { + "External id": 28842,"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": 2338707, "tid": 2379456, + "ts": 6197196786774.193, "dur": 27.366, + "args": { + "External id": 28843,"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": 2338707, "tid": 2379456, + "ts": 6197196786807.814, "dur": 29.942, + "args": { + "External id": 28844,"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": 2338707, "tid": 2379456, + "ts": 6197196786860.860, "dur": 24.318, + "args": { + "External id": 28845,"kernel_hash": "c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/6w/c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7.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": 2338707, "tid": 2379456, + "ts": 6197196786905.351, "dur": 24.785, + "args": { + "External id": 28846,"kernel_hash": "ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx", "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/kj/ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx.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": 2338707, "tid": 2379456, + "ts": 6197196786947.681, "dur": 16.308, + "args": { + "External id": 28847,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197196786983.807, "dur": 13.938, + "args": { + "External id": 28848,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197196787013.168, "dur": 16.393, + "args": { + "External id": 28849,"kernel_hash": "cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/eb/cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b.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": 2338707, "tid": 2379456, + "ts": 6197196787145.241, "dur": 17.331, + "args": { + "External id": 28850,"Record function id": 0, "Ev Idx": 1713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197196787149.103, "dur": 12.230, + "args": { + "External id": 28851,"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": 2338707, "tid": 2379456, + "ts": 6197196787153.563, "dur": 6.528, + "args": { + "External id": 28852,"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": 2338707, "tid": 2379456, + "ts": 6197196787155.041, "dur": 4.900, + "args": { + "External id": 28853,"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": 2338707, "tid": 2379456, + "ts": 6197196787179.351, "dur": 9.144, + "args": { + "External id": 28854,"Record function id": 0, "Ev Idx": 1717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197196787181.982, "dur": 5.676, + "args": { + "External id": 28855,"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": 2338707, "tid": 2379456, + "ts": 6197196787183.450, "dur": 2.425, + "args": { + "External id": 28856,"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": 2338707, "tid": 2379456, + "ts": 6197196787184.247, "dur": 1.404, + "args": { + "External id": 28857,"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": 2338707, "tid": 2379456, + "ts": 6197196787191.989, "dur": 5.204, + "args": { + "External id": 28858,"Record function id": 0, "Ev Idx": 1721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197196787193.598, "dur": 3.171, + "args": { + "External id": 28859,"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": 2338707, "tid": 2379456, + "ts": 6197196787194.125, "dur": 1.997, + "args": { + "External id": 28860,"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": 2338707, "tid": 2379456, + "ts": 6197196787195.439, "dur": 0.568, + "args": { + "External id": 28861,"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": 2338707, "tid": 2379456, + "ts": 6197196787200.476, "dur": 6.699, + "args": { + "External id": 28862,"Record function id": 0, "Ev Idx": 1725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197196787201.927, "dur": 4.824, + "args": { + "External id": 28863,"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": 2338707, "tid": 2379456, + "ts": 6197196787202.643, "dur": 3.636, + "args": { + "External id": 28864,"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": 2338707, "tid": 2379456, + "ts": 6197196787202.930, "dur": 3.288, + "args": { + "External id": 28865,"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": 2338707, "tid": 2379456, + "ts": 6197196787210.198, "dur": 14.178, + "args": { + "External id": 28866,"Record function id": 0, "Ev Idx": 1729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197196787211.972, "dur": 11.976, + "args": { + "External id": 28867,"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": 2338707, "tid": 2379456, + "ts": 6197196787222.262, "dur": 1.143, + "args": { + "External id": 28868,"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": 2338707, "tid": 2379456, + "ts": 6197196787222.586, "dur": 0.736, + "args": { + "External id": 28869,"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": 2338707, "tid": 2379456, + "ts": 6197196787227.425, "dur": 6.020, + "args": { + "External id": 28870,"Record function id": 0, "Ev Idx": 1733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197196787228.892, "dur": 4.149, + "args": { + "External id": 28871,"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": 2338707, "tid": 2379456, + "ts": 6197196787229.622, "dur": 3.019, + "args": { + "External id": 28872,"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": 2338707, "tid": 2379456, + "ts": 6197196787231.961, "dur": 0.562, + "args": { + "External id": 28873,"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": 2338707, "tid": 2379456, + "ts": 6197196787237.809, "dur": 4.336, + "args": { + "External id": 28874,"Record function id": 0, "Ev Idx": 1737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197196787239.281, "dur": 2.474, + "args": { + "External id": 28875,"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": 2338707, "tid": 2379456, + "ts": 6197196787239.956, "dur": 1.147, + "args": { + "External id": 28876,"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": 2338707, "tid": 2379456, + "ts": 6197196787240.384, "dur": 0.635, + "args": { + "External id": 28877,"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": 2338707, "tid": 2379456, + "ts": 6197196787245.286, "dur": 4.107, + "args": { + "External id": 28878,"Record function id": 0, "Ev Idx": 1741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197196787246.667, "dur": 2.318, + "args": { + "External id": 28879,"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": 2338707, "tid": 2379456, + "ts": 6197196787247.396, "dur": 1.055, + "args": { + "External id": 28880,"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": 2338707, "tid": 2379456, + "ts": 6197196787247.693, "dur": 0.694, + "args": { + "External id": 28881,"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": 2338707, "tid": 2379456, + "ts": 6197196787252.571, "dur": 4.469, + "args": { + "External id": 28882,"Record function id": 0, "Ev Idx": 1745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197196787254.206, "dur": 2.443, + "args": { + "External id": 28883,"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": 2338707, "tid": 2379456, + "ts": 6197196787255.147, "dur": 1.027, + "args": { + "External id": 28884,"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": 2338707, "tid": 2379456, + "ts": 6197196787255.506, "dur": 0.605, + "args": { + "External id": 28885,"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": 2338707, "tid": 2379456, + "ts": 6197196787261.558, "dur": 288043.966, + "args": { + "External id": 28886,"Record function id": 0, "Sequence number": 479817, "Fwd thread id": 1, "Ev Idx": 1749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197196787263.614, "dur": 288032.038, + "args": { + "External id": 28887,"Sequence number": 479817, "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": 2338707, "tid": 2379456, "ts": 6197196787263.614, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.25)", "pid": 2338707, "tid": 2379456, + "ts": 6197196787300.251, "dur": 47.778, + "args": { + "External id": 28888,"Record function id": 0, "Ev Idx": 1751 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.25)", "pid": 2338707, "tid": 2379456, + "ts": 6197196787356.620, "dur": 83.707, + "args": { + "External id": 28889,"Record function id": 0, "Ev Idx": 1752 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.25)", "pid": 2338707, "tid": 2379456, + "ts": 6197196787447.037, "dur": 287839.963, + "args": { + "External id": 28890,"Record function id": 0, "Ev Idx": 1753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197196787506.815, "dur": 8.223, + "args": { + "External id": 28891,"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": 2338707, "tid": 2379456, + "ts": 6197196787524.612, "dur": 4.301, + "args": { + "External id": 28892,"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": 2338707, "tid": 2379456, + "ts": 6197196787546.931, "dur": 286876.773, + "args": { + "External id": 28893,"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": 2338707, "tid": 2379456, + "ts": 6197196787561.170, "dur": 286848.952, + "args": { + "External id": 28894,"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": 2338707, "tid": 2379456, + "ts": 6197196787680.174, "dur": 7.436, + "args": { + "External id": 28895,"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": 2338707, "tid": 2379456, + "ts": 6197196787731.615, "dur": 286630.588, + "args": { + "External id": 28896,"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": 2338707, "tid": 2379456, + "ts": 6197196787734.384, "dur": 286626.669, + "args": { + "External id": 28897,"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": 2338707, "tid": 2379456, + "ts": 6197196787739.474, "dur": 16.190, + "args": { + "External id": 28898,"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": 2338707, "tid": 2379456, + "ts": 6197196787757.992, "dur": 286597.755, + "args": { + "External id": 28899,"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": 2338707, "tid": 2379456, + "ts": 6197197074537.907, "dur": 17.553, + "args": { + "External id": 28900,"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": 2338707, "tid": 2379456, + "ts": 6197197074545.580, "dur": 9.461, + "args": { + "External id": 28901,"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": 2338707, "tid": 2379456, + "ts": 6197197074593.837, "dur": 324.240, + "args": { + "External id": 28902,"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": 2338707, "tid": 2379456, + "ts": 6197197074627.526, "dur": 285.340, + "args": { + "External id": 28903,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197197074638.997, "dur": 267.794, + "args": { + "External id": 28904,"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": 2338707, "tid": 2379456, + "ts": 6197197074942.617, "dur": 2.116, + "args": { + "External id": 28905,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2379456, + "ts": 6197197075006.075, "dur": 6.919, + "args": { + "External id": 28906,"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": 2338707, "tid": 2379456, + "ts": 6197197075109.020, "dur": 2.418, + "args": { + "External id": 28907,"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": 2338707, "tid": 2379456, + "ts": 6197197075130.440, "dur": 1.506, + "args": { + "External id": 28908,"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": 2338707, "tid": 2379456, + "ts": 6197197075148.746, "dur": 0.920, + "args": { + "External id": 28909,"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": 2338707, "tid": 2379456, + "ts": 6197197075163.032, "dur": 0.860, + "args": { + "External id": 28910,"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": 2338707, "tid": 2379456, + "ts": 6197197075175.825, "dur": 0.808, + "args": { + "External id": 28911,"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": 2338707, "tid": 2379456, + "ts": 6197197075188.195, "dur": 1.084, + "args": { + "External id": 28912,"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": 2338707, "tid": 2379456, + "ts": 6197197075206.425, "dur": 2.976, + "args": { + "External id": 28913,"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": 2338707, "tid": 2379456, + "ts": 6197197075219.491, "dur": 0.929, + "args": { + "External id": 28914,"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": 2338707, "tid": 2379456, + "ts": 6197197075321.354, "dur": 3040.235, + "args": { + "External id": 28915,"Record function id": 0, "Ev Idx": 1778 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.24)", "pid": 2338707, "tid": 2379456, + "ts": 6197197075342.541, "dur": 1165.477, + "args": { + "External id": 28916,"Record function id": 0, "Ev Idx": 1779 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.24)", "pid": 2338707, "tid": 2379456, + "ts": 6197197075358.025, "dur": 378.649, + "args": { + "External id": 28917,"Record function id": 0, "Ev Idx": 1780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6197197075451.307, "dur": 4.583, + "args": { + "External id": 28918,"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": 2338707, "tid": 2379456, + "ts": 6197197075459.662, "dur": 1.130, + "args": { + "External id": 28919,"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": 2338707, "tid": 2379456, + "ts": 6197197075462.665, "dur": 1.026, + "args": { + "External id": 28920,"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": 2338707, "tid": 2379456, + "ts": 6197197075465.671, "dur": 2.785, + "args": { + "External id": 28921,"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": 2338707, "tid": 2379456, + "ts": 6197197075470.331, "dur": 1.392, + "args": { + "External id": 28922,"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": 2338707, "tid": 2379456, + "ts": 6197197075475.148, "dur": 0.793, + "args": { + "External id": 28923,"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": 2338707, "tid": 2379456, + "ts": 6197197075477.648, "dur": 2.752, + "args": { + "External id": 28924,"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": 2338707, "tid": 2379456, + "ts": 6197197075482.165, "dur": 0.945, + "args": { + "External id": 28925,"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": 2338707, "tid": 2379456, + "ts": 6197197075484.968, "dur": 0.969, + "args": { + "External id": 28926,"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": 2338707, "tid": 2379456, + "ts": 6197197075489.502, "dur": 1.163, + "args": { + "External id": 28927,"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": 2338707, "tid": 2379456, + "ts": 6197197075509.954, "dur": 176.684, + "args": { + "External id": 28928,"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": 2338707, "tid": 2379456, + "ts": 6197197075527.112, "dur": 154.684, + "args": { + "External id": 28929,"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": 2338707, "tid": 2379456, + "ts": 6197197075556.784, "dur": 15.606, + "args": { + "External id": 28930,"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": 2338707, "tid": 2379456, + "ts": 6197197075577.487, "dur": 71.224, + "args": { + "External id": 28931,"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": 2338707, "tid": 2379456, + "ts": 6197197075579.972, "dur": 68.331, + "args": { + "External id": 28932,"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": 2338707, "tid": 2379456, + "ts": 6197197075586.191, "dur": 8.750, + "args": { + "External id": 28933,"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": 2338707, "tid": 2379456, + "ts": 6197197075596.480, "dur": 51.136, + "args": { + "External id": 28934,"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": 2338707, "tid": 2379456, + "ts": 6197197075834.400, "dur": 664.619, + "args": { + "External id": 28935,"Record function id": 0, "Ev Idx": 1798 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.23)", "pid": 2338707, "tid": 2379456, + "ts": 6197197075852.585, "dur": 633.824, + "args": { + "External id": 28936,"Record function id": 0, "Ev Idx": 1799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197197075919.131, "dur": 5.716, + "args": { + "External id": 28937,"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": 2338707, "tid": 2379456, + "ts": 6197197075940.242, "dur": 35.562, + "args": { + "External id": 28938,"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": 2338707, "tid": 2379456, + "ts": 6197197075945.412, "dur": 1.996, + "args": { + "External id": 28939,"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": 2338707, "tid": 2379456, + "ts": 6197197075949.682, "dur": 1.364, + "args": { + "External id": 28940,"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": 2338707, "tid": 2379456, + "ts": 6197197075952.860, "dur": 0.247, + "args": { + "External id": 28941,"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": 2338707, "tid": 2379456, + "ts": 6197197075954.278, "dur": 0.437, + "args": { + "External id": 28942,"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": 2338707, "tid": 2379456, + "ts": 6197197075957.143, "dur": 0.355, + "args": { + "External id": 28943,"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": 2338707, "tid": 2379456, + "ts": 6197197075958.833, "dur": 0.369, + "args": { + "External id": 28944,"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": 2338707, "tid": 2379456, + "ts": 6197197075960.603, "dur": 2.534, + "args": { + "External id": 28945,"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": 2338707, "tid": 2379456, + "ts": 6197197075966.042, "dur": 0.461, + "args": { + "External id": 28946,"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": 2338707, "tid": 2379456, + "ts": 6197197075967.807, "dur": 0.424, + "args": { + "External id": 28947,"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": 2338707, "tid": 2379456, + "ts": 6197197075986.998, "dur": 49.753, + "args": { + "External id": 28948,"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": 2338707, "tid": 2379456, + "ts": 6197197076106.655, "dur": 135.521, + "args": { + "External id": 28949,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2379456, + "ts": 6197197076118.614, "dur": 5.342, + "args": { + "External id": 28950,"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": 2338707, "tid": 2379456, + "ts": 6197197076129.819, "dur": 17.434, + "args": { + "External id": 28951,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2379456, + "ts": 6197197076140.379, "dur": 6.442, + "args": { + "External id": 28952,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2379456, + "ts": 6197197076144.487, "dur": 0.534, + "args": { + "External id": 28953,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197197076154.693, "dur": 29.656, + "args": { + "External id": 28954,"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": 2338707, "tid": 2379456, + "ts": 6197197076157.200, "dur": 0.585, + "args": { + "External id": 28955,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197197076160.905, "dur": 0.422, + "args": { + "External id": 28956,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2379456, + "ts": 6197197076162.969, "dur": 0.344, + "args": { + "External id": 28957,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2379456, + "ts": 6197197076164.882, "dur": 3.397, + "args": { + "External id": 28958,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2379456, + "ts": 6197197076169.687, "dur": 0.265, + "args": { + "External id": 28959,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2379456, + "ts": 6197197076171.206, "dur": 0.441, + "args": { + "External id": 28960,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2379456, + "ts": 6197197076174.381, "dur": 0.272, + "args": { + "External id": 28961,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2379456, + "ts": 6197197076175.918, "dur": 0.286, + "args": { + "External id": 28962,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2379456, + "ts": 6197197076177.558, "dur": 0.254, + "args": { + "External id": 28963,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2379456, + "ts": 6197197076198.482, "dur": 34.606, + "args": { + "External id": 28964,"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": 2338707, "tid": 2379456, + "ts": 6197197076290.615, "dur": 125.154, + "args": { + "External id": 28965,"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": 2338707, "tid": 2379456, + "ts": 6197197076325.165, "dur": 87.322, + "args": { + "External id": 28966,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197197076334.376, "dur": 73.840, + "args": { + "External id": 28967,"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": 2338707, "tid": 2379456, + "ts": 6197197076433.467, "dur": 1.880, + "args": { + "External id": 28968,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197197076515.043, "dur": 1823.413, + "args": { + "External id": 28969,"Sequence number": 479816, "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": 2338707, "tid": 2379456, "ts": 6197197076515.043, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6197197076625.856, "dur": 128.605, + "args": { + "External id": 28970,"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": 2338707, "tid": 2379456, + "ts": 6197197076803.336, "dur": 42.572, + "args": { + "External id": 28971,"kernel_hash": "cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/u7/cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs.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": 2338707, "tid": 2379456, + "ts": 6197197076864.123, "dur": 55.980, + "args": { + "External id": 28972,"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": 2338707, "tid": 2379456, + "ts": 6197197076930.590, "dur": 31.355, + "args": { + "External id": 28973,"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": 2338707, "tid": 2379456, + "ts": 6197197076970.301, "dur": 31.679, + "args": { + "External id": 28974,"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": 2338707, "tid": 2379456, + "ts": 6197197077008.688, "dur": 26.941, + "args": { + "External id": 28975,"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": 2338707, "tid": 2379456, + "ts": 6197197077042.953, "dur": 69.233, + "args": { + "External id": 28976,"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": 2338707, "tid": 2379456, + "ts": 6197197077144.741, "dur": 25.437, + "args": { + "External id": 28977,"kernel_hash": "cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/wm/cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s.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": 2338707, "tid": 2379456, + "ts": 6197197077193.833, "dur": 29.552, + "args": { + "External id": 28978,"kernel_hash": "cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql", "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/qt/cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql.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": 2338707, "tid": 2379456, + "ts": 6197197077244.765, "dur": 18.827, + "args": { + "External id": 28979,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197197077278.385, "dur": 15.829, + "args": { + "External id": 28980,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197197077302.856, "dur": 42.156, + "args": { + "External id": 28981,"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": 2338707, "tid": 2379456, + "ts": 6197197077348.756, "dur": 32.821, + "args": { + "External id": 28982,"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": 2338707, "tid": 2379456, + "ts": 6197197077415.876, "dur": 253.805, + "args": { + "External id": 28983,"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": 2338707, "tid": 2379456, + "ts": 6197197077493.017, "dur": 6.146, + "args": { + "External id": 28984,"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": 2338707, "tid": 2379456, + "ts": 6197197077501.225, "dur": 2.809, + "args": { + "External id": 28985,"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": 2338707, "tid": 2379456, + "ts": 6197197077505.373, "dur": 3.539, + "args": { + "External id": 28986,"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": 2338707, "tid": 2379456, + "ts": 6197197077510.222, "dur": 1.906, + "args": { + "External id": 28987,"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": 2338707, "tid": 2379456, + "ts": 6197197077558.493, "dur": 5.295, + "args": { + "External id": 28988,"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": 2338707, "tid": 2379456, + "ts": 6197197077560.813, "dur": 2.770, + "args": { + "External id": 28989,"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": 2338707, "tid": 2379456, + "ts": 6197197077565.537, "dur": 34.593, + "args": { + "External id": 28990,"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": 2338707, "tid": 2379456, + "ts": 6197197077571.190, "dur": 3.209, + "args": { + "External id": 28991,"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": 2338707, "tid": 2379456, + "ts": 6197197077601.756, "dur": 1.876, + "args": { + "External id": 28992,"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": 2338707, "tid": 2379456, + "ts": 6197197077603.009, "dur": 0.537, + "args": { + "External id": 28993,"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": 2338707, "tid": 2379456, + "ts": 6197197077604.719, "dur": 23.249, + "args": { + "External id": 28994,"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": 2338707, "tid": 2379456, + "ts": 6197197077607.838, "dur": 2.984, + "args": { + "External id": 28995,"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": 2338707, "tid": 2379456, + "ts": 6197197077726.555, "dur": 31.555, + "args": { + "External id": 28996,"kernel_hash": "cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4", "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/yk/cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4.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": 2338707, "tid": 2379456, + "ts": 6197197077778.072, "dur": 15.961, + "args": { + "External id": 28997,"kernel_hash": "ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg", "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/eu/ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg.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": 2338707, "tid": 2379456, + "ts": 6197197077802.621, "dur": 46.449, + "args": { + "External id": 28998,"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": 2338707, "tid": 2379456, + "ts": 6197197077855.642, "dur": 39.920, + "args": { + "External id": 28999,"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": 2338707, "tid": 2379456, + "ts": 6197197077906.422, "dur": 20.493, + "args": { + "External id": 29000,"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": 2338707, "tid": 2379456, + "ts": 6197197077932.586, "dur": 30.210, + "args": { + "External id": 29001,"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": 2338707, "tid": 2379456, + "ts": 6197197077969.895, "dur": 27.467, + "args": { + "External id": 29002,"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": 2338707, "tid": 2379456, + "ts": 6197197078004.062, "dur": 43.941, + "args": { + "External id": 29003,"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": 2338707, "tid": 2379456, + "ts": 6197197078118.061, "dur": 33.930, + "args": { + "External id": 29004,"kernel_hash": "c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/6w/c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7.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": 2338707, "tid": 2379456, + "ts": 6197197078171.603, "dur": 29.337, + "args": { + "External id": 29005,"kernel_hash": "ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx", "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/kj/ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx.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": 2338707, "tid": 2379456, + "ts": 6197197078218.043, "dur": 17.942, + "args": { + "External id": 29006,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197197078257.797, "dur": 13.634, + "args": { + "External id": 29007,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197197078288.782, "dur": 17.475, + "args": { + "External id": 29008,"kernel_hash": "cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/eb/cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b.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": 2338707, "tid": 2379456, + "ts": 6197197078383.598, "dur": 15.253, + "args": { + "External id": 29009,"Record function id": 0, "Ev Idx": 1872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197078387.263, "dur": 10.506, + "args": { + "External id": 29010,"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": 2338707, "tid": 2379456, + "ts": 6197197078391.169, "dur": 5.530, + "args": { + "External id": 29011,"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": 2338707, "tid": 2379456, + "ts": 6197197078392.549, "dur": 4.060, + "args": { + "External id": 29012,"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": 2338707, "tid": 2379456, + "ts": 6197197078402.932, "dur": 5.147, + "args": { + "External id": 29013,"Record function id": 0, "Ev Idx": 1876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197078404.824, "dur": 2.781, + "args": { + "External id": 29014,"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": 2338707, "tid": 2379456, + "ts": 6197197078405.688, "dur": 1.267, + "args": { + "External id": 29015,"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": 2338707, "tid": 2379456, + "ts": 6197197078406.211, "dur": 0.653, + "args": { + "External id": 29016,"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": 2338707, "tid": 2379456, + "ts": 6197197078411.663, "dur": 4.718, + "args": { + "External id": 29017,"Record function id": 0, "Ev Idx": 1880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197078413.176, "dur": 2.779, + "args": { + "External id": 29018,"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": 2338707, "tid": 2379456, + "ts": 6197197078413.873, "dur": 1.645, + "args": { + "External id": 29019,"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": 2338707, "tid": 2379456, + "ts": 6197197078414.567, "dur": 0.855, + "args": { + "External id": 29020,"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": 2338707, "tid": 2379456, + "ts": 6197197078419.713, "dur": 4.253, + "args": { + "External id": 29021,"Record function id": 0, "Ev Idx": 1884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197078421.128, "dur": 2.454, + "args": { + "External id": 29022,"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": 2338707, "tid": 2379456, + "ts": 6197197078421.651, "dur": 1.308, + "args": { + "External id": 29023,"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": 2338707, "tid": 2379456, + "ts": 6197197078422.295, "dur": 0.563, + "args": { + "External id": 29024,"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": 2338707, "tid": 2379456, + "ts": 6197197078427.064, "dur": 3.598, + "args": { + "External id": 29025,"Record function id": 0, "Ev Idx": 1888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197078428.104, "dur": 2.150, + "args": { + "External id": 29026,"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": 2338707, "tid": 2379456, + "ts": 6197197078428.680, "dur": 1.038, + "args": { + "External id": 29027,"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": 2338707, "tid": 2379456, + "ts": 6197197078428.964, "dur": 0.688, + "args": { + "External id": 29028,"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": 2338707, "tid": 2379456, + "ts": 6197197078433.715, "dur": 5.698, + "args": { + "External id": 29029,"Record function id": 0, "Ev Idx": 1892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197078435.058, "dur": 3.946, + "args": { + "External id": 29030,"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": 2338707, "tid": 2379456, + "ts": 6197197078435.754, "dur": 2.830, + "args": { + "External id": 29031,"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": 2338707, "tid": 2379456, + "ts": 6197197078436.173, "dur": 2.349, + "args": { + "External id": 29032,"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": 2338707, "tid": 2379456, + "ts": 6197197078442.665, "dur": 12.047, + "args": { + "External id": 29033,"Record function id": 0, "Ev Idx": 1896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197078444.253, "dur": 10.066, + "args": { + "External id": 29034,"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": 2338707, "tid": 2379456, + "ts": 6197197078445.072, "dur": 8.809, + "args": { + "External id": 29035,"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": 2338707, "tid": 2379456, + "ts": 6197197078453.075, "dur": 0.722, + "args": { + "External id": 29036,"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": 2338707, "tid": 2379456, + "ts": 6197197078457.863, "dur": 3.769, + "args": { + "External id": 29037,"Record function id": 0, "Ev Idx": 1900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197078459.112, "dur": 2.137, + "args": { + "External id": 29038,"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": 2338707, "tid": 2379456, + "ts": 6197197078459.592, "dur": 0.953, + "args": { + "External id": 29039,"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": 2338707, "tid": 2379456, + "ts": 6197197078459.898, "dur": 0.567, + "args": { + "External id": 29040,"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": 2338707, "tid": 2379456, + "ts": 6197197078464.682, "dur": 4.197, + "args": { + "External id": 29041,"Record function id": 0, "Ev Idx": 1904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197078466.098, "dur": 2.374, + "args": { + "External id": 29042,"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": 2338707, "tid": 2379456, + "ts": 6197197078466.982, "dur": 0.924, + "args": { + "External id": 29043,"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": 2338707, "tid": 2379456, + "ts": 6197197078467.261, "dur": 0.577, + "args": { + "External id": 29044,"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": 2338707, "tid": 2379456, + "ts": 6197197078473.086, "dur": 94653.870, + "args": { + "External id": 29045,"Record function id": 0, "Sequence number": 479815, "Fwd thread id": 1, "Ev Idx": 1908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197197078475.000, "dur": 94641.788, + "args": { + "External id": 29046,"Sequence number": 479815, "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": 2338707, "tid": 2379456, "ts": 6197197078475.000, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.24)", "pid": 2338707, "tid": 2379456, + "ts": 6197197078505.547, "dur": 42.222, + "args": { + "External id": 29047,"Record function id": 0, "Ev Idx": 1910 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.24)", "pid": 2338707, "tid": 2379456, + "ts": 6197197078555.991, "dur": 70.022, + "args": { + "External id": 29048,"Record function id": 0, "Ev Idx": 1911 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.24)", "pid": 2338707, "tid": 2379456, + "ts": 6197197078632.833, "dur": 94474.783, + "args": { + "External id": 29049,"Record function id": 0, "Ev Idx": 1912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197197078742.631, "dur": 8.376, + "args": { + "External id": 29050,"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": 2338707, "tid": 2379456, + "ts": 6197197078762.358, "dur": 5.124, + "args": { + "External id": 29051,"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": 2338707, "tid": 2379456, + "ts": 6197197078782.718, "dur": 93443.390, + "args": { + "External id": 29052,"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": 2338707, "tid": 2379456, + "ts": 6197197078797.294, "dur": 93415.250, + "args": { + "External id": 29053,"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": 2338707, "tid": 2379456, + "ts": 6197197078908.473, "dur": 18.443, + "args": { + "External id": 29054,"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": 2338707, "tid": 2379456, + "ts": 6197197078950.379, "dur": 93215.818, + "args": { + "External id": 29055,"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": 2338707, "tid": 2379456, + "ts": 6197197078953.068, "dur": 93212.065, + "args": { + "External id": 29056,"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": 2338707, "tid": 2379456, + "ts": 6197197078957.567, "dur": 9.704, + "args": { + "External id": 29057,"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": 2338707, "tid": 2379456, + "ts": 6197197078969.526, "dur": 93190.386, + "args": { + "External id": 29058,"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": 2338707, "tid": 2379456, + "ts": 6197197172331.270, "dur": 12.398, + "args": { + "External id": 29059,"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": 2338707, "tid": 2379456, + "ts": 6197197172334.848, "dur": 8.376, + "args": { + "External id": 29060,"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": 2338707, "tid": 2379456, + "ts": 6197197172375.389, "dur": 394.919, + "args": { + "External id": 29061,"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": 2338707, "tid": 2379456, + "ts": 6197197172408.399, "dur": 356.394, + "args": { + "External id": 29062,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197197172421.148, "dur": 337.911, + "args": { + "External id": 29063,"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": 2338707, "tid": 2379456, + "ts": 6197197172795.277, "dur": 2.575, + "args": { + "External id": 29064,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2379456, + "ts": 6197197172859.636, "dur": 6.655, + "args": { + "External id": 29065,"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": 2338707, "tid": 2379456, + "ts": 6197197172913.258, "dur": 1.325, + "args": { + "External id": 29066,"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": 2338707, "tid": 2379456, + "ts": 6197197172929.880, "dur": 1.429, + "args": { + "External id": 29067,"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": 2338707, "tid": 2379456, + "ts": 6197197172943.774, "dur": 0.972, + "args": { + "External id": 29068,"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": 2338707, "tid": 2379456, + "ts": 6197197172959.760, "dur": 0.799, + "args": { + "External id": 29069,"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": 2338707, "tid": 2379456, + "ts": 6197197172973.188, "dur": 0.830, + "args": { + "External id": 29070,"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": 2338707, "tid": 2379456, + "ts": 6197197172984.084, "dur": 1.228, + "args": { + "External id": 29071,"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": 2338707, "tid": 2379456, + "ts": 6197197172996.164, "dur": 3.336, + "args": { + "External id": 29072,"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": 2338707, "tid": 2379456, + "ts": 6197197173008.972, "dur": 0.778, + "args": { + "External id": 29073,"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": 2338707, "tid": 2379456, + "ts": 6197197173143.160, "dur": 2983.014, + "args": { + "External id": 29074,"Record function id": 0, "Ev Idx": 1937 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.23)", "pid": 2338707, "tid": 2379456, + "ts": 6197197173165.264, "dur": 1149.482, + "args": { + "External id": 29075,"Record function id": 0, "Ev Idx": 1938 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.23)", "pid": 2338707, "tid": 2379456, + "ts": 6197197173180.253, "dur": 363.643, + "args": { + "External id": 29076,"Record function id": 0, "Ev Idx": 1939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6197197173272.996, "dur": 4.919, + "args": { + "External id": 29077,"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": 2338707, "tid": 2379456, + "ts": 6197197173281.612, "dur": 1.150, + "args": { + "External id": 29078,"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": 2338707, "tid": 2379456, + "ts": 6197197173284.518, "dur": 1.164, + "args": { + "External id": 29079,"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": 2338707, "tid": 2379456, + "ts": 6197197173287.388, "dur": 0.819, + "args": { + "External id": 29080,"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": 2338707, "tid": 2379456, + "ts": 6197197173291.800, "dur": 0.889, + "args": { + "External id": 29081,"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": 2338707, "tid": 2379456, + "ts": 6197197173294.522, "dur": 1.192, + "args": { + "External id": 29082,"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": 2338707, "tid": 2379456, + "ts": 6197197173297.289, "dur": 3.067, + "args": { + "External id": 29083,"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": 2338707, "tid": 2379456, + "ts": 6197197173301.723, "dur": 2.993, + "args": { + "External id": 29084,"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": 2338707, "tid": 2379456, + "ts": 6197197173307.713, "dur": 0.834, + "args": { + "External id": 29085,"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": 2338707, "tid": 2379456, + "ts": 6197197173310.048, "dur": 0.941, + "args": { + "External id": 29086,"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": 2338707, "tid": 2379456, + "ts": 6197197173340.112, "dur": 173.292, + "args": { + "External id": 29087,"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": 2338707, "tid": 2379456, + "ts": 6197197173358.509, "dur": 150.022, + "args": { + "External id": 29088,"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": 2338707, "tid": 2379456, + "ts": 6197197173385.245, "dur": 16.188, + "args": { + "External id": 29089,"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": 2338707, "tid": 2379456, + "ts": 6197197173407.606, "dur": 70.437, + "args": { + "External id": 29090,"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": 2338707, "tid": 2379456, + "ts": 6197197173412.176, "dur": 65.484, + "args": { + "External id": 29091,"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": 2338707, "tid": 2379456, + "ts": 6197197173416.650, "dur": 7.051, + "args": { + "External id": 29092,"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": 2338707, "tid": 2379456, + "ts": 6197197173425.587, "dur": 51.361, + "args": { + "External id": 29093,"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": 2338707, "tid": 2379456, + "ts": 6197197173633.500, "dur": 672.181, + "args": { + "External id": 29094,"Record function id": 0, "Ev Idx": 1957 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.22)", "pid": 2338707, "tid": 2379456, + "ts": 6197197173651.361, "dur": 641.851, + "args": { + "External id": 29095,"Record function id": 0, "Ev Idx": 1958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197197173729.793, "dur": 6.522, + "args": { + "External id": 29096,"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": 2338707, "tid": 2379456, + "ts": 6197197173752.829, "dur": 38.176, + "args": { + "External id": 29097,"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": 2338707, "tid": 2379456, + "ts": 6197197173758.629, "dur": 1.784, + "args": { + "External id": 29098,"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": 2338707, "tid": 2379456, + "ts": 6197197173763.216, "dur": 1.549, + "args": { + "External id": 29099,"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": 2338707, "tid": 2379456, + "ts": 6197197173766.505, "dur": 2.631, + "args": { + "External id": 29100,"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": 2338707, "tid": 2379456, + "ts": 6197197173770.552, "dur": 0.369, + "args": { + "External id": 29101,"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": 2338707, "tid": 2379456, + "ts": 6197197173776.457, "dur": 0.359, + "args": { + "External id": 29102,"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": 2338707, "tid": 2379456, + "ts": 6197197173778.205, "dur": 0.315, + "args": { + "External id": 29103,"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": 2338707, "tid": 2379456, + "ts": 6197197173779.719, "dur": 0.404, + "args": { + "External id": 29104,"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": 2338707, "tid": 2379456, + "ts": 6197197173782.137, "dur": 0.443, + "args": { + "External id": 29105,"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": 2338707, "tid": 2379456, + "ts": 6197197173783.865, "dur": 0.480, + "args": { + "External id": 29106,"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": 2338707, "tid": 2379456, + "ts": 6197197173802.813, "dur": 49.397, + "args": { + "External id": 29107,"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": 2338707, "tid": 2379456, + "ts": 6197197173883.809, "dur": 121.659, + "args": { + "External id": 29108,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2379456, + "ts": 6197197173893.993, "dur": 3.509, + "args": { + "External id": 29109,"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": 2338707, "tid": 2379456, + "ts": 6197197173902.676, "dur": 12.737, + "args": { + "External id": 29110,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2379456, + "ts": 6197197173906.839, "dur": 8.153, + "args": { + "External id": 29111,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2379456, + "ts": 6197197173910.623, "dur": 3.016, + "args": { + "External id": 29112,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197197173922.683, "dur": 30.391, + "args": { + "External id": 29113,"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": 2338707, "tid": 2379456, + "ts": 6197197173924.955, "dur": 0.508, + "args": { + "External id": 29114,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197197173928.224, "dur": 0.694, + "args": { + "External id": 29115,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2379456, + "ts": 6197197173930.380, "dur": 0.545, + "args": { + "External id": 29116,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2379456, + "ts": 6197197173932.596, "dur": 1.444, + "args": { + "External id": 29117,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2379456, + "ts": 6197197173935.789, "dur": 0.394, + "args": { + "External id": 29118,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2379456, + "ts": 6197197173937.522, "dur": 0.436, + "args": { + "External id": 29119,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2379456, + "ts": 6197197173940.968, "dur": 0.485, + "args": { + "External id": 29120,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2379456, + "ts": 6197197173942.721, "dur": 2.355, + "args": { + "External id": 29121,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2379456, + "ts": 6197197173946.719, "dur": 0.248, + "args": { + "External id": 29122,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2379456, + "ts": 6197197173963.797, "dur": 33.666, + "args": { + "External id": 29123,"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": 2338707, "tid": 2379456, + "ts": 6197197174050.690, "dur": 167.277, + "args": { + "External id": 29124,"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": 2338707, "tid": 2379456, + "ts": 6197197174119.500, "dur": 94.808, + "args": { + "External id": 29125,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197197174130.419, "dur": 79.629, + "args": { + "External id": 29126,"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": 2338707, "tid": 2379456, + "ts": 6197197174236.008, "dur": 2.021, + "args": { + "External id": 29127,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197197174322.061, "dur": 1777.215, + "args": { + "External id": 29128,"Sequence number": 479814, "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": 2338707, "tid": 2379456, "ts": 6197197174322.061, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6197197174434.106, "dur": 105.826, + "args": { + "External id": 29129,"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": 2338707, "tid": 2379456, + "ts": 6197197174582.180, "dur": 39.703, + "args": { + "External id": 29130,"kernel_hash": "cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/u7/cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs.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": 2338707, "tid": 2379456, + "ts": 6197197174642.820, "dur": 50.390, + "args": { + "External id": 29131,"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": 2338707, "tid": 2379456, + "ts": 6197197174722.842, "dur": 39.666, + "args": { + "External id": 29132,"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": 2338707, "tid": 2379456, + "ts": 6197197174770.490, "dur": 33.536, + "args": { + "External id": 29133,"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": 2338707, "tid": 2379456, + "ts": 6197197174810.768, "dur": 29.083, + "args": { + "External id": 29134,"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": 2338707, "tid": 2379456, + "ts": 6197197174850.301, "dur": 29.376, + "args": { + "External id": 29135,"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": 2338707, "tid": 2379456, + "ts": 6197197174907.160, "dur": 25.507, + "args": { + "External id": 29136,"kernel_hash": "cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/wm/cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s.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": 2338707, "tid": 2379456, + "ts": 6197197174951.177, "dur": 28.968, + "args": { + "External id": 29137,"kernel_hash": "cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql", "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/qt/cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql.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": 2338707, "tid": 2379456, + "ts": 6197197175004.052, "dur": 20.738, + "args": { + "External id": 29138,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197197175037.828, "dur": 54.933, + "args": { + "External id": 29139,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197197175106.707, "dur": 46.792, + "args": { + "External id": 29140,"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": 2338707, "tid": 2379456, + "ts": 6197197175157.470, "dur": 34.216, + "args": { + "External id": 29141,"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": 2338707, "tid": 2379456, + "ts": 6197197175223.316, "dur": 252.338, + "args": { + "External id": 29142,"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": 2338707, "tid": 2379456, + "ts": 6197197175305.046, "dur": 6.274, + "args": { + "External id": 29143,"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": 2338707, "tid": 2379456, + "ts": 6197197175313.682, "dur": 2.444, + "args": { + "External id": 29144,"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": 2338707, "tid": 2379456, + "ts": 6197197175317.437, "dur": 6.166, + "args": { + "External id": 29145,"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": 2338707, "tid": 2379456, + "ts": 6197197175324.999, "dur": 2.285, + "args": { + "External id": 29146,"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": 2338707, "tid": 2379456, + "ts": 6197197175373.170, "dur": 5.185, + "args": { + "External id": 29147,"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": 2338707, "tid": 2379456, + "ts": 6197197175375.408, "dur": 2.730, + "args": { + "External id": 29148,"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": 2338707, "tid": 2379456, + "ts": 6197197175380.205, "dur": 33.086, + "args": { + "External id": 29149,"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": 2338707, "tid": 2379456, + "ts": 6197197175385.724, "dur": 3.324, + "args": { + "External id": 29150,"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": 2338707, "tid": 2379456, + "ts": 6197197175414.752, "dur": 1.778, + "args": { + "External id": 29151,"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": 2338707, "tid": 2379456, + "ts": 6197197175415.887, "dur": 0.559, + "args": { + "External id": 29152,"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": 2338707, "tid": 2379456, + "ts": 6197197175417.900, "dur": 15.599, + "args": { + "External id": 29153,"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": 2338707, "tid": 2379456, + "ts": 6197197175421.394, "dur": 0.594, + "args": { + "External id": 29154,"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": 2338707, "tid": 2379456, + "ts": 6197197175516.108, "dur": 29.312, + "args": { + "External id": 29155,"kernel_hash": "cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4", "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/yk/cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4.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": 2338707, "tid": 2379456, + "ts": 6197197175565.937, "dur": 17.775, + "args": { + "External id": 29156,"kernel_hash": "ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg", "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/eu/ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg.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": 2338707, "tid": 2379456, + "ts": 6197197175591.404, "dur": 41.474, + "args": { + "External id": 29157,"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": 2338707, "tid": 2379456, + "ts": 6197197175639.505, "dur": 40.477, + "args": { + "External id": 29158,"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": 2338707, "tid": 2379456, + "ts": 6197197175687.596, "dur": 40.820, + "args": { + "External id": 29159,"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": 2338707, "tid": 2379456, + "ts": 6197197175739.440, "dur": 35.293, + "args": { + "External id": 29160,"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": 2338707, "tid": 2379456, + "ts": 6197197175782.420, "dur": 28.729, + "args": { + "External id": 29161,"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": 2338707, "tid": 2379456, + "ts": 6197197175818.358, "dur": 30.438, + "args": { + "External id": 29162,"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": 2338707, "tid": 2379456, + "ts": 6197197175870.464, "dur": 27.450, + "args": { + "External id": 29163,"kernel_hash": "c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/6w/c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7.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": 2338707, "tid": 2379456, + "ts": 6197197175917.708, "dur": 23.969, + "args": { + "External id": 29164,"kernel_hash": "ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx", "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/kj/ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx.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": 2338707, "tid": 2379456, + "ts": 6197197175959.075, "dur": 16.534, + "args": { + "External id": 29165,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197197175991.805, "dur": 13.112, + "args": { + "External id": 29166,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197197176019.963, "dur": 14.983, + "args": { + "External id": 29167,"kernel_hash": "cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/eb/cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b.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": 2338707, "tid": 2379456, + "ts": 6197197176148.770, "dur": 15.030, + "args": { + "External id": 29168,"Record function id": 0, "Ev Idx": 2031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197176152.402, "dur": 10.435, + "args": { + "External id": 29169,"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": 2338707, "tid": 2379456, + "ts": 6197197176156.497, "dur": 5.341, + "args": { + "External id": 29170,"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": 2338707, "tid": 2379456, + "ts": 6197197176158.085, "dur": 3.675, + "args": { + "External id": 29171,"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": 2338707, "tid": 2379456, + "ts": 6197197176167.553, "dur": 4.554, + "args": { + "External id": 29172,"Record function id": 0, "Ev Idx": 2035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197176169.120, "dur": 2.573, + "args": { + "External id": 29173,"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": 2338707, "tid": 2379456, + "ts": 6197197176169.820, "dur": 1.413, + "args": { + "External id": 29174,"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": 2338707, "tid": 2379456, + "ts": 6197197176170.513, "dur": 0.653, + "args": { + "External id": 29175,"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": 2338707, "tid": 2379456, + "ts": 6197197176175.602, "dur": 4.928, + "args": { + "External id": 29176,"Record function id": 0, "Ev Idx": 2039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197176177.186, "dur": 2.918, + "args": { + "External id": 29177,"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": 2338707, "tid": 2379456, + "ts": 6197197176177.927, "dur": 1.718, + "args": { + "External id": 29178,"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": 2338707, "tid": 2379456, + "ts": 6197197176178.953, "dur": 0.591, + "args": { + "External id": 29179,"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": 2338707, "tid": 2379456, + "ts": 6197197176183.739, "dur": 3.547, + "args": { + "External id": 29180,"Record function id": 0, "Ev Idx": 2043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197176184.846, "dur": 2.052, + "args": { + "External id": 29181,"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": 2338707, "tid": 2379456, + "ts": 6197197176185.346, "dur": 1.132, + "args": { + "External id": 29182,"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": 2338707, "tid": 2379456, + "ts": 6197197176185.635, "dur": 0.751, + "args": { + "External id": 29183,"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": 2338707, "tid": 2379456, + "ts": 6197197176190.438, "dur": 44.445, + "args": { + "External id": 29184,"Record function id": 0, "Ev Idx": 2047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197176232.045, "dur": 2.243, + "args": { + "External id": 29185,"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": 2338707, "tid": 2379456, + "ts": 6197197176232.644, "dur": 1.066, + "args": { + "External id": 29186,"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": 2338707, "tid": 2379456, + "ts": 6197197176232.959, "dur": 0.681, + "args": { + "External id": 29187,"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": 2338707, "tid": 2379456, + "ts": 6197197176238.333, "dur": 13.231, + "args": { + "External id": 29188,"Record function id": 0, "Ev Idx": 2051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197176246.624, "dur": 4.522, + "args": { + "External id": 29189,"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": 2338707, "tid": 2379456, + "ts": 6197197176247.135, "dur": 3.587, + "args": { + "External id": 29190,"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": 2338707, "tid": 2379456, + "ts": 6197197176249.840, "dur": 0.795, + "args": { + "External id": 29191,"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": 2338707, "tid": 2379456, + "ts": 6197197176256.726, "dur": 6.363, + "args": { + "External id": 29192,"Record function id": 0, "Ev Idx": 2055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197176258.239, "dur": 4.459, + "args": { + "External id": 29193,"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": 2338707, "tid": 2379456, + "ts": 6197197176258.728, "dur": 3.165, + "args": { + "External id": 29194,"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": 2338707, "tid": 2379456, + "ts": 6197197176259.131, "dur": 2.696, + "args": { + "External id": 29195,"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": 2338707, "tid": 2379456, + "ts": 6197197176266.418, "dur": 3.817, + "args": { + "External id": 29196,"Record function id": 0, "Ev Idx": 2059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197176267.747, "dur": 2.101, + "args": { + "External id": 29197,"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": 2338707, "tid": 2379456, + "ts": 6197197176268.255, "dur": 1.084, + "args": { + "External id": 29198,"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": 2338707, "tid": 2379456, + "ts": 6197197176268.526, "dur": 0.727, + "args": { + "External id": 29199,"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": 2338707, "tid": 2379456, + "ts": 6197197176273.429, "dur": 3.956, + "args": { + "External id": 29200,"Record function id": 0, "Ev Idx": 2063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197176274.685, "dur": 2.291, + "args": { + "External id": 29201,"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": 2338707, "tid": 2379456, + "ts": 6197197176275.143, "dur": 1.418, + "args": { + "External id": 29202,"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": 2338707, "tid": 2379456, + "ts": 6197197176275.676, "dur": 0.806, + "args": { + "External id": 29203,"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": 2338707, "tid": 2379456, + "ts": 6197197176281.708, "dur": 84919.707, + "args": { + "External id": 29204,"Record function id": 0, "Sequence number": 479813, "Fwd thread id": 1, "Ev Idx": 2067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197197176295.895, "dur": 84896.358, + "args": { + "External id": 29205,"Sequence number": 479813, "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": 2338707, "tid": 2379456, "ts": 6197197176295.895, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.23)", "pid": 2338707, "tid": 2379456, + "ts": 6197197176331.369, "dur": 42.252, + "args": { + "External id": 29206,"Record function id": 0, "Ev Idx": 2069 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.23)", "pid": 2338707, "tid": 2379456, + "ts": 6197197176381.520, "dur": 85.633, + "args": { + "External id": 29207,"Record function id": 0, "Ev Idx": 2070 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.23)", "pid": 2338707, "tid": 2379456, + "ts": 6197197176475.663, "dur": 84708.741, + "args": { + "External id": 29208,"Record function id": 0, "Ev Idx": 2071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197197176571.961, "dur": 8.208, + "args": { + "External id": 29209,"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": 2338707, "tid": 2379456, + "ts": 6197197176590.394, "dur": 4.659, + "args": { + "External id": 29210,"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": 2338707, "tid": 2379456, + "ts": 6197197176614.373, "dur": 83638.449, + "args": { + "External id": 29211,"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": 2338707, "tid": 2379456, + "ts": 6197197176627.895, "dur": 83611.569, + "args": { + "External id": 29212,"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": 2338707, "tid": 2379456, + "ts": 6197197176744.887, "dur": 19.795, + "args": { + "External id": 29213,"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": 2338707, "tid": 2379456, + "ts": 6197197176785.834, "dur": 83409.856, + "args": { + "External id": 29214,"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": 2338707, "tid": 2379456, + "ts": 6197197176788.755, "dur": 83405.781, + "args": { + "External id": 29215,"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": 2338707, "tid": 2379456, + "ts": 6197197176793.646, "dur": 11.200, + "args": { + "External id": 29216,"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": 2338707, "tid": 2379456, + "ts": 6197197176806.995, "dur": 83382.548, + "args": { + "External id": 29217,"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": 2338707, "tid": 2379456, + "ts": 6197197260356.852, "dur": 12.519, + "args": { + "External id": 29218,"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": 2338707, "tid": 2379456, + "ts": 6197197260360.357, "dur": 8.567, + "args": { + "External id": 29219,"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": 2338707, "tid": 2379456, + "ts": 6197197260398.002, "dur": 441.724, + "args": { + "External id": 29220,"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": 2338707, "tid": 2379456, + "ts": 6197197260431.811, "dur": 401.761, + "args": { + "External id": 29221,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197197260445.477, "dur": 382.268, + "args": { + "External id": 29222,"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": 2338707, "tid": 2379456, + "ts": 6197197260867.335, "dur": 2.222, + "args": { + "External id": 29223,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2379456, + "ts": 6197197260933.066, "dur": 6.813, + "args": { + "External id": 29224,"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": 2338707, "tid": 2379456, + "ts": 6197197260985.322, "dur": 3.960, + "args": { + "External id": 29225,"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": 2338707, "tid": 2379456, + "ts": 6197197261005.640, "dur": 1.272, + "args": { + "External id": 29226,"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": 2338707, "tid": 2379456, + "ts": 6197197261018.306, "dur": 0.954, + "args": { + "External id": 29227,"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": 2338707, "tid": 2379456, + "ts": 6197197261029.906, "dur": 0.972, + "args": { + "External id": 29228,"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": 2338707, "tid": 2379456, + "ts": 6197197261041.417, "dur": 3.178, + "args": { + "External id": 29229,"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": 2338707, "tid": 2379456, + "ts": 6197197261087.308, "dur": 2.145, + "args": { + "External id": 29230,"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": 2338707, "tid": 2379456, + "ts": 6197197261103.603, "dur": 3.317, + "args": { + "External id": 29231,"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": 2338707, "tid": 2379456, + "ts": 6197197261118.662, "dur": 0.976, + "args": { + "External id": 29232,"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": 2338707, "tid": 2379456, + "ts": 6197197261217.260, "dur": 2986.033, + "args": { + "External id": 29233,"Record function id": 0, "Ev Idx": 2096 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.22)", "pid": 2338707, "tid": 2379456, + "ts": 6197197261237.612, "dur": 1137.322, + "args": { + "External id": 29234,"Record function id": 0, "Ev Idx": 2097 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.22)", "pid": 2338707, "tid": 2379456, + "ts": 6197197261253.040, "dur": 353.943, + "args": { + "External id": 29235,"Record function id": 0, "Ev Idx": 2098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6197197261348.377, "dur": 6.569, + "args": { + "External id": 29236,"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": 2338707, "tid": 2379456, + "ts": 6197197261358.431, "dur": 1.200, + "args": { + "External id": 29237,"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": 2338707, "tid": 2379456, + "ts": 6197197261361.473, "dur": 1.271, + "args": { + "External id": 29238,"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": 2338707, "tid": 2379456, + "ts": 6197197261364.636, "dur": 0.780, + "args": { + "External id": 29239,"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": 2338707, "tid": 2379456, + "ts": 6197197261366.942, "dur": 1.000, + "args": { + "External id": 29240,"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": 2338707, "tid": 2379456, + "ts": 6197197261369.262, "dur": 0.873, + "args": { + "External id": 29241,"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": 2338707, "tid": 2379456, + "ts": 6197197261371.617, "dur": 3.031, + "args": { + "External id": 29242,"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": 2338707, "tid": 2379456, + "ts": 6197197261378.166, "dur": 0.710, + "args": { + "External id": 29243,"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": 2338707, "tid": 2379456, + "ts": 6197197261380.435, "dur": 2.764, + "args": { + "External id": 29244,"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": 2338707, "tid": 2379456, + "ts": 6197197261384.767, "dur": 0.934, + "args": { + "External id": 29245,"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": 2338707, "tid": 2379456, + "ts": 6197197261404.242, "dur": 172.794, + "args": { + "External id": 29246,"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": 2338707, "tid": 2379456, + "ts": 6197197261420.775, "dur": 151.648, + "args": { + "External id": 29247,"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": 2338707, "tid": 2379456, + "ts": 6197197261452.822, "dur": 16.002, + "args": { + "External id": 29248,"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": 2338707, "tid": 2379456, + "ts": 6197197261474.203, "dur": 67.308, + "args": { + "External id": 29249,"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": 2338707, "tid": 2379456, + "ts": 6197197261477.517, "dur": 63.630, + "args": { + "External id": 29250,"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": 2338707, "tid": 2379456, + "ts": 6197197261481.753, "dur": 6.220, + "args": { + "External id": 29251,"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": 2338707, "tid": 2379456, + "ts": 6197197261489.817, "dur": 50.729, + "args": { + "External id": 29252,"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": 2338707, "tid": 2379456, + "ts": 6197197261698.355, "dur": 668.266, + "args": { + "External id": 29253,"Record function id": 0, "Ev Idx": 2116 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.21)", "pid": 2338707, "tid": 2379456, + "ts": 6197197261735.360, "dur": 618.061, + "args": { + "External id": 29254,"Record function id": 0, "Ev Idx": 2117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197197261803.033, "dur": 6.734, + "args": { + "External id": 29255,"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": 2338707, "tid": 2379456, + "ts": 6197197261826.149, "dur": 36.294, + "args": { + "External id": 29256,"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": 2338707, "tid": 2379456, + "ts": 6197197261831.580, "dur": 1.678, + "args": { + "External id": 29257,"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": 2338707, "tid": 2379456, + "ts": 6197197261836.866, "dur": 0.359, + "args": { + "External id": 29258,"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": 2338707, "tid": 2379456, + "ts": 6197197261838.523, "dur": 0.561, + "args": { + "External id": 29259,"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": 2338707, "tid": 2379456, + "ts": 6197197261840.388, "dur": 2.596, + "args": { + "External id": 29260,"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": 2338707, "tid": 2379456, + "ts": 6197197261845.372, "dur": 0.464, + "args": { + "External id": 29261,"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": 2338707, "tid": 2379456, + "ts": 6197197261847.448, "dur": 0.531, + "args": { + "External id": 29262,"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": 2338707, "tid": 2379456, + "ts": 6197197261849.640, "dur": 1.318, + "args": { + "External id": 29263,"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": 2338707, "tid": 2379456, + "ts": 6197197261852.798, "dur": 0.308, + "args": { + "External id": 29264,"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": 2338707, "tid": 2379456, + "ts": 6197197261854.678, "dur": 0.246, + "args": { + "External id": 29265,"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": 2338707, "tid": 2379456, + "ts": 6197197261873.526, "dur": 46.409, + "args": { + "External id": 29266,"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": 2338707, "tid": 2379456, + "ts": 6197197261949.612, "dur": 160.221, + "args": { + "External id": 29267,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2379456, + "ts": 6197197261959.479, "dur": 3.430, + "args": { + "External id": 29268,"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": 2338707, "tid": 2379456, + "ts": 6197197261968.296, "dur": 9.966, + "args": { + "External id": 29269,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2379456, + "ts": 6197197261972.543, "dur": 5.300, + "args": { + "External id": 29270,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2379456, + "ts": 6197197261976.125, "dur": 0.527, + "args": { + "External id": 29271,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197197261985.146, "dur": 32.257, + "args": { + "External id": 29272,"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": 2338707, "tid": 2379456, + "ts": 6197197261987.627, "dur": 2.549, + "args": { + "External id": 29273,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197197261992.277, "dur": 0.326, + "args": { + "External id": 29274,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2379456, + "ts": 6197197261994.239, "dur": 0.424, + "args": { + "External id": 29275,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2379456, + "ts": 6197197261996.981, "dur": 0.388, + "args": { + "External id": 29276,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2379456, + "ts": 6197197261998.695, "dur": 0.620, + "args": { + "External id": 29277,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2379456, + "ts": 6197197262000.964, "dur": 0.549, + "args": { + "External id": 29278,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2379456, + "ts": 6197197262003.652, "dur": 0.587, + "args": { + "External id": 29279,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2379456, + "ts": 6197197262005.723, "dur": 0.438, + "args": { + "External id": 29280,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2379456, + "ts": 6197197262007.396, "dur": 3.069, + "args": { + "External id": 29281,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2379456, + "ts": 6197197262030.701, "dur": 68.910, + "args": { + "External id": 29282,"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": 2338707, "tid": 2379456, + "ts": 6197197262159.832, "dur": 122.837, + "args": { + "External id": 29283,"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": 2338707, "tid": 2379456, + "ts": 6197197262191.073, "dur": 87.983, + "args": { + "External id": 29284,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197197262202.113, "dur": 72.607, + "args": { + "External id": 29285,"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": 2338707, "tid": 2379456, + "ts": 6197197262299.432, "dur": 2.068, + "args": { + "External id": 29286,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197197262382.319, "dur": 1793.567, + "args": { + "External id": 29287,"Sequence number": 479812, "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": 2338707, "tid": 2379456, "ts": 6197197262382.319, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6197197262492.863, "dur": 106.614, + "args": { + "External id": 29288,"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": 2338707, "tid": 2379456, + "ts": 6197197262642.622, "dur": 39.720, + "args": { + "External id": 29289,"kernel_hash": "cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/u7/cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs.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": 2338707, "tid": 2379456, + "ts": 6197197262722.746, "dur": 58.341, + "args": { + "External id": 29290,"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": 2338707, "tid": 2379456, + "ts": 6197197262805.274, "dur": 34.655, + "args": { + "External id": 29291,"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": 2338707, "tid": 2379456, + "ts": 6197197262846.871, "dur": 32.901, + "args": { + "External id": 29292,"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": 2338707, "tid": 2379456, + "ts": 6197197262886.702, "dur": 27.728, + "args": { + "External id": 29293,"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": 2338707, "tid": 2379456, + "ts": 6197197262924.148, "dur": 29.581, + "args": { + "External id": 29294,"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": 2338707, "tid": 2379456, + "ts": 6197197262984.908, "dur": 26.052, + "args": { + "External id": 29295,"kernel_hash": "cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/wm/cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s.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": 2338707, "tid": 2379456, + "ts": 6197197263030.614, "dur": 66.154, + "args": { + "External id": 29296,"kernel_hash": "cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql", "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/qt/cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql.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": 2338707, "tid": 2379456, + "ts": 6197197263125.284, "dur": 23.902, + "args": { + "External id": 29297,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197197263163.907, "dur": 15.897, + "args": { + "External id": 29298,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197197263191.048, "dur": 43.105, + "args": { + "External id": 29299,"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": 2338707, "tid": 2379456, + "ts": 6197197263237.888, "dur": 34.478, + "args": { + "External id": 29300,"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": 2338707, "tid": 2379456, + "ts": 6197197263302.053, "dur": 253.334, + "args": { + "External id": 29301,"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": 2338707, "tid": 2379456, + "ts": 6197197263384.737, "dur": 6.091, + "args": { + "External id": 29302,"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": 2338707, "tid": 2379456, + "ts": 6197197263392.969, "dur": 2.638, + "args": { + "External id": 29303,"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": 2338707, "tid": 2379456, + "ts": 6197197263397.208, "dur": 4.575, + "args": { + "External id": 29304,"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": 2338707, "tid": 2379456, + "ts": 6197197263403.041, "dur": 3.754, + "args": { + "External id": 29305,"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": 2338707, "tid": 2379456, + "ts": 6197197263452.952, "dur": 7.081, + "args": { + "External id": 29306,"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": 2338707, "tid": 2379456, + "ts": 6197197263457.019, "dur": 2.823, + "args": { + "External id": 29307,"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": 2338707, "tid": 2379456, + "ts": 6197197263462.344, "dur": 32.167, + "args": { + "External id": 29308,"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": 2338707, "tid": 2379456, + "ts": 6197197263468.297, "dur": 1.815, + "args": { + "External id": 29309,"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": 2338707, "tid": 2379456, + "ts": 6197197263495.860, "dur": 1.910, + "args": { + "External id": 29310,"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": 2338707, "tid": 2379456, + "ts": 6197197263497.041, "dur": 0.639, + "args": { + "External id": 29311,"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": 2338707, "tid": 2379456, + "ts": 6197197263499.021, "dur": 13.878, + "args": { + "External id": 29312,"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": 2338707, "tid": 2379456, + "ts": 6197197263500.954, "dur": 0.601, + "args": { + "External id": 29313,"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": 2338707, "tid": 2379456, + "ts": 6197197263593.035, "dur": 25.861, + "args": { + "External id": 29314,"kernel_hash": "cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4", "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/yk/cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4.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": 2338707, "tid": 2379456, + "ts": 6197197263637.625, "dur": 16.348, + "args": { + "External id": 29315,"kernel_hash": "ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg", "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/eu/ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg.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": 2338707, "tid": 2379456, + "ts": 6197197263661.824, "dur": 58.584, + "args": { + "External id": 29316,"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": 2338707, "tid": 2379456, + "ts": 6197197263729.773, "dur": 44.475, + "args": { + "External id": 29317,"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": 2338707, "tid": 2379456, + "ts": 6197197263784.037, "dur": 21.685, + "args": { + "External id": 29318,"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": 2338707, "tid": 2379456, + "ts": 6197197263813.994, "dur": 31.928, + "args": { + "External id": 29319,"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": 2338707, "tid": 2379456, + "ts": 6197197263853.489, "dur": 28.748, + "args": { + "External id": 29320,"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": 2338707, "tid": 2379456, + "ts": 6197197263890.193, "dur": 30.527, + "args": { + "External id": 29321,"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": 2338707, "tid": 2379456, + "ts": 6197197263941.985, "dur": 24.548, + "args": { + "External id": 29322,"kernel_hash": "c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/6w/c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7.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": 2338707, "tid": 2379456, + "ts": 6197197263985.831, "dur": 23.418, + "args": { + "External id": 29323,"kernel_hash": "ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx", "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/kj/ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx.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": 2338707, "tid": 2379456, + "ts": 6197197264026.309, "dur": 15.619, + "args": { + "External id": 29324,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197197264092.177, "dur": 18.830, + "args": { + "External id": 29325,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197197264128.095, "dur": 15.684, + "args": { + "External id": 29326,"kernel_hash": "cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/eb/cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b.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": 2338707, "tid": 2379456, + "ts": 6197197264225.082, "dur": 15.012, + "args": { + "External id": 29327,"Record function id": 0, "Ev Idx": 2190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197264228.218, "dur": 10.807, + "args": { + "External id": 29328,"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": 2338707, "tid": 2379456, + "ts": 6197197264232.696, "dur": 5.365, + "args": { + "External id": 29329,"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": 2338707, "tid": 2379456, + "ts": 6197197264234.055, "dur": 3.878, + "args": { + "External id": 29330,"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": 2338707, "tid": 2379456, + "ts": 6197197264244.077, "dur": 5.621, + "args": { + "External id": 29331,"Record function id": 0, "Ev Idx": 2194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197264245.887, "dur": 3.328, + "args": { + "External id": 29332,"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": 2338707, "tid": 2379456, + "ts": 6197197264247.351, "dur": 1.395, + "args": { + "External id": 29333,"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": 2338707, "tid": 2379456, + "ts": 6197197264247.919, "dur": 0.686, + "args": { + "External id": 29334,"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": 2338707, "tid": 2379456, + "ts": 6197197264253.058, "dur": 4.779, + "args": { + "External id": 29335,"Record function id": 0, "Ev Idx": 2198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197264254.490, "dur": 2.894, + "args": { + "External id": 29336,"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": 2338707, "tid": 2379456, + "ts": 6197197264255.115, "dur": 1.836, + "args": { + "External id": 29337,"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": 2338707, "tid": 2379456, + "ts": 6197197264255.973, "dur": 0.869, + "args": { + "External id": 29338,"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": 2338707, "tid": 2379456, + "ts": 6197197264261.095, "dur": 4.903, + "args": { + "External id": 29339,"Record function id": 0, "Ev Idx": 2202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197264262.770, "dur": 2.819, + "args": { + "External id": 29340,"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": 2338707, "tid": 2379456, + "ts": 6197197264263.711, "dur": 1.460, + "args": { + "External id": 29341,"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": 2338707, "tid": 2379456, + "ts": 6197197264264.427, "dur": 0.660, + "args": { + "External id": 29342,"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": 2338707, "tid": 2379456, + "ts": 6197197264269.123, "dur": 4.244, + "args": { + "External id": 29343,"Record function id": 0, "Ev Idx": 2206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197264270.498, "dur": 2.437, + "args": { + "External id": 29344,"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": 2338707, "tid": 2379456, + "ts": 6197197264271.352, "dur": 1.111, + "args": { + "External id": 29345,"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": 2338707, "tid": 2379456, + "ts": 6197197264271.752, "dur": 0.647, + "args": { + "External id": 29346,"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": 2338707, "tid": 2379456, + "ts": 6197197264276.483, "dur": 6.335, + "args": { + "External id": 29347,"Record function id": 0, "Ev Idx": 2210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197264277.878, "dur": 4.522, + "args": { + "External id": 29348,"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": 2338707, "tid": 2379456, + "ts": 6197197264278.860, "dur": 3.149, + "args": { + "External id": 29349,"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": 2338707, "tid": 2379456, + "ts": 6197197264279.247, "dur": 2.691, + "args": { + "External id": 29350,"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": 2338707, "tid": 2379456, + "ts": 6197197264286.175, "dur": 4.054, + "args": { + "External id": 29351,"Record function id": 0, "Ev Idx": 2214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197264287.642, "dur": 2.157, + "args": { + "External id": 29352,"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": 2338707, "tid": 2379456, + "ts": 6197197264288.131, "dur": 1.044, + "args": { + "External id": 29353,"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": 2338707, "tid": 2379456, + "ts": 6197197264288.381, "dur": 0.722, + "args": { + "External id": 29354,"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": 2338707, "tid": 2379456, + "ts": 6197197264293.318, "dur": 6.053, + "args": { + "External id": 29355,"Record function id": 0, "Ev Idx": 2218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197264294.568, "dur": 4.377, + "args": { + "External id": 29356,"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": 2338707, "tid": 2379456, + "ts": 6197197264295.129, "dur": 3.406, + "args": { + "External id": 29357,"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": 2338707, "tid": 2379456, + "ts": 6197197264297.859, "dur": 0.610, + "args": { + "External id": 29358,"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": 2338707, "tid": 2379456, + "ts": 6197197264302.521, "dur": 4.717, + "args": { + "External id": 29359,"Record function id": 0, "Ev Idx": 2222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197264303.957, "dur": 2.865, + "args": { + "External id": 29360,"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": 2338707, "tid": 2379456, + "ts": 6197197264304.666, "dur": 1.745, + "args": { + "External id": 29361,"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": 2338707, "tid": 2379456, + "ts": 6197197264305.622, "dur": 0.723, + "args": { + "External id": 29362,"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": 2338707, "tid": 2379456, + "ts": 6197197264311.699, "dur": 78870.554, + "args": { + "External id": 29363,"Record function id": 0, "Sequence number": 479811, "Fwd thread id": 1, "Ev Idx": 2226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197197264313.775, "dur": 78858.637, + "args": { + "External id": 29364,"Sequence number": 479811, "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": 2338707, "tid": 2379456, "ts": 6197197264313.775, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.22)", "pid": 2338707, "tid": 2379456, + "ts": 6197197264343.485, "dur": 54.578, + "args": { + "External id": 29365,"Record function id": 0, "Ev Idx": 2228 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.22)", "pid": 2338707, "tid": 2379456, + "ts": 6197197264410.078, "dur": 69.344, + "args": { + "External id": 29366,"Record function id": 0, "Ev Idx": 2229 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.22)", "pid": 2338707, "tid": 2379456, + "ts": 6197197264485.020, "dur": 78679.231, + "args": { + "External id": 29367,"Record function id": 0, "Ev Idx": 2230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197197264584.480, "dur": 7.697, + "args": { + "External id": 29368,"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": 2338707, "tid": 2379456, + "ts": 6197197264602.178, "dur": 4.737, + "args": { + "External id": 29369,"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": 2338707, "tid": 2379456, + "ts": 6197197264624.487, "dur": 77638.787, + "args": { + "External id": 29370,"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": 2338707, "tid": 2379456, + "ts": 6197197264640.136, "dur": 77609.550, + "args": { + "External id": 29371,"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": 2338707, "tid": 2379456, + "ts": 6197197264754.634, "dur": 18.718, + "args": { + "External id": 29372,"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": 2338707, "tid": 2379456, + "ts": 6197197264794.416, "dur": 77410.164, + "args": { + "External id": 29373,"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": 2338707, "tid": 2379456, + "ts": 6197197264797.023, "dur": 77406.460, + "args": { + "External id": 29374,"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": 2338707, "tid": 2379456, + "ts": 6197197264801.802, "dur": 13.684, + "args": { + "External id": 29375,"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": 2338707, "tid": 2379456, + "ts": 6197197264817.712, "dur": 77380.720, + "args": { + "External id": 29376,"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": 2338707, "tid": 2379456, + "ts": 6197197342366.479, "dur": 11.824, + "args": { + "External id": 29377,"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": 2338707, "tid": 2379456, + "ts": 6197197342370.079, "dur": 7.809, + "args": { + "External id": 29378,"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": 2338707, "tid": 2379456, + "ts": 6197197342409.750, "dur": 403.514, + "args": { + "External id": 29379,"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": 2338707, "tid": 2379456, + "ts": 6197197342442.060, "dur": 365.475, + "args": { + "External id": 29380,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197197342454.435, "dur": 346.449, + "args": { + "External id": 29381,"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": 2338707, "tid": 2379456, + "ts": 6197197342843.089, "dur": 2.684, + "args": { + "External id": 29382,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2379456, + "ts": 6197197342911.387, "dur": 6.987, + "args": { + "External id": 29383,"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": 2338707, "tid": 2379456, + "ts": 6197197342966.419, "dur": 1.554, + "args": { + "External id": 29384,"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": 2338707, "tid": 2379456, + "ts": 6197197342982.625, "dur": 1.112, + "args": { + "External id": 29385,"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": 2338707, "tid": 2379456, + "ts": 6197197342996.246, "dur": 1.058, + "args": { + "External id": 29386,"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": 2338707, "tid": 2379456, + "ts": 6197197343009.146, "dur": 1.196, + "args": { + "External id": 29387,"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": 2338707, "tid": 2379456, + "ts": 6197197343022.790, "dur": 0.895, + "args": { + "External id": 29388,"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": 2338707, "tid": 2379456, + "ts": 6197197343033.772, "dur": 1.292, + "args": { + "External id": 29389,"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": 2338707, "tid": 2379456, + "ts": 6197197343044.612, "dur": 3.805, + "args": { + "External id": 29390,"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": 2338707, "tid": 2379456, + "ts": 6197197343096.611, "dur": 2.033, + "args": { + "External id": 29391,"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": 2338707, "tid": 2379456, + "ts": 6197197343198.242, "dur": 2984.202, + "args": { + "External id": 29392,"Record function id": 0, "Ev Idx": 2255 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.21)", "pid": 2338707, "tid": 2379456, + "ts": 6197197343219.638, "dur": 1127.697, + "args": { + "External id": 29393,"Record function id": 0, "Ev Idx": 2256 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.21)", "pid": 2338707, "tid": 2379456, + "ts": 6197197343233.051, "dur": 348.226, + "args": { + "External id": 29394,"Record function id": 0, "Ev Idx": 2257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6197197343326.724, "dur": 4.549, + "args": { + "External id": 29395,"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": 2338707, "tid": 2379456, + "ts": 6197197343334.479, "dur": 2.161, + "args": { + "External id": 29396,"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": 2338707, "tid": 2379456, + "ts": 6197197343338.580, "dur": 1.254, + "args": { + "External id": 29397,"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": 2338707, "tid": 2379456, + "ts": 6197197343341.688, "dur": 1.056, + "args": { + "External id": 29398,"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": 2338707, "tid": 2379456, + "ts": 6197197343345.221, "dur": 1.371, + "args": { + "External id": 29399,"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": 2338707, "tid": 2379456, + "ts": 6197197343347.904, "dur": 1.076, + "args": { + "External id": 29400,"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": 2338707, "tid": 2379456, + "ts": 6197197343350.653, "dur": 3.239, + "args": { + "External id": 29401,"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": 2338707, "tid": 2379456, + "ts": 6197197343357.180, "dur": 3.002, + "args": { + "External id": 29402,"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": 2338707, "tid": 2379456, + "ts": 6197197343361.647, "dur": 0.973, + "args": { + "External id": 29403,"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": 2338707, "tid": 2379456, + "ts": 6197197343364.434, "dur": 1.021, + "args": { + "External id": 29404,"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": 2338707, "tid": 2379456, + "ts": 6197197343385.022, "dur": 165.912, + "args": { + "External id": 29405,"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": 2338707, "tid": 2379456, + "ts": 6197197343401.572, "dur": 144.370, + "args": { + "External id": 29406,"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": 2338707, "tid": 2379456, + "ts": 6197197343431.553, "dur": 15.565, + "args": { + "External id": 29407,"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": 2338707, "tid": 2379456, + "ts": 6197197343452.178, "dur": 66.675, + "args": { + "External id": 29408,"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": 2338707, "tid": 2379456, + "ts": 6197197343454.584, "dur": 63.894, + "args": { + "External id": 29409,"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": 2338707, "tid": 2379456, + "ts": 6197197343460.469, "dur": 6.273, + "args": { + "External id": 29410,"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": 2338707, "tid": 2379456, + "ts": 6197197343468.427, "dur": 49.240, + "args": { + "External id": 29411,"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": 2338707, "tid": 2379456, + "ts": 6197197343670.129, "dur": 668.670, + "args": { + "External id": 29412,"Record function id": 0, "Ev Idx": 2275 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.20)", "pid": 2338707, "tid": 2379456, + "ts": 6197197343686.604, "dur": 640.224, + "args": { + "External id": 29413,"Record function id": 0, "Ev Idx": 2276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197197343770.943, "dur": 6.227, + "args": { + "External id": 29414,"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": 2338707, "tid": 2379456, + "ts": 6197197343792.503, "dur": 36.118, + "args": { + "External id": 29415,"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": 2338707, "tid": 2379456, + "ts": 6197197343797.857, "dur": 1.632, + "args": { + "External id": 29416,"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": 2338707, "tid": 2379456, + "ts": 6197197343801.727, "dur": 1.489, + "args": { + "External id": 29417,"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": 2338707, "tid": 2379456, + "ts": 6197197343804.870, "dur": 2.686, + "args": { + "External id": 29418,"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": 2338707, "tid": 2379456, + "ts": 6197197343809.139, "dur": 0.494, + "args": { + "External id": 29419,"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": 2338707, "tid": 2379456, + "ts": 6197197343812.267, "dur": 0.456, + "args": { + "External id": 29420,"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": 2338707, "tid": 2379456, + "ts": 6197197343814.121, "dur": 0.476, + "args": { + "External id": 29421,"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": 2338707, "tid": 2379456, + "ts": 6197197343815.896, "dur": 0.581, + "args": { + "External id": 29422,"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": 2338707, "tid": 2379456, + "ts": 6197197343819.883, "dur": 0.340, + "args": { + "External id": 29423,"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": 2338707, "tid": 2379456, + "ts": 6197197343821.546, "dur": 0.629, + "args": { + "External id": 29424,"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": 2338707, "tid": 2379456, + "ts": 6197197343840.089, "dur": 46.989, + "args": { + "External id": 29425,"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": 2338707, "tid": 2379456, + "ts": 6197197343919.700, "dur": 122.493, + "args": { + "External id": 29426,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2379456, + "ts": 6197197343929.800, "dur": 2.752, + "args": { + "External id": 29427,"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": 2338707, "tid": 2379456, + "ts": 6197197343937.707, "dur": 12.518, + "args": { + "External id": 29428,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2379456, + "ts": 6197197343942.177, "dur": 7.614, + "args": { + "External id": 29429,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2379456, + "ts": 6197197343945.624, "dur": 2.872, + "args": { + "External id": 29430,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197197343956.917, "dur": 32.175, + "args": { + "External id": 29431,"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": 2338707, "tid": 2379456, + "ts": 6197197343959.415, "dur": 0.735, + "args": { + "External id": 29432,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197197343963.061, "dur": 0.559, + "args": { + "External id": 29433,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2379456, + "ts": 6197197343964.791, "dur": 0.627, + "args": { + "External id": 29434,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2379456, + "ts": 6197197343967.293, "dur": 1.530, + "args": { + "External id": 29435,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2379456, + "ts": 6197197343970.661, "dur": 0.422, + "args": { + "External id": 29436,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2379456, + "ts": 6197197343972.632, "dur": 0.474, + "args": { + "External id": 29437,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2379456, + "ts": 6197197343975.504, "dur": 0.427, + "args": { + "External id": 29438,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2379456, + "ts": 6197197343977.344, "dur": 2.536, + "args": { + "External id": 29439,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2379456, + "ts": 6197197343981.594, "dur": 0.465, + "args": { + "External id": 29440,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2379456, + "ts": 6197197344000.463, "dur": 33.390, + "args": { + "External id": 29441,"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": 2338707, "tid": 2379456, + "ts": 6197197344125.289, "dur": 125.910, + "args": { + "External id": 29442,"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": 2338707, "tid": 2379456, + "ts": 6197197344156.429, "dur": 91.048, + "args": { + "External id": 29443,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197197344167.300, "dur": 75.934, + "args": { + "External id": 29444,"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": 2338707, "tid": 2379456, + "ts": 6197197344270.152, "dur": 2.185, + "args": { + "External id": 29445,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197197344354.434, "dur": 1804.892, + "args": { + "External id": 29446,"Sequence number": 479810, "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": 2338707, "tid": 2379456, "ts": 6197197344354.434, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6197197344465.980, "dur": 106.995, + "args": { + "External id": 29447,"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": 2338707, "tid": 2379456, + "ts": 6197197344614.740, "dur": 39.242, + "args": { + "External id": 29448,"kernel_hash": "cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/u7/cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs.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": 2338707, "tid": 2379456, + "ts": 6197197344672.608, "dur": 78.974, + "args": { + "External id": 29449,"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": 2338707, "tid": 2379456, + "ts": 6197197344766.321, "dur": 35.743, + "args": { + "External id": 29450,"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": 2338707, "tid": 2379456, + "ts": 6197197344808.869, "dur": 32.609, + "args": { + "External id": 29451,"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": 2338707, "tid": 2379456, + "ts": 6197197344847.505, "dur": 28.597, + "args": { + "External id": 29452,"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": 2338707, "tid": 2379456, + "ts": 6197197344885.501, "dur": 29.154, + "args": { + "External id": 29453,"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": 2338707, "tid": 2379456, + "ts": 6197197344943.417, "dur": 24.846, + "args": { + "External id": 29454,"kernel_hash": "cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/wm/cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s.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": 2338707, "tid": 2379456, + "ts": 6197197344986.383, "dur": 28.336, + "args": { + "External id": 29455,"kernel_hash": "cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql", "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/qt/cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql.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": 2338707, "tid": 2379456, + "ts": 6197197345039.402, "dur": 57.055, + "args": { + "External id": 29456,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197197345114.369, "dur": 19.895, + "args": { + "External id": 29457,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197197345144.742, "dur": 44.042, + "args": { + "External id": 29458,"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": 2338707, "tid": 2379456, + "ts": 6197197345192.644, "dur": 33.318, + "args": { + "External id": 29459,"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": 2338707, "tid": 2379456, + "ts": 6197197345255.737, "dur": 248.080, + "args": { + "External id": 29460,"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": 2338707, "tid": 2379456, + "ts": 6197197345335.285, "dur": 6.160, + "args": { + "External id": 29461,"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": 2338707, "tid": 2379456, + "ts": 6197197345343.621, "dur": 2.958, + "args": { + "External id": 29462,"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": 2338707, "tid": 2379456, + "ts": 6197197345348.009, "dur": 4.803, + "args": { + "External id": 29463,"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": 2338707, "tid": 2379456, + "ts": 6197197345354.137, "dur": 1.784, + "args": { + "External id": 29464,"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": 2338707, "tid": 2379456, + "ts": 6197197345400.092, "dur": 7.367, + "args": { + "External id": 29465,"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": 2338707, "tid": 2379456, + "ts": 6197197345404.407, "dur": 2.857, + "args": { + "External id": 29466,"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": 2338707, "tid": 2379456, + "ts": 6197197345409.433, "dur": 31.888, + "args": { + "External id": 29467,"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": 2338707, "tid": 2379456, + "ts": 6197197345414.872, "dur": 2.692, + "args": { + "External id": 29468,"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": 2338707, "tid": 2379456, + "ts": 6197197345442.905, "dur": 1.940, + "args": { + "External id": 29469,"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": 2338707, "tid": 2379456, + "ts": 6197197345444.146, "dur": 0.618, + "args": { + "External id": 29470,"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": 2338707, "tid": 2379456, + "ts": 6197197345445.901, "dur": 15.373, + "args": { + "External id": 29471,"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": 2338707, "tid": 2379456, + "ts": 6197197345448.928, "dur": 0.571, + "args": { + "External id": 29472,"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": 2338707, "tid": 2379456, + "ts": 6197197345541.528, "dur": 25.901, + "args": { + "External id": 29473,"kernel_hash": "cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4", "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/yk/cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4.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": 2338707, "tid": 2379456, + "ts": 6197197345586.408, "dur": 16.304, + "args": { + "External id": 29474,"kernel_hash": "ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg", "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/eu/ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg.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": 2338707, "tid": 2379456, + "ts": 6197197345609.957, "dur": 39.379, + "args": { + "External id": 29475,"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": 2338707, "tid": 2379456, + "ts": 6197197345655.788, "dur": 38.151, + "args": { + "External id": 29476,"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": 2338707, "tid": 2379456, + "ts": 6197197345720.553, "dur": 26.115, + "args": { + "External id": 29477,"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": 2338707, "tid": 2379456, + "ts": 6197197345755.517, "dur": 31.618, + "args": { + "External id": 29478,"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": 2338707, "tid": 2379456, + "ts": 6197197345794.992, "dur": 28.316, + "args": { + "External id": 29479,"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": 2338707, "tid": 2379456, + "ts": 6197197345829.908, "dur": 31.465, + "args": { + "External id": 29480,"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": 2338707, "tid": 2379456, + "ts": 6197197345883.566, "dur": 25.246, + "args": { + "External id": 29481,"kernel_hash": "c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/6w/c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7.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": 2338707, "tid": 2379456, + "ts": 6197197345933.404, "dur": 24.958, + "args": { + "External id": 29482,"kernel_hash": "ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx", "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/kj/ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx.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": 2338707, "tid": 2379456, + "ts": 6197197345977.856, "dur": 16.557, + "args": { + "External id": 29483,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197197346027.466, "dur": 20.361, + "args": { + "External id": 29484,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197197346104.060, "dur": 18.956, + "args": { + "External id": 29485,"kernel_hash": "cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/eb/cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b.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": 2338707, "tid": 2379456, + "ts": 6197197346204.176, "dur": 19.370, + "args": { + "External id": 29486,"Record function id": 0, "Ev Idx": 2349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197346211.019, "dur": 11.529, + "args": { + "External id": 29487,"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": 2338707, "tid": 2379456, + "ts": 6197197346215.083, "dur": 6.606, + "args": { + "External id": 29488,"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": 2338707, "tid": 2379456, + "ts": 6197197346216.959, "dur": 4.603, + "args": { + "External id": 29489,"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": 2338707, "tid": 2379456, + "ts": 6197197346227.390, "dur": 5.187, + "args": { + "External id": 29490,"Record function id": 0, "Ev Idx": 2353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197346228.913, "dur": 3.137, + "args": { + "External id": 29491,"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": 2338707, "tid": 2379456, + "ts": 6197197346229.877, "dur": 1.717, + "args": { + "External id": 29492,"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": 2338707, "tid": 2379456, + "ts": 6197197346230.477, "dur": 1.001, + "args": { + "External id": 29493,"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": 2338707, "tid": 2379456, + "ts": 6197197346235.817, "dur": 5.166, + "args": { + "External id": 29494,"Record function id": 0, "Ev Idx": 2357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197346237.346, "dur": 3.190, + "args": { + "External id": 29495,"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": 2338707, "tid": 2379456, + "ts": 6197197346238.374, "dur": 1.750, + "args": { + "External id": 29496,"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": 2338707, "tid": 2379456, + "ts": 6197197346239.233, "dur": 0.786, + "args": { + "External id": 29497,"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": 2338707, "tid": 2379456, + "ts": 6197197346244.382, "dur": 4.401, + "args": { + "External id": 29498,"Record function id": 0, "Ev Idx": 2361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197346245.789, "dur": 2.588, + "args": { + "External id": 29499,"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": 2338707, "tid": 2379456, + "ts": 6197197346246.773, "dur": 0.990, + "args": { + "External id": 29500,"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": 2338707, "tid": 2379456, + "ts": 6197197346247.123, "dur": 0.575, + "args": { + "External id": 29501,"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": 2338707, "tid": 2379456, + "ts": 6197197346251.935, "dur": 3.698, + "args": { + "External id": 29502,"Record function id": 0, "Ev Idx": 2365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197346253.303, "dur": 1.930, + "args": { + "External id": 29503,"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": 2338707, "tid": 2379456, + "ts": 6197197346253.803, "dur": 1.047, + "args": { + "External id": 29504,"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": 2338707, "tid": 2379456, + "ts": 6197197346254.143, "dur": 0.641, + "args": { + "External id": 29505,"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": 2338707, "tid": 2379456, + "ts": 6197197346258.916, "dur": 3.666, + "args": { + "External id": 29506,"Record function id": 0, "Ev Idx": 2369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197346259.962, "dur": 2.217, + "args": { + "External id": 29507,"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": 2338707, "tid": 2379456, + "ts": 6197197346260.437, "dur": 1.363, + "args": { + "External id": 29508,"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": 2338707, "tid": 2379456, + "ts": 6197197346260.817, "dur": 0.918, + "args": { + "External id": 29509,"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": 2338707, "tid": 2379456, + "ts": 6197197346265.941, "dur": 6.139, + "args": { + "External id": 29510,"Record function id": 0, "Ev Idx": 2373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197346267.045, "dur": 4.610, + "args": { + "External id": 29511,"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": 2338707, "tid": 2379456, + "ts": 6197197346267.493, "dur": 3.639, + "args": { + "External id": 29512,"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": 2338707, "tid": 2379456, + "ts": 6197197346267.765, "dur": 3.306, + "args": { + "External id": 29513,"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": 2338707, "tid": 2379456, + "ts": 6197197346275.385, "dur": 6.918, + "args": { + "External id": 29514,"Record function id": 0, "Ev Idx": 2377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197346276.553, "dur": 5.344, + "args": { + "External id": 29515,"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": 2338707, "tid": 2379456, + "ts": 6197197346277.438, "dur": 3.839, + "args": { + "External id": 29516,"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": 2338707, "tid": 2379456, + "ts": 6197197346280.271, "dur": 0.891, + "args": { + "External id": 29517,"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": 2338707, "tid": 2379456, + "ts": 6197197346285.345, "dur": 3.672, + "args": { + "External id": 29518,"Record function id": 0, "Ev Idx": 2381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197346286.432, "dur": 2.198, + "args": { + "External id": 29519,"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": 2338707, "tid": 2379456, + "ts": 6197197346287.093, "dur": 1.098, + "args": { + "External id": 29520,"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": 2338707, "tid": 2379456, + "ts": 6197197346287.351, "dur": 0.762, + "args": { + "External id": 29521,"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": 2338707, "tid": 2379456, + "ts": 6197197346293.288, "dur": 63006.832, + "args": { + "External id": 29522,"Record function id": 0, "Sequence number": 479809, "Fwd thread id": 1, "Ev Idx": 2385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197197346295.408, "dur": 62994.915, + "args": { + "External id": 29523,"Sequence number": 479809, "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": 2338707, "tid": 2379456, "ts": 6197197346295.408, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.21)", "pid": 2338707, "tid": 2379456, + "ts": 6197197346325.520, "dur": 38.566, + "args": { + "External id": 29524,"Record function id": 0, "Ev Idx": 2387 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.21)", "pid": 2338707, "tid": 2379456, + "ts": 6197197346371.619, "dur": 66.299, + "args": { + "External id": 29525,"Record function id": 0, "Ev Idx": 2388 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.21)", "pid": 2338707, "tid": 2379456, + "ts": 6197197346444.122, "dur": 62837.713, + "args": { + "External id": 29526,"Record function id": 0, "Ev Idx": 2389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197197346531.288, "dur": 7.022, + "args": { + "External id": 29527,"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": 2338707, "tid": 2379456, + "ts": 6197197346548.216, "dur": 4.769, + "args": { + "External id": 29528,"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": 2338707, "tid": 2379456, + "ts": 6197197346566.782, "dur": 61775.062, + "args": { + "External id": 29529,"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": 2338707, "tid": 2379456, + "ts": 6197197346584.485, "dur": 61744.470, + "args": { + "External id": 29530,"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": 2338707, "tid": 2379456, + "ts": 6197197346677.332, "dur": 17.415, + "args": { + "External id": 29531,"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": 2338707, "tid": 2379456, + "ts": 6197197346735.405, "dur": 61550.467, + "args": { + "External id": 29532,"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": 2338707, "tid": 2379456, + "ts": 6197197346741.464, "dur": 61543.341, + "args": { + "External id": 29533,"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": 2338707, "tid": 2379456, + "ts": 6197197346746.526, "dur": 13.712, + "args": { + "External id": 29534,"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": 2338707, "tid": 2379456, + "ts": 6197197346762.478, "dur": 61517.365, + "args": { + "External id": 29535,"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": 2338707, "tid": 2379456, + "ts": 6197197408448.291, "dur": 13.449, + "args": { + "External id": 29536,"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": 2338707, "tid": 2379456, + "ts": 6197197408452.521, "dur": 8.784, + "args": { + "External id": 29537,"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": 2338707, "tid": 2379456, + "ts": 6197197408492.005, "dur": 433.780, + "args": { + "External id": 29538,"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": 2338707, "tid": 2379456, + "ts": 6197197408525.532, "dur": 394.904, + "args": { + "External id": 29539,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197197408538.971, "dur": 375.061, + "args": { + "External id": 29540,"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": 2338707, "tid": 2379456, + "ts": 6197197408960.856, "dur": 2.667, + "args": { + "External id": 29541,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2379456, + "ts": 6197197409028.815, "dur": 7.090, + "args": { + "External id": 29542,"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": 2338707, "tid": 2379456, + "ts": 6197197409120.508, "dur": 2.467, + "args": { + "External id": 29543,"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": 2338707, "tid": 2379456, + "ts": 6197197409139.195, "dur": 1.204, + "args": { + "External id": 29544,"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": 2338707, "tid": 2379456, + "ts": 6197197409152.316, "dur": 1.123, + "args": { + "External id": 29545,"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": 2338707, "tid": 2379456, + "ts": 6197197409164.810, "dur": 1.077, + "args": { + "External id": 29546,"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": 2338707, "tid": 2379456, + "ts": 6197197409179.343, "dur": 0.852, + "args": { + "External id": 29547,"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": 2338707, "tid": 2379456, + "ts": 6197197409190.801, "dur": 1.254, + "args": { + "External id": 29548,"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": 2338707, "tid": 2379456, + "ts": 6197197409201.739, "dur": 3.218, + "args": { + "External id": 29549,"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": 2338707, "tid": 2379456, + "ts": 6197197409216.836, "dur": 0.848, + "args": { + "External id": 29550,"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": 2338707, "tid": 2379456, + "ts": 6197197409316.115, "dur": 2982.092, + "args": { + "External id": 29551,"Record function id": 0, "Ev Idx": 2414 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.20)", "pid": 2338707, "tid": 2379456, + "ts": 6197197409337.832, "dur": 1120.596, + "args": { + "External id": 29552,"Record function id": 0, "Ev Idx": 2415 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.20)", "pid": 2338707, "tid": 2379456, + "ts": 6197197409355.273, "dur": 340.491, + "args": { + "External id": 29553,"Record function id": 0, "Ev Idx": 2416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6197197409447.497, "dur": 4.392, + "args": { + "External id": 29554,"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": 2338707, "tid": 2379456, + "ts": 6197197409455.497, "dur": 1.170, + "args": { + "External id": 29555,"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": 2338707, "tid": 2379456, + "ts": 6197197409458.537, "dur": 1.041, + "args": { + "External id": 29556,"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": 2338707, "tid": 2379456, + "ts": 6197197409461.438, "dur": 1.055, + "args": { + "External id": 29557,"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": 2338707, "tid": 2379456, + "ts": 6197197409464.145, "dur": 1.214, + "args": { + "External id": 29558,"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": 2338707, "tid": 2379456, + "ts": 6197197409467.043, "dur": 1.002, + "args": { + "External id": 29559,"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": 2338707, "tid": 2379456, + "ts": 6197197409469.487, "dur": 3.619, + "args": { + "External id": 29560,"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": 2338707, "tid": 2379456, + "ts": 6197197409477.239, "dur": 3.125, + "args": { + "External id": 29561,"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": 2338707, "tid": 2379456, + "ts": 6197197409481.902, "dur": 0.946, + "args": { + "External id": 29562,"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": 2338707, "tid": 2379456, + "ts": 6197197409484.560, "dur": 0.983, + "args": { + "External id": 29563,"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": 2338707, "tid": 2379456, + "ts": 6197197409503.754, "dur": 162.685, + "args": { + "External id": 29564,"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": 2338707, "tid": 2379456, + "ts": 6197197409519.816, "dur": 141.686, + "args": { + "External id": 29565,"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": 2338707, "tid": 2379456, + "ts": 6197197409548.237, "dur": 14.134, + "args": { + "External id": 29566,"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": 2338707, "tid": 2379456, + "ts": 6197197409566.665, "dur": 65.890, + "args": { + "External id": 29567,"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": 2338707, "tid": 2379456, + "ts": 6197197409569.326, "dur": 62.766, + "args": { + "External id": 29568,"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": 2338707, "tid": 2379456, + "ts": 6197197409573.735, "dur": 6.616, + "args": { + "External id": 29569,"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": 2338707, "tid": 2379456, + "ts": 6197197409582.118, "dur": 49.206, + "args": { + "External id": 29570,"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": 2338707, "tid": 2379456, + "ts": 6197197409809.132, "dur": 641.231, + "args": { + "External id": 29571,"Record function id": 0, "Ev Idx": 2434 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.19)", "pid": 2338707, "tid": 2379456, + "ts": 6197197409829.510, "dur": 607.777, + "args": { + "External id": 29572,"Record function id": 0, "Ev Idx": 2435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197197409892.816, "dur": 5.952, + "args": { + "External id": 29573,"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": 2338707, "tid": 2379456, + "ts": 6197197409913.899, "dur": 35.923, + "args": { + "External id": 29574,"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": 2338707, "tid": 2379456, + "ts": 6197197409918.995, "dur": 2.501, + "args": { + "External id": 29575,"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": 2338707, "tid": 2379456, + "ts": 6197197409923.346, "dur": 0.375, + "args": { + "External id": 29576,"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": 2338707, "tid": 2379456, + "ts": 6197197409925.186, "dur": 2.512, + "args": { + "External id": 29577,"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": 2338707, "tid": 2379456, + "ts": 6197197409930.917, "dur": 0.296, + "args": { + "External id": 29578,"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": 2338707, "tid": 2379456, + "ts": 6197197409932.476, "dur": 0.265, + "args": { + "External id": 29579,"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": 2338707, "tid": 2379456, + "ts": 6197197409934.213, "dur": 0.547, + "args": { + "External id": 29580,"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": 2338707, "tid": 2379456, + "ts": 6197197409937.166, "dur": 0.666, + "args": { + "External id": 29581,"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": 2338707, "tid": 2379456, + "ts": 6197197409939.253, "dur": 0.592, + "args": { + "External id": 29582,"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": 2338707, "tid": 2379456, + "ts": 6197197409941.320, "dur": 1.195, + "args": { + "External id": 29583,"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": 2338707, "tid": 2379456, + "ts": 6197197409960.490, "dur": 45.872, + "args": { + "External id": 29584,"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": 2338707, "tid": 2379456, + "ts": 6197197410036.243, "dur": 162.349, + "args": { + "External id": 29585,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2379456, + "ts": 6197197410046.020, "dur": 2.893, + "args": { + "External id": 29586,"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": 2338707, "tid": 2379456, + "ts": 6197197410088.742, "dur": 13.393, + "args": { + "External id": 29587,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2379456, + "ts": 6197197410092.813, "dur": 8.921, + "args": { + "External id": 29588,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2379456, + "ts": 6197197410096.820, "dur": 3.021, + "args": { + "External id": 29589,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197197410111.345, "dur": 31.016, + "args": { + "External id": 29590,"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": 2338707, "tid": 2379456, + "ts": 6197197410114.284, "dur": 0.577, + "args": { + "External id": 29591,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197197410116.668, "dur": 0.297, + "args": { + "External id": 29592,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2379456, + "ts": 6197197410118.692, "dur": 1.496, + "args": { + "External id": 29593,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2379456, + "ts": 6197197410121.519, "dur": 0.564, + "args": { + "External id": 29594,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2379456, + "ts": 6197197410123.435, "dur": 0.398, + "args": { + "External id": 29595,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2379456, + "ts": 6197197410126.874, "dur": 0.250, + "args": { + "External id": 29596,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2379456, + "ts": 6197197410128.711, "dur": 0.775, + "args": { + "External id": 29597,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2379456, + "ts": 6197197410130.701, "dur": 2.518, + "args": { + "External id": 29598,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2379456, + "ts": 6197197410135.648, "dur": 0.298, + "args": { + "External id": 29599,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2379456, + "ts": 6197197410157.541, "dur": 32.642, + "args": { + "External id": 29600,"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": 2338707, "tid": 2379456, + "ts": 6197197410244.773, "dur": 122.832, + "args": { + "External id": 29601,"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": 2338707, "tid": 2379456, + "ts": 6197197410275.097, "dur": 89.095, + "args": { + "External id": 29602,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197197410286.003, "dur": 73.755, + "args": { + "External id": 29603,"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": 2338707, "tid": 2379456, + "ts": 6197197410385.238, "dur": 1.667, + "args": { + "External id": 29604,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197197410465.996, "dur": 1807.180, + "args": { + "External id": 29605,"Sequence number": 479808, "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": 2338707, "tid": 2379456, "ts": 6197197410465.996, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6197197410577.096, "dur": 104.766, + "args": { + "External id": 29606,"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": 2338707, "tid": 2379456, + "ts": 6197197410746.757, "dur": 41.296, + "args": { + "External id": 29607,"kernel_hash": "cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/u7/cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs.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": 2338707, "tid": 2379456, + "ts": 6197197410809.210, "dur": 56.879, + "args": { + "External id": 29608,"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": 2338707, "tid": 2379456, + "ts": 6197197410876.784, "dur": 32.401, + "args": { + "External id": 29609,"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": 2338707, "tid": 2379456, + "ts": 6197197410916.425, "dur": 32.753, + "args": { + "External id": 29610,"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": 2338707, "tid": 2379456, + "ts": 6197197410955.989, "dur": 27.760, + "args": { + "External id": 29611,"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": 2338707, "tid": 2379456, + "ts": 6197197410993.721, "dur": 29.939, + "args": { + "External id": 29612,"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": 2338707, "tid": 2379456, + "ts": 6197197411048.759, "dur": 62.240, + "args": { + "External id": 29613,"kernel_hash": "cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/wm/cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s.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": 2338707, "tid": 2379456, + "ts": 6197197411133.990, "dur": 26.512, + "args": { + "External id": 29614,"kernel_hash": "cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql", "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/qt/cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql.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": 2338707, "tid": 2379456, + "ts": 6197197411184.938, "dur": 18.091, + "args": { + "External id": 29615,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197197411216.805, "dur": 13.547, + "args": { + "External id": 29616,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197197411239.532, "dur": 41.682, + "args": { + "External id": 29617,"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": 2338707, "tid": 2379456, + "ts": 6197197411284.636, "dur": 32.720, + "args": { + "External id": 29618,"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": 2338707, "tid": 2379456, + "ts": 6197197411348.303, "dur": 248.197, + "args": { + "External id": 29619,"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": 2338707, "tid": 2379456, + "ts": 6197197411428.453, "dur": 6.188, + "args": { + "External id": 29620,"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": 2338707, "tid": 2379456, + "ts": 6197197411437.124, "dur": 2.357, + "args": { + "External id": 29621,"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": 2338707, "tid": 2379456, + "ts": 6197197411440.928, "dur": 5.606, + "args": { + "External id": 29622,"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": 2338707, "tid": 2379456, + "ts": 6197197411447.941, "dur": 1.914, + "args": { + "External id": 29623,"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": 2338707, "tid": 2379456, + "ts": 6197197411491.916, "dur": 7.944, + "args": { + "External id": 29624,"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": 2338707, "tid": 2379456, + "ts": 6197197411496.988, "dur": 2.653, + "args": { + "External id": 29625,"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": 2338707, "tid": 2379456, + "ts": 6197197411502.049, "dur": 31.005, + "args": { + "External id": 29626,"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": 2338707, "tid": 2379456, + "ts": 6197197411507.741, "dur": 1.569, + "args": { + "External id": 29627,"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": 2338707, "tid": 2379456, + "ts": 6197197411534.745, "dur": 1.812, + "args": { + "External id": 29628,"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": 2338707, "tid": 2379456, + "ts": 6197197411535.660, "dur": 0.675, + "args": { + "External id": 29629,"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": 2338707, "tid": 2379456, + "ts": 6197197411538.156, "dur": 16.609, + "args": { + "External id": 29630,"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": 2338707, "tid": 2379456, + "ts": 6197197411541.837, "dur": 0.928, + "args": { + "External id": 29631,"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": 2338707, "tid": 2379456, + "ts": 6197197411633.985, "dur": 25.554, + "args": { + "External id": 29632,"kernel_hash": "cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4", "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/yk/cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4.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": 2338707, "tid": 2379456, + "ts": 6197197411681.089, "dur": 15.841, + "args": { + "External id": 29633,"kernel_hash": "ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg", "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/eu/ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg.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": 2338707, "tid": 2379456, + "ts": 6197197411723.195, "dur": 46.395, + "args": { + "External id": 29634,"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": 2338707, "tid": 2379456, + "ts": 6197197411776.217, "dur": 37.821, + "args": { + "External id": 29635,"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": 2338707, "tid": 2379456, + "ts": 6197197411822.777, "dur": 19.649, + "args": { + "External id": 29636,"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": 2338707, "tid": 2379456, + "ts": 6197197411850.447, "dur": 30.237, + "args": { + "External id": 29637,"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": 2338707, "tid": 2379456, + "ts": 6197197411888.424, "dur": 42.143, + "args": { + "External id": 29638,"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": 2338707, "tid": 2379456, + "ts": 6197197411945.000, "dur": 37.031, + "args": { + "External id": 29639,"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": 2338707, "tid": 2379456, + "ts": 6197197412006.118, "dur": 26.751, + "args": { + "External id": 29640,"kernel_hash": "c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/6w/c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7.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": 2338707, "tid": 2379456, + "ts": 6197197412100.132, "dur": 33.360, + "args": { + "External id": 29641,"kernel_hash": "ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx", "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/kj/ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx.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": 2338707, "tid": 2379456, + "ts": 6197197412156.283, "dur": 18.844, + "args": { + "External id": 29642,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197197412190.466, "dur": 17.098, + "args": { + "External id": 29643,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197197412222.917, "dur": 17.496, + "args": { + "External id": 29644,"kernel_hash": "cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/eb/cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b.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": 2338707, "tid": 2379456, + "ts": 6197197412319.911, "dur": 15.482, + "args": { + "External id": 29645,"Record function id": 0, "Ev Idx": 2508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197412323.577, "dur": 10.737, + "args": { + "External id": 29646,"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": 2338707, "tid": 2379456, + "ts": 6197197412327.920, "dur": 5.430, + "args": { + "External id": 29647,"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": 2338707, "tid": 2379456, + "ts": 6197197412329.403, "dur": 3.850, + "args": { + "External id": 29648,"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": 2338707, "tid": 2379456, + "ts": 6197197412339.270, "dur": 4.943, + "args": { + "External id": 29649,"Record function id": 0, "Ev Idx": 2512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197412340.817, "dur": 2.960, + "args": { + "External id": 29650,"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": 2338707, "tid": 2379456, + "ts": 6197197412341.880, "dur": 1.400, + "args": { + "External id": 29651,"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": 2338707, "tid": 2379456, + "ts": 6197197412342.206, "dur": 0.980, + "args": { + "External id": 29652,"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": 2338707, "tid": 2379456, + "ts": 6197197412347.548, "dur": 4.837, + "args": { + "External id": 29653,"Record function id": 0, "Ev Idx": 2516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197412349.561, "dur": 2.401, + "args": { + "External id": 29654,"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": 2338707, "tid": 2379456, + "ts": 6197197412350.066, "dur": 1.471, + "args": { + "External id": 29655,"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": 2338707, "tid": 2379456, + "ts": 6197197412350.587, "dur": 0.860, + "args": { + "External id": 29656,"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": 2338707, "tid": 2379456, + "ts": 6197197412355.624, "dur": 4.557, + "args": { + "External id": 29657,"Record function id": 0, "Ev Idx": 2520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197412357.070, "dur": 2.711, + "args": { + "External id": 29658,"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": 2338707, "tid": 2379456, + "ts": 6197197412357.578, "dur": 1.549, + "args": { + "External id": 29659,"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": 2338707, "tid": 2379456, + "ts": 6197197412358.337, "dur": 0.724, + "args": { + "External id": 29660,"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": 2338707, "tid": 2379456, + "ts": 6197197412363.427, "dur": 3.850, + "args": { + "External id": 29661,"Record function id": 0, "Ev Idx": 2524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197412364.727, "dur": 2.145, + "args": { + "External id": 29662,"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": 2338707, "tid": 2379456, + "ts": 6197197412365.427, "dur": 0.979, + "args": { + "External id": 29663,"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": 2338707, "tid": 2379456, + "ts": 6197197412365.712, "dur": 0.628, + "args": { + "External id": 29664,"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": 2338707, "tid": 2379456, + "ts": 6197197412370.494, "dur": 5.912, + "args": { + "External id": 29665,"Record function id": 0, "Ev Idx": 2528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197412371.786, "dur": 4.213, + "args": { + "External id": 29666,"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": 2338707, "tid": 2379456, + "ts": 6197197412372.273, "dur": 3.032, + "args": { + "External id": 29667,"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": 2338707, "tid": 2379456, + "ts": 6197197412372.640, "dur": 2.606, + "args": { + "External id": 29668,"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": 2338707, "tid": 2379456, + "ts": 6197197412379.612, "dur": 4.168, + "args": { + "External id": 29669,"Record function id": 0, "Ev Idx": 2532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197412380.854, "dur": 2.519, + "args": { + "External id": 29670,"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": 2338707, "tid": 2379456, + "ts": 6197197412381.634, "dur": 1.184, + "args": { + "External id": 29671,"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": 2338707, "tid": 2379456, + "ts": 6197197412381.935, "dur": 0.818, + "args": { + "External id": 29672,"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": 2338707, "tid": 2379456, + "ts": 6197197412386.882, "dur": 7.085, + "args": { + "External id": 29673,"Record function id": 0, "Ev Idx": 2536 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197412388.340, "dur": 5.233, + "args": { + "External id": 29674,"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": 2338707, "tid": 2379456, + "ts": 6197197412388.983, "dur": 3.947, + "args": { + "External id": 29675,"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": 2338707, "tid": 2379456, + "ts": 6197197412391.646, "dur": 1.219, + "args": { + "External id": 29676,"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": 2338707, "tid": 2379456, + "ts": 6197197412398.513, "dur": 4.251, + "args": { + "External id": 29677,"Record function id": 0, "Ev Idx": 2540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197412399.840, "dur": 2.501, + "args": { + "External id": 29678,"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": 2338707, "tid": 2379456, + "ts": 6197197412400.531, "dur": 1.268, + "args": { + "External id": 29679,"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": 2338707, "tid": 2379456, + "ts": 6197197412400.879, "dur": 0.854, + "args": { + "External id": 29680,"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": 2338707, "tid": 2379456, + "ts": 6197197412407.130, "dur": 73054.326, + "args": { + "External id": 29681,"Record function id": 0, "Sequence number": 479807, "Fwd thread id": 1, "Ev Idx": 2544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197197412409.403, "dur": 73042.333, + "args": { + "External id": 29682,"Sequence number": 479807, "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": 2338707, "tid": 2379456, "ts": 6197197412409.403, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.20)", "pid": 2338707, "tid": 2379456, + "ts": 6197197412438.672, "dur": 40.692, + "args": { + "External id": 29683,"Record function id": 0, "Ev Idx": 2546 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.20)", "pid": 2338707, "tid": 2379456, + "ts": 6197197412487.247, "dur": 67.529, + "args": { + "External id": 29684,"Record function id": 0, "Ev Idx": 2547 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.20)", "pid": 2338707, "tid": 2379456, + "ts": 6197197412560.301, "dur": 72883.727, + "args": { + "External id": 29685,"Record function id": 0, "Ev Idx": 2548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197197412648.770, "dur": 6.271, + "args": { + "External id": 29686,"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": 2338707, "tid": 2379456, + "ts": 6197197412664.558, "dur": 4.693, + "args": { + "External id": 29687,"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": 2338707, "tid": 2379456, + "ts": 6197197412684.010, "dur": 71841.155, + "args": { + "External id": 29688,"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": 2338707, "tid": 2379456, + "ts": 6197197412699.319, "dur": 71812.658, + "args": { + "External id": 29689,"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": 2338707, "tid": 2379456, + "ts": 6197197412808.640, "dur": 18.552, + "args": { + "External id": 29690,"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": 2338707, "tid": 2379456, + "ts": 6197197412850.296, "dur": 71614.981, + "args": { + "External id": 29691,"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": 2338707, "tid": 2379456, + "ts": 6197197412853.103, "dur": 71611.118, + "args": { + "External id": 29692,"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": 2338707, "tid": 2379456, + "ts": 6197197412859.156, "dur": 9.937, + "args": { + "External id": 29693,"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": 2338707, "tid": 2379456, + "ts": 6197197412874.491, "dur": 71584.833, + "args": { + "External id": 29694,"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": 2338707, "tid": 2379456, + "ts": 6197197484630.465, "dur": 12.464, + "args": { + "External id": 29695,"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": 2338707, "tid": 2379456, + "ts": 6197197484634.317, "dur": 8.208, + "args": { + "External id": 29696,"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": 2338707, "tid": 2379456, + "ts": 6197197484720.090, "dur": 414.879, + "args": { + "External id": 29697,"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": 2338707, "tid": 2379456, + "ts": 6197197484754.824, "dur": 374.428, + "args": { + "External id": 29698,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197197484768.304, "dur": 355.308, + "args": { + "External id": 29699,"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": 2338707, "tid": 2379456, + "ts": 6197197485160.767, "dur": 1.939, + "args": { + "External id": 29700,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2379456, + "ts": 6197197485231.581, "dur": 6.816, + "args": { + "External id": 29701,"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": 2338707, "tid": 2379456, + "ts": 6197197485284.610, "dur": 1.151, + "args": { + "External id": 29702,"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": 2338707, "tid": 2379456, + "ts": 6197197485301.139, "dur": 1.994, + "args": { + "External id": 29703,"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": 2338707, "tid": 2379456, + "ts": 6197197485314.896, "dur": 0.985, + "args": { + "External id": 29704,"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": 2338707, "tid": 2379456, + "ts": 6197197485330.270, "dur": 1.041, + "args": { + "External id": 29705,"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": 2338707, "tid": 2379456, + "ts": 6197197485344.256, "dur": 0.861, + "args": { + "External id": 29706,"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": 2338707, "tid": 2379456, + "ts": 6197197485355.421, "dur": 1.148, + "args": { + "External id": 29707,"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": 2338707, "tid": 2379456, + "ts": 6197197485366.817, "dur": 3.025, + "args": { + "External id": 29708,"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": 2338707, "tid": 2379456, + "ts": 6197197485378.889, "dur": 1.695, + "args": { + "External id": 29709,"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": 2338707, "tid": 2379456, + "ts": 6197197485475.630, "dur": 2966.729, + "args": { + "External id": 29710,"Record function id": 0, "Ev Idx": 2573 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.19)", "pid": 2338707, "tid": 2379456, + "ts": 6197197485498.282, "dur": 1103.850, + "args": { + "External id": 29711,"Record function id": 0, "Ev Idx": 2574 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.19)", "pid": 2338707, "tid": 2379456, + "ts": 6197197485513.684, "dur": 361.202, + "args": { + "External id": 29712,"Record function id": 0, "Ev Idx": 2575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6197197485601.960, "dur": 4.109, + "args": { + "External id": 29713,"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": 2338707, "tid": 2379456, + "ts": 6197197485609.423, "dur": 0.978, + "args": { + "External id": 29714,"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": 2338707, "tid": 2379456, + "ts": 6197197485612.430, "dur": 1.106, + "args": { + "External id": 29715,"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": 2338707, "tid": 2379456, + "ts": 6197197485615.479, "dur": 0.793, + "args": { + "External id": 29716,"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": 2338707, "tid": 2379456, + "ts": 6197197485617.639, "dur": 1.322, + "args": { + "External id": 29717,"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": 2338707, "tid": 2379456, + "ts": 6197197485620.758, "dur": 0.965, + "args": { + "External id": 29718,"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": 2338707, "tid": 2379456, + "ts": 6197197485623.390, "dur": 3.066, + "args": { + "External id": 29719,"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": 2338707, "tid": 2379456, + "ts": 6197197485629.863, "dur": 2.747, + "args": { + "External id": 29720,"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": 2338707, "tid": 2379456, + "ts": 6197197485633.926, "dur": 1.198, + "args": { + "External id": 29721,"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": 2338707, "tid": 2379456, + "ts": 6197197485636.643, "dur": 0.903, + "args": { + "External id": 29722,"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": 2338707, "tid": 2379456, + "ts": 6197197485656.461, "dur": 184.790, + "args": { + "External id": 29723,"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": 2338707, "tid": 2379456, + "ts": 6197197485672.721, "dur": 163.091, + "args": { + "External id": 29724,"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": 2338707, "tid": 2379456, + "ts": 6197197485698.102, "dur": 30.684, + "args": { + "External id": 29725,"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": 2338707, "tid": 2379456, + "ts": 6197197485736.299, "dur": 69.771, + "args": { + "External id": 29726,"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": 2338707, "tid": 2379456, + "ts": 6197197485738.949, "dur": 66.743, + "args": { + "External id": 29727,"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": 2338707, "tid": 2379456, + "ts": 6197197485743.904, "dur": 7.293, + "args": { + "External id": 29728,"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": 2338707, "tid": 2379456, + "ts": 6197197485752.872, "dur": 51.937, + "args": { + "External id": 29729,"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": 2338707, "tid": 2379456, + "ts": 6197197485964.886, "dur": 629.563, + "args": { + "External id": 29730,"Record function id": 0, "Ev Idx": 2593 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.18)", "pid": 2338707, "tid": 2379456, + "ts": 6197197485983.204, "dur": 599.158, + "args": { + "External id": 29731,"Record function id": 0, "Ev Idx": 2594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197197486045.567, "dur": 5.110, + "args": { + "External id": 29732,"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": 2338707, "tid": 2379456, + "ts": 6197197486103.402, "dur": 36.927, + "args": { + "External id": 29733,"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": 2338707, "tid": 2379456, + "ts": 6197197486109.260, "dur": 2.072, + "args": { + "External id": 29734,"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": 2338707, "tid": 2379456, + "ts": 6197197486113.288, "dur": 1.229, + "args": { + "External id": 29735,"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": 2338707, "tid": 2379456, + "ts": 6197197486116.233, "dur": 2.432, + "args": { + "External id": 29736,"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": 2338707, "tid": 2379456, + "ts": 6197197486119.719, "dur": 0.658, + "args": { + "External id": 29737,"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": 2338707, "tid": 2379456, + "ts": 6197197486123.494, "dur": 0.319, + "args": { + "External id": 29738,"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": 2338707, "tid": 2379456, + "ts": 6197197486125.233, "dur": 0.282, + "args": { + "External id": 29739,"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": 2338707, "tid": 2379456, + "ts": 6197197486126.608, "dur": 0.525, + "args": { + "External id": 29740,"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": 2338707, "tid": 2379456, + "ts": 6197197486130.299, "dur": 0.483, + "args": { + "External id": 29741,"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": 2338707, "tid": 2379456, + "ts": 6197197486132.826, "dur": 0.393, + "args": { + "External id": 29742,"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": 2338707, "tid": 2379456, + "ts": 6197197486151.975, "dur": 46.291, + "args": { + "External id": 29743,"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": 2338707, "tid": 2379456, + "ts": 6197197486230.146, "dur": 118.929, + "args": { + "External id": 29744,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2379456, + "ts": 6197197486241.072, "dur": 4.431, + "args": { + "External id": 29745,"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": 2338707, "tid": 2379456, + "ts": 6197197486250.706, "dur": 12.482, + "args": { + "External id": 29746,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2379456, + "ts": 6197197486254.800, "dur": 7.968, + "args": { + "External id": 29747,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2379456, + "ts": 6197197486258.663, "dur": 2.578, + "args": { + "External id": 29748,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197197486270.396, "dur": 28.991, + "args": { + "External id": 29749,"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": 2338707, "tid": 2379456, + "ts": 6197197486272.747, "dur": 0.297, + "args": { + "External id": 29750,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197197486275.449, "dur": 0.373, + "args": { + "External id": 29751,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2379456, + "ts": 6197197486277.347, "dur": 0.394, + "args": { + "External id": 29752,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2379456, + "ts": 6197197486278.993, "dur": 1.702, + "args": { + "External id": 29753,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2379456, + "ts": 6197197486281.986, "dur": 0.368, + "args": { + "External id": 29754,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2379456, + "ts": 6197197486283.920, "dur": 0.440, + "args": { + "External id": 29755,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2379456, + "ts": 6197197486287.066, "dur": 0.291, + "args": { + "External id": 29756,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2379456, + "ts": 6197197486288.659, "dur": 2.328, + "args": { + "External id": 29757,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2379456, + "ts": 6197197486292.468, "dur": 0.456, + "args": { + "External id": 29758,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2379456, + "ts": 6197197486310.870, "dur": 30.229, + "args": { + "External id": 29759,"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": 2338707, "tid": 2379456, + "ts": 6197197486393.727, "dur": 117.821, + "args": { + "External id": 29760,"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": 2338707, "tid": 2379456, + "ts": 6197197486423.594, "dur": 84.504, + "args": { + "External id": 29761,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197197486432.854, "dur": 70.861, + "args": { + "External id": 29762,"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": 2338707, "tid": 2379456, + "ts": 6197197486531.681, "dur": 1.934, + "args": { + "External id": 29763,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197197486609.128, "dur": 1810.090, + "args": { + "External id": 29764,"Sequence number": 479806, "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": 2338707, "tid": 2379456, "ts": 6197197486609.128, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6197197486737.400, "dur": 110.744, + "args": { + "External id": 29765,"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": 2338707, "tid": 2379456, + "ts": 6197197486891.453, "dur": 41.260, + "args": { + "External id": 29766,"kernel_hash": "cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/u7/cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs.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": 2338707, "tid": 2379456, + "ts": 6197197486951.915, "dur": 53.157, + "args": { + "External id": 29767,"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": 2338707, "tid": 2379456, + "ts": 6197197487014.781, "dur": 31.662, + "args": { + "External id": 29768,"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": 2338707, "tid": 2379456, + "ts": 6197197487088.745, "dur": 40.062, + "args": { + "External id": 29769,"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": 2338707, "tid": 2379456, + "ts": 6197197487138.445, "dur": 28.062, + "args": { + "External id": 29770,"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": 2338707, "tid": 2379456, + "ts": 6197197487176.253, "dur": 29.504, + "args": { + "External id": 29771,"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": 2338707, "tid": 2379456, + "ts": 6197197487233.630, "dur": 23.839, + "args": { + "External id": 29772,"kernel_hash": "cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/wm/cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s.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": 2338707, "tid": 2379456, + "ts": 6197197487279.132, "dur": 29.152, + "args": { + "External id": 29773,"kernel_hash": "cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql", "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/qt/cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql.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": 2338707, "tid": 2379456, + "ts": 6197197487332.204, "dur": 18.163, + "args": { + "External id": 29774,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197197487362.371, "dur": 16.173, + "args": { + "External id": 29775,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197197487388.642, "dur": 38.673, + "args": { + "External id": 29776,"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": 2338707, "tid": 2379456, + "ts": 6197197487430.900, "dur": 32.848, + "args": { + "External id": 29777,"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": 2338707, "tid": 2379456, + "ts": 6197197487492.215, "dur": 272.726, + "args": { + "External id": 29778,"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": 2338707, "tid": 2379456, + "ts": 6197197487571.906, "dur": 6.039, + "args": { + "External id": 29779,"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": 2338707, "tid": 2379456, + "ts": 6197197487579.871, "dur": 2.368, + "args": { + "External id": 29780,"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": 2338707, "tid": 2379456, + "ts": 6197197487583.606, "dur": 5.203, + "args": { + "External id": 29781,"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": 2338707, "tid": 2379456, + "ts": 6197197487590.238, "dur": 1.889, + "args": { + "External id": 29782,"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": 2338707, "tid": 2379456, + "ts": 6197197487638.708, "dur": 4.874, + "args": { + "External id": 29783,"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": 2338707, "tid": 2379456, + "ts": 6197197487640.694, "dur": 2.687, + "args": { + "External id": 29784,"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": 2338707, "tid": 2379456, + "ts": 6197197487647.421, "dur": 33.508, + "args": { + "External id": 29785,"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": 2338707, "tid": 2379456, + "ts": 6197197487653.013, "dur": 2.367, + "args": { + "External id": 29786,"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": 2338707, "tid": 2379456, + "ts": 6197197487682.399, "dur": 1.310, + "args": { + "External id": 29787,"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": 2338707, "tid": 2379456, + "ts": 6197197487683.097, "dur": 0.512, + "args": { + "External id": 29788,"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": 2338707, "tid": 2379456, + "ts": 6197197487684.635, "dur": 34.611, + "args": { + "External id": 29789,"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": 2338707, "tid": 2379456, + "ts": 6197197487687.796, "dur": 0.376, + "args": { + "External id": 29790,"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": 2338707, "tid": 2379456, + "ts": 6197197487806.281, "dur": 28.724, + "args": { + "External id": 29791,"kernel_hash": "cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4", "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/yk/cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4.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": 2338707, "tid": 2379456, + "ts": 6197197487854.962, "dur": 17.902, + "args": { + "External id": 29792,"kernel_hash": "ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg", "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/eu/ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg.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": 2338707, "tid": 2379456, + "ts": 6197197487880.741, "dur": 46.383, + "args": { + "External id": 29793,"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": 2338707, "tid": 2379456, + "ts": 6197197487933.809, "dur": 39.932, + "args": { + "External id": 29794,"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": 2338707, "tid": 2379456, + "ts": 6197197487981.663, "dur": 22.064, + "args": { + "External id": 29795,"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": 2338707, "tid": 2379456, + "ts": 6197197488011.535, "dur": 31.650, + "args": { + "External id": 29796,"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": 2338707, "tid": 2379456, + "ts": 6197197488050.508, "dur": 70.011, + "args": { + "External id": 29797,"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": 2338707, "tid": 2379456, + "ts": 6197197488131.587, "dur": 31.445, + "args": { + "External id": 29798,"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": 2338707, "tid": 2379456, + "ts": 6197197488186.628, "dur": 43.076, + "args": { + "External id": 29799,"kernel_hash": "c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/6w/c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7.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": 2338707, "tid": 2379456, + "ts": 6197197488254.781, "dur": 26.158, + "args": { + "External id": 29800,"kernel_hash": "ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx", "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/kj/ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx.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": 2338707, "tid": 2379456, + "ts": 6197197488297.255, "dur": 19.475, + "args": { + "External id": 29801,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197197488337.178, "dur": 15.185, + "args": { + "External id": 29802,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197197488368.162, "dur": 20.127, + "args": { + "External id": 29803,"kernel_hash": "cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/eb/cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b.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": 2338707, "tid": 2379456, + "ts": 6197197488464.416, "dur": 15.080, + "args": { + "External id": 29804,"Record function id": 0, "Ev Idx": 2667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197488467.978, "dur": 10.657, + "args": { + "External id": 29805,"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": 2338707, "tid": 2379456, + "ts": 6197197488472.189, "dur": 5.634, + "args": { + "External id": 29806,"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": 2338707, "tid": 2379456, + "ts": 6197197488473.810, "dur": 3.922, + "args": { + "External id": 29807,"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": 2338707, "tid": 2379456, + "ts": 6197197488483.399, "dur": 4.763, + "args": { + "External id": 29808,"Record function id": 0, "Ev Idx": 2671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197488484.923, "dur": 2.729, + "args": { + "External id": 29809,"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": 2338707, "tid": 2379456, + "ts": 6197197488485.748, "dur": 1.455, + "args": { + "External id": 29810,"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": 2338707, "tid": 2379456, + "ts": 6197197488486.472, "dur": 0.620, + "args": { + "External id": 29811,"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": 2338707, "tid": 2379456, + "ts": 6197197488491.545, "dur": 4.232, + "args": { + "External id": 29812,"Record function id": 0, "Ev Idx": 2675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197488492.706, "dur": 2.629, + "args": { + "External id": 29813,"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": 2338707, "tid": 2379456, + "ts": 6197197488493.393, "dur": 1.524, + "args": { + "External id": 29814,"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": 2338707, "tid": 2379456, + "ts": 6197197488494.258, "dur": 0.550, + "args": { + "External id": 29815,"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": 2338707, "tid": 2379456, + "ts": 6197197488498.959, "dur": 4.040, + "args": { + "External id": 29816,"Record function id": 0, "Ev Idx": 2679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197488500.363, "dur": 2.203, + "args": { + "External id": 29817,"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": 2338707, "tid": 2379456, + "ts": 6197197488501.245, "dur": 0.932, + "args": { + "External id": 29818,"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": 2338707, "tid": 2379456, + "ts": 6197197488501.557, "dur": 0.537, + "args": { + "External id": 29819,"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": 2338707, "tid": 2379456, + "ts": 6197197488506.359, "dur": 4.220, + "args": { + "External id": 29820,"Record function id": 0, "Ev Idx": 2683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197488507.873, "dur": 2.284, + "args": { + "External id": 29821,"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": 2338707, "tid": 2379456, + "ts": 6197197488508.359, "dur": 1.262, + "args": { + "External id": 29822,"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": 2338707, "tid": 2379456, + "ts": 6197197488508.856, "dur": 0.703, + "args": { + "External id": 29823,"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": 2338707, "tid": 2379456, + "ts": 6197197488513.810, "dur": 6.482, + "args": { + "External id": 29824,"Record function id": 0, "Ev Idx": 2687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197488515.110, "dur": 4.778, + "args": { + "External id": 29825,"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": 2338707, "tid": 2379456, + "ts": 6197197488515.807, "dur": 3.650, + "args": { + "External id": 29826,"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": 2338707, "tid": 2379456, + "ts": 6197197488516.254, "dur": 3.143, + "args": { + "External id": 29827,"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": 2338707, "tid": 2379456, + "ts": 6197197488523.588, "dur": 4.808, + "args": { + "External id": 29828,"Record function id": 0, "Ev Idx": 2691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197488525.108, "dur": 2.859, + "args": { + "External id": 29829,"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": 2338707, "tid": 2379456, + "ts": 6197197488525.722, "dur": 1.542, + "args": { + "External id": 29830,"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": 2338707, "tid": 2379456, + "ts": 6197197488526.230, "dur": 0.973, + "args": { + "External id": 29831,"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": 2338707, "tid": 2379456, + "ts": 6197197488531.517, "dur": 5.792, + "args": { + "External id": 29832,"Record function id": 0, "Ev Idx": 2695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197488532.686, "dur": 4.215, + "args": { + "External id": 29833,"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": 2338707, "tid": 2379456, + "ts": 6197197488533.345, "dur": 3.159, + "args": { + "External id": 29834,"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": 2338707, "tid": 2379456, + "ts": 6197197488535.739, "dur": 0.669, + "args": { + "External id": 29835,"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": 2338707, "tid": 2379456, + "ts": 6197197488540.359, "dur": 4.826, + "args": { + "External id": 29836,"Record function id": 0, "Ev Idx": 2699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197488541.855, "dur": 2.919, + "args": { + "External id": 29837,"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": 2338707, "tid": 2379456, + "ts": 6197197488542.571, "dur": 1.551, + "args": { + "External id": 29838,"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": 2338707, "tid": 2379456, + "ts": 6197197488543.385, "dur": 0.675, + "args": { + "External id": 29839,"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": 2338707, "tid": 2379456, + "ts": 6197197488549.310, "dur": 76596.331, + "args": { + "External id": 29840,"Record function id": 0, "Sequence number": 479805, "Fwd thread id": 1, "Ev Idx": 2703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197197488551.191, "dur": 76584.398, + "args": { + "External id": 29841,"Sequence number": 479805, "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": 2338707, "tid": 2379456, "ts": 6197197488551.191, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.19)", "pid": 2338707, "tid": 2379456, + "ts": 6197197488580.613, "dur": 39.324, + "args": { + "External id": 29842,"Record function id": 0, "Ev Idx": 2705 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.19)", "pid": 2338707, "tid": 2379456, + "ts": 6197197488627.902, "dur": 63.761, + "args": { + "External id": 29843,"Record function id": 0, "Ev Idx": 2706 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.19)", "pid": 2338707, "tid": 2379456, + "ts": 6197197488697.989, "dur": 76428.856, + "args": { + "External id": 29844,"Record function id": 0, "Ev Idx": 2707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197197488807.205, "dur": 7.608, + "args": { + "External id": 29845,"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": 2338707, "tid": 2379456, + "ts": 6197197488825.458, "dur": 4.785, + "args": { + "External id": 29846,"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": 2338707, "tid": 2379456, + "ts": 6197197488845.521, "dur": 75407.088, + "args": { + "External id": 29847,"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": 2338707, "tid": 2379456, + "ts": 6197197488860.346, "dur": 75379.370, + "args": { + "External id": 29848,"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": 2338707, "tid": 2379456, + "ts": 6197197488957.407, "dur": 18.755, + "args": { + "External id": 29849,"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": 2338707, "tid": 2379456, + "ts": 6197197488995.979, "dur": 75196.150, + "args": { + "External id": 29850,"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": 2338707, "tid": 2379456, + "ts": 6197197489001.389, "dur": 75189.785, + "args": { + "External id": 29851,"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": 2338707, "tid": 2379456, + "ts": 6197197489005.772, "dur": 11.720, + "args": { + "External id": 29852,"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": 2338707, "tid": 2379456, + "ts": 6197197489019.363, "dur": 75166.631, + "args": { + "External id": 29853,"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": 2338707, "tid": 2379456, + "ts": 6197197564356.642, "dur": 12.554, + "args": { + "External id": 29854,"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": 2338707, "tid": 2379456, + "ts": 6197197564360.324, "dur": 8.454, + "args": { + "External id": 29855,"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": 2338707, "tid": 2379456, + "ts": 6197197564397.048, "dur": 388.815, + "args": { + "External id": 29856,"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": 2338707, "tid": 2379456, + "ts": 6197197564430.210, "dur": 349.956, + "args": { + "External id": 29857,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197197564442.591, "dur": 332.076, + "args": { + "External id": 29858,"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": 2338707, "tid": 2379456, + "ts": 6197197564810.568, "dur": 2.249, + "args": { + "External id": 29859,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2379456, + "ts": 6197197564873.857, "dur": 6.522, + "args": { + "External id": 29860,"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": 2338707, "tid": 2379456, + "ts": 6197197564927.259, "dur": 1.838, + "args": { + "External id": 29861,"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": 2338707, "tid": 2379456, + "ts": 6197197564944.334, "dur": 1.312, + "args": { + "External id": 29862,"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": 2338707, "tid": 2379456, + "ts": 6197197564957.698, "dur": 0.920, + "args": { + "External id": 29863,"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": 2338707, "tid": 2379456, + "ts": 6197197564970.247, "dur": 0.849, + "args": { + "External id": 29864,"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": 2338707, "tid": 2379456, + "ts": 6197197564983.353, "dur": 0.800, + "args": { + "External id": 29865,"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": 2338707, "tid": 2379456, + "ts": 6197197564994.855, "dur": 1.036, + "args": { + "External id": 29866,"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": 2338707, "tid": 2379456, + "ts": 6197197565008.070, "dur": 3.321, + "args": { + "External id": 29867,"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": 2338707, "tid": 2379456, + "ts": 6197197565026.931, "dur": 0.879, + "args": { + "External id": 29868,"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": 2338707, "tid": 2379456, + "ts": 6197197565162.186, "dur": 2886.248, + "args": { + "External id": 29869,"Record function id": 0, "Ev Idx": 2732 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.18)", "pid": 2338707, "tid": 2379456, + "ts": 6197197565182.884, "dur": 1106.031, + "args": { + "External id": 29870,"Record function id": 0, "Ev Idx": 2733 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.18)", "pid": 2338707, "tid": 2379456, + "ts": 6197197565197.715, "dur": 340.554, + "args": { + "External id": 29871,"Record function id": 0, "Ev Idx": 2734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6197197565290.790, "dur": 5.132, + "args": { + "External id": 29872,"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": 2338707, "tid": 2379456, + "ts": 6197197565299.545, "dur": 0.893, + "args": { + "External id": 29873,"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": 2338707, "tid": 2379456, + "ts": 6197197565302.194, "dur": 1.177, + "args": { + "External id": 29874,"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": 2338707, "tid": 2379456, + "ts": 6197197565305.258, "dur": 1.039, + "args": { + "External id": 29875,"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": 2338707, "tid": 2379456, + "ts": 6197197565307.650, "dur": 1.103, + "args": { + "External id": 29876,"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": 2338707, "tid": 2379456, + "ts": 6197197565312.309, "dur": 1.066, + "args": { + "External id": 29877,"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": 2338707, "tid": 2379456, + "ts": 6197197565314.855, "dur": 2.611, + "args": { + "External id": 29878,"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": 2338707, "tid": 2379456, + "ts": 6197197565318.877, "dur": 2.725, + "args": { + "External id": 29879,"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": 2338707, "tid": 2379456, + "ts": 6197197565323.229, "dur": 0.875, + "args": { + "External id": 29880,"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": 2338707, "tid": 2379456, + "ts": 6197197565327.370, "dur": 1.057, + "args": { + "External id": 29881,"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": 2338707, "tid": 2379456, + "ts": 6197197565345.516, "dur": 162.170, + "args": { + "External id": 29882,"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": 2338707, "tid": 2379456, + "ts": 6197197565361.093, "dur": 141.736, + "args": { + "External id": 29883,"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": 2338707, "tid": 2379456, + "ts": 6197197565387.251, "dur": 16.025, + "args": { + "External id": 29884,"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": 2338707, "tid": 2379456, + "ts": 6197197565407.072, "dur": 66.485, + "args": { + "External id": 29885,"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": 2338707, "tid": 2379456, + "ts": 6197197565409.860, "dur": 63.387, + "args": { + "External id": 29886,"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": 2338707, "tid": 2379456, + "ts": 6197197565413.633, "dur": 6.390, + "args": { + "External id": 29887,"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": 2338707, "tid": 2379456, + "ts": 6197197565421.476, "dur": 50.919, + "args": { + "External id": 29888,"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": 2338707, "tid": 2379456, + "ts": 6197197565626.935, "dur": 654.240, + "args": { + "External id": 29889,"Record function id": 0, "Ev Idx": 2752 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.17)", "pid": 2338707, "tid": 2379456, + "ts": 6197197565643.431, "dur": 625.545, + "args": { + "External id": 29890,"Record function id": 0, "Ev Idx": 2753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197197565721.029, "dur": 6.974, + "args": { + "External id": 29891,"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": 2338707, "tid": 2379456, + "ts": 6197197565744.753, "dur": 32.646, + "args": { + "External id": 29892,"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": 2338707, "tid": 2379456, + "ts": 6197197565749.901, "dur": 1.985, + "args": { + "External id": 29893,"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": 2338707, "tid": 2379456, + "ts": 6197197565753.430, "dur": 1.746, + "args": { + "External id": 29894,"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": 2338707, "tid": 2379456, + "ts": 6197197565756.138, "dur": 3.051, + "args": { + "External id": 29895,"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": 2338707, "tid": 2379456, + "ts": 6197197565760.195, "dur": 0.352, + "args": { + "External id": 29896,"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": 2338707, "tid": 2379456, + "ts": 6197197565763.498, "dur": 0.404, + "args": { + "External id": 29897,"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": 2338707, "tid": 2379456, + "ts": 6197197565765.000, "dur": 0.485, + "args": { + "External id": 29898,"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": 2338707, "tid": 2379456, + "ts": 6197197565766.569, "dur": 0.364, + "args": { + "External id": 29899,"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": 2338707, "tid": 2379456, + "ts": 6197197565769.176, "dur": 0.366, + "args": { + "External id": 29900,"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": 2338707, "tid": 2379456, + "ts": 6197197565770.318, "dur": 0.507, + "args": { + "External id": 29901,"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": 2338707, "tid": 2379456, + "ts": 6197197565791.237, "dur": 43.996, + "args": { + "External id": 29902,"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": 2338707, "tid": 2379456, + "ts": 6197197565866.663, "dur": 118.592, + "args": { + "External id": 29903,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2379456, + "ts": 6197197565876.684, "dur": 4.304, + "args": { + "External id": 29904,"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": 2338707, "tid": 2379456, + "ts": 6197197565886.091, "dur": 14.323, + "args": { + "External id": 29905,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2379456, + "ts": 6197197565893.106, "dur": 6.873, + "args": { + "External id": 29906,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2379456, + "ts": 6197197565896.418, "dur": 2.221, + "args": { + "External id": 29907,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197197565907.473, "dur": 27.290, + "args": { + "External id": 29908,"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": 2338707, "tid": 2379456, + "ts": 6197197565909.535, "dur": 0.390, + "args": { + "External id": 29909,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197197565910.921, "dur": 1.813, + "args": { + "External id": 29910,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2379456, + "ts": 6197197565914.001, "dur": 0.340, + "args": { + "External id": 29911,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2379456, + "ts": 6197197565915.513, "dur": 0.315, + "args": { + "External id": 29912,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2379456, + "ts": 6197197565918.821, "dur": 0.359, + "args": { + "External id": 29913,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2379456, + "ts": 6197197565920.332, "dur": 0.347, + "args": { + "External id": 29914,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2379456, + "ts": 6197197565921.574, "dur": 0.299, + "args": { + "External id": 29915,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2379456, + "ts": 6197197565924.359, "dur": 2.412, + "args": { + "External id": 29916,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2379456, + "ts": 6197197565927.738, "dur": 0.449, + "args": { + "External id": 29917,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2379456, + "ts": 6197197565947.360, "dur": 30.111, + "args": { + "External id": 29918,"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": 2338707, "tid": 2379456, + "ts": 6197197566029.916, "dur": 164.986, + "args": { + "External id": 29919,"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": 2338707, "tid": 2379456, + "ts": 6197197566095.575, "dur": 95.180, + "args": { + "External id": 29920,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197197566106.920, "dur": 78.860, + "args": { + "External id": 29921,"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": 2338707, "tid": 2379456, + "ts": 6197197566213.546, "dur": 1.615, + "args": { + "External id": 29922,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197197566297.115, "dur": 1729.088, + "args": { + "External id": 29923,"Sequence number": 479804, "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": 2338707, "tid": 2379456, "ts": 6197197566297.115, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6197197566405.424, "dur": 108.180, + "args": { + "External id": 29924,"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": 2338707, "tid": 2379456, + "ts": 6197197566556.045, "dur": 39.025, + "args": { + "External id": 29925,"kernel_hash": "cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/u7/cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs.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": 2338707, "tid": 2379456, + "ts": 6197197566614.716, "dur": 51.291, + "args": { + "External id": 29926,"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": 2338707, "tid": 2379456, + "ts": 6197197566676.371, "dur": 49.679, + "args": { + "External id": 29927,"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": 2338707, "tid": 2379456, + "ts": 6197197566736.584, "dur": 36.780, + "args": { + "External id": 29928,"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": 2338707, "tid": 2379456, + "ts": 6197197566780.494, "dur": 28.682, + "args": { + "External id": 29929,"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": 2338707, "tid": 2379456, + "ts": 6197197566818.488, "dur": 28.803, + "args": { + "External id": 29930,"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": 2338707, "tid": 2379456, + "ts": 6197197566873.366, "dur": 24.772, + "args": { + "External id": 29931,"kernel_hash": "cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/wm/cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s.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": 2338707, "tid": 2379456, + "ts": 6197197566918.422, "dur": 28.002, + "args": { + "External id": 29932,"kernel_hash": "cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql", "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/qt/cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql.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": 2338707, "tid": 2379456, + "ts": 6197197566968.536, "dur": 19.613, + "args": { + "External id": 29933,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197197567002.870, "dur": 14.421, + "args": { + "External id": 29934,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197197567028.010, "dur": 73.333, + "args": { + "External id": 29935,"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": 2338707, "tid": 2379456, + "ts": 6197197567107.380, "dur": 37.148, + "args": { + "External id": 29936,"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": 2338707, "tid": 2379456, + "ts": 6197197567174.826, "dur": 244.464, + "args": { + "External id": 29937,"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": 2338707, "tid": 2379456, + "ts": 6197197567253.470, "dur": 7.052, + "args": { + "External id": 29938,"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": 2338707, "tid": 2379456, + "ts": 6197197567262.840, "dur": 5.096, + "args": { + "External id": 29939,"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": 2338707, "tid": 2379456, + "ts": 6197197567269.069, "dur": 3.718, + "args": { + "External id": 29940,"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": 2338707, "tid": 2379456, + "ts": 6197197567273.839, "dur": 1.703, + "args": { + "External id": 29941,"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": 2338707, "tid": 2379456, + "ts": 6197197567317.740, "dur": 4.586, + "args": { + "External id": 29942,"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": 2338707, "tid": 2379456, + "ts": 6197197567319.399, "dur": 2.742, + "args": { + "External id": 29943,"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": 2338707, "tid": 2379456, + "ts": 6197197567324.320, "dur": 29.972, + "args": { + "External id": 29944,"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": 2338707, "tid": 2379456, + "ts": 6197197567329.474, "dur": 1.722, + "args": { + "External id": 29945,"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": 2338707, "tid": 2379456, + "ts": 6197197567355.946, "dur": 1.673, + "args": { + "External id": 29946,"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": 2338707, "tid": 2379456, + "ts": 6197197567356.919, "dur": 0.615, + "args": { + "External id": 29947,"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": 2338707, "tid": 2379456, + "ts": 6197197567358.888, "dur": 15.552, + "args": { + "External id": 29948,"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": 2338707, "tid": 2379456, + "ts": 6197197567361.380, "dur": 1.629, + "args": { + "External id": 29949,"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": 2338707, "tid": 2379456, + "ts": 6197197567458.861, "dur": 27.640, + "args": { + "External id": 29950,"kernel_hash": "cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4", "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/yk/cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4.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": 2338707, "tid": 2379456, + "ts": 6197197567504.204, "dur": 16.344, + "args": { + "External id": 29951,"kernel_hash": "ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg", "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/eu/ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg.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": 2338707, "tid": 2379456, + "ts": 6197197567527.646, "dur": 39.893, + "args": { + "External id": 29952,"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": 2338707, "tid": 2379456, + "ts": 6197197567573.852, "dur": 37.216, + "args": { + "External id": 29953,"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": 2338707, "tid": 2379456, + "ts": 6197197567619.266, "dur": 21.333, + "args": { + "External id": 29954,"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": 2338707, "tid": 2379456, + "ts": 6197197567647.828, "dur": 31.494, + "args": { + "External id": 29955,"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": 2338707, "tid": 2379456, + "ts": 6197197567686.030, "dur": 44.799, + "args": { + "External id": 29956,"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": 2338707, "tid": 2379456, + "ts": 6197197567741.081, "dur": 33.753, + "args": { + "External id": 29957,"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": 2338707, "tid": 2379456, + "ts": 6197197567798.316, "dur": 24.580, + "args": { + "External id": 29958,"kernel_hash": "c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/6w/c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7.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": 2338707, "tid": 2379456, + "ts": 6197197567844.062, "dur": 24.586, + "args": { + "External id": 29959,"kernel_hash": "ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx", "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/kj/ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx.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": 2338707, "tid": 2379456, + "ts": 6197197567882.367, "dur": 18.968, + "args": { + "External id": 29960,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197197567918.170, "dur": 35.167, + "args": { + "External id": 29961,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197197567974.331, "dur": 20.232, + "args": { + "External id": 29962,"kernel_hash": "cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/eb/cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b.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": 2338707, "tid": 2379456, + "ts": 6197197568107.680, "dur": 19.932, + "args": { + "External id": 29963,"Record function id": 0, "Ev Idx": 2826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197568111.551, "dur": 14.887, + "args": { + "External id": 29964,"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": 2338707, "tid": 2379456, + "ts": 6197197568119.396, "dur": 5.780, + "args": { + "External id": 29965,"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": 2338707, "tid": 2379456, + "ts": 6197197568121.007, "dur": 3.933, + "args": { + "External id": 29966,"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": 2338707, "tid": 2379456, + "ts": 6197197568131.495, "dur": 4.627, + "args": { + "External id": 29967,"Record function id": 0, "Ev Idx": 2830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197568132.925, "dur": 2.720, + "args": { + "External id": 29968,"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": 2338707, "tid": 2379456, + "ts": 6197197568133.782, "dur": 1.109, + "args": { + "External id": 29969,"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": 2338707, "tid": 2379456, + "ts": 6197197568134.127, "dur": 0.694, + "args": { + "External id": 29970,"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": 2338707, "tid": 2379456, + "ts": 6197197568139.666, "dur": 4.349, + "args": { + "External id": 29971,"Record function id": 0, "Ev Idx": 2834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197568140.743, "dur": 2.832, + "args": { + "External id": 29972,"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": 2338707, "tid": 2379456, + "ts": 6197197568141.390, "dur": 1.542, + "args": { + "External id": 29973,"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": 2338707, "tid": 2379456, + "ts": 6197197568141.957, "dur": 0.909, + "args": { + "External id": 29974,"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": 2338707, "tid": 2379456, + "ts": 6197197568147.240, "dur": 3.701, + "args": { + "External id": 29975,"Record function id": 0, "Ev Idx": 2838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197568148.330, "dur": 2.173, + "args": { + "External id": 29976,"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": 2338707, "tid": 2379456, + "ts": 6197197568148.868, "dur": 1.230, + "args": { + "External id": 29977,"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": 2338707, "tid": 2379456, + "ts": 6197197568149.471, "dur": 0.561, + "args": { + "External id": 29978,"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": 2338707, "tid": 2379456, + "ts": 6197197568154.070, "dur": 3.755, + "args": { + "External id": 29979,"Record function id": 0, "Ev Idx": 2842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197568155.072, "dur": 2.292, + "args": { + "External id": 29980,"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": 2338707, "tid": 2379456, + "ts": 6197197568155.737, "dur": 1.031, + "args": { + "External id": 29981,"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": 2338707, "tid": 2379456, + "ts": 6197197568156.026, "dur": 0.679, + "args": { + "External id": 29982,"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": 2338707, "tid": 2379456, + "ts": 6197197568161.261, "dur": 7.800, + "args": { + "External id": 29983,"Record function id": 0, "Ev Idx": 2846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197568162.424, "dur": 6.181, + "args": { + "External id": 29984,"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": 2338707, "tid": 2379456, + "ts": 6197197568162.948, "dur": 5.040, + "args": { + "External id": 29985,"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": 2338707, "tid": 2379456, + "ts": 6197197568165.309, "dur": 2.587, + "args": { + "External id": 29986,"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": 2338707, "tid": 2379456, + "ts": 6197197568175.420, "dur": 3.637, + "args": { + "External id": 29987,"Record function id": 0, "Ev Idx": 2850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197568176.537, "dur": 2.078, + "args": { + "External id": 29988,"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": 2338707, "tid": 2379456, + "ts": 6197197568177.061, "dur": 1.142, + "args": { + "External id": 29989,"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": 2338707, "tid": 2379456, + "ts": 6197197568177.468, "dur": 0.671, + "args": { + "External id": 29990,"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": 2338707, "tid": 2379456, + "ts": 6197197568182.086, "dur": 3.993, + "args": { + "External id": 29991,"Record function id": 0, "Ev Idx": 2854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197568183.084, "dur": 2.568, + "args": { + "External id": 29992,"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": 2338707, "tid": 2379456, + "ts": 6197197568183.715, "dur": 1.414, + "args": { + "External id": 29993,"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": 2338707, "tid": 2379456, + "ts": 6197197568184.253, "dur": 0.811, + "args": { + "External id": 29994,"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": 2338707, "tid": 2379456, + "ts": 6197197568189.571, "dur": 3.772, + "args": { + "External id": 29995,"Record function id": 0, "Ev Idx": 2858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197568190.913, "dur": 1.941, + "args": { + "External id": 29996,"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": 2338707, "tid": 2379456, + "ts": 6197197568191.381, "dur": 1.037, + "args": { + "External id": 29997,"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": 2338707, "tid": 2379456, + "ts": 6197197568191.775, "dur": 0.576, + "args": { + "External id": 29998,"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": 2338707, "tid": 2379456, + "ts": 6197197568197.227, "dur": 68967.564, + "args": { + "External id": 29999,"Record function id": 0, "Sequence number": 479803, "Fwd thread id": 1, "Ev Idx": 2862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197197568198.809, "dur": 68955.849, + "args": { + "External id": 30000,"Sequence number": 479803, "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": 2338707, "tid": 2379456, "ts": 6197197568198.809, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.18)", "pid": 2338707, "tid": 2379456, + "ts": 6197197568229.014, "dur": 40.052, + "args": { + "External id": 30001,"Record function id": 0, "Ev Idx": 2864 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.18)", "pid": 2338707, "tid": 2379456, + "ts": 6197197568276.605, "dur": 65.294, + "args": { + "External id": 30002,"Record function id": 0, "Ev Idx": 2865 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.18)", "pid": 2338707, "tid": 2379456, + "ts": 6197197568347.539, "dur": 68798.399, + "args": { + "External id": 30003,"Record function id": 0, "Ev Idx": 2866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197197568435.848, "dur": 7.528, + "args": { + "External id": 30004,"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": 2338707, "tid": 2379456, + "ts": 6197197568453.076, "dur": 4.878, + "args": { + "External id": 30005,"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": 2338707, "tid": 2379456, + "ts": 6197197568474.802, "dur": 67769.182, + "args": { + "External id": 30006,"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": 2338707, "tid": 2379456, + "ts": 6197197568488.731, "dur": 67742.084, + "args": { + "External id": 30007,"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": 2338707, "tid": 2379456, + "ts": 6197197568580.141, "dur": 18.204, + "args": { + "External id": 30008,"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": 2338707, "tid": 2379456, + "ts": 6197197568618.791, "dur": 67565.949, + "args": { + "External id": 30009,"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": 2338707, "tid": 2379456, + "ts": 6197197568622.815, "dur": 67560.984, + "args": { + "External id": 30010,"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": 2338707, "tid": 2379456, + "ts": 6197197568627.098, "dur": 9.380, + "args": { + "External id": 30011,"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": 2338707, "tid": 2379456, + "ts": 6197197568638.527, "dur": 67540.279, + "args": { + "External id": 30012,"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": 2338707, "tid": 2379456, + "ts": 6197197636349.776, "dur": 12.189, + "args": { + "External id": 30013,"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": 2338707, "tid": 2379456, + "ts": 6197197636353.224, "dur": 8.274, + "args": { + "External id": 30014,"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": 2338707, "tid": 2379456, + "ts": 6197197636389.869, "dur": 421.638, + "args": { + "External id": 30015,"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": 2338707, "tid": 2379456, + "ts": 6197197636421.287, "dur": 384.471, + "args": { + "External id": 30016,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197197636433.624, "dur": 365.679, + "args": { + "External id": 30017,"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": 2338707, "tid": 2379456, + "ts": 6197197636836.911, "dur": 2.208, + "args": { + "External id": 30018,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2379456, + "ts": 6197197636900.540, "dur": 6.481, + "args": { + "External id": 30019,"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": 2338707, "tid": 2379456, + "ts": 6197197636953.596, "dur": 1.276, + "args": { + "External id": 30020,"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": 2338707, "tid": 2379456, + "ts": 6197197636970.227, "dur": 1.423, + "args": { + "External id": 30021,"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": 2338707, "tid": 2379456, + "ts": 6197197636982.605, "dur": 1.221, + "args": { + "External id": 30022,"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": 2338707, "tid": 2379456, + "ts": 6197197636997.023, "dur": 0.865, + "args": { + "External id": 30023,"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": 2338707, "tid": 2379456, + "ts": 6197197637011.233, "dur": 0.868, + "args": { + "External id": 30024,"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": 2338707, "tid": 2379456, + "ts": 6197197637022.065, "dur": 1.572, + "args": { + "External id": 30025,"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": 2338707, "tid": 2379456, + "ts": 6197197637032.660, "dur": 3.180, + "args": { + "External id": 30026,"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": 2338707, "tid": 2379456, + "ts": 6197197637044.247, "dur": 1.172, + "args": { + "External id": 30027,"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": 2338707, "tid": 2379456, + "ts": 6197197637181.054, "dur": 2927.918, + "args": { + "External id": 30028,"Record function id": 0, "Ev Idx": 2891 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.17)", "pid": 2338707, "tid": 2379456, + "ts": 6197197637200.378, "dur": 1087.079, + "args": { + "External id": 30029,"Record function id": 0, "Ev Idx": 2892 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.17)", "pid": 2338707, "tid": 2379456, + "ts": 6197197637213.683, "dur": 341.475, + "args": { + "External id": 30030,"Record function id": 0, "Ev Idx": 2893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6197197637304.434, "dur": 4.705, + "args": { + "External id": 30031,"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": 2338707, "tid": 2379456, + "ts": 6197197637312.489, "dur": 1.183, + "args": { + "External id": 30032,"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": 2338707, "tid": 2379456, + "ts": 6197197637315.265, "dur": 1.326, + "args": { + "External id": 30033,"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": 2338707, "tid": 2379456, + "ts": 6197197637318.294, "dur": 1.369, + "args": { + "External id": 30034,"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": 2338707, "tid": 2379456, + "ts": 6197197637322.994, "dur": 0.890, + "args": { + "External id": 30035,"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": 2338707, "tid": 2379456, + "ts": 6197197637325.184, "dur": 1.130, + "args": { + "External id": 30036,"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": 2338707, "tid": 2379456, + "ts": 6197197637327.938, "dur": 2.754, + "args": { + "External id": 30037,"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": 2338707, "tid": 2379456, + "ts": 6197197637332.032, "dur": 3.182, + "args": { + "External id": 30038,"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": 2338707, "tid": 2379456, + "ts": 6197197637338.639, "dur": 0.691, + "args": { + "External id": 30039,"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": 2338707, "tid": 2379456, + "ts": 6197197637340.806, "dur": 1.004, + "args": { + "External id": 30040,"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": 2338707, "tid": 2379456, + "ts": 6197197637364.505, "dur": 162.421, + "args": { + "External id": 30041,"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": 2338707, "tid": 2379456, + "ts": 6197197637380.114, "dur": 142.140, + "args": { + "External id": 30042,"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": 2338707, "tid": 2379456, + "ts": 6197197637405.624, "dur": 15.270, + "args": { + "External id": 30043,"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": 2338707, "tid": 2379456, + "ts": 6197197637424.439, "dur": 68.047, + "args": { + "External id": 30044,"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": 2338707, "tid": 2379456, + "ts": 6197197637429.091, "dur": 62.896, + "args": { + "External id": 30045,"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": 2338707, "tid": 2379456, + "ts": 6197197637433.286, "dur": 5.266, + "args": { + "External id": 30046,"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": 2338707, "tid": 2379456, + "ts": 6197197637440.232, "dur": 51.109, + "args": { + "External id": 30047,"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": 2338707, "tid": 2379456, + "ts": 6197197637638.595, "dur": 640.453, + "args": { + "External id": 30048,"Record function id": 0, "Ev Idx": 2911 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.16)", "pid": 2338707, "tid": 2379456, + "ts": 6197197637655.123, "dur": 611.659, + "args": { + "External id": 30049,"Record function id": 0, "Ev Idx": 2912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197197637732.801, "dur": 6.389, + "args": { + "External id": 30050,"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": 2338707, "tid": 2379456, + "ts": 6197197637755.150, "dur": 33.160, + "args": { + "External id": 30051,"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": 2338707, "tid": 2379456, + "ts": 6197197637760.318, "dur": 1.875, + "args": { + "External id": 30052,"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": 2338707, "tid": 2379456, + "ts": 6197197637764.332, "dur": 1.764, + "args": { + "External id": 30053,"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": 2338707, "tid": 2379456, + "ts": 6197197637767.499, "dur": 2.810, + "args": { + "External id": 30054,"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": 2338707, "tid": 2379456, + "ts": 6197197637771.612, "dur": 0.412, + "args": { + "External id": 30055,"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": 2338707, "tid": 2379456, + "ts": 6197197637774.049, "dur": 0.328, + "args": { + "External id": 30056,"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": 2338707, "tid": 2379456, + "ts": 6197197637775.423, "dur": 0.369, + "args": { + "External id": 30057,"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": 2338707, "tid": 2379456, + "ts": 6197197637776.895, "dur": 0.242, + "args": { + "External id": 30058,"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": 2338707, "tid": 2379456, + "ts": 6197197637778.710, "dur": 0.369, + "args": { + "External id": 30059,"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": 2338707, "tid": 2379456, + "ts": 6197197637779.793, "dur": 0.374, + "args": { + "External id": 30060,"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": 2338707, "tid": 2379456, + "ts": 6197197637798.850, "dur": 43.682, + "args": { + "External id": 30061,"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": 2338707, "tid": 2379456, + "ts": 6197197637872.002, "dur": 115.296, + "args": { + "External id": 30062,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2379456, + "ts": 6197197637881.299, "dur": 3.433, + "args": { + "External id": 30063,"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": 2338707, "tid": 2379456, + "ts": 6197197637890.332, "dur": 14.891, + "args": { + "External id": 30064,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2379456, + "ts": 6197197637897.417, "dur": 7.368, + "args": { + "External id": 30065,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2379456, + "ts": 6197197637900.586, "dur": 2.926, + "args": { + "External id": 30066,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197197637911.696, "dur": 26.294, + "args": { + "External id": 30067,"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": 2338707, "tid": 2379456, + "ts": 6197197637913.923, "dur": 0.775, + "args": { + "External id": 30068,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197197637916.473, "dur": 0.523, + "args": { + "External id": 30069,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2379456, + "ts": 6197197637918.099, "dur": 0.651, + "args": { + "External id": 30070,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2379456, + "ts": 6197197637919.797, "dur": 0.920, + "args": { + "External id": 30071,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2379456, + "ts": 6197197637921.742, "dur": 0.295, + "args": { + "External id": 30072,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2379456, + "ts": 6197197637923.162, "dur": 0.321, + "args": { + "External id": 30073,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2379456, + "ts": 6197197637925.712, "dur": 0.351, + "args": { + "External id": 30074,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2379456, + "ts": 6197197637926.983, "dur": 2.669, + "args": { + "External id": 30075,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2379456, + "ts": 6197197637930.510, "dur": 0.273, + "args": { + "External id": 30076,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2379456, + "ts": 6197197637947.579, "dur": 32.097, + "args": { + "External id": 30077,"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": 2338707, "tid": 2379456, + "ts": 6197197638030.583, "dur": 159.432, + "args": { + "External id": 30078,"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": 2338707, "tid": 2379456, + "ts": 6197197638093.896, "dur": 92.154, + "args": { + "External id": 30079,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197197638104.382, "dur": 77.511, + "args": { + "External id": 30080,"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": 2338707, "tid": 2379456, + "ts": 6197197638211.126, "dur": 1.898, + "args": { + "External id": 30081,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197197638294.532, "dur": 1751.186, + "args": { + "External id": 30082,"Sequence number": 479802, "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": 2338707, "tid": 2379456, "ts": 6197197638294.532, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6197197638403.736, "dur": 107.829, + "args": { + "External id": 30083,"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": 2338707, "tid": 2379456, + "ts": 6197197638554.279, "dur": 41.570, + "args": { + "External id": 30084,"kernel_hash": "cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/u7/cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs.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": 2338707, "tid": 2379456, + "ts": 6197197638615.138, "dur": 53.053, + "args": { + "External id": 30085,"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": 2338707, "tid": 2379456, + "ts": 6197197638677.935, "dur": 51.477, + "args": { + "External id": 30086,"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": 2338707, "tid": 2379456, + "ts": 6197197638739.489, "dur": 36.566, + "args": { + "External id": 30087,"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": 2338707, "tid": 2379456, + "ts": 6197197638782.331, "dur": 28.366, + "args": { + "External id": 30088,"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": 2338707, "tid": 2379456, + "ts": 6197197638820.538, "dur": 29.212, + "args": { + "External id": 30089,"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": 2338707, "tid": 2379456, + "ts": 6197197638876.806, "dur": 25.557, + "args": { + "External id": 30090,"kernel_hash": "cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/wm/cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s.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": 2338707, "tid": 2379456, + "ts": 6197197638929.012, "dur": 27.808, + "args": { + "External id": 30091,"kernel_hash": "cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql", "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/qt/cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql.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": 2338707, "tid": 2379456, + "ts": 6197197638979.231, "dur": 18.317, + "args": { + "External id": 30092,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197197639012.845, "dur": 12.976, + "args": { + "External id": 30093,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197197639035.899, "dur": 79.424, + "args": { + "External id": 30094,"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": 2338707, "tid": 2379456, + "ts": 6197197639121.515, "dur": 37.109, + "args": { + "External id": 30095,"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": 2338707, "tid": 2379456, + "ts": 6197197639190.734, "dur": 248.945, + "args": { + "External id": 30096,"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": 2338707, "tid": 2379456, + "ts": 6197197639271.316, "dur": 7.077, + "args": { + "External id": 30097,"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": 2338707, "tid": 2379456, + "ts": 6197197639280.249, "dur": 3.001, + "args": { + "External id": 30098,"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": 2338707, "tid": 2379456, + "ts": 6197197639288.142, "dur": 4.845, + "args": { + "External id": 30099,"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": 2338707, "tid": 2379456, + "ts": 6197197639293.771, "dur": 2.845, + "args": { + "External id": 30100,"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": 2338707, "tid": 2379456, + "ts": 6197197639338.439, "dur": 5.663, + "args": { + "External id": 30101,"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": 2338707, "tid": 2379456, + "ts": 6197197639341.139, "dur": 2.749, + "args": { + "External id": 30102,"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": 2338707, "tid": 2379456, + "ts": 6197197639345.933, "dur": 31.139, + "args": { + "External id": 30103,"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": 2338707, "tid": 2379456, + "ts": 6197197639351.347, "dur": 1.753, + "args": { + "External id": 30104,"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": 2338707, "tid": 2379456, + "ts": 6197197639380.128, "dur": 1.263, + "args": { + "External id": 30105,"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": 2338707, "tid": 2379456, + "ts": 6197197639380.651, "dur": 0.662, + "args": { + "External id": 30106,"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": 2338707, "tid": 2379456, + "ts": 6197197639382.267, "dur": 15.686, + "args": { + "External id": 30107,"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": 2338707, "tid": 2379456, + "ts": 6197197639383.707, "dur": 0.682, + "args": { + "External id": 30108,"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": 2338707, "tid": 2379456, + "ts": 6197197639479.454, "dur": 28.061, + "args": { + "External id": 30109,"kernel_hash": "cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4", "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/yk/cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4.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": 2338707, "tid": 2379456, + "ts": 6197197639524.052, "dur": 18.774, + "args": { + "External id": 30110,"kernel_hash": "ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg", "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/eu/ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg.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": 2338707, "tid": 2379456, + "ts": 6197197639550.033, "dur": 42.650, + "args": { + "External id": 30111,"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": 2338707, "tid": 2379456, + "ts": 6197197639599.305, "dur": 39.148, + "args": { + "External id": 30112,"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": 2338707, "tid": 2379456, + "ts": 6197197639646.020, "dur": 21.621, + "args": { + "External id": 30113,"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": 2338707, "tid": 2379456, + "ts": 6197197639675.933, "dur": 47.686, + "args": { + "External id": 30114,"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": 2338707, "tid": 2379456, + "ts": 6197197639735.125, "dur": 33.694, + "args": { + "External id": 30115,"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": 2338707, "tid": 2379456, + "ts": 6197197639775.583, "dur": 40.826, + "args": { + "External id": 30116,"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": 2338707, "tid": 2379456, + "ts": 6197197639846.871, "dur": 28.193, + "args": { + "External id": 30117,"kernel_hash": "c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/6w/c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7.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": 2338707, "tid": 2379456, + "ts": 6197197639893.897, "dur": 23.503, + "args": { + "External id": 30118,"kernel_hash": "ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx", "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/kj/ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx.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": 2338707, "tid": 2379456, + "ts": 6197197639935.338, "dur": 19.022, + "args": { + "External id": 30119,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197197639967.625, "dur": 13.900, + "args": { + "External id": 30120,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197197639998.720, "dur": 15.229, + "args": { + "External id": 30121,"kernel_hash": "cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/eb/cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b.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": 2338707, "tid": 2379456, + "ts": 6197197640132.232, "dur": 16.035, + "args": { + "External id": 30122,"Record function id": 0, "Ev Idx": 2985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197640135.733, "dur": 11.548, + "args": { + "External id": 30123,"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": 2338707, "tid": 2379456, + "ts": 6197197640139.954, "dur": 6.277, + "args": { + "External id": 30124,"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": 2338707, "tid": 2379456, + "ts": 6197197640141.788, "dur": 4.348, + "args": { + "External id": 30125,"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": 2338707, "tid": 2379456, + "ts": 6197197640152.047, "dur": 5.094, + "args": { + "External id": 30126,"Record function id": 0, "Ev Idx": 2989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197640153.722, "dur": 2.994, + "args": { + "External id": 30127,"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": 2338707, "tid": 2379456, + "ts": 6197197640154.411, "dur": 1.704, + "args": { + "External id": 30128,"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": 2338707, "tid": 2379456, + "ts": 6197197640155.021, "dur": 0.999, + "args": { + "External id": 30129,"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": 2338707, "tid": 2379456, + "ts": 6197197640160.527, "dur": 4.543, + "args": { + "External id": 30130,"Record function id": 0, "Ev Idx": 2993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197640161.974, "dur": 2.641, + "args": { + "External id": 30131,"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": 2338707, "tid": 2379456, + "ts": 6197197640162.474, "dur": 1.620, + "args": { + "External id": 30132,"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": 2338707, "tid": 2379456, + "ts": 6197197640163.162, "dur": 0.819, + "args": { + "External id": 30133,"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": 2338707, "tid": 2379456, + "ts": 6197197640168.327, "dur": 3.802, + "args": { + "External id": 30134,"Record function id": 0, "Ev Idx": 2997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197640169.527, "dur": 2.214, + "args": { + "External id": 30135,"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": 2338707, "tid": 2379456, + "ts": 6197197640170.021, "dur": 1.176, + "args": { + "External id": 30136,"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": 2338707, "tid": 2379456, + "ts": 6197197640170.467, "dur": 0.645, + "args": { + "External id": 30137,"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": 2338707, "tid": 2379456, + "ts": 6197197640175.174, "dur": 3.592, + "args": { + "External id": 30138,"Record function id": 0, "Ev Idx": 3001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197640176.168, "dur": 2.216, + "args": { + "External id": 30139,"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": 2338707, "tid": 2379456, + "ts": 6197197640176.795, "dur": 1.172, + "args": { + "External id": 30140,"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": 2338707, "tid": 2379456, + "ts": 6197197640177.195, "dur": 0.706, + "args": { + "External id": 30141,"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": 2338707, "tid": 2379456, + "ts": 6197197640181.814, "dur": 6.587, + "args": { + "External id": 30142,"Record function id": 0, "Ev Idx": 3005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197640183.268, "dur": 4.736, + "args": { + "External id": 30143,"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": 2338707, "tid": 2379456, + "ts": 6197197640183.778, "dur": 3.662, + "args": { + "External id": 30144,"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": 2338707, "tid": 2379456, + "ts": 6197197640184.305, "dur": 3.068, + "args": { + "External id": 30145,"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": 2338707, "tid": 2379456, + "ts": 6197197640191.647, "dur": 3.768, + "args": { + "External id": 30146,"Record function id": 0, "Ev Idx": 3009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197640192.993, "dur": 2.016, + "args": { + "External id": 30147,"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": 2338707, "tid": 2379456, + "ts": 6197197640193.450, "dur": 1.140, + "args": { + "External id": 30148,"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": 2338707, "tid": 2379456, + "ts": 6197197640193.751, "dur": 0.772, + "args": { + "External id": 30149,"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": 2338707, "tid": 2379456, + "ts": 6197197640198.862, "dur": 4.150, + "args": { + "External id": 30150,"Record function id": 0, "Ev Idx": 3013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197640200.269, "dur": 2.358, + "args": { + "External id": 30151,"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": 2338707, "tid": 2379456, + "ts": 6197197640200.695, "dur": 1.531, + "args": { + "External id": 30152,"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": 2338707, "tid": 2379456, + "ts": 6197197640201.318, "dur": 0.840, + "args": { + "External id": 30153,"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": 2338707, "tid": 2379456, + "ts": 6197197640206.349, "dur": 5.672, + "args": { + "External id": 30154,"Record function id": 0, "Ev Idx": 3017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197640207.605, "dur": 3.997, + "args": { + "External id": 30155,"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": 2338707, "tid": 2379456, + "ts": 6197197640208.015, "dur": 3.186, + "args": { + "External id": 30156,"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": 2338707, "tid": 2379456, + "ts": 6197197640210.544, "dur": 0.594, + "args": { + "External id": 30157,"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": 2338707, "tid": 2379456, + "ts": 6197197640216.139, "dur": 62638.107, + "args": { + "External id": 30158,"Record function id": 0, "Sequence number": 479801, "Fwd thread id": 1, "Ev Idx": 3021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197197640217.532, "dur": 62627.012, + "args": { + "External id": 30159,"Sequence number": 479801, "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": 2338707, "tid": 2379456, "ts": 6197197640217.532, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.17)", "pid": 2338707, "tid": 2379456, + "ts": 6197197640246.962, "dur": 38.840, + "args": { + "External id": 30160,"Record function id": 0, "Ev Idx": 3023 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.17)", "pid": 2338707, "tid": 2379456, + "ts": 6197197640293.936, "dur": 63.852, + "args": { + "External id": 30161,"Record function id": 0, "Ev Idx": 3024 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.17)", "pid": 2338707, "tid": 2379456, + "ts": 6197197640363.518, "dur": 62472.333, + "args": { + "External id": 30162,"Record function id": 0, "Ev Idx": 3025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197197640451.674, "dur": 6.944, + "args": { + "External id": 30163,"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": 2338707, "tid": 2379456, + "ts": 6197197640470.638, "dur": 4.545, + "args": { + "External id": 30164,"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": 2338707, "tid": 2379456, + "ts": 6197197640489.256, "dur": 61479.697, + "args": { + "External id": 30165,"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": 2338707, "tid": 2379456, + "ts": 6197197640503.843, "dur": 61451.885, + "args": { + "External id": 30166,"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": 2338707, "tid": 2379456, + "ts": 6197197640593.845, "dur": 17.040, + "args": { + "External id": 30167,"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": 2338707, "tid": 2379456, + "ts": 6197197640631.424, "dur": 61280.669, + "args": { + "External id": 30168,"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": 2338707, "tid": 2379456, + "ts": 6197197640634.190, "dur": 61276.827, + "args": { + "External id": 30169,"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": 2338707, "tid": 2379456, + "ts": 6197197640639.672, "dur": 9.018, + "args": { + "External id": 30170,"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": 2338707, "tid": 2379456, + "ts": 6197197640650.574, "dur": 61255.701, + "args": { + "External id": 30171,"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": 2338707, "tid": 2379456, + "ts": 6197197702100.380, "dur": 13.102, + "args": { + "External id": 30172,"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": 2338707, "tid": 2379456, + "ts": 6197197702104.111, "dur": 8.778, + "args": { + "External id": 30173,"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": 2338707, "tid": 2379456, + "ts": 6197197702144.563, "dur": 374.397, + "args": { + "External id": 30174,"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": 2338707, "tid": 2379456, + "ts": 6197197702176.879, "dur": 337.027, + "args": { + "External id": 30175,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197197702190.042, "dur": 318.451, + "args": { + "External id": 30176,"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": 2338707, "tid": 2379456, + "ts": 6197197702541.661, "dur": 2.272, + "args": { + "External id": 30177,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2379456, + "ts": 6197197702602.197, "dur": 6.787, + "args": { + "External id": 30178,"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": 2338707, "tid": 2379456, + "ts": 6197197702654.702, "dur": 1.182, + "args": { + "External id": 30179,"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": 2338707, "tid": 2379456, + "ts": 6197197702671.112, "dur": 1.116, + "args": { + "External id": 30180,"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": 2338707, "tid": 2379456, + "ts": 6197197702683.676, "dur": 0.937, + "args": { + "External id": 30181,"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": 2338707, "tid": 2379456, + "ts": 6197197702694.573, "dur": 1.015, + "args": { + "External id": 30182,"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": 2338707, "tid": 2379456, + "ts": 6197197702729.495, "dur": 1.575, + "args": { + "External id": 30183,"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": 2338707, "tid": 2379456, + "ts": 6197197702743.044, "dur": 1.102, + "args": { + "External id": 30184,"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": 2338707, "tid": 2379456, + "ts": 6197197702757.435, "dur": 2.303, + "args": { + "External id": 30185,"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": 2338707, "tid": 2379456, + "ts": 6197197702770.273, "dur": 0.722, + "args": { + "External id": 30186,"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": 2338707, "tid": 2379456, + "ts": 6197197702869.325, "dur": 3011.023, + "args": { + "External id": 30187,"Record function id": 0, "Ev Idx": 3050 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.16)", "pid": 2338707, "tid": 2379456, + "ts": 6197197702889.442, "dur": 1136.634, + "args": { + "External id": 30188,"Record function id": 0, "Ev Idx": 3051 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.16)", "pid": 2338707, "tid": 2379456, + "ts": 6197197702904.905, "dur": 385.820, + "args": { + "External id": 30189,"Record function id": 0, "Ev Idx": 3052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6197197702997.686, "dur": 4.185, + "args": { + "External id": 30190,"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": 2338707, "tid": 2379456, + "ts": 6197197703004.999, "dur": 0.641, + "args": { + "External id": 30191,"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": 2338707, "tid": 2379456, + "ts": 6197197703007.538, "dur": 0.712, + "args": { + "External id": 30192,"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": 2338707, "tid": 2379456, + "ts": 6197197703009.748, "dur": 0.778, + "args": { + "External id": 30193,"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": 2338707, "tid": 2379456, + "ts": 6197197703012.046, "dur": 0.879, + "args": { + "External id": 30194,"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": 2338707, "tid": 2379456, + "ts": 6197197703014.045, "dur": 0.928, + "args": { + "External id": 30195,"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": 2338707, "tid": 2379456, + "ts": 6197197703018.223, "dur": 1.759, + "args": { + "External id": 30196,"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": 2338707, "tid": 2379456, + "ts": 6197197703021.320, "dur": 2.686, + "args": { + "External id": 30197,"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": 2338707, "tid": 2379456, + "ts": 6197197703025.543, "dur": 0.730, + "args": { + "External id": 30198,"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": 2338707, "tid": 2379456, + "ts": 6197197703027.585, "dur": 0.545, + "args": { + "External id": 30199,"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": 2338707, "tid": 2379456, + "ts": 6197197703087.716, "dur": 168.793, + "args": { + "External id": 30200,"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": 2338707, "tid": 2379456, + "ts": 6197197703106.952, "dur": 144.566, + "args": { + "External id": 30201,"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": 2338707, "tid": 2379456, + "ts": 6197197703135.375, "dur": 15.721, + "args": { + "External id": 30202,"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": 2338707, "tid": 2379456, + "ts": 6197197703154.694, "dur": 67.862, + "args": { + "External id": 30203,"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": 2338707, "tid": 2379456, + "ts": 6197197703157.403, "dur": 64.862, + "args": { + "External id": 30204,"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": 2338707, "tid": 2379456, + "ts": 6197197703161.327, "dur": 6.587, + "args": { + "External id": 30205,"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": 2338707, "tid": 2379456, + "ts": 6197197703169.449, "dur": 52.118, + "args": { + "External id": 30206,"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": 2338707, "tid": 2379456, + "ts": 6197197703390.708, "dur": 627.838, + "args": { + "External id": 30207,"Record function id": 0, "Ev Idx": 3070 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.15)", "pid": 2338707, "tid": 2379456, + "ts": 6197197703406.857, "dur": 599.927, + "args": { + "External id": 30208,"Record function id": 0, "Ev Idx": 3071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197197703504.035, "dur": 5.545, + "args": { + "External id": 30209,"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": 2338707, "tid": 2379456, + "ts": 6197197703525.375, "dur": 35.590, + "args": { + "External id": 30210,"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": 2338707, "tid": 2379456, + "ts": 6197197703530.558, "dur": 1.760, + "args": { + "External id": 30211,"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": 2338707, "tid": 2379456, + "ts": 6197197703535.637, "dur": 0.327, + "args": { + "External id": 30212,"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": 2338707, "tid": 2379456, + "ts": 6197197703540.740, "dur": 3.064, + "args": { + "External id": 30213,"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": 2338707, "tid": 2379456, + "ts": 6197197703545.284, "dur": 1.292, + "args": { + "External id": 30214,"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": 2338707, "tid": 2379456, + "ts": 6197197703547.552, "dur": 0.390, + "args": { + "External id": 30215,"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": 2338707, "tid": 2379456, + "ts": 6197197703549.162, "dur": 0.369, + "args": { + "External id": 30216,"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": 2338707, "tid": 2379456, + "ts": 6197197703552.423, "dur": 0.348, + "args": { + "External id": 30217,"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": 2338707, "tid": 2379456, + "ts": 6197197703554.388, "dur": 0.255, + "args": { + "External id": 30218,"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": 2338707, "tid": 2379456, + "ts": 6197197703555.722, "dur": 0.376, + "args": { + "External id": 30219,"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": 2338707, "tid": 2379456, + "ts": 6197197703571.808, "dur": 42.742, + "args": { + "External id": 30220,"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": 2338707, "tid": 2379456, + "ts": 6197197703643.891, "dur": 131.479, + "args": { + "External id": 30221,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2379456, + "ts": 6197197703653.674, "dur": 3.336, + "args": { + "External id": 30222,"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": 2338707, "tid": 2379456, + "ts": 6197197703662.471, "dur": 12.554, + "args": { + "External id": 30223,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2379456, + "ts": 6197197703666.827, "dur": 7.747, + "args": { + "External id": 30224,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2379456, + "ts": 6197197703670.088, "dur": 3.328, + "args": { + "External id": 30225,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197197703680.694, "dur": 39.381, + "args": { + "External id": 30226,"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": 2338707, "tid": 2379456, + "ts": 6197197703682.322, "dur": 0.372, + "args": { + "External id": 30227,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197197703684.323, "dur": 0.476, + "args": { + "External id": 30228,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2379456, + "ts": 6197197703686.051, "dur": 0.280, + "args": { + "External id": 30229,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2379456, + "ts": 6197197703688.440, "dur": 0.334, + "args": { + "External id": 30230,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2379456, + "ts": 6197197703689.541, "dur": 0.322, + "args": { + "External id": 30231,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2379456, + "ts": 6197197703690.827, "dur": 1.253, + "args": { + "External id": 30232,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2379456, + "ts": 6197197703692.980, "dur": 0.257, + "args": { + "External id": 30233,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2379456, + "ts": 6197197703694.076, "dur": 2.265, + "args": { + "External id": 30234,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2379456, + "ts": 6197197703698.078, "dur": 0.263, + "args": { + "External id": 30235,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2379456, + "ts": 6197197703734.173, "dur": 33.412, + "args": { + "External id": 30236,"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": 2338707, "tid": 2379456, + "ts": 6197197703820.827, "dur": 116.993, + "args": { + "External id": 30237,"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": 2338707, "tid": 2379456, + "ts": 6197197703850.631, "dur": 83.870, + "args": { + "External id": 30238,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197197703859.845, "dur": 70.575, + "args": { + "External id": 30239,"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": 2338707, "tid": 2379456, + "ts": 6197197703953.939, "dur": 1.612, + "args": { + "External id": 30240,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197197704033.934, "dur": 1819.461, + "args": { + "External id": 30241,"Sequence number": 479800, "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": 2338707, "tid": 2379456, "ts": 6197197704033.934, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6197197704181.749, "dur": 111.549, + "args": { + "External id": 30242,"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": 2338707, "tid": 2379456, + "ts": 6197197704347.399, "dur": 42.861, + "args": { + "External id": 30243,"kernel_hash": "cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/u7/cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs.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": 2338707, "tid": 2379456, + "ts": 6197197704410.321, "dur": 53.839, + "args": { + "External id": 30244,"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": 2338707, "tid": 2379456, + "ts": 6197197704475.175, "dur": 34.178, + "args": { + "External id": 30245,"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": 2338707, "tid": 2379456, + "ts": 6197197704515.472, "dur": 33.586, + "args": { + "External id": 30246,"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": 2338707, "tid": 2379456, + "ts": 6197197704555.264, "dur": 27.546, + "args": { + "External id": 30247,"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": 2338707, "tid": 2379456, + "ts": 6197197704591.529, "dur": 29.173, + "args": { + "External id": 30248,"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": 2338707, "tid": 2379456, + "ts": 6197197704646.970, "dur": 23.139, + "args": { + "External id": 30249,"kernel_hash": "cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/wm/cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s.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": 2338707, "tid": 2379456, + "ts": 6197197704688.562, "dur": 47.494, + "args": { + "External id": 30250,"kernel_hash": "cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql", "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/qt/cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql.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": 2338707, "tid": 2379456, + "ts": 6197197704762.972, "dur": 19.938, + "args": { + "External id": 30251,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197197704797.953, "dur": 13.687, + "args": { + "External id": 30252,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197197704820.908, "dur": 40.864, + "args": { + "External id": 30253,"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": 2338707, "tid": 2379456, + "ts": 6197197704865.626, "dur": 32.787, + "args": { + "External id": 30254,"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": 2338707, "tid": 2379456, + "ts": 6197197704927.032, "dur": 293.339, + "args": { + "External id": 30255,"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": 2338707, "tid": 2379456, + "ts": 6197197705008.159, "dur": 6.488, + "args": { + "External id": 30256,"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": 2338707, "tid": 2379456, + "ts": 6197197705017.012, "dur": 2.917, + "args": { + "External id": 30257,"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": 2338707, "tid": 2379456, + "ts": 6197197705020.851, "dur": 4.011, + "args": { + "External id": 30258,"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": 2338707, "tid": 2379456, + "ts": 6197197705026.075, "dur": 2.933, + "args": { + "External id": 30259,"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": 2338707, "tid": 2379456, + "ts": 6197197705111.311, "dur": 7.279, + "args": { + "External id": 30260,"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": 2338707, "tid": 2379456, + "ts": 6197197705115.421, "dur": 2.813, + "args": { + "External id": 30261,"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": 2338707, "tid": 2379456, + "ts": 6197197705120.385, "dur": 32.489, + "args": { + "External id": 30262,"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": 2338707, "tid": 2379456, + "ts": 6197197705126.804, "dur": 1.771, + "args": { + "External id": 30263,"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": 2338707, "tid": 2379456, + "ts": 6197197705154.624, "dur": 1.932, + "args": { + "External id": 30264,"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": 2338707, "tid": 2379456, + "ts": 6197197705155.951, "dur": 0.520, + "args": { + "External id": 30265,"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": 2338707, "tid": 2379456, + "ts": 6197197705157.371, "dur": 18.146, + "args": { + "External id": 30266,"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": 2338707, "tid": 2379456, + "ts": 6197197705159.848, "dur": 0.786, + "args": { + "External id": 30267,"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": 2338707, "tid": 2379456, + "ts": 6197197705268.112, "dur": 32.559, + "args": { + "External id": 30268,"kernel_hash": "cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4", "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/yk/cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4.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": 2338707, "tid": 2379456, + "ts": 6197197705320.951, "dur": 17.133, + "args": { + "External id": 30269,"kernel_hash": "ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg", "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/eu/ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg.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": 2338707, "tid": 2379456, + "ts": 6197197705346.566, "dur": 51.387, + "args": { + "External id": 30270,"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": 2338707, "tid": 2379456, + "ts": 6197197705404.600, "dur": 39.425, + "args": { + "External id": 30271,"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": 2338707, "tid": 2379456, + "ts": 6197197705452.367, "dur": 20.178, + "args": { + "External id": 30272,"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": 2338707, "tid": 2379456, + "ts": 6197197705480.718, "dur": 31.001, + "args": { + "External id": 30273,"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": 2338707, "tid": 2379456, + "ts": 6197197705518.827, "dur": 28.301, + "args": { + "External id": 30274,"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": 2338707, "tid": 2379456, + "ts": 6197197705553.934, "dur": 30.209, + "args": { + "External id": 30275,"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": 2338707, "tid": 2379456, + "ts": 6197197705607.254, "dur": 22.256, + "args": { + "External id": 30276,"kernel_hash": "c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/6w/c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7.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": 2338707, "tid": 2379456, + "ts": 6197197705645.314, "dur": 38.050, + "args": { + "External id": 30277,"kernel_hash": "ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx", "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/kj/ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx.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": 2338707, "tid": 2379456, + "ts": 6197197705725.030, "dur": 24.501, + "args": { + "External id": 30278,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197197705771.036, "dur": 15.495, + "args": { + "External id": 30279,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197197705800.226, "dur": 22.294, + "args": { + "External id": 30280,"kernel_hash": "cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/eb/cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b.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": 2338707, "tid": 2379456, + "ts": 6197197705902.465, "dur": 15.195, + "args": { + "External id": 30281,"Record function id": 0, "Ev Idx": 3144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197705905.862, "dur": 10.754, + "args": { + "External id": 30282,"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": 2338707, "tid": 2379456, + "ts": 6197197705910.396, "dur": 5.389, + "args": { + "External id": 30283,"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": 2338707, "tid": 2379456, + "ts": 6197197705911.689, "dur": 4.004, + "args": { + "External id": 30284,"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": 2338707, "tid": 2379456, + "ts": 6197197705921.540, "dur": 9.256, + "args": { + "External id": 30285,"Record function id": 0, "Ev Idx": 3148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197705923.333, "dur": 6.990, + "args": { + "External id": 30286,"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": 2338707, "tid": 2379456, + "ts": 6197197705924.167, "dur": 5.395, + "args": { + "External id": 30287,"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": 2338707, "tid": 2379456, + "ts": 6197197705928.824, "dur": 0.637, + "args": { + "External id": 30288,"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": 2338707, "tid": 2379456, + "ts": 6197197705934.242, "dur": 6.534, + "args": { + "External id": 30289,"Record function id": 0, "Ev Idx": 3152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197705935.576, "dur": 4.778, + "args": { + "External id": 30290,"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": 2338707, "tid": 2379456, + "ts": 6197197705936.373, "dur": 3.524, + "args": { + "External id": 30291,"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": 2338707, "tid": 2379456, + "ts": 6197197705938.982, "dur": 0.799, + "args": { + "External id": 30292,"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": 2338707, "tid": 2379456, + "ts": 6197197705943.953, "dur": 4.956, + "args": { + "External id": 30293,"Record function id": 0, "Ev Idx": 3156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197705945.449, "dur": 3.052, + "args": { + "External id": 30294,"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": 2338707, "tid": 2379456, + "ts": 6197197705946.432, "dur": 1.645, + "args": { + "External id": 30295,"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": 2338707, "tid": 2379456, + "ts": 6197197705947.112, "dur": 0.846, + "args": { + "External id": 30296,"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": 2338707, "tid": 2379456, + "ts": 6197197705951.933, "dur": 4.083, + "args": { + "External id": 30297,"Record function id": 0, "Ev Idx": 3160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197705953.002, "dur": 2.624, + "args": { + "External id": 30298,"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": 2338707, "tid": 2379456, + "ts": 6197197705954.018, "dur": 1.115, + "args": { + "External id": 30299,"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": 2338707, "tid": 2379456, + "ts": 6197197705954.483, "dur": 0.585, + "args": { + "External id": 30300,"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": 2338707, "tid": 2379456, + "ts": 6197197705959.082, "dur": 6.680, + "args": { + "External id": 30301,"Record function id": 0, "Ev Idx": 3164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197705960.133, "dur": 5.239, + "args": { + "External id": 30302,"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": 2338707, "tid": 2379456, + "ts": 6197197705961.004, "dur": 3.957, + "args": { + "External id": 30303,"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": 2338707, "tid": 2379456, + "ts": 6197197705961.657, "dur": 3.207, + "args": { + "External id": 30304,"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": 2338707, "tid": 2379456, + "ts": 6197197705969.222, "dur": 6.362, + "args": { + "External id": 30305,"Record function id": 0, "Ev Idx": 3168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197705970.521, "dur": 4.675, + "args": { + "External id": 30306,"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": 2338707, "tid": 2379456, + "ts": 6197197705971.316, "dur": 3.486, + "args": { + "External id": 30307,"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": 2338707, "tid": 2379456, + "ts": 6197197705973.961, "dur": 0.759, + "args": { + "External id": 30308,"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": 2338707, "tid": 2379456, + "ts": 6197197705978.735, "dur": 3.733, + "args": { + "External id": 30309,"Record function id": 0, "Ev Idx": 3172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197705979.949, "dur": 2.107, + "args": { + "External id": 30310,"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": 2338707, "tid": 2379456, + "ts": 6197197705980.654, "dur": 1.008, + "args": { + "External id": 30311,"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": 2338707, "tid": 2379456, + "ts": 6197197705980.933, "dur": 0.644, + "args": { + "External id": 30312,"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": 2338707, "tid": 2379456, + "ts": 6197197705985.592, "dur": 3.897, + "args": { + "External id": 30313,"Record function id": 0, "Ev Idx": 3176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197705986.767, "dur": 2.329, + "args": { + "External id": 30314,"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": 2338707, "tid": 2379456, + "ts": 6197197705987.516, "dur": 1.139, + "args": { + "External id": 30315,"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": 2338707, "tid": 2379456, + "ts": 6197197705987.949, "dur": 0.611, + "args": { + "External id": 30316,"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": 2338707, "tid": 2379456, + "ts": 6197197705993.229, "dur": 63921.991, + "args": { + "External id": 30317,"Record function id": 0, "Sequence number": 479799, "Fwd thread id": 1, "Ev Idx": 3180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197197705994.844, "dur": 63910.463, + "args": { + "External id": 30318,"Sequence number": 479799, "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": 2338707, "tid": 2379456, "ts": 6197197705994.844, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.16)", "pid": 2338707, "tid": 2379456, + "ts": 6197197706025.586, "dur": 74.253, + "args": { + "External id": 30319,"Record function id": 0, "Ev Idx": 3182 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.16)", "pid": 2338707, "tid": 2379456, + "ts": 6197197706109.568, "dur": 72.474, + "args": { + "External id": 30320,"Record function id": 0, "Ev Idx": 3183 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.16)", "pid": 2338707, "tid": 2379456, + "ts": 6197197706187.752, "dur": 63709.895, + "args": { + "External id": 30321,"Record function id": 0, "Ev Idx": 3184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197197706277.851, "dur": 7.435, + "args": { + "External id": 30322,"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": 2338707, "tid": 2379456, + "ts": 6197197706295.955, "dur": 4.956, + "args": { + "External id": 30323,"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": 2338707, "tid": 2379456, + "ts": 6197197706316.113, "dur": 62708.902, + "args": { + "External id": 30324,"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": 2338707, "tid": 2379456, + "ts": 6197197706331.934, "dur": 62680.128, + "args": { + "External id": 30325,"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": 2338707, "tid": 2379456, + "ts": 6197197706420.252, "dur": 16.620, + "args": { + "External id": 30326,"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": 2338707, "tid": 2379456, + "ts": 6197197706456.836, "dur": 62511.466, + "args": { + "External id": 30327,"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": 2338707, "tid": 2379456, + "ts": 6197197706459.705, "dur": 62507.547, + "args": { + "External id": 30328,"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": 2338707, "tid": 2379456, + "ts": 6197197706463.595, "dur": 10.837, + "args": { + "External id": 30329,"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": 2338707, "tid": 2379456, + "ts": 6197197706476.268, "dur": 62486.364, + "args": { + "External id": 30330,"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": 2338707, "tid": 2379456, + "ts": 6197197769156.077, "dur": 11.966, + "args": { + "External id": 30331,"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": 2338707, "tid": 2379456, + "ts": 6197197769159.677, "dur": 7.789, + "args": { + "External id": 30332,"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": 2338707, "tid": 2379456, + "ts": 6197197769197.750, "dur": 382.921, + "args": { + "External id": 30333,"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": 2338707, "tid": 2379456, + "ts": 6197197769232.401, "dur": 343.204, + "args": { + "External id": 30334,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197197769244.010, "dur": 326.590, + "args": { + "External id": 30335,"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": 2338707, "tid": 2379456, + "ts": 6197197769603.860, "dur": 2.021, + "args": { + "External id": 30336,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2379456, + "ts": 6197197769663.462, "dur": 6.282, + "args": { + "External id": 30337,"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": 2338707, "tid": 2379456, + "ts": 6197197769734.698, "dur": 1.951, + "args": { + "External id": 30338,"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": 2338707, "tid": 2379456, + "ts": 6197197769752.912, "dur": 1.249, + "args": { + "External id": 30339,"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": 2338707, "tid": 2379456, + "ts": 6197197769766.770, "dur": 0.814, + "args": { + "External id": 30340,"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": 2338707, "tid": 2379456, + "ts": 6197197769780.019, "dur": 0.729, + "args": { + "External id": 30341,"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": 2338707, "tid": 2379456, + "ts": 6197197769794.163, "dur": 1.137, + "args": { + "External id": 30342,"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": 2338707, "tid": 2379456, + "ts": 6197197769808.373, "dur": 1.023, + "args": { + "External id": 30343,"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": 2338707, "tid": 2379456, + "ts": 6197197769820.091, "dur": 2.687, + "args": { + "External id": 30344,"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": 2338707, "tid": 2379456, + "ts": 6197197769832.883, "dur": 0.704, + "args": { + "External id": 30345,"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": 2338707, "tid": 2379456, + "ts": 6197197769930.462, "dur": 2915.762, + "args": { + "External id": 30346,"Record function id": 0, "Ev Idx": 3209 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.15)", "pid": 2338707, "tid": 2379456, + "ts": 6197197769951.461, "dur": 1092.104, + "args": { + "External id": 30347,"Record function id": 0, "Ev Idx": 3210 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.15)", "pid": 2338707, "tid": 2379456, + "ts": 6197197769966.389, "dur": 387.174, + "args": { + "External id": 30348,"Record function id": 0, "Ev Idx": 3211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6197197770090.363, "dur": 5.057, + "args": { + "External id": 30349,"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": 2338707, "tid": 2379456, + "ts": 6197197770099.633, "dur": 1.022, + "args": { + "External id": 30350,"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": 2338707, "tid": 2379456, + "ts": 6197197770102.554, "dur": 0.655, + "args": { + "External id": 30351,"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": 2338707, "tid": 2379456, + "ts": 6197197770104.769, "dur": 1.086, + "args": { + "External id": 30352,"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": 2338707, "tid": 2379456, + "ts": 6197197770107.503, "dur": 1.093, + "args": { + "External id": 30353,"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": 2338707, "tid": 2379456, + "ts": 6197197770112.524, "dur": 0.831, + "args": { + "External id": 30354,"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": 2338707, "tid": 2379456, + "ts": 6197197770114.661, "dur": 2.170, + "args": { + "External id": 30355,"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": 2338707, "tid": 2379456, + "ts": 6197197770118.441, "dur": 2.981, + "args": { + "External id": 30356,"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": 2338707, "tid": 2379456, + "ts": 6197197770122.715, "dur": 0.867, + "args": { + "External id": 30357,"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": 2338707, "tid": 2379456, + "ts": 6197197770127.075, "dur": 0.779, + "args": { + "External id": 30358,"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": 2338707, "tid": 2379456, + "ts": 6197197770145.584, "dur": 172.972, + "args": { + "External id": 30359,"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": 2338707, "tid": 2379456, + "ts": 6197197770165.617, "dur": 147.668, + "args": { + "External id": 30360,"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": 2338707, "tid": 2379456, + "ts": 6197197770181.006, "dur": 15.428, + "args": { + "External id": 30361,"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": 2338707, "tid": 2379456, + "ts": 6197197770199.873, "dur": 77.283, + "args": { + "External id": 30362,"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": 2338707, "tid": 2379456, + "ts": 6197197770202.378, "dur": 74.394, + "args": { + "External id": 30363,"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": 2338707, "tid": 2379456, + "ts": 6197197770216.309, "dur": 6.807, + "args": { + "External id": 30364,"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": 2338707, "tid": 2379456, + "ts": 6197197770224.620, "dur": 51.507, + "args": { + "External id": 30365,"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": 2338707, "tid": 2379456, + "ts": 6197197770447.843, "dur": 587.770, + "args": { + "External id": 30366,"Record function id": 0, "Ev Idx": 3229 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.14)", "pid": 2338707, "tid": 2379456, + "ts": 6197197770467.748, "dur": 555.351, + "args": { + "External id": 30367,"Record function id": 0, "Ev Idx": 3230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197197770530.257, "dur": 4.557, + "args": { + "External id": 30368,"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": 2338707, "tid": 2379456, + "ts": 6197197770550.395, "dur": 31.711, + "args": { + "External id": 30369,"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": 2338707, "tid": 2379456, + "ts": 6197197770555.901, "dur": 1.883, + "args": { + "External id": 30370,"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": 2338707, "tid": 2379456, + "ts": 6197197770559.637, "dur": 1.704, + "args": { + "External id": 30371,"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": 2338707, "tid": 2379456, + "ts": 6197197770562.620, "dur": 2.691, + "args": { + "External id": 30372,"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": 2338707, "tid": 2379456, + "ts": 6197197770566.560, "dur": 0.385, + "args": { + "External id": 30373,"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": 2338707, "tid": 2379456, + "ts": 6197197770569.423, "dur": 0.278, + "args": { + "External id": 30374,"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": 2338707, "tid": 2379456, + "ts": 6197197770571.024, "dur": 0.369, + "args": { + "External id": 30375,"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": 2338707, "tid": 2379456, + "ts": 6197197770572.361, "dur": 0.571, + "args": { + "External id": 30376,"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": 2338707, "tid": 2379456, + "ts": 6197197770575.086, "dur": 0.305, + "args": { + "External id": 30377,"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": 2338707, "tid": 2379456, + "ts": 6197197770576.544, "dur": 0.362, + "args": { + "External id": 30378,"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": 2338707, "tid": 2379456, + "ts": 6197197770592.234, "dur": 41.050, + "args": { + "External id": 30379,"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": 2338707, "tid": 2379456, + "ts": 6197197770661.166, "dur": 129.659, + "args": { + "External id": 30380,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2379456, + "ts": 6197197770669.974, "dur": 3.009, + "args": { + "External id": 30381,"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": 2338707, "tid": 2379456, + "ts": 6197197770678.180, "dur": 11.279, + "args": { + "External id": 30382,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2379456, + "ts": 6197197770682.328, "dur": 6.687, + "args": { + "External id": 30383,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2379456, + "ts": 6197197770685.266, "dur": 2.539, + "args": { + "External id": 30384,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197197770696.354, "dur": 42.237, + "args": { + "External id": 30385,"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": 2338707, "tid": 2379456, + "ts": 6197197770697.709, "dur": 0.610, + "args": { + "External id": 30386,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197197770717.723, "dur": 0.556, + "args": { + "External id": 30387,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2379456, + "ts": 6197197770720.171, "dur": 0.478, + "args": { + "External id": 30388,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2379456, + "ts": 6197197770721.758, "dur": 1.098, + "args": { + "External id": 30389,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2379456, + "ts": 6197197770723.969, "dur": 0.365, + "args": { + "External id": 30390,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2379456, + "ts": 6197197770725.320, "dur": 0.309, + "args": { + "External id": 30391,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2379456, + "ts": 6197197770727.912, "dur": 0.303, + "args": { + "External id": 30392,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2379456, + "ts": 6197197770729.516, "dur": 2.564, + "args": { + "External id": 30393,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2379456, + "ts": 6197197770733.210, "dur": 0.422, + "args": { + "External id": 30394,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2379456, + "ts": 6197197770750.645, "dur": 32.460, + "args": { + "External id": 30395,"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": 2338707, "tid": 2379456, + "ts": 6197197770835.832, "dur": 116.333, + "args": { + "External id": 30396,"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": 2338707, "tid": 2379456, + "ts": 6197197770864.121, "dur": 84.944, + "args": { + "External id": 30397,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197197770873.214, "dur": 71.545, + "args": { + "External id": 30398,"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": 2338707, "tid": 2379456, + "ts": 6197197770971.783, "dur": 1.724, + "args": { + "External id": 30399,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197197771050.939, "dur": 1765.674, + "args": { + "External id": 30400,"Sequence number": 479798, "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": 2338707, "tid": 2379456, "ts": 6197197771050.939, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6197197771201.588, "dur": 110.994, + "args": { + "External id": 30401,"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": 2338707, "tid": 2379456, + "ts": 6197197771356.782, "dur": 41.143, + "args": { + "External id": 30402,"kernel_hash": "cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/u7/cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs.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": 2338707, "tid": 2379456, + "ts": 6197197771416.833, "dur": 49.816, + "args": { + "External id": 30403,"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": 2338707, "tid": 2379456, + "ts": 6197197771477.107, "dur": 30.642, + "args": { + "External id": 30404,"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": 2338707, "tid": 2379456, + "ts": 6197197771514.044, "dur": 31.875, + "args": { + "External id": 30405,"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": 2338707, "tid": 2379456, + "ts": 6197197771552.356, "dur": 26.680, + "args": { + "External id": 30406,"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": 2338707, "tid": 2379456, + "ts": 6197197771588.160, "dur": 28.240, + "args": { + "External id": 30407,"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": 2338707, "tid": 2379456, + "ts": 6197197771640.603, "dur": 22.753, + "args": { + "External id": 30408,"kernel_hash": "cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/wm/cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s.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": 2338707, "tid": 2379456, + "ts": 6197197771680.590, "dur": 44.271, + "args": { + "External id": 30409,"kernel_hash": "cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql", "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/qt/cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql.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": 2338707, "tid": 2379456, + "ts": 6197197771750.135, "dur": 19.455, + "args": { + "External id": 30410,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197197771786.491, "dur": 14.319, + "args": { + "External id": 30411,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197197771810.470, "dur": 39.935, + "args": { + "External id": 30412,"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": 2338707, "tid": 2379456, + "ts": 6197197771854.092, "dur": 32.248, + "args": { + "External id": 30413,"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": 2338707, "tid": 2379456, + "ts": 6197197771914.627, "dur": 295.974, + "args": { + "External id": 30414,"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": 2338707, "tid": 2379456, + "ts": 6197197771992.541, "dur": 6.089, + "args": { + "External id": 30415,"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": 2338707, "tid": 2379456, + "ts": 6197197772000.813, "dur": 3.046, + "args": { + "External id": 30416,"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": 2338707, "tid": 2379456, + "ts": 6197197772005.001, "dur": 3.978, + "args": { + "External id": 30417,"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": 2338707, "tid": 2379456, + "ts": 6197197772010.215, "dur": 2.371, + "args": { + "External id": 30418,"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": 2338707, "tid": 2379456, + "ts": 6197197772096.215, "dur": 6.224, + "args": { + "External id": 30419,"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": 2338707, "tid": 2379456, + "ts": 6197197772098.245, "dur": 3.799, + "args": { + "External id": 30420,"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": 2338707, "tid": 2379456, + "ts": 6197197772104.192, "dur": 37.768, + "args": { + "External id": 30421,"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": 2338707, "tid": 2379456, + "ts": 6197197772113.505, "dur": 1.788, + "args": { + "External id": 30422,"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": 2338707, "tid": 2379456, + "ts": 6197197772143.926, "dur": 3.862, + "args": { + "External id": 30423,"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": 2338707, "tid": 2379456, + "ts": 6197197772147.141, "dur": 0.563, + "args": { + "External id": 30424,"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": 2338707, "tid": 2379456, + "ts": 6197197772149.004, "dur": 15.566, + "args": { + "External id": 30425,"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": 2338707, "tid": 2379456, + "ts": 6197197772150.770, "dur": 0.393, + "args": { + "External id": 30426,"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": 2338707, "tid": 2379456, + "ts": 6197197772251.361, "dur": 28.143, + "args": { + "External id": 30427,"kernel_hash": "cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4", "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/yk/cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4.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": 2338707, "tid": 2379456, + "ts": 6197197772296.520, "dur": 18.874, + "args": { + "External id": 30428,"kernel_hash": "ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg", "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/eu/ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg.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": 2338707, "tid": 2379456, + "ts": 6197197772323.227, "dur": 51.375, + "args": { + "External id": 30429,"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": 2338707, "tid": 2379456, + "ts": 6197197772381.109, "dur": 39.638, + "args": { + "External id": 30430,"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": 2338707, "tid": 2379456, + "ts": 6197197772429.024, "dur": 22.123, + "args": { + "External id": 30431,"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": 2338707, "tid": 2379456, + "ts": 6197197772458.469, "dur": 30.699, + "args": { + "External id": 30432,"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": 2338707, "tid": 2379456, + "ts": 6197197772495.960, "dur": 27.261, + "args": { + "External id": 30433,"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": 2338707, "tid": 2379456, + "ts": 6197197772529.493, "dur": 29.549, + "args": { + "External id": 30434,"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": 2338707, "tid": 2379456, + "ts": 6197197772579.609, "dur": 21.326, + "args": { + "External id": 30435,"kernel_hash": "c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/6w/c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7.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": 2338707, "tid": 2379456, + "ts": 6197197772618.425, "dur": 41.209, + "args": { + "External id": 30436,"kernel_hash": "ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx", "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/kj/ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx.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": 2338707, "tid": 2379456, + "ts": 6197197772683.478, "dur": 33.171, + "args": { + "External id": 30437,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197197772736.968, "dur": 16.269, + "args": { + "External id": 30438,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197197772769.950, "dur": 15.430, + "args": { + "External id": 30439,"kernel_hash": "cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/eb/cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b.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": 2338707, "tid": 2379456, + "ts": 6197197772868.342, "dur": 19.075, + "args": { + "External id": 30440,"Record function id": 0, "Ev Idx": 3303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197772871.517, "dur": 14.890, + "args": { + "External id": 30441,"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": 2338707, "tid": 2379456, + "ts": 6197197772875.533, "dur": 10.077, + "args": { + "External id": 30442,"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": 2338707, "tid": 2379456, + "ts": 6197197772880.483, "dur": 5.027, + "args": { + "External id": 30443,"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": 2338707, "tid": 2379456, + "ts": 6197197772891.590, "dur": 5.011, + "args": { + "External id": 30444,"Record function id": 0, "Ev Idx": 3307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197772892.988, "dur": 3.083, + "args": { + "External id": 30445,"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": 2338707, "tid": 2379456, + "ts": 6197197772894.072, "dur": 1.518, + "args": { + "External id": 30446,"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": 2338707, "tid": 2379456, + "ts": 6197197772894.513, "dur": 0.991, + "args": { + "External id": 30447,"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": 2338707, "tid": 2379456, + "ts": 6197197772899.884, "dur": 4.523, + "args": { + "External id": 30448,"Record function id": 0, "Ev Idx": 3311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197772901.160, "dur": 2.816, + "args": { + "External id": 30449,"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": 2338707, "tid": 2379456, + "ts": 6197197772901.938, "dur": 1.567, + "args": { + "External id": 30450,"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": 2338707, "tid": 2379456, + "ts": 6197197772902.763, "dur": 0.637, + "args": { + "External id": 30451,"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": 2338707, "tid": 2379456, + "ts": 6197197772907.677, "dur": 3.863, + "args": { + "External id": 30452,"Record function id": 0, "Ev Idx": 3315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197772908.899, "dur": 2.222, + "args": { + "External id": 30453,"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": 2338707, "tid": 2379456, + "ts": 6197197772909.400, "dur": 1.133, + "args": { + "External id": 30454,"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": 2338707, "tid": 2379456, + "ts": 6197197772909.820, "dur": 0.634, + "args": { + "External id": 30455,"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": 2338707, "tid": 2379456, + "ts": 6197197772914.666, "dur": 4.319, + "args": { + "External id": 30456,"Record function id": 0, "Ev Idx": 3319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197772916.084, "dur": 2.492, + "args": { + "External id": 30457,"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": 2338707, "tid": 2379456, + "ts": 6197197772916.748, "dur": 1.176, + "args": { + "External id": 30458,"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": 2338707, "tid": 2379456, + "ts": 6197197772917.031, "dur": 0.826, + "args": { + "External id": 30459,"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": 2338707, "tid": 2379456, + "ts": 6197197772922.076, "dur": 6.115, + "args": { + "External id": 30460,"Record function id": 0, "Ev Idx": 3323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197772923.480, "dur": 4.293, + "args": { + "External id": 30461,"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": 2338707, "tid": 2379456, + "ts": 6197197772924.096, "dur": 3.238, + "args": { + "External id": 30462,"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": 2338707, "tid": 2379456, + "ts": 6197197772924.497, "dur": 2.775, + "args": { + "External id": 30463,"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": 2338707, "tid": 2379456, + "ts": 6197197772931.532, "dur": 3.957, + "args": { + "External id": 30464,"Record function id": 0, "Ev Idx": 3327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197772932.812, "dur": 2.264, + "args": { + "External id": 30465,"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": 2338707, "tid": 2379456, + "ts": 6197197772933.437, "dur": 1.205, + "args": { + "External id": 30466,"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": 2338707, "tid": 2379456, + "ts": 6197197772933.775, "dur": 0.807, + "args": { + "External id": 30467,"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": 2338707, "tid": 2379456, + "ts": 6197197772938.626, "dur": 3.722, + "args": { + "External id": 30468,"Record function id": 0, "Ev Idx": 3331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197772939.781, "dur": 2.156, + "args": { + "External id": 30469,"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": 2338707, "tid": 2379456, + "ts": 6197197772940.613, "dur": 0.904, + "args": { + "External id": 30470,"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": 2338707, "tid": 2379456, + "ts": 6197197772940.871, "dur": 0.579, + "args": { + "External id": 30471,"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": 2338707, "tid": 2379456, + "ts": 6197197772945.751, "dur": 6.425, + "args": { + "External id": 30472,"Record function id": 0, "Ev Idx": 3335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197772947.114, "dur": 4.596, + "args": { + "External id": 30473,"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": 2338707, "tid": 2379456, + "ts": 6197197772947.993, "dur": 3.074, + "args": { + "External id": 30474,"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": 2338707, "tid": 2379456, + "ts": 6197197772950.399, "dur": 0.604, + "args": { + "External id": 30475,"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": 2338707, "tid": 2379456, + "ts": 6197197772956.176, "dur": 63676.532, + "args": { + "External id": 30476,"Record function id": 0, "Sequence number": 479797, "Fwd thread id": 1, "Ev Idx": 3339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197197772957.800, "dur": 63666.031, + "args": { + "External id": 30477,"Sequence number": 479797, "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": 2338707, "tid": 2379456, "ts": 6197197772957.800, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.15)", "pid": 2338707, "tid": 2379456, + "ts": 6197197772987.109, "dur": 37.456, + "args": { + "External id": 30478,"Record function id": 0, "Ev Idx": 3341 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.15)", "pid": 2338707, "tid": 2379456, + "ts": 6197197773031.978, "dur": 102.464, + "args": { + "External id": 30479,"Record function id": 0, "Ev Idx": 3342 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.15)", "pid": 2338707, "tid": 2379456, + "ts": 6197197773145.300, "dur": 63470.895, + "args": { + "External id": 30480,"Record function id": 0, "Ev Idx": 3343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197197773237.326, "dur": 7.516, + "args": { + "External id": 30481,"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": 2338707, "tid": 2379456, + "ts": 6197197773255.224, "dur": 8.162, + "args": { + "External id": 30482,"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": 2338707, "tid": 2379456, + "ts": 6197197773277.127, "dur": 62411.821, + "args": { + "External id": 30483,"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": 2338707, "tid": 2379456, + "ts": 6197197773291.069, "dur": 62384.829, + "args": { + "External id": 30484,"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": 2338707, "tid": 2379456, + "ts": 6197197773382.232, "dur": 17.404, + "args": { + "External id": 30485,"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": 2338707, "tid": 2379456, + "ts": 6197197773419.756, "dur": 62212.139, + "args": { + "External id": 30486,"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": 2338707, "tid": 2379456, + "ts": 6197197773422.387, "dur": 62208.355, + "args": { + "External id": 30487,"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": 2338707, "tid": 2379456, + "ts": 6197197773426.609, "dur": 10.351, + "args": { + "External id": 30488,"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": 2338707, "tid": 2379456, + "ts": 6197197773441.678, "dur": 62184.261, + "args": { + "External id": 30489,"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": 2338707, "tid": 2379456, + "ts": 6197197835805.500, "dur": 12.409, + "args": { + "External id": 30490,"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": 2338707, "tid": 2379456, + "ts": 6197197835809.145, "dur": 8.134, + "args": { + "External id": 30491,"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": 2338707, "tid": 2379456, + "ts": 6197197835847.780, "dur": 459.969, + "args": { + "External id": 30492,"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": 2338707, "tid": 2379456, + "ts": 6197197835879.816, "dur": 421.785, + "args": { + "External id": 30493,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197197835893.118, "dur": 401.801, + "args": { + "External id": 30494,"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": 2338707, "tid": 2379456, + "ts": 6197197836334.828, "dur": 2.685, + "args": { + "External id": 30495,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2379456, + "ts": 6197197836402.641, "dur": 6.699, + "args": { + "External id": 30496,"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": 2338707, "tid": 2379456, + "ts": 6197197836456.263, "dur": 1.437, + "args": { + "External id": 30497,"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": 2338707, "tid": 2379456, + "ts": 6197197836473.469, "dur": 1.311, + "args": { + "External id": 30498,"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": 2338707, "tid": 2379456, + "ts": 6197197836486.050, "dur": 0.797, + "args": { + "External id": 30499,"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": 2338707, "tid": 2379456, + "ts": 6197197836498.380, "dur": 1.113, + "args": { + "External id": 30500,"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": 2338707, "tid": 2379456, + "ts": 6197197836512.185, "dur": 0.700, + "args": { + "External id": 30501,"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": 2338707, "tid": 2379456, + "ts": 6197197836523.114, "dur": 1.071, + "args": { + "External id": 30502,"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": 2338707, "tid": 2379456, + "ts": 6197197836538.734, "dur": 2.433, + "args": { + "External id": 30503,"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": 2338707, "tid": 2379456, + "ts": 6197197836553.448, "dur": 0.800, + "args": { + "External id": 30504,"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": 2338707, "tid": 2379456, + "ts": 6197197836647.195, "dur": 2991.756, + "args": { + "External id": 30505,"Record function id": 0, "Ev Idx": 3368 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.14)", "pid": 2338707, "tid": 2379456, + "ts": 6197197836666.306, "dur": 1135.332, + "args": { + "External id": 30506,"Record function id": 0, "Ev Idx": 3369 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.14)", "pid": 2338707, "tid": 2379456, + "ts": 6197197836679.387, "dur": 359.569, + "args": { + "External id": 30507,"Record function id": 0, "Ev Idx": 3370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6197197836794.373, "dur": 4.911, + "args": { + "External id": 30508,"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": 2338707, "tid": 2379456, + "ts": 6197197836802.631, "dur": 0.850, + "args": { + "External id": 30509,"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": 2338707, "tid": 2379456, + "ts": 6197197836804.974, "dur": 0.889, + "args": { + "External id": 30510,"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": 2338707, "tid": 2379456, + "ts": 6197197836808.026, "dur": 0.874, + "args": { + "External id": 30511,"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": 2338707, "tid": 2379456, + "ts": 6197197836810.127, "dur": 0.843, + "args": { + "External id": 30512,"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": 2338707, "tid": 2379456, + "ts": 6197197836812.148, "dur": 0.830, + "args": { + "External id": 30513,"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": 2338707, "tid": 2379456, + "ts": 6197197836816.657, "dur": 2.211, + "args": { + "External id": 30514,"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": 2338707, "tid": 2379456, + "ts": 6197197836820.440, "dur": 2.707, + "args": { + "External id": 30515,"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": 2338707, "tid": 2379456, + "ts": 6197197836824.482, "dur": 1.100, + "args": { + "External id": 30516,"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": 2338707, "tid": 2379456, + "ts": 6197197836827.555, "dur": 0.633, + "args": { + "External id": 30517,"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": 2338707, "tid": 2379456, + "ts": 6197197836848.622, "dur": 159.641, + "args": { + "External id": 30518,"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": 2338707, "tid": 2379456, + "ts": 6197197836864.111, "dur": 139.277, + "args": { + "External id": 30519,"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": 2338707, "tid": 2379456, + "ts": 6197197836879.355, "dur": 14.661, + "args": { + "External id": 30520,"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": 2338707, "tid": 2379456, + "ts": 6197197836897.230, "dur": 77.236, + "args": { + "External id": 30521,"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": 2338707, "tid": 2379456, + "ts": 6197197836899.722, "dur": 74.398, + "args": { + "External id": 30522,"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": 2338707, "tid": 2379456, + "ts": 6197197836913.504, "dur": 6.506, + "args": { + "External id": 30523,"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": 2338707, "tid": 2379456, + "ts": 6197197836921.768, "dur": 51.512, + "args": { + "External id": 30524,"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": 2338707, "tid": 2379456, + "ts": 6197197837187.437, "dur": 601.439, + "args": { + "External id": 30525,"Record function id": 0, "Ev Idx": 3388 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.13)", "pid": 2338707, "tid": 2379456, + "ts": 6197197837205.216, "dur": 571.375, + "args": { + "External id": 30526,"Record function id": 0, "Ev Idx": 3389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197197837270.597, "dur": 6.290, + "args": { + "External id": 30527,"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": 2338707, "tid": 2379456, + "ts": 6197197837291.783, "dur": 34.041, + "args": { + "External id": 30528,"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": 2338707, "tid": 2379456, + "ts": 6197197837300.541, "dur": 1.696, + "args": { + "External id": 30529,"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": 2338707, "tid": 2379456, + "ts": 6197197837304.516, "dur": 0.390, + "args": { + "External id": 30530,"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": 2338707, "tid": 2379456, + "ts": 6197197837305.980, "dur": 2.653, + "args": { + "External id": 30531,"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": 2338707, "tid": 2379456, + "ts": 6197197837309.538, "dur": 1.892, + "args": { + "External id": 30532,"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": 2338707, "tid": 2379456, + "ts": 6197197837312.720, "dur": 0.469, + "args": { + "External id": 30533,"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": 2338707, "tid": 2379456, + "ts": 6197197837314.382, "dur": 0.340, + "args": { + "External id": 30534,"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": 2338707, "tid": 2379456, + "ts": 6197197837317.075, "dur": 0.376, + "args": { + "External id": 30535,"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": 2338707, "tid": 2379456, + "ts": 6197197837318.490, "dur": 0.277, + "args": { + "External id": 30536,"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": 2338707, "tid": 2379456, + "ts": 6197197837319.774, "dur": 0.419, + "args": { + "External id": 30537,"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": 2338707, "tid": 2379456, + "ts": 6197197837336.420, "dur": 48.623, + "args": { + "External id": 30538,"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": 2338707, "tid": 2379456, + "ts": 6197197837413.632, "dur": 107.724, + "args": { + "External id": 30539,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2379456, + "ts": 6197197837423.410, "dur": 2.784, + "args": { + "External id": 30540,"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": 2338707, "tid": 2379456, + "ts": 6197197837430.913, "dur": 12.647, + "args": { + "External id": 30541,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2379456, + "ts": 6197197837435.125, "dur": 7.997, + "args": { + "External id": 30542,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2379456, + "ts": 6197197837438.285, "dur": 3.462, + "args": { + "External id": 30543,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197197837450.047, "dur": 21.691, + "args": { + "External id": 30544,"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": 2338707, "tid": 2379456, + "ts": 6197197837451.378, "dur": 0.460, + "args": { + "External id": 30545,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197197837452.888, "dur": 0.430, + "args": { + "External id": 30546,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2379456, + "ts": 6197197837454.487, "dur": 0.385, + "args": { + "External id": 30547,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2379456, + "ts": 6197197837456.843, "dur": 0.289, + "args": { + "External id": 30548,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2379456, + "ts": 6197197837458.265, "dur": 0.417, + "args": { + "External id": 30549,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2379456, + "ts": 6197197837459.921, "dur": 0.911, + "args": { + "External id": 30550,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2379456, + "ts": 6197197837461.918, "dur": 0.295, + "args": { + "External id": 30551,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2379456, + "ts": 6197197837463.157, "dur": 2.335, + "args": { + "External id": 30552,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2379456, + "ts": 6197197837466.827, "dur": 0.236, + "args": { + "External id": 30553,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2379456, + "ts": 6197197837483.876, "dur": 30.171, + "args": { + "External id": 30554,"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": 2338707, "tid": 2379456, + "ts": 6197197837566.112, "dur": 112.105, + "args": { + "External id": 30555,"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": 2338707, "tid": 2379456, + "ts": 6197197837593.752, "dur": 80.859, + "args": { + "External id": 30556,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197197837603.309, "dur": 67.334, + "args": { + "External id": 30557,"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": 2338707, "tid": 2379456, + "ts": 6197197837697.640, "dur": 19.994, + "args": { + "External id": 30558,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197197837809.367, "dur": 1807.470, + "args": { + "External id": 30559,"Sequence number": 479796, "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": 2338707, "tid": 2379456, "ts": 6197197837809.367, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6197197837920.214, "dur": 117.229, + "args": { + "External id": 30560,"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": 2338707, "tid": 2379456, + "ts": 6197197838117.341, "dur": 41.997, + "args": { + "External id": 30561,"kernel_hash": "cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/u7/cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs.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": 2338707, "tid": 2379456, + "ts": 6197197838181.061, "dur": 59.259, + "args": { + "External id": 30562,"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": 2338707, "tid": 2379456, + "ts": 6197197838250.618, "dur": 33.385, + "args": { + "External id": 30563,"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": 2338707, "tid": 2379456, + "ts": 6197197838290.050, "dur": 32.571, + "args": { + "External id": 30564,"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": 2338707, "tid": 2379456, + "ts": 6197197838328.996, "dur": 27.940, + "args": { + "External id": 30565,"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": 2338707, "tid": 2379456, + "ts": 6197197838366.924, "dur": 29.971, + "args": { + "External id": 30566,"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": 2338707, "tid": 2379456, + "ts": 6197197838422.634, "dur": 24.300, + "args": { + "External id": 30567,"kernel_hash": "cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/wm/cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s.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": 2338707, "tid": 2379456, + "ts": 6197197838465.557, "dur": 28.729, + "args": { + "External id": 30568,"kernel_hash": "cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql", "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/qt/cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql.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": 2338707, "tid": 2379456, + "ts": 6197197838516.978, "dur": 18.886, + "args": { + "External id": 30569,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197197838549.651, "dur": 15.303, + "args": { + "External id": 30570,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197197838575.868, "dur": 39.216, + "args": { + "External id": 30571,"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": 2338707, "tid": 2379456, + "ts": 6197197838618.799, "dur": 34.523, + "args": { + "External id": 30572,"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": 2338707, "tid": 2379456, + "ts": 6197197838682.456, "dur": 273.694, + "args": { + "External id": 30573,"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": 2338707, "tid": 2379456, + "ts": 6197197838779.489, "dur": 6.943, + "args": { + "External id": 30574,"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": 2338707, "tid": 2379456, + "ts": 6197197838789.188, "dur": 2.842, + "args": { + "External id": 30575,"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": 2338707, "tid": 2379456, + "ts": 6197197838793.081, "dur": 4.513, + "args": { + "External id": 30576,"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": 2338707, "tid": 2379456, + "ts": 6197197838798.823, "dur": 2.170, + "args": { + "External id": 30577,"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": 2338707, "tid": 2379456, + "ts": 6197197838849.701, "dur": 5.330, + "args": { + "External id": 30578,"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": 2338707, "tid": 2379456, + "ts": 6197197838851.948, "dur": 2.873, + "args": { + "External id": 30579,"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": 2338707, "tid": 2379456, + "ts": 6197197838856.941, "dur": 34.772, + "args": { + "External id": 30580,"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": 2338707, "tid": 2379456, + "ts": 6197197838863.341, "dur": 1.728, + "args": { + "External id": 30581,"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": 2338707, "tid": 2379456, + "ts": 6197197838893.182, "dur": 2.308, + "args": { + "External id": 30582,"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": 2338707, "tid": 2379456, + "ts": 6197197838894.526, "dur": 0.888, + "args": { + "External id": 30583,"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": 2338707, "tid": 2379456, + "ts": 6197197838897.008, "dur": 16.718, + "args": { + "External id": 30584,"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": 2338707, "tid": 2379456, + "ts": 6197197838899.190, "dur": 0.656, + "args": { + "External id": 30585,"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": 2338707, "tid": 2379456, + "ts": 6197197838990.487, "dur": 29.991, + "args": { + "External id": 30586,"kernel_hash": "cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4", "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/yk/cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4.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": 2338707, "tid": 2379456, + "ts": 6197197839036.788, "dur": 58.375, + "args": { + "External id": 30587,"kernel_hash": "ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg", "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/eu/ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg.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": 2338707, "tid": 2379456, + "ts": 6197197839108.095, "dur": 54.785, + "args": { + "External id": 30588,"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": 2338707, "tid": 2379456, + "ts": 6197197839170.828, "dur": 41.138, + "args": { + "External id": 30589,"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": 2338707, "tid": 2379456, + "ts": 6197197839224.082, "dur": 20.843, + "args": { + "External id": 30590,"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": 2338707, "tid": 2379456, + "ts": 6197197839252.123, "dur": 48.276, + "args": { + "External id": 30591,"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": 2338707, "tid": 2379456, + "ts": 6197197839315.282, "dur": 35.109, + "args": { + "External id": 30592,"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": 2338707, "tid": 2379456, + "ts": 6197197839359.017, "dur": 33.982, + "args": { + "External id": 30593,"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": 2338707, "tid": 2379456, + "ts": 6197197839414.273, "dur": 30.905, + "args": { + "External id": 30594,"kernel_hash": "c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/6w/c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7.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": 2338707, "tid": 2379456, + "ts": 6197197839460.824, "dur": 25.459, + "args": { + "External id": 30595,"kernel_hash": "ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx", "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/kj/ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx.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": 2338707, "tid": 2379456, + "ts": 6197197839504.206, "dur": 17.022, + "args": { + "External id": 30596,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197197839535.156, "dur": 15.547, + "args": { + "External id": 30597,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197197839568.229, "dur": 16.493, + "args": { + "External id": 30598,"kernel_hash": "cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/eb/cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b.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": 2338707, "tid": 2379456, + "ts": 6197197839664.451, "dur": 15.661, + "args": { + "External id": 30599,"Record function id": 0, "Ev Idx": 3462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197839667.711, "dur": 11.362, + "args": { + "External id": 30600,"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": 2338707, "tid": 2379456, + "ts": 6197197839671.644, "dur": 6.394, + "args": { + "External id": 30601,"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": 2338707, "tid": 2379456, + "ts": 6197197839673.871, "dur": 4.037, + "args": { + "External id": 30602,"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": 2338707, "tid": 2379456, + "ts": 6197197839683.966, "dur": 5.769, + "args": { + "External id": 30603,"Record function id": 0, "Ev Idx": 3466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197839685.367, "dur": 3.909, + "args": { + "External id": 30604,"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": 2338707, "tid": 2379456, + "ts": 6197197839686.463, "dur": 2.085, + "args": { + "External id": 30605,"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": 2338707, "tid": 2379456, + "ts": 6197197839687.313, "dur": 1.166, + "args": { + "External id": 30606,"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": 2338707, "tid": 2379456, + "ts": 6197197839693.101, "dur": 4.646, + "args": { + "External id": 30607,"Record function id": 0, "Ev Idx": 3470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197839694.518, "dur": 2.766, + "args": { + "External id": 30608,"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": 2338707, "tid": 2379456, + "ts": 6197197839695.231, "dur": 1.594, + "args": { + "External id": 30609,"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": 2338707, "tid": 2379456, + "ts": 6197197839695.573, "dur": 1.187, + "args": { + "External id": 30610,"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": 2338707, "tid": 2379456, + "ts": 6197197839725.791, "dur": 9.694, + "args": { + "External id": 30611,"Record function id": 0, "Ev Idx": 3474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197839728.009, "dur": 6.802, + "args": { + "External id": 30612,"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": 2338707, "tid": 2379456, + "ts": 6197197839729.144, "dur": 4.867, + "args": { + "External id": 30613,"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": 2338707, "tid": 2379456, + "ts": 6197197839729.804, "dur": 4.004, + "args": { + "External id": 30614,"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": 2338707, "tid": 2379456, + "ts": 6197197839739.142, "dur": 4.028, + "args": { + "External id": 30615,"Record function id": 0, "Ev Idx": 3478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197839740.338, "dur": 2.387, + "args": { + "External id": 30616,"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": 2338707, "tid": 2379456, + "ts": 6197197839741.062, "dur": 1.221, + "args": { + "External id": 30617,"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": 2338707, "tid": 2379456, + "ts": 6197197839741.464, "dur": 0.754, + "args": { + "External id": 30618,"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": 2338707, "tid": 2379456, + "ts": 6197197839746.408, "dur": 4.509, + "args": { + "External id": 30619,"Record function id": 0, "Ev Idx": 3482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197839747.567, "dur": 2.931, + "args": { + "External id": 30620,"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": 2338707, "tid": 2379456, + "ts": 6197197839748.719, "dur": 1.256, + "args": { + "External id": 30621,"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": 2338707, "tid": 2379456, + "ts": 6197197839749.299, "dur": 0.579, + "args": { + "External id": 30622,"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": 2338707, "tid": 2379456, + "ts": 6197197839754.169, "dur": 4.071, + "args": { + "External id": 30623,"Record function id": 0, "Ev Idx": 3486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197839755.311, "dur": 2.495, + "args": { + "External id": 30624,"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": 2338707, "tid": 2379456, + "ts": 6197197839756.096, "dur": 1.283, + "args": { + "External id": 30625,"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": 2338707, "tid": 2379456, + "ts": 6197197839756.472, "dur": 0.846, + "args": { + "External id": 30626,"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": 2338707, "tid": 2379456, + "ts": 6197197839761.273, "dur": 4.155, + "args": { + "External id": 30627,"Record function id": 0, "Ev Idx": 3490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197839762.579, "dur": 2.441, + "args": { + "External id": 30628,"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": 2338707, "tid": 2379456, + "ts": 6197197839763.332, "dur": 1.270, + "args": { + "External id": 30629,"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": 2338707, "tid": 2379456, + "ts": 6197197839763.942, "dur": 0.571, + "args": { + "External id": 30630,"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": 2338707, "tid": 2379456, + "ts": 6197197839768.454, "dur": 3.799, + "args": { + "External id": 30631,"Record function id": 0, "Ev Idx": 3494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197839769.522, "dur": 2.317, + "args": { + "External id": 30632,"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": 2338707, "tid": 2379456, + "ts": 6197197839769.994, "dur": 1.417, + "args": { + "External id": 30633,"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": 2338707, "tid": 2379456, + "ts": 6197197839770.571, "dur": 0.740, + "args": { + "External id": 30634,"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": 2338707, "tid": 2379456, + "ts": 6197197839776.771, "dur": 62581.491, + "args": { + "External id": 30635,"Record function id": 0, "Sequence number": 479795, "Fwd thread id": 1, "Ev Idx": 3498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197197839778.095, "dur": 62570.965, + "args": { + "External id": 30636,"Sequence number": 479795, "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": 2338707, "tid": 2379456, "ts": 6197197839778.095, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.14)", "pid": 2338707, "tid": 2379456, + "ts": 6197197839809.133, "dur": 39.075, + "args": { + "External id": 30637,"Record function id": 0, "Ev Idx": 3500 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.14)", "pid": 2338707, "tid": 2379456, + "ts": 6197197839856.758, "dur": 63.333, + "args": { + "External id": 30638,"Record function id": 0, "Ev Idx": 3501 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.14)", "pid": 2338707, "tid": 2379456, + "ts": 6197197839925.351, "dur": 62415.716, + "args": { + "External id": 30639,"Record function id": 0, "Ev Idx": 3502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197197840021.723, "dur": 7.202, + "args": { + "External id": 30640,"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": 2338707, "tid": 2379456, + "ts": 6197197840039.063, "dur": 4.730, + "args": { + "External id": 30641,"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": 2338707, "tid": 2379456, + "ts": 6197197840094.898, "dur": 61373.469, + "args": { + "External id": 30642,"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": 2338707, "tid": 2379456, + "ts": 6197197840110.009, "dur": 61344.382, + "args": { + "External id": 30643,"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": 2338707, "tid": 2379456, + "ts": 6197197840208.131, "dur": 18.596, + "args": { + "External id": 30644,"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": 2338707, "tid": 2379456, + "ts": 6197197840247.422, "dur": 61160.290, + "args": { + "External id": 30645,"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": 2338707, "tid": 2379456, + "ts": 6197197840250.189, "dur": 61156.497, + "args": { + "External id": 30646,"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": 2338707, "tid": 2379456, + "ts": 6197197840254.640, "dur": 13.320, + "args": { + "External id": 30647,"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": 2338707, "tid": 2379456, + "ts": 6197197840270.122, "dur": 61131.594, + "args": { + "External id": 30648,"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": 2338707, "tid": 2379456, + "ts": 6197197901574.089, "dur": 11.768, + "args": { + "External id": 30649,"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": 2338707, "tid": 2379456, + "ts": 6197197901577.618, "dur": 7.832, + "args": { + "External id": 30650,"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": 2338707, "tid": 2379456, + "ts": 6197197901617.264, "dur": 397.377, + "args": { + "External id": 30651,"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": 2338707, "tid": 2379456, + "ts": 6197197901648.044, "dur": 361.236, + "args": { + "External id": 30652,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197197901659.705, "dur": 342.897, + "args": { + "External id": 30653,"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": 2338707, "tid": 2379456, + "ts": 6197197902037.261, "dur": 2.358, + "args": { + "External id": 30654,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2379456, + "ts": 6197197902134.374, "dur": 6.912, + "args": { + "External id": 30655,"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": 2338707, "tid": 2379456, + "ts": 6197197902187.085, "dur": 1.387, + "args": { + "External id": 30656,"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": 2338707, "tid": 2379456, + "ts": 6197197902203.736, "dur": 1.502, + "args": { + "External id": 30657,"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": 2338707, "tid": 2379456, + "ts": 6197197902216.645, "dur": 2.896, + "args": { + "External id": 30658,"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": 2338707, "tid": 2379456, + "ts": 6197197902231.058, "dur": 0.844, + "args": { + "External id": 30659,"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": 2338707, "tid": 2379456, + "ts": 6197197902242.312, "dur": 0.966, + "args": { + "External id": 30660,"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": 2338707, "tid": 2379456, + "ts": 6197197902253.213, "dur": 1.133, + "args": { + "External id": 30661,"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": 2338707, "tid": 2379456, + "ts": 6197197902264.683, "dur": 5.110, + "args": { + "External id": 30662,"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": 2338707, "tid": 2379456, + "ts": 6197197902278.782, "dur": 1.294, + "args": { + "External id": 30663,"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": 2338707, "tid": 2379456, + "ts": 6197197902374.028, "dur": 3029.049, + "args": { + "External id": 30664,"Record function id": 0, "Ev Idx": 3527 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.13)", "pid": 2338707, "tid": 2379456, + "ts": 6197197902394.267, "dur": 1107.110, + "args": { + "External id": 30665,"Record function id": 0, "Ev Idx": 3528 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.13)", "pid": 2338707, "tid": 2379456, + "ts": 6197197902409.392, "dur": 356.014, + "args": { + "External id": 30666,"Record function id": 0, "Ev Idx": 3529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6197197902501.890, "dur": 4.360, + "args": { + "External id": 30667,"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": 2338707, "tid": 2379456, + "ts": 6197197902509.911, "dur": 1.124, + "args": { + "External id": 30668,"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": 2338707, "tid": 2379456, + "ts": 6197197902512.727, "dur": 0.876, + "args": { + "External id": 30669,"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": 2338707, "tid": 2379456, + "ts": 6197197902515.335, "dur": 1.055, + "args": { + "External id": 30670,"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": 2338707, "tid": 2379456, + "ts": 6197197902517.688, "dur": 2.867, + "args": { + "External id": 30671,"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": 2338707, "tid": 2379456, + "ts": 6197197902521.750, "dur": 0.825, + "args": { + "External id": 30672,"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": 2338707, "tid": 2379456, + "ts": 6197197902524.155, "dur": 2.218, + "args": { + "External id": 30673,"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": 2338707, "tid": 2379456, + "ts": 6197197902527.669, "dur": 0.819, + "args": { + "External id": 30674,"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": 2338707, "tid": 2379456, + "ts": 6197197902532.222, "dur": 0.537, + "args": { + "External id": 30675,"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": 2338707, "tid": 2379456, + "ts": 6197197902534.345, "dur": 0.729, + "args": { + "External id": 30676,"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": 2338707, "tid": 2379456, + "ts": 6197197902552.111, "dur": 180.553, + "args": { + "External id": 30677,"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": 2338707, "tid": 2379456, + "ts": 6197197902568.023, "dur": 159.458, + "args": { + "External id": 30678,"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": 2338707, "tid": 2379456, + "ts": 6197197902593.219, "dur": 15.943, + "args": { + "External id": 30679,"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": 2338707, "tid": 2379456, + "ts": 6197197902612.862, "dur": 65.344, + "args": { + "External id": 30680,"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": 2338707, "tid": 2379456, + "ts": 6197197902615.492, "dur": 62.383, + "args": { + "External id": 30681,"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": 2338707, "tid": 2379456, + "ts": 6197197902619.640, "dur": 5.799, + "args": { + "External id": 30682,"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": 2338707, "tid": 2379456, + "ts": 6197197902627.005, "dur": 50.087, + "args": { + "External id": 30683,"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": 2338707, "tid": 2379456, + "ts": 6197197902858.163, "dur": 634.956, + "args": { + "External id": 30684,"Record function id": 0, "Ev Idx": 3547 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.12)", "pid": 2338707, "tid": 2379456, + "ts": 6197197902876.295, "dur": 601.796, + "args": { + "External id": 30685,"Record function id": 0, "Ev Idx": 3548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197197902939.061, "dur": 8.253, + "args": { + "External id": 30686,"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": 2338707, "tid": 2379456, + "ts": 6197197902962.248, "dur": 35.367, + "args": { + "External id": 30687,"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": 2338707, "tid": 2379456, + "ts": 6197197902967.478, "dur": 1.581, + "args": { + "External id": 30688,"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": 2338707, "tid": 2379456, + "ts": 6197197902971.238, "dur": 0.425, + "args": { + "External id": 30689,"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": 2338707, "tid": 2379456, + "ts": 6197197902973.032, "dur": 0.716, + "args": { + "External id": 30690,"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": 2338707, "tid": 2379456, + "ts": 6197197902974.750, "dur": 0.477, + "args": { + "External id": 30691,"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": 2338707, "tid": 2379456, + "ts": 6197197902976.989, "dur": 0.652, + "args": { + "External id": 30692,"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": 2338707, "tid": 2379456, + "ts": 6197197902979.431, "dur": 0.328, + "args": { + "External id": 30693,"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": 2338707, "tid": 2379456, + "ts": 6197197902980.738, "dur": 0.352, + "args": { + "External id": 30694,"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": 2338707, "tid": 2379456, + "ts": 6197197902987.340, "dur": 2.497, + "args": { + "External id": 30695,"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": 2338707, "tid": 2379456, + "ts": 6197197902991.578, "dur": 0.282, + "args": { + "External id": 30696,"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": 2338707, "tid": 2379456, + "ts": 6197197903011.501, "dur": 78.070, + "args": { + "External id": 30697,"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": 2338707, "tid": 2379456, + "ts": 6197197903124.532, "dur": 119.181, + "args": { + "External id": 30698,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2379456, + "ts": 6197197903136.950, "dur": 4.817, + "args": { + "External id": 30699,"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": 2338707, "tid": 2379456, + "ts": 6197197903146.819, "dur": 11.056, + "args": { + "External id": 30700,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2379456, + "ts": 6197197903151.341, "dur": 6.116, + "args": { + "External id": 30701,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2379456, + "ts": 6197197903155.056, "dur": 0.877, + "args": { + "External id": 30702,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197197903164.597, "dur": 25.109, + "args": { + "External id": 30703,"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": 2338707, "tid": 2379456, + "ts": 6197197903166.481, "dur": 0.422, + "args": { + "External id": 30704,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197197903167.871, "dur": 0.684, + "args": { + "External id": 30705,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2379456, + "ts": 6197197903170.379, "dur": 0.516, + "args": { + "External id": 30706,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2379456, + "ts": 6197197903172.363, "dur": 0.389, + "args": { + "External id": 30707,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2379456, + "ts": 6197197903173.678, "dur": 2.822, + "args": { + "External id": 30708,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2379456, + "ts": 6197197903178.284, "dur": 0.385, + "args": { + "External id": 30709,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2379456, + "ts": 6197197903180.222, "dur": 0.540, + "args": { + "External id": 30710,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2379456, + "ts": 6197197903181.655, "dur": 0.484, + "args": { + "External id": 30711,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2379456, + "ts": 6197197903183.555, "dur": 0.269, + "args": { + "External id": 30712,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2379456, + "ts": 6197197903200.066, "dur": 35.865, + "args": { + "External id": 30713,"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": 2338707, "tid": 2379456, + "ts": 6197197903293.168, "dur": 114.428, + "args": { + "External id": 30714,"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": 2338707, "tid": 2379456, + "ts": 6197197903319.720, "dur": 84.802, + "args": { + "External id": 30715,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197197903329.835, "dur": 70.368, + "args": { + "External id": 30716,"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": 2338707, "tid": 2379456, + "ts": 6197197903424.558, "dur": 5.057, + "args": { + "External id": 30717,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197197903509.552, "dur": 1870.238, + "args": { + "External id": 30718,"Sequence number": 479794, "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": 2338707, "tid": 2379456, "ts": 6197197903509.552, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6197197903619.315, "dur": 128.709, + "args": { + "External id": 30719,"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": 2338707, "tid": 2379456, + "ts": 6197197903793.217, "dur": 42.274, + "args": { + "External id": 30720,"kernel_hash": "cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/u7/cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs.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": 2338707, "tid": 2379456, + "ts": 6197197903876.357, "dur": 61.448, + "args": { + "External id": 30721,"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": 2338707, "tid": 2379456, + "ts": 6197197903947.214, "dur": 32.778, + "args": { + "External id": 30722,"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": 2338707, "tid": 2379456, + "ts": 6197197903998.619, "dur": 36.459, + "args": { + "External id": 30723,"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": 2338707, "tid": 2379456, + "ts": 6197197904042.715, "dur": 68.674, + "args": { + "External id": 30724,"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": 2338707, "tid": 2379456, + "ts": 6197197904123.155, "dur": 34.103, + "args": { + "External id": 30725,"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": 2338707, "tid": 2379456, + "ts": 6197197904181.639, "dur": 26.328, + "args": { + "External id": 30726,"kernel_hash": "cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/wm/cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s.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": 2338707, "tid": 2379456, + "ts": 6197197904228.336, "dur": 30.164, + "args": { + "External id": 30727,"kernel_hash": "cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql", "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/qt/cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql.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": 2338707, "tid": 2379456, + "ts": 6197197904282.145, "dur": 19.461, + "args": { + "External id": 30728,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197197904314.274, "dur": 13.627, + "args": { + "External id": 30729,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197197904336.802, "dur": 38.490, + "args": { + "External id": 30730,"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": 2338707, "tid": 2379456, + "ts": 6197197904379.173, "dur": 33.266, + "args": { + "External id": 30731,"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": 2338707, "tid": 2379456, + "ts": 6197197904445.572, "dur": 243.307, + "args": { + "External id": 30732,"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": 2338707, "tid": 2379456, + "ts": 6197197904526.348, "dur": 6.428, + "args": { + "External id": 30733,"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": 2338707, "tid": 2379456, + "ts": 6197197904534.846, "dur": 2.886, + "args": { + "External id": 30734,"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": 2338707, "tid": 2379456, + "ts": 6197197904539.312, "dur": 2.060, + "args": { + "External id": 30735,"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": 2338707, "tid": 2379456, + "ts": 6197197904542.876, "dur": 2.458, + "args": { + "External id": 30736,"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": 2338707, "tid": 2379456, + "ts": 6197197904589.265, "dur": 5.611, + "args": { + "External id": 30737,"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": 2338707, "tid": 2379456, + "ts": 6197197904591.663, "dur": 3.021, + "args": { + "External id": 30738,"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": 2338707, "tid": 2379456, + "ts": 6197197904596.474, "dur": 30.718, + "args": { + "External id": 30739,"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": 2338707, "tid": 2379456, + "ts": 6197197904601.880, "dur": 1.822, + "args": { + "External id": 30740,"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": 2338707, "tid": 2379456, + "ts": 6197197904628.924, "dur": 1.889, + "args": { + "External id": 30741,"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": 2338707, "tid": 2379456, + "ts": 6197197904630.074, "dur": 0.623, + "args": { + "External id": 30742,"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": 2338707, "tid": 2379456, + "ts": 6197197904631.792, "dur": 14.689, + "args": { + "External id": 30743,"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": 2338707, "tid": 2379456, + "ts": 6197197904633.645, "dur": 0.662, + "args": { + "External id": 30744,"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": 2338707, "tid": 2379456, + "ts": 6197197904744.710, "dur": 31.542, + "args": { + "External id": 30745,"kernel_hash": "cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4", "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/yk/cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4.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": 2338707, "tid": 2379456, + "ts": 6197197904793.489, "dur": 17.896, + "args": { + "External id": 30746,"kernel_hash": "ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg", "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/eu/ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg.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": 2338707, "tid": 2379456, + "ts": 6197197904820.202, "dur": 51.300, + "args": { + "External id": 30747,"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": 2338707, "tid": 2379456, + "ts": 6197197904880.716, "dur": 44.434, + "args": { + "External id": 30748,"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": 2338707, "tid": 2379456, + "ts": 6197197904934.463, "dur": 21.045, + "args": { + "External id": 30749,"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": 2338707, "tid": 2379456, + "ts": 6197197904961.818, "dur": 32.356, + "args": { + "External id": 30750,"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": 2338707, "tid": 2379456, + "ts": 6197197905002.084, "dur": 28.683, + "args": { + "External id": 30751,"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": 2338707, "tid": 2379456, + "ts": 6197197905038.256, "dur": 81.388, + "args": { + "External id": 30752,"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": 2338707, "tid": 2379456, + "ts": 6197197905160.181, "dur": 33.446, + "args": { + "External id": 30753,"kernel_hash": "c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/6w/c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7.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": 2338707, "tid": 2379456, + "ts": 6197197905212.084, "dur": 30.813, + "args": { + "External id": 30754,"kernel_hash": "ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx", "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/kj/ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx.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": 2338707, "tid": 2379456, + "ts": 6197197905258.347, "dur": 19.405, + "args": { + "External id": 30755,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197197905297.617, "dur": 15.904, + "args": { + "External id": 30756,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197197905326.454, "dur": 18.880, + "args": { + "External id": 30757,"kernel_hash": "cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/eb/cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b.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": 2338707, "tid": 2379456, + "ts": 6197197905428.689, "dur": 16.116, + "args": { + "External id": 30758,"Record function id": 0, "Ev Idx": 3621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197905432.125, "dur": 11.559, + "args": { + "External id": 30759,"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": 2338707, "tid": 2379456, + "ts": 6197197905436.567, "dur": 6.222, + "args": { + "External id": 30760,"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": 2338707, "tid": 2379456, + "ts": 6197197905438.603, "dur": 4.046, + "args": { + "External id": 30761,"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": 2338707, "tid": 2379456, + "ts": 6197197905448.830, "dur": 7.371, + "args": { + "External id": 30762,"Record function id": 0, "Ev Idx": 3625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197905450.188, "dur": 5.557, + "args": { + "External id": 30763,"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": 2338707, "tid": 2379456, + "ts": 6197197905450.851, "dur": 4.301, + "args": { + "External id": 30764,"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": 2338707, "tid": 2379456, + "ts": 6197197905451.598, "dur": 3.495, + "args": { + "External id": 30765,"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": 2338707, "tid": 2379456, + "ts": 6197197905459.645, "dur": 3.846, + "args": { + "External id": 30766,"Record function id": 0, "Ev Idx": 3629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197905460.664, "dur": 2.409, + "args": { + "External id": 30767,"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": 2338707, "tid": 2379456, + "ts": 6197197905461.203, "dur": 1.446, + "args": { + "External id": 30768,"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": 2338707, "tid": 2379456, + "ts": 6197197905461.596, "dur": 0.989, + "args": { + "External id": 30769,"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": 2338707, "tid": 2379456, + "ts": 6197197905466.679, "dur": 4.178, + "args": { + "External id": 30770,"Record function id": 0, "Ev Idx": 3633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197905468.267, "dur": 2.160, + "args": { + "External id": 30771,"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": 2338707, "tid": 2379456, + "ts": 6197197905468.851, "dur": 1.160, + "args": { + "External id": 30772,"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": 2338707, "tid": 2379456, + "ts": 6197197905469.296, "dur": 0.650, + "args": { + "External id": 30773,"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": 2338707, "tid": 2379456, + "ts": 6197197905474.016, "dur": 4.170, + "args": { + "External id": 30774,"Record function id": 0, "Ev Idx": 3637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197905475.272, "dur": 2.506, + "args": { + "External id": 30775,"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": 2338707, "tid": 2379456, + "ts": 6197197905475.965, "dur": 1.259, + "args": { + "External id": 30776,"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": 2338707, "tid": 2379456, + "ts": 6197197905476.451, "dur": 0.708, + "args": { + "External id": 30777,"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": 2338707, "tid": 2379456, + "ts": 6197197905481.633, "dur": 4.026, + "args": { + "External id": 30778,"Record function id": 0, "Ev Idx": 3641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197905482.841, "dur": 2.382, + "args": { + "External id": 30779,"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": 2338707, "tid": 2379456, + "ts": 6197197905483.313, "dur": 1.369, + "args": { + "External id": 30780,"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": 2338707, "tid": 2379456, + "ts": 6197197905483.948, "dur": 0.635, + "args": { + "External id": 30781,"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": 2338707, "tid": 2379456, + "ts": 6197197905488.988, "dur": 3.825, + "args": { + "External id": 30782,"Record function id": 0, "Ev Idx": 3645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197905490.243, "dur": 2.160, + "args": { + "External id": 30783,"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": 2338707, "tid": 2379456, + "ts": 6197197905490.891, "dur": 1.116, + "args": { + "External id": 30784,"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": 2338707, "tid": 2379456, + "ts": 6197197905491.174, "dur": 0.758, + "args": { + "External id": 30785,"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": 2338707, "tid": 2379456, + "ts": 6197197905496.538, "dur": 3.621, + "args": { + "External id": 30786,"Record function id": 0, "Ev Idx": 3649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197905497.877, "dur": 1.827, + "args": { + "External id": 30787,"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": 2338707, "tid": 2379456, + "ts": 6197197905498.343, "dur": 0.954, + "args": { + "External id": 30788,"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": 2338707, "tid": 2379456, + "ts": 6197197905498.661, "dur": 0.531, + "args": { + "External id": 30789,"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": 2338707, "tid": 2379456, + "ts": 6197197905503.674, "dur": 5.793, + "args": { + "External id": 30790,"Record function id": 0, "Ev Idx": 3653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197905504.544, "dur": 4.518, + "args": { + "External id": 30791,"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": 2338707, "tid": 2379456, + "ts": 6197197905505.017, "dur": 3.517, + "args": { + "External id": 30792,"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": 2338707, "tid": 2379456, + "ts": 6197197905505.485, "dur": 2.941, + "args": { + "External id": 30793,"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": 2338707, "tid": 2379456, + "ts": 6197197905514.047, "dur": 65603.377, + "args": { + "External id": 30794,"Record function id": 0, "Sequence number": 479793, "Fwd thread id": 1, "Ev Idx": 3657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197197905515.500, "dur": 65592.673, + "args": { + "External id": 30795,"Sequence number": 479793, "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": 2338707, "tid": 2379456, "ts": 6197197905515.500, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.13)", "pid": 2338707, "tid": 2379456, + "ts": 6197197905545.659, "dur": 39.101, + "args": { + "External id": 30796,"Record function id": 0, "Ev Idx": 3659 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.13)", "pid": 2338707, "tid": 2379456, + "ts": 6197197905592.406, "dur": 64.079, + "args": { + "External id": 30797,"Record function id": 0, "Ev Idx": 3660 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.13)", "pid": 2338707, "tid": 2379456, + "ts": 6197197905662.259, "dur": 65436.220, + "args": { + "External id": 30798,"Record function id": 0, "Ev Idx": 3661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197197905770.096, "dur": 7.741, + "args": { + "External id": 30799,"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": 2338707, "tid": 2379456, + "ts": 6197197905789.056, "dur": 4.877, + "args": { + "External id": 30800,"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": 2338707, "tid": 2379456, + "ts": 6197197905809.546, "dur": 64377.645, + "args": { + "External id": 30801,"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": 2338707, "tid": 2379456, + "ts": 6197197905823.917, "dur": 64350.110, + "args": { + "External id": 30802,"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": 2338707, "tid": 2379456, + "ts": 6197197905924.328, "dur": 17.467, + "args": { + "External id": 30803,"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": 2338707, "tid": 2379456, + "ts": 6197197905965.842, "dur": 64160.504, + "args": { + "External id": 30804,"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": 2338707, "tid": 2379456, + "ts": 6197197905968.608, "dur": 64156.751, + "args": { + "External id": 30805,"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": 2338707, "tid": 2379456, + "ts": 6197197905973.135, "dur": 8.955, + "args": { + "External id": 30806,"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": 2338707, "tid": 2379456, + "ts": 6197197905984.408, "dur": 64135.889, + "args": { + "External id": 30807,"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": 2338707, "tid": 2379456, + "ts": 6197197970293.835, "dur": 12.533, + "args": { + "External id": 30808,"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": 2338707, "tid": 2379456, + "ts": 6197197970297.302, "dur": 8.640, + "args": { + "External id": 30809,"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": 2338707, "tid": 2379456, + "ts": 6197197970336.051, "dur": 432.783, + "args": { + "External id": 30810,"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": 2338707, "tid": 2379456, + "ts": 6197197970369.646, "dur": 393.763, + "args": { + "External id": 30811,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197197970381.775, "dur": 375.105, + "args": { + "External id": 30812,"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": 2338707, "tid": 2379456, + "ts": 6197197970791.891, "dur": 2.320, + "args": { + "External id": 30813,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2379456, + "ts": 6197197970858.239, "dur": 6.319, + "args": { + "External id": 30814,"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": 2338707, "tid": 2379456, + "ts": 6197197970909.589, "dur": 1.139, + "args": { + "External id": 30815,"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": 2338707, "tid": 2379456, + "ts": 6197197970927.526, "dur": 1.138, + "args": { + "External id": 30816,"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": 2338707, "tid": 2379456, + "ts": 6197197970939.757, "dur": 1.182, + "args": { + "External id": 30817,"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": 2338707, "tid": 2379456, + "ts": 6197197970952.362, "dur": 1.163, + "args": { + "External id": 30818,"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": 2338707, "tid": 2379456, + "ts": 6197197970964.468, "dur": 1.195, + "args": { + "External id": 30819,"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": 2338707, "tid": 2379456, + "ts": 6197197970979.222, "dur": 1.428, + "args": { + "External id": 30820,"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": 2338707, "tid": 2379456, + "ts": 6197197970991.906, "dur": 2.726, + "args": { + "External id": 30821,"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": 2338707, "tid": 2379456, + "ts": 6197197971004.565, "dur": 0.960, + "args": { + "External id": 30822,"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": 2338707, "tid": 2379456, + "ts": 6197197971133.741, "dur": 3032.569, + "args": { + "External id": 30823,"Record function id": 0, "Ev Idx": 3686 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.12)", "pid": 2338707, "tid": 2379456, + "ts": 6197197971154.740, "dur": 1139.853, + "args": { + "External id": 30824,"Record function id": 0, "Ev Idx": 3687 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.12)", "pid": 2338707, "tid": 2379456, + "ts": 6197197971168.964, "dur": 350.824, + "args": { + "External id": 30825,"Record function id": 0, "Ev Idx": 3688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6197197971266.435, "dur": 4.779, + "args": { + "External id": 30826,"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": 2338707, "tid": 2379456, + "ts": 6197197971274.751, "dur": 3.809, + "args": { + "External id": 30827,"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": 2338707, "tid": 2379456, + "ts": 6197197971280.287, "dur": 1.175, + "args": { + "External id": 30828,"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": 2338707, "tid": 2379456, + "ts": 6197197971283.646, "dur": 0.751, + "args": { + "External id": 30829,"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": 2338707, "tid": 2379456, + "ts": 6197197971285.707, "dur": 1.036, + "args": { + "External id": 30830,"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": 2338707, "tid": 2379456, + "ts": 6197197971288.025, "dur": 0.877, + "args": { + "External id": 30831,"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": 2338707, "tid": 2379456, + "ts": 6197197971290.362, "dur": 2.623, + "args": { + "External id": 30832,"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": 2338707, "tid": 2379456, + "ts": 6197197971294.831, "dur": 0.957, + "args": { + "External id": 30833,"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": 2338707, "tid": 2379456, + "ts": 6197197971297.347, "dur": 0.797, + "args": { + "External id": 30834,"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": 2338707, "tid": 2379456, + "ts": 6197197971299.649, "dur": 2.703, + "args": { + "External id": 30835,"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": 2338707, "tid": 2379456, + "ts": 6197197971319.110, "dur": 169.692, + "args": { + "External id": 30836,"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": 2338707, "tid": 2379456, + "ts": 6197197971344.246, "dur": 139.726, + "args": { + "External id": 30837,"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": 2338707, "tid": 2379456, + "ts": 6197197971368.374, "dur": 14.549, + "args": { + "External id": 30838,"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": 2338707, "tid": 2379456, + "ts": 6197197971386.858, "dur": 65.586, + "args": { + "External id": 30839,"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": 2338707, "tid": 2379456, + "ts": 6197197971389.698, "dur": 62.424, + "args": { + "External id": 30840,"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": 2338707, "tid": 2379456, + "ts": 6197197971394.205, "dur": 5.416, + "args": { + "External id": 30841,"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": 2338707, "tid": 2379456, + "ts": 6197197971401.702, "dur": 49.694, + "args": { + "External id": 30842,"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": 2338707, "tid": 2379456, + "ts": 6197197971611.811, "dur": 674.406, + "args": { + "External id": 30843,"Record function id": 0, "Ev Idx": 3706 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.11)", "pid": 2338707, "tid": 2379456, + "ts": 6197197971628.665, "dur": 644.800, + "args": { + "External id": 30844,"Record function id": 0, "Ev Idx": 3707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197197971694.944, "dur": 4.515, + "args": { + "External id": 30845,"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": 2338707, "tid": 2379456, + "ts": 6197197971733.831, "dur": 31.779, + "args": { + "External id": 30846,"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": 2338707, "tid": 2379456, + "ts": 6197197971739.223, "dur": 1.720, + "args": { + "External id": 30847,"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": 2338707, "tid": 2379456, + "ts": 6197197971742.614, "dur": 0.816, + "args": { + "External id": 30848,"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": 2338707, "tid": 2379456, + "ts": 6197197971745.085, "dur": 0.566, + "args": { + "External id": 30849,"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": 2338707, "tid": 2379456, + "ts": 6197197971747.479, "dur": 0.346, + "args": { + "External id": 30850,"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": 2338707, "tid": 2379456, + "ts": 6197197971748.983, "dur": 2.489, + "args": { + "External id": 30851,"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": 2338707, "tid": 2379456, + "ts": 6197197971753.006, "dur": 0.424, + "args": { + "External id": 30852,"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": 2338707, "tid": 2379456, + "ts": 6197197971754.896, "dur": 0.541, + "args": { + "External id": 30853,"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": 2338707, "tid": 2379456, + "ts": 6197197971756.563, "dur": 0.418, + "args": { + "External id": 30854,"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": 2338707, "tid": 2379456, + "ts": 6197197971759.003, "dur": 0.344, + "args": { + "External id": 30855,"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": 2338707, "tid": 2379456, + "ts": 6197197971776.104, "dur": 55.606, + "args": { + "External id": 30856,"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": 2338707, "tid": 2379456, + "ts": 6197197971870.215, "dur": 115.830, + "args": { + "External id": 30857,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2379456, + "ts": 6197197971881.243, "dur": 3.995, + "args": { + "External id": 30858,"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": 2338707, "tid": 2379456, + "ts": 6197197971890.444, "dur": 10.321, + "args": { + "External id": 30859,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2379456, + "ts": 6197197971894.747, "dur": 5.574, + "args": { + "External id": 30860,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2379456, + "ts": 6197197971898.549, "dur": 0.492, + "args": { + "External id": 30861,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197197971907.527, "dur": 28.751, + "args": { + "External id": 30862,"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": 2338707, "tid": 2379456, + "ts": 6197197971909.334, "dur": 0.538, + "args": { + "External id": 30863,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197197971911.508, "dur": 2.444, + "args": { + "External id": 30864,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2379456, + "ts": 6197197971915.344, "dur": 0.602, + "args": { + "External id": 30865,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2379456, + "ts": 6197197971916.925, "dur": 0.439, + "args": { + "External id": 30866,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2379456, + "ts": 6197197971919.116, "dur": 0.425, + "args": { + "External id": 30867,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2379456, + "ts": 6197197971921.404, "dur": 0.312, + "args": { + "External id": 30868,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2379456, + "ts": 6197197971922.790, "dur": 0.428, + "args": { + "External id": 30869,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2379456, + "ts": 6197197971928.657, "dur": 0.374, + "args": { + "External id": 30870,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2379456, + "ts": 6197197971931.101, "dur": 0.284, + "args": { + "External id": 30871,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2379456, + "ts": 6197197971946.407, "dur": 30.357, + "args": { + "External id": 30872,"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": 2338707, "tid": 2379456, + "ts": 6197197972034.051, "dur": 161.912, + "args": { + "External id": 30873,"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": 2338707, "tid": 2379456, + "ts": 6197197972098.805, "dur": 93.161, + "args": { + "External id": 30874,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197197972111.018, "dur": 76.781, + "args": { + "External id": 30875,"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": 2338707, "tid": 2379456, + "ts": 6197197972215.006, "dur": 1.820, + "args": { + "External id": 30876,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197197972303.198, "dur": 1840.750, + "args": { + "External id": 30877,"Sequence number": 479792, "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": 2338707, "tid": 2379456, "ts": 6197197972303.198, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6197197972415.313, "dur": 107.788, + "args": { + "External id": 30878,"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": 2338707, "tid": 2379456, + "ts": 6197197972562.574, "dur": 43.132, + "args": { + "External id": 30879,"kernel_hash": "cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/u7/cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs.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": 2338707, "tid": 2379456, + "ts": 6197197972625.435, "dur": 51.871, + "args": { + "External id": 30880,"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": 2338707, "tid": 2379456, + "ts": 6197197972687.239, "dur": 52.581, + "args": { + "External id": 30881,"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": 2338707, "tid": 2379456, + "ts": 6197197972749.135, "dur": 37.267, + "args": { + "External id": 30882,"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": 2338707, "tid": 2379456, + "ts": 6197197972793.604, "dur": 28.153, + "args": { + "External id": 30883,"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": 2338707, "tid": 2379456, + "ts": 6197197972831.235, "dur": 35.804, + "args": { + "External id": 30884,"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": 2338707, "tid": 2379456, + "ts": 6197197972892.270, "dur": 29.324, + "args": { + "External id": 30885,"kernel_hash": "cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/wm/cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s.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": 2338707, "tid": 2379456, + "ts": 6197197972939.776, "dur": 31.092, + "args": { + "External id": 30886,"kernel_hash": "cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql", "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/qt/cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql.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": 2338707, "tid": 2379456, + "ts": 6197197972992.950, "dur": 22.528, + "args": { + "External id": 30887,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197197973029.370, "dur": 17.714, + "args": { + "External id": 30888,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197197973108.150, "dur": 47.276, + "args": { + "External id": 30889,"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": 2338707, "tid": 2379456, + "ts": 6197197973163.746, "dur": 34.965, + "args": { + "External id": 30890,"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": 2338707, "tid": 2379456, + "ts": 6197197973236.328, "dur": 256.428, + "args": { + "External id": 30891,"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": 2338707, "tid": 2379456, + "ts": 6197197973320.321, "dur": 6.711, + "args": { + "External id": 30892,"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": 2338707, "tid": 2379456, + "ts": 6197197973329.297, "dur": 3.534, + "args": { + "External id": 30893,"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": 2338707, "tid": 2379456, + "ts": 6197197973334.144, "dur": 5.533, + "args": { + "External id": 30894,"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": 2338707, "tid": 2379456, + "ts": 6197197973340.906, "dur": 4.120, + "args": { + "External id": 30895,"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": 2338707, "tid": 2379456, + "ts": 6197197973388.488, "dur": 5.108, + "args": { + "External id": 30896,"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": 2338707, "tid": 2379456, + "ts": 6197197973390.517, "dur": 2.898, + "args": { + "External id": 30897,"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": 2338707, "tid": 2379456, + "ts": 6197197973395.359, "dur": 31.280, + "args": { + "External id": 30898,"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": 2338707, "tid": 2379456, + "ts": 6197197973401.284, "dur": 1.855, + "args": { + "External id": 30899,"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": 2338707, "tid": 2379456, + "ts": 6197197973428.138, "dur": 1.890, + "args": { + "External id": 30900,"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": 2338707, "tid": 2379456, + "ts": 6197197973429.149, "dur": 0.784, + "args": { + "External id": 30901,"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": 2338707, "tid": 2379456, + "ts": 6197197973431.302, "dur": 15.309, + "args": { + "External id": 30902,"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": 2338707, "tid": 2379456, + "ts": 6197197973433.573, "dur": 0.602, + "args": { + "External id": 30903,"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": 2338707, "tid": 2379456, + "ts": 6197197973528.944, "dur": 30.662, + "args": { + "External id": 30904,"kernel_hash": "cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4", "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/yk/cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4.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": 2338707, "tid": 2379456, + "ts": 6197197973575.851, "dur": 17.309, + "args": { + "External id": 30905,"kernel_hash": "ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg", "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/eu/ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg.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": 2338707, "tid": 2379456, + "ts": 6197197973601.564, "dur": 39.914, + "args": { + "External id": 30906,"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": 2338707, "tid": 2379456, + "ts": 6197197973648.614, "dur": 37.296, + "args": { + "External id": 30907,"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": 2338707, "tid": 2379456, + "ts": 6197197973695.285, "dur": 39.436, + "args": { + "External id": 30908,"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": 2338707, "tid": 2379456, + "ts": 6197197973745.982, "dur": 34.908, + "args": { + "External id": 30909,"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": 2338707, "tid": 2379456, + "ts": 6197197973802.580, "dur": 40.688, + "args": { + "External id": 30910,"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": 2338707, "tid": 2379456, + "ts": 6197197973855.875, "dur": 36.686, + "args": { + "External id": 30911,"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": 2338707, "tid": 2379456, + "ts": 6197197973914.059, "dur": 27.321, + "args": { + "External id": 30912,"kernel_hash": "c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/6w/c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7.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": 2338707, "tid": 2379456, + "ts": 6197197973957.527, "dur": 24.670, + "args": { + "External id": 30913,"kernel_hash": "ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx", "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/kj/ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx.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": 2338707, "tid": 2379456, + "ts": 6197197973999.102, "dur": 17.268, + "args": { + "External id": 30914,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197197974030.069, "dur": 13.706, + "args": { + "External id": 30915,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197197974089.803, "dur": 19.934, + "args": { + "External id": 30916,"kernel_hash": "cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/eb/cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b.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": 2338707, "tid": 2379456, + "ts": 6197197974187.893, "dur": 15.170, + "args": { + "External id": 30917,"Record function id": 0, "Ev Idx": 3780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197974191.069, "dur": 10.978, + "args": { + "External id": 30918,"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": 2338707, "tid": 2379456, + "ts": 6197197974195.144, "dur": 5.947, + "args": { + "External id": 30919,"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": 2338707, "tid": 2379456, + "ts": 6197197974196.954, "dur": 4.024, + "args": { + "External id": 30920,"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": 2338707, "tid": 2379456, + "ts": 6197197974207.132, "dur": 5.238, + "args": { + "External id": 30921,"Record function id": 0, "Ev Idx": 3784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197974208.456, "dur": 3.427, + "args": { + "External id": 30922,"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": 2338707, "tid": 2379456, + "ts": 6197197974209.265, "dur": 2.066, + "args": { + "External id": 30923,"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": 2338707, "tid": 2379456, + "ts": 6197197974210.140, "dur": 1.077, + "args": { + "External id": 30924,"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": 2338707, "tid": 2379456, + "ts": 6197197974215.720, "dur": 4.146, + "args": { + "External id": 30925,"Record function id": 0, "Ev Idx": 3788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197974216.741, "dur": 2.713, + "args": { + "External id": 30926,"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": 2338707, "tid": 2379456, + "ts": 6197197974217.406, "dur": 1.614, + "args": { + "External id": 30927,"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": 2338707, "tid": 2379456, + "ts": 6197197974217.793, "dur": 1.160, + "args": { + "External id": 30928,"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": 2338707, "tid": 2379456, + "ts": 6197197974223.105, "dur": 4.886, + "args": { + "External id": 30929,"Record function id": 0, "Ev Idx": 3792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197974224.651, "dur": 2.894, + "args": { + "External id": 30930,"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": 2338707, "tid": 2379456, + "ts": 6197197974225.594, "dur": 1.259, + "args": { + "External id": 30931,"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": 2338707, "tid": 2379456, + "ts": 6197197974226.096, "dur": 0.690, + "args": { + "External id": 30932,"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": 2338707, "tid": 2379456, + "ts": 6197197974231.147, "dur": 4.203, + "args": { + "External id": 30933,"Record function id": 0, "Ev Idx": 3796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197974232.336, "dur": 2.595, + "args": { + "External id": 30934,"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": 2338707, "tid": 2379456, + "ts": 6197197974232.978, "dur": 1.508, + "args": { + "External id": 30935,"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": 2338707, "tid": 2379456, + "ts": 6197197974233.644, "dur": 0.771, + "args": { + "External id": 30936,"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": 2338707, "tid": 2379456, + "ts": 6197197974238.562, "dur": 6.265, + "args": { + "External id": 30937,"Record function id": 0, "Ev Idx": 3800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197974239.854, "dur": 4.510, + "args": { + "External id": 30938,"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": 2338707, "tid": 2379456, + "ts": 6197197974240.368, "dur": 3.248, + "args": { + "External id": 30939,"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": 2338707, "tid": 2379456, + "ts": 6197197974240.887, "dur": 2.634, + "args": { + "External id": 30940,"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": 2338707, "tid": 2379456, + "ts": 6197197974248.120, "dur": 3.716, + "args": { + "External id": 30941,"Record function id": 0, "Ev Idx": 3804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197974249.306, "dur": 2.091, + "args": { + "External id": 30942,"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": 2338707, "tid": 2379456, + "ts": 6197197974249.731, "dur": 1.225, + "args": { + "External id": 30943,"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": 2338707, "tid": 2379456, + "ts": 6197197974250.009, "dur": 0.853, + "args": { + "External id": 30944,"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": 2338707, "tid": 2379456, + "ts": 6197197974255.127, "dur": 4.337, + "args": { + "External id": 30945,"Record function id": 0, "Ev Idx": 3808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197974256.411, "dur": 2.613, + "args": { + "External id": 30946,"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": 2338707, "tid": 2379456, + "ts": 6197197974256.866, "dur": 1.582, + "args": { + "External id": 30947,"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": 2338707, "tid": 2379456, + "ts": 6197197974257.460, "dur": 0.879, + "args": { + "External id": 30948,"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": 2338707, "tid": 2379456, + "ts": 6197197974262.735, "dur": 4.238, + "args": { + "External id": 30949,"Record function id": 0, "Ev Idx": 3812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197197974264.089, "dur": 2.441, + "args": { + "External id": 30950,"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": 2338707, "tid": 2379456, + "ts": 6197197974264.516, "dur": 1.587, + "args": { + "External id": 30951,"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": 2338707, "tid": 2379456, + "ts": 6197197974265.023, "dur": 0.969, + "args": { + "External id": 30952,"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": 2338707, "tid": 2379456, + "ts": 6197197974270.881, "dur": 63372.735, + "args": { + "External id": 30953,"Record function id": 0, "Sequence number": 479791, "Fwd thread id": 1, "Ev Idx": 3816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197197974272.066, "dur": 63362.570, + "args": { + "External id": 30954,"Sequence number": 479791, "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": 2338707, "tid": 2379456, "ts": 6197197974272.066, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.12)", "pid": 2338707, "tid": 2379456, + "ts": 6197197974300.166, "dur": 38.171, + "args": { + "External id": 30955,"Record function id": 0, "Ev Idx": 3818 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.12)", "pid": 2338707, "tid": 2379456, + "ts": 6197197974345.589, "dur": 64.150, + "args": { + "External id": 30956,"Record function id": 0, "Ev Idx": 3819 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.12)", "pid": 2338707, "tid": 2379456, + "ts": 6197197974415.954, "dur": 63211.439, + "args": { + "External id": 30957,"Record function id": 0, "Ev Idx": 3820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197197974500.993, "dur": 6.760, + "args": { + "External id": 30958,"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": 2338707, "tid": 2379456, + "ts": 6197197974520.867, "dur": 4.656, + "args": { + "External id": 30959,"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": 2338707, "tid": 2379456, + "ts": 6197197974539.952, "dur": 62223.601, + "args": { + "External id": 30960,"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": 2338707, "tid": 2379456, + "ts": 6197197974554.240, "dur": 62196.201, + "args": { + "External id": 30961,"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": 2338707, "tid": 2379456, + "ts": 6197197974652.848, "dur": 17.227, + "args": { + "External id": 30962,"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": 2338707, "tid": 2379456, + "ts": 6197197974693.778, "dur": 62000.175, + "args": { + "External id": 30963,"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": 2338707, "tid": 2379456, + "ts": 6197197974696.580, "dur": 61996.346, + "args": { + "External id": 30964,"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": 2338707, "tid": 2379456, + "ts": 6197197974720.923, "dur": 13.448, + "args": { + "External id": 30965,"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": 2338707, "tid": 2379456, + "ts": 6197197974737.005, "dur": 61951.110, + "args": { + "External id": 30966,"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": 2338707, "tid": 2379456, + "ts": 6197198036868.679, "dur": 12.095, + "args": { + "External id": 30967,"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": 2338707, "tid": 2379456, + "ts": 6197198036871.961, "dur": 8.398, + "args": { + "External id": 30968,"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": 2338707, "tid": 2379456, + "ts": 6197198036912.477, "dur": 416.332, + "args": { + "External id": 30969,"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": 2338707, "tid": 2379456, + "ts": 6197198036942.031, "dur": 380.810, + "args": { + "External id": 30970,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197198036954.837, "dur": 361.567, + "args": { + "External id": 30971,"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": 2338707, "tid": 2379456, + "ts": 6197198037352.909, "dur": 2.255, + "args": { + "External id": 30972,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2379456, + "ts": 6197198037420.240, "dur": 6.800, + "args": { + "External id": 30973,"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": 2338707, "tid": 2379456, + "ts": 6197198037474.406, "dur": 1.340, + "args": { + "External id": 30974,"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": 2338707, "tid": 2379456, + "ts": 6197198037491.042, "dur": 0.977, + "args": { + "External id": 30975,"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": 2338707, "tid": 2379456, + "ts": 6197198037502.851, "dur": 0.969, + "args": { + "External id": 30976,"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": 2338707, "tid": 2379456, + "ts": 6197198037514.778, "dur": 1.258, + "args": { + "External id": 30977,"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": 2338707, "tid": 2379456, + "ts": 6197198037529.254, "dur": 1.209, + "args": { + "External id": 30978,"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": 2338707, "tid": 2379456, + "ts": 6197198037540.171, "dur": 1.171, + "args": { + "External id": 30979,"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": 2338707, "tid": 2379456, + "ts": 6197198037551.588, "dur": 2.845, + "args": { + "External id": 30980,"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": 2338707, "tid": 2379456, + "ts": 6197198037563.829, "dur": 1.115, + "args": { + "External id": 30981,"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": 2338707, "tid": 2379456, + "ts": 6197198037658.884, "dur": 2975.873, + "args": { + "External id": 30982,"Record function id": 0, "Ev Idx": 3845 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.11)", "pid": 2338707, "tid": 2379456, + "ts": 6197198037679.971, "dur": 1124.234, + "args": { + "External id": 30983,"Record function id": 0, "Ev Idx": 3846 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.11)", "pid": 2338707, "tid": 2379456, + "ts": 6197198037694.864, "dur": 353.003, + "args": { + "External id": 30984,"Record function id": 0, "Ev Idx": 3847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6197198037807.764, "dur": 5.187, + "args": { + "External id": 30985,"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": 2338707, "tid": 2379456, + "ts": 6197198037816.681, "dur": 1.317, + "args": { + "External id": 30986,"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": 2338707, "tid": 2379456, + "ts": 6197198037819.614, "dur": 0.956, + "args": { + "External id": 30987,"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": 2338707, "tid": 2379456, + "ts": 6197198037822.794, "dur": 0.737, + "args": { + "External id": 30988,"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": 2338707, "tid": 2379456, + "ts": 6197198037824.998, "dur": 0.950, + "args": { + "External id": 30989,"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": 2338707, "tid": 2379456, + "ts": 6197198037827.251, "dur": 0.736, + "args": { + "External id": 30990,"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": 2338707, "tid": 2379456, + "ts": 6197198037829.805, "dur": 2.346, + "args": { + "External id": 30991,"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": 2338707, "tid": 2379456, + "ts": 6197198037833.741, "dur": 2.581, + "args": { + "External id": 30992,"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": 2338707, "tid": 2379456, + "ts": 6197198037837.490, "dur": 0.796, + "args": { + "External id": 30993,"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": 2338707, "tid": 2379456, + "ts": 6197198037839.853, "dur": 0.739, + "args": { + "External id": 30994,"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": 2338707, "tid": 2379456, + "ts": 6197198037858.264, "dur": 157.810, + "args": { + "External id": 30995,"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": 2338707, "tid": 2379456, + "ts": 6197198037874.560, "dur": 137.099, + "args": { + "External id": 30996,"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": 2338707, "tid": 2379456, + "ts": 6197198037899.682, "dur": 13.491, + "args": { + "External id": 30997,"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": 2338707, "tid": 2379456, + "ts": 6197198037916.951, "dur": 66.119, + "args": { + "External id": 30998,"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": 2338707, "tid": 2379456, + "ts": 6197198037919.751, "dur": 63.007, + "args": { + "External id": 30999,"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": 2338707, "tid": 2379456, + "ts": 6197198037924.304, "dur": 5.807, + "args": { + "External id": 31000,"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": 2338707, "tid": 2379456, + "ts": 6197198037931.969, "dur": 50.158, + "args": { + "External id": 31001,"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": 2338707, "tid": 2379456, + "ts": 6197198038180.815, "dur": 616.183, + "args": { + "External id": 31002,"Record function id": 0, "Ev Idx": 3865 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.10)", "pid": 2338707, "tid": 2379456, + "ts": 6197198038198.318, "dur": 585.905, + "args": { + "External id": 31003,"Record function id": 0, "Ev Idx": 3866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197198038271.299, "dur": 6.132, + "args": { + "External id": 31004,"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": 2338707, "tid": 2379456, + "ts": 6197198038292.663, "dur": 32.470, + "args": { + "External id": 31005,"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": 2338707, "tid": 2379456, + "ts": 6197198038298.261, "dur": 1.794, + "args": { + "External id": 31006,"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": 2338707, "tid": 2379456, + "ts": 6197198038301.871, "dur": 0.780, + "args": { + "External id": 31007,"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": 2338707, "tid": 2379456, + "ts": 6197198038304.318, "dur": 3.025, + "args": { + "External id": 31008,"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": 2338707, "tid": 2379456, + "ts": 6197198038308.955, "dur": 0.249, + "args": { + "External id": 31009,"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": 2338707, "tid": 2379456, + "ts": 6197198038310.202, "dur": 0.510, + "args": { + "External id": 31010,"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": 2338707, "tid": 2379456, + "ts": 6197198038312.289, "dur": 0.578, + "args": { + "External id": 31011,"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": 2338707, "tid": 2379456, + "ts": 6197198038314.865, "dur": 0.380, + "args": { + "External id": 31012,"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": 2338707, "tid": 2379456, + "ts": 6197198038316.358, "dur": 0.586, + "args": { + "External id": 31013,"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": 2338707, "tid": 2379456, + "ts": 6197198038318.388, "dur": 0.461, + "args": { + "External id": 31014,"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": 2338707, "tid": 2379456, + "ts": 6197198038336.308, "dur": 44.748, + "args": { + "External id": 31015,"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": 2338707, "tid": 2379456, + "ts": 6197198038410.581, "dur": 116.202, + "args": { + "External id": 31016,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2379456, + "ts": 6197198038420.563, "dur": 2.935, + "args": { + "External id": 31017,"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": 2338707, "tid": 2379456, + "ts": 6197198038428.255, "dur": 11.783, + "args": { + "External id": 31018,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2379456, + "ts": 6197198038432.603, "dur": 7.033, + "args": { + "External id": 31019,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2379456, + "ts": 6197198038435.651, "dur": 2.841, + "args": { + "External id": 31020,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197198038446.516, "dur": 29.754, + "args": { + "External id": 31021,"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": 2338707, "tid": 2379456, + "ts": 6197198038448.200, "dur": 0.927, + "args": { + "External id": 31022,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197198038451.114, "dur": 0.555, + "args": { + "External id": 31023,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2379456, + "ts": 6197198038457.275, "dur": 0.421, + "args": { + "External id": 31024,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2379456, + "ts": 6197198038459.510, "dur": 0.383, + "args": { + "External id": 31025,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2379456, + "ts": 6197198038461.137, "dur": 0.494, + "args": { + "External id": 31026,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2379456, + "ts": 6197198038462.958, "dur": 0.383, + "args": { + "External id": 31027,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2379456, + "ts": 6197198038465.150, "dur": 0.461, + "args": { + "External id": 31028,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2379456, + "ts": 6197198038466.554, "dur": 2.697, + "args": { + "External id": 31029,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2379456, + "ts": 6197198038470.996, "dur": 0.456, + "args": { + "External id": 31030,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2379456, + "ts": 6197198038486.150, "dur": 32.366, + "args": { + "External id": 31031,"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": 2338707, "tid": 2379456, + "ts": 6197198038568.829, "dur": 117.555, + "args": { + "External id": 31032,"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": 2338707, "tid": 2379456, + "ts": 6197198038592.884, "dur": 90.235, + "args": { + "External id": 31033,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197198038602.950, "dur": 72.828, + "args": { + "External id": 31034,"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": 2338707, "tid": 2379456, + "ts": 6197198038723.631, "dur": 2.923, + "args": { + "External id": 31035,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197198038811.237, "dur": 1802.596, + "args": { + "External id": 31036,"Sequence number": 479790, "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": 2338707, "tid": 2379456, "ts": 6197198038811.237, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6197198038922.491, "dur": 108.618, + "args": { + "External id": 31037,"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": 2338707, "tid": 2379456, + "ts": 6197198039110.229, "dur": 47.594, + "args": { + "External id": 31038,"kernel_hash": "cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/u7/cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs.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": 2338707, "tid": 2379456, + "ts": 6197198039179.517, "dur": 60.726, + "args": { + "External id": 31039,"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": 2338707, "tid": 2379456, + "ts": 6197198039249.943, "dur": 32.670, + "args": { + "External id": 31040,"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": 2338707, "tid": 2379456, + "ts": 6197198039289.234, "dur": 37.442, + "args": { + "External id": 31041,"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": 2338707, "tid": 2379456, + "ts": 6197198039334.483, "dur": 27.657, + "args": { + "External id": 31042,"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": 2338707, "tid": 2379456, + "ts": 6197198039375.094, "dur": 29.169, + "args": { + "External id": 31043,"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": 2338707, "tid": 2379456, + "ts": 6197198039431.941, "dur": 24.131, + "args": { + "External id": 31044,"kernel_hash": "cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/wm/cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s.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": 2338707, "tid": 2379456, + "ts": 6197198039474.798, "dur": 29.334, + "args": { + "External id": 31045,"kernel_hash": "cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql", "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/qt/cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql.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": 2338707, "tid": 2379456, + "ts": 6197198039526.100, "dur": 19.033, + "args": { + "External id": 31046,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197198039559.146, "dur": 15.104, + "args": { + "External id": 31047,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197198039585.002, "dur": 39.128, + "args": { + "External id": 31048,"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": 2338707, "tid": 2379456, + "ts": 6197198039628.089, "dur": 34.222, + "args": { + "External id": 31049,"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": 2338707, "tid": 2379456, + "ts": 6197198039689.756, "dur": 277.754, + "args": { + "External id": 31050,"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": 2338707, "tid": 2379456, + "ts": 6197198039783.452, "dur": 6.938, + "args": { + "External id": 31051,"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": 2338707, "tid": 2379456, + "ts": 6197198039792.709, "dur": 2.876, + "args": { + "External id": 31052,"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": 2338707, "tid": 2379456, + "ts": 6197198039796.857, "dur": 4.551, + "args": { + "External id": 31053,"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": 2338707, "tid": 2379456, + "ts": 6197198039802.969, "dur": 2.236, + "args": { + "External id": 31054,"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": 2338707, "tid": 2379456, + "ts": 6197198039858.591, "dur": 5.567, + "args": { + "External id": 31055,"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": 2338707, "tid": 2379456, + "ts": 6197198039861.114, "dur": 2.830, + "args": { + "External id": 31056,"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": 2338707, "tid": 2379456, + "ts": 6197198039866.055, "dur": 37.973, + "args": { + "External id": 31057,"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": 2338707, "tid": 2379456, + "ts": 6197198039875.401, "dur": 1.976, + "args": { + "External id": 31058,"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": 2338707, "tid": 2379456, + "ts": 6197198039905.804, "dur": 1.813, + "args": { + "External id": 31059,"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": 2338707, "tid": 2379456, + "ts": 6197198039906.924, "dur": 0.614, + "args": { + "External id": 31060,"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": 2338707, "tid": 2379456, + "ts": 6197198039908.738, "dur": 17.216, + "args": { + "External id": 31061,"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": 2338707, "tid": 2379456, + "ts": 6197198039911.001, "dur": 0.617, + "args": { + "External id": 31062,"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": 2338707, "tid": 2379456, + "ts": 6197198040002.966, "dur": 29.374, + "args": { + "External id": 31063,"kernel_hash": "cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4", "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/yk/cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4.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": 2338707, "tid": 2379456, + "ts": 6197198040049.212, "dur": 54.284, + "args": { + "External id": 31064,"kernel_hash": "ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg", "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/eu/ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg.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": 2338707, "tid": 2379456, + "ts": 6197198040115.831, "dur": 49.855, + "args": { + "External id": 31065,"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": 2338707, "tid": 2379456, + "ts": 6197198040173.044, "dur": 41.502, + "args": { + "External id": 31066,"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": 2338707, "tid": 2379456, + "ts": 6197198040224.261, "dur": 21.225, + "args": { + "External id": 31067,"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": 2338707, "tid": 2379456, + "ts": 6197198040254.386, "dur": 32.416, + "args": { + "External id": 31068,"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": 2338707, "tid": 2379456, + "ts": 6197198040294.127, "dur": 29.326, + "args": { + "External id": 31069,"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": 2338707, "tid": 2379456, + "ts": 6197198040331.340, "dur": 52.146, + "args": { + "External id": 31070,"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": 2338707, "tid": 2379456, + "ts": 6197198040413.996, "dur": 25.555, + "args": { + "External id": 31071,"kernel_hash": "c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/6w/c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7.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": 2338707, "tid": 2379456, + "ts": 6197198040454.901, "dur": 30.708, + "args": { + "External id": 31072,"kernel_hash": "ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx", "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/kj/ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx.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": 2338707, "tid": 2379456, + "ts": 6197198040498.833, "dur": 18.137, + "args": { + "External id": 31073,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197198040531.774, "dur": 19.546, + "args": { + "External id": 31074,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197198040563.357, "dur": 18.663, + "args": { + "External id": 31075,"kernel_hash": "cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/eb/cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b.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": 2338707, "tid": 2379456, + "ts": 6197198040656.795, "dur": 15.785, + "args": { + "External id": 31076,"Record function id": 0, "Ev Idx": 3939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198040660.377, "dur": 11.198, + "args": { + "External id": 31077,"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": 2338707, "tid": 2379456, + "ts": 6197198040664.344, "dur": 6.276, + "args": { + "External id": 31078,"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": 2338707, "tid": 2379456, + "ts": 6197198040666.443, "dur": 4.016, + "args": { + "External id": 31079,"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": 2338707, "tid": 2379456, + "ts": 6197198040676.724, "dur": 4.835, + "args": { + "External id": 31080,"Record function id": 0, "Ev Idx": 3943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198040678.244, "dur": 2.891, + "args": { + "External id": 31081,"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": 2338707, "tid": 2379456, + "ts": 6197198040679.004, "dur": 1.663, + "args": { + "External id": 31082,"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": 2338707, "tid": 2379456, + "ts": 6197198040679.851, "dur": 0.750, + "args": { + "External id": 31083,"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": 2338707, "tid": 2379456, + "ts": 6197198040685.126, "dur": 3.987, + "args": { + "External id": 31084,"Record function id": 0, "Ev Idx": 3947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198040686.595, "dur": 2.106, + "args": { + "External id": 31085,"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": 2338707, "tid": 2379456, + "ts": 6197198040687.074, "dur": 1.188, + "args": { + "External id": 31086,"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": 2338707, "tid": 2379456, + "ts": 6197198040687.557, "dur": 0.641, + "args": { + "External id": 31087,"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": 2338707, "tid": 2379456, + "ts": 6197198040692.321, "dur": 4.096, + "args": { + "External id": 31088,"Record function id": 0, "Ev Idx": 3951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198040693.780, "dur": 2.206, + "args": { + "External id": 31089,"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": 2338707, "tid": 2379456, + "ts": 6197198040694.282, "dur": 1.275, + "args": { + "External id": 31090,"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": 2338707, "tid": 2379456, + "ts": 6197198040694.873, "dur": 0.584, + "args": { + "External id": 31091,"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": 2338707, "tid": 2379456, + "ts": 6197198040716.848, "dur": 8.034, + "args": { + "External id": 31092,"Record function id": 0, "Ev Idx": 3955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198040719.905, "dur": 4.306, + "args": { + "External id": 31093,"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": 2338707, "tid": 2379456, + "ts": 6197198040721.117, "dur": 2.294, + "args": { + "External id": 31094,"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": 2338707, "tid": 2379456, + "ts": 6197198040721.661, "dur": 1.521, + "args": { + "External id": 31095,"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": 2338707, "tid": 2379456, + "ts": 6197198040729.336, "dur": 6.307, + "args": { + "External id": 31096,"Record function id": 0, "Ev Idx": 3959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198040730.384, "dur": 4.812, + "args": { + "External id": 31097,"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": 2338707, "tid": 2379456, + "ts": 6197198040731.189, "dur": 3.620, + "args": { + "External id": 31098,"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": 2338707, "tid": 2379456, + "ts": 6197198040731.806, "dur": 2.923, + "args": { + "External id": 31099,"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": 2338707, "tid": 2379456, + "ts": 6197198040738.842, "dur": 14.787, + "args": { + "External id": 31100,"Record function id": 0, "Ev Idx": 3963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198040740.496, "dur": 12.664, + "args": { + "External id": 31101,"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": 2338707, "tid": 2379456, + "ts": 6197198040741.725, "dur": 11.001, + "args": { + "External id": 31102,"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": 2338707, "tid": 2379456, + "ts": 6197198040751.942, "dur": 0.671, + "args": { + "External id": 31103,"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": 2338707, "tid": 2379456, + "ts": 6197198040757.090, "dur": 4.133, + "args": { + "External id": 31104,"Record function id": 0, "Ev Idx": 3967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198040758.404, "dur": 2.372, + "args": { + "External id": 31105,"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": 2338707, "tid": 2379456, + "ts": 6197198040759.016, "dur": 1.367, + "args": { + "External id": 31106,"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": 2338707, "tid": 2379456, + "ts": 6197198040759.496, "dur": 0.808, + "args": { + "External id": 31107,"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": 2338707, "tid": 2379456, + "ts": 6197198040764.965, "dur": 4.029, + "args": { + "External id": 31108,"Record function id": 0, "Ev Idx": 3971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198040766.253, "dur": 2.298, + "args": { + "External id": 31109,"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": 2338707, "tid": 2379456, + "ts": 6197198040766.891, "dur": 1.277, + "args": { + "External id": 31110,"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": 2338707, "tid": 2379456, + "ts": 6197198040767.144, "dur": 0.940, + "args": { + "External id": 31111,"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": 2338707, "tid": 2379456, + "ts": 6197198040773.239, "dur": 62462.109, + "args": { + "External id": 31112,"Record function id": 0, "Sequence number": 479789, "Fwd thread id": 1, "Ev Idx": 3975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197198040774.576, "dur": 62451.588, + "args": { + "External id": 31113,"Sequence number": 479789, "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": 2338707, "tid": 2379456, "ts": 6197198040774.576, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.11)", "pid": 2338707, "tid": 2379456, + "ts": 6197198040804.985, "dur": 40.315, + "args": { + "External id": 31114,"Record function id": 0, "Ev Idx": 3977 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.11)", "pid": 2338707, "tid": 2379456, + "ts": 6197198040853.017, "dur": 62.748, + "args": { + "External id": 31115,"Record function id": 0, "Ev Idx": 3978 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.11)", "pid": 2338707, "tid": 2379456, + "ts": 6197198040920.988, "dur": 62296.929, + "args": { + "External id": 31116,"Record function id": 0, "Ev Idx": 3979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197198041014.943, "dur": 6.997, + "args": { + "External id": 31117,"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": 2338707, "tid": 2379456, + "ts": 6197198041032.181, "dur": 4.710, + "args": { + "External id": 31118,"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": 2338707, "tid": 2379456, + "ts": 6197198041090.889, "dur": 61252.153, + "args": { + "External id": 31119,"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": 2338707, "tid": 2379456, + "ts": 6197198041108.000, "dur": 61222.149, + "args": { + "External id": 31120,"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": 2338707, "tid": 2379456, + "ts": 6197198041198.185, "dur": 18.564, + "args": { + "External id": 31121,"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": 2338707, "tid": 2379456, + "ts": 6197198041237.033, "dur": 61049.533, + "args": { + "External id": 31122,"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": 2338707, "tid": 2379456, + "ts": 6197198041239.853, "dur": 61045.800, + "args": { + "External id": 31123,"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": 2338707, "tid": 2379456, + "ts": 6197198041244.759, "dur": 11.133, + "args": { + "External id": 31124,"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": 2338707, "tid": 2379456, + "ts": 6197198041258.080, "dur": 61022.566, + "args": { + "External id": 31125,"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": 2338707, "tid": 2379456, + "ts": 6197198102449.463, "dur": 13.138, + "args": { + "External id": 31126,"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": 2338707, "tid": 2379456, + "ts": 6197198102452.770, "dur": 9.407, + "args": { + "External id": 31127,"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": 2338707, "tid": 2379456, + "ts": 6197198102493.168, "dur": 389.091, + "args": { + "External id": 31128,"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": 2338707, "tid": 2379456, + "ts": 6197198102521.652, "dur": 355.409, + "args": { + "External id": 31129,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197198102535.285, "dur": 335.731, + "args": { + "External id": 31130,"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": 2338707, "tid": 2379456, + "ts": 6197198102905.476, "dur": 2.241, + "args": { + "External id": 31131,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2379456, + "ts": 6197198102968.252, "dur": 6.752, + "args": { + "External id": 31132,"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": 2338707, "tid": 2379456, + "ts": 6197198103022.118, "dur": 1.272, + "args": { + "External id": 31133,"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": 2338707, "tid": 2379456, + "ts": 6197198103038.245, "dur": 1.218, + "args": { + "External id": 31134,"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": 2338707, "tid": 2379456, + "ts": 6197198103049.897, "dur": 1.166, + "args": { + "External id": 31135,"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": 2338707, "tid": 2379456, + "ts": 6197198103101.221, "dur": 1.676, + "args": { + "External id": 31136,"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": 2338707, "tid": 2379456, + "ts": 6197198103115.679, "dur": 1.799, + "args": { + "External id": 31137,"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": 2338707, "tid": 2379456, + "ts": 6197198103128.306, "dur": 1.038, + "args": { + "External id": 31138,"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": 2338707, "tid": 2379456, + "ts": 6197198103138.930, "dur": 2.107, + "args": { + "External id": 31139,"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": 2338707, "tid": 2379456, + "ts": 6197198103150.572, "dur": 0.895, + "args": { + "External id": 31140,"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": 2338707, "tid": 2379456, + "ts": 6197198103251.642, "dur": 3054.586, + "args": { + "External id": 31141,"Record function id": 0, "Ev Idx": 4004 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.10)", "pid": 2338707, "tid": 2379456, + "ts": 6197198103271.392, "dur": 1114.797, + "args": { + "External id": 31142,"Record function id": 0, "Ev Idx": 4005 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.10)", "pid": 2338707, "tid": 2379456, + "ts": 6197198103287.859, "dur": 342.445, + "args": { + "External id": 31143,"Record function id": 0, "Ev Idx": 4006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6197198103381.403, "dur": 4.221, + "args": { + "External id": 31144,"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": 2338707, "tid": 2379456, + "ts": 6197198103389.286, "dur": 1.047, + "args": { + "External id": 31145,"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": 2338707, "tid": 2379456, + "ts": 6197198103392.541, "dur": 1.039, + "args": { + "External id": 31146,"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": 2338707, "tid": 2379456, + "ts": 6197198103395.653, "dur": 0.687, + "args": { + "External id": 31147,"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": 2338707, "tid": 2379456, + "ts": 6197198103397.600, "dur": 0.859, + "args": { + "External id": 31148,"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": 2338707, "tid": 2379456, + "ts": 6197198103399.611, "dur": 1.129, + "args": { + "External id": 31149,"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": 2338707, "tid": 2379456, + "ts": 6197198103402.351, "dur": 1.917, + "args": { + "External id": 31150,"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": 2338707, "tid": 2379456, + "ts": 6197198103405.779, "dur": 2.866, + "args": { + "External id": 31151,"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": 2338707, "tid": 2379456, + "ts": 6197198103410.026, "dur": 0.926, + "args": { + "External id": 31152,"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": 2338707, "tid": 2379456, + "ts": 6197198103412.345, "dur": 0.663, + "args": { + "External id": 31153,"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": 2338707, "tid": 2379456, + "ts": 6197198103432.619, "dur": 165.031, + "args": { + "External id": 31154,"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": 2338707, "tid": 2379456, + "ts": 6197198103448.412, "dur": 145.065, + "args": { + "External id": 31155,"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": 2338707, "tid": 2379456, + "ts": 6197198103473.227, "dur": 15.959, + "args": { + "External id": 31156,"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": 2338707, "tid": 2379456, + "ts": 6197198103492.770, "dur": 66.322, + "args": { + "External id": 31157,"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": 2338707, "tid": 2379456, + "ts": 6197198103495.648, "dur": 63.088, + "args": { + "External id": 31158,"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": 2338707, "tid": 2379456, + "ts": 6197198103499.785, "dur": 5.125, + "args": { + "External id": 31159,"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": 2338707, "tid": 2379456, + "ts": 6197198103506.788, "dur": 51.317, + "args": { + "External id": 31160,"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": 2338707, "tid": 2379456, + "ts": 6197198103746.972, "dur": 631.168, + "args": { + "External id": 31161,"Record function id": 0, "Ev Idx": 4024 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.9)", "pid": 2338707, "tid": 2379456, + "ts": 6197198103767.284, "dur": 598.478, + "args": { + "External id": 31162,"Record function id": 0, "Ev Idx": 4025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197198103835.144, "dur": 5.901, + "args": { + "External id": 31163,"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": 2338707, "tid": 2379456, + "ts": 6197198103856.490, "dur": 29.825, + "args": { + "External id": 31164,"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": 2338707, "tid": 2379456, + "ts": 6197198103861.954, "dur": 1.767, + "args": { + "External id": 31165,"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": 2338707, "tid": 2379456, + "ts": 6197198103865.397, "dur": 0.699, + "args": { + "External id": 31166,"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": 2338707, "tid": 2379456, + "ts": 6197198103867.921, "dur": 2.332, + "args": { + "External id": 31167,"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": 2338707, "tid": 2379456, + "ts": 6197198103871.691, "dur": 0.504, + "args": { + "External id": 31168,"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": 2338707, "tid": 2379456, + "ts": 6197198103873.210, "dur": 0.390, + "args": { + "External id": 31169,"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": 2338707, "tid": 2379456, + "ts": 6197198103875.132, "dur": 0.394, + "args": { + "External id": 31170,"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": 2338707, "tid": 2379456, + "ts": 6197198103876.803, "dur": 0.580, + "args": { + "External id": 31171,"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": 2338707, "tid": 2379456, + "ts": 6197198103878.475, "dur": 0.366, + "args": { + "External id": 31172,"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": 2338707, "tid": 2379456, + "ts": 6197198103880.442, "dur": 0.425, + "args": { + "External id": 31173,"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": 2338707, "tid": 2379456, + "ts": 6197198103897.462, "dur": 44.172, + "args": { + "External id": 31174,"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": 2338707, "tid": 2379456, + "ts": 6197198103971.609, "dur": 151.181, + "args": { + "External id": 31175,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2379456, + "ts": 6197198103981.394, "dur": 2.834, + "args": { + "External id": 31176,"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": 2338707, "tid": 2379456, + "ts": 6197198103989.483, "dur": 12.520, + "args": { + "External id": 31177,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2379456, + "ts": 6197198103993.897, "dur": 7.666, + "args": { + "External id": 31178,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2379456, + "ts": 6197198103997.178, "dur": 2.698, + "args": { + "External id": 31179,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197198104008.516, "dur": 25.144, + "args": { + "External id": 31180,"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": 2338707, "tid": 2379456, + "ts": 6197198104010.241, "dur": 0.506, + "args": { + "External id": 31181,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197198104012.559, "dur": 0.368, + "args": { + "External id": 31182,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2379456, + "ts": 6197198104014.739, "dur": 0.406, + "args": { + "External id": 31183,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2379456, + "ts": 6197198104016.119, "dur": 0.488, + "args": { + "External id": 31184,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2379456, + "ts": 6197198104018.206, "dur": 0.464, + "args": { + "External id": 31185,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2379456, + "ts": 6197198104020.630, "dur": 0.300, + "args": { + "External id": 31186,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2379456, + "ts": 6197198104021.892, "dur": 0.467, + "args": { + "External id": 31187,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2379456, + "ts": 6197198104024.347, "dur": 2.521, + "args": { + "External id": 31188,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2379456, + "ts": 6197198104028.379, "dur": 0.380, + "args": { + "External id": 31189,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2379456, + "ts": 6197198104046.950, "dur": 65.754, + "args": { + "External id": 31190,"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": 2338707, "tid": 2379456, + "ts": 6197198104171.304, "dur": 121.686, + "args": { + "External id": 31191,"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": 2338707, "tid": 2379456, + "ts": 6197198104201.100, "dur": 88.322, + "args": { + "External id": 31192,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197198104211.286, "dur": 74.040, + "args": { + "External id": 31193,"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": 2338707, "tid": 2379456, + "ts": 6197198104310.748, "dur": 1.650, + "args": { + "External id": 31194,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197198104394.400, "dur": 1887.321, + "args": { + "External id": 31195,"Sequence number": 479788, "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": 2338707, "tid": 2379456, "ts": 6197198104394.400, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6197198104504.000, "dur": 107.845, + "args": { + "External id": 31196,"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": 2338707, "tid": 2379456, + "ts": 6197198104651.252, "dur": 40.270, + "args": { + "External id": 31197,"kernel_hash": "cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/u7/cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs.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": 2338707, "tid": 2379456, + "ts": 6197198104730.569, "dur": 59.538, + "args": { + "External id": 31198,"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": 2338707, "tid": 2379456, + "ts": 6197198104800.364, "dur": 32.195, + "args": { + "External id": 31199,"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": 2338707, "tid": 2379456, + "ts": 6197198104838.648, "dur": 34.267, + "args": { + "External id": 31200,"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": 2338707, "tid": 2379456, + "ts": 6197198104879.984, "dur": 27.488, + "args": { + "External id": 31201,"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": 2338707, "tid": 2379456, + "ts": 6197198104916.875, "dur": 29.547, + "args": { + "External id": 31202,"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": 2338707, "tid": 2379456, + "ts": 6197198104974.122, "dur": 26.780, + "args": { + "External id": 31203,"kernel_hash": "cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/wm/cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s.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": 2338707, "tid": 2379456, + "ts": 6197198105020.311, "dur": 80.607, + "args": { + "External id": 31204,"kernel_hash": "cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql", "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/qt/cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql.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": 2338707, "tid": 2379456, + "ts": 6197198105129.090, "dur": 24.079, + "args": { + "External id": 31205,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197198105169.131, "dur": 18.397, + "args": { + "External id": 31206,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197198105203.026, "dur": 45.720, + "args": { + "External id": 31207,"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": 2338707, "tid": 2379456, + "ts": 6197198105253.026, "dur": 37.884, + "args": { + "External id": 31208,"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": 2338707, "tid": 2379456, + "ts": 6197198105320.630, "dur": 257.982, + "args": { + "External id": 31209,"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": 2338707, "tid": 2379456, + "ts": 6197198105406.624, "dur": 6.428, + "args": { + "External id": 31210,"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": 2338707, "tid": 2379456, + "ts": 6197198105415.118, "dur": 2.805, + "args": { + "External id": 31211,"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": 2338707, "tid": 2379456, + "ts": 6197198105419.000, "dur": 4.551, + "args": { + "External id": 31212,"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": 2338707, "tid": 2379456, + "ts": 6197198105424.687, "dur": 2.337, + "args": { + "External id": 31213,"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": 2338707, "tid": 2379456, + "ts": 6197198105475.009, "dur": 5.042, + "args": { + "External id": 31214,"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": 2338707, "tid": 2379456, + "ts": 6197198105476.965, "dur": 2.901, + "args": { + "External id": 31215,"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": 2338707, "tid": 2379456, + "ts": 6197198105481.816, "dur": 32.994, + "args": { + "External id": 31216,"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": 2338707, "tid": 2379456, + "ts": 6197198105486.886, "dur": 1.642, + "args": { + "External id": 31217,"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": 2338707, "tid": 2379456, + "ts": 6197198105516.276, "dur": 2.099, + "args": { + "External id": 31218,"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": 2338707, "tid": 2379456, + "ts": 6197198105517.486, "dur": 0.774, + "args": { + "External id": 31219,"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": 2338707, "tid": 2379456, + "ts": 6197198105519.969, "dur": 16.922, + "args": { + "External id": 31220,"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": 2338707, "tid": 2379456, + "ts": 6197198105522.327, "dur": 0.711, + "args": { + "External id": 31221,"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": 2338707, "tid": 2379456, + "ts": 6197198105613.284, "dur": 27.263, + "args": { + "External id": 31222,"kernel_hash": "cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4", "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/yk/cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4.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": 2338707, "tid": 2379456, + "ts": 6197198105656.859, "dur": 17.834, + "args": { + "External id": 31223,"kernel_hash": "ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg", "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/eu/ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg.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": 2338707, "tid": 2379456, + "ts": 6197198105682.126, "dur": 60.555, + "args": { + "External id": 31224,"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": 2338707, "tid": 2379456, + "ts": 6197198105751.686, "dur": 46.031, + "args": { + "External id": 31225,"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": 2338707, "tid": 2379456, + "ts": 6197198105807.512, "dur": 23.427, + "args": { + "External id": 31226,"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": 2338707, "tid": 2379456, + "ts": 6197198105839.335, "dur": 33.994, + "args": { + "External id": 31227,"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": 2338707, "tid": 2379456, + "ts": 6197198105881.086, "dur": 30.074, + "args": { + "External id": 31228,"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": 2338707, "tid": 2379456, + "ts": 6197198105918.760, "dur": 32.461, + "args": { + "External id": 31229,"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": 2338707, "tid": 2379456, + "ts": 6197198105970.130, "dur": 25.849, + "args": { + "External id": 31230,"kernel_hash": "c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/6w/c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7.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": 2338707, "tid": 2379456, + "ts": 6197198106011.614, "dur": 26.831, + "args": { + "External id": 31231,"kernel_hash": "ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx", "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/kj/ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx.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": 2338707, "tid": 2379456, + "ts": 6197198106107.736, "dur": 30.824, + "args": { + "External id": 31232,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197198106192.439, "dur": 17.949, + "args": { + "External id": 31233,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197198106225.111, "dur": 18.538, + "args": { + "External id": 31234,"kernel_hash": "cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/eb/cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b.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": 2338707, "tid": 2379456, + "ts": 6197198106332.492, "dur": 15.451, + "args": { + "External id": 31235,"Record function id": 0, "Ev Idx": 4098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198106335.856, "dur": 11.100, + "args": { + "External id": 31236,"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": 2338707, "tid": 2379456, + "ts": 6197198106339.909, "dur": 6.135, + "args": { + "External id": 31237,"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": 2338707, "tid": 2379456, + "ts": 6197198106341.784, "dur": 4.144, + "args": { + "External id": 31238,"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": 2338707, "tid": 2379456, + "ts": 6197198106351.875, "dur": 4.888, + "args": { + "External id": 31239,"Record function id": 0, "Ev Idx": 4102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198106353.344, "dur": 2.971, + "args": { + "External id": 31240,"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": 2338707, "tid": 2379456, + "ts": 6197198106353.986, "dur": 1.866, + "args": { + "External id": 31241,"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": 2338707, "tid": 2379456, + "ts": 6197198106354.751, "dur": 1.034, + "args": { + "External id": 31242,"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": 2338707, "tid": 2379456, + "ts": 6197198106360.098, "dur": 4.139, + "args": { + "External id": 31243,"Record function id": 0, "Ev Idx": 4106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198106361.307, "dur": 2.492, + "args": { + "External id": 31244,"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": 2338707, "tid": 2379456, + "ts": 6197198106361.906, "dur": 1.308, + "args": { + "External id": 31245,"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": 2338707, "tid": 2379456, + "ts": 6197198106362.308, "dur": 0.842, + "args": { + "External id": 31246,"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": 2338707, "tid": 2379456, + "ts": 6197198106367.380, "dur": 3.816, + "args": { + "External id": 31247,"Record function id": 0, "Ev Idx": 4110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198106368.448, "dur": 2.355, + "args": { + "External id": 31248,"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": 2338707, "tid": 2379456, + "ts": 6197198106369.172, "dur": 1.213, + "args": { + "External id": 31249,"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": 2338707, "tid": 2379456, + "ts": 6197198106369.607, "dur": 0.716, + "args": { + "External id": 31250,"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": 2338707, "tid": 2379456, + "ts": 6197198106374.316, "dur": 4.321, + "args": { + "External id": 31251,"Record function id": 0, "Ev Idx": 4114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198106375.643, "dur": 2.553, + "args": { + "External id": 31252,"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": 2338707, "tid": 2379456, + "ts": 6197198106376.283, "dur": 1.482, + "args": { + "External id": 31253,"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": 2338707, "tid": 2379456, + "ts": 6197198106376.939, "dur": 0.763, + "args": { + "External id": 31254,"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": 2338707, "tid": 2379456, + "ts": 6197198106381.804, "dur": 6.714, + "args": { + "External id": 31255,"Record function id": 0, "Ev Idx": 4118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198106383.097, "dur": 4.983, + "args": { + "External id": 31256,"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": 2338707, "tid": 2379456, + "ts": 6197198106383.681, "dur": 3.900, + "args": { + "External id": 31257,"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": 2338707, "tid": 2379456, + "ts": 6197198106384.126, "dur": 3.353, + "args": { + "External id": 31258,"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": 2338707, "tid": 2379456, + "ts": 6197198106391.861, "dur": 4.072, + "args": { + "External id": 31259,"Record function id": 0, "Ev Idx": 4122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198106393.363, "dur": 2.138, + "args": { + "External id": 31260,"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": 2338707, "tid": 2379456, + "ts": 6197198106393.823, "dur": 1.133, + "args": { + "External id": 31261,"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": 2338707, "tid": 2379456, + "ts": 6197198106394.128, "dur": 0.763, + "args": { + "External id": 31262,"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": 2338707, "tid": 2379456, + "ts": 6197198106399.563, "dur": 3.614, + "args": { + "External id": 31263,"Record function id": 0, "Ev Idx": 4126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198106400.737, "dur": 2.015, + "args": { + "External id": 31264,"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": 2338707, "tid": 2379456, + "ts": 6197198106401.325, "dur": 1.016, + "args": { + "External id": 31265,"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": 2338707, "tid": 2379456, + "ts": 6197198106401.610, "dur": 0.633, + "args": { + "External id": 31266,"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": 2338707, "tid": 2379456, + "ts": 6197198106407.102, "dur": 4.493, + "args": { + "External id": 31267,"Record function id": 0, "Ev Idx": 4130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198106408.415, "dur": 2.742, + "args": { + "External id": 31268,"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": 2338707, "tid": 2379456, + "ts": 6197198106409.263, "dur": 1.427, + "args": { + "External id": 31269,"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": 2338707, "tid": 2379456, + "ts": 6197198106409.923, "dur": 0.649, + "args": { + "External id": 31270,"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": 2338707, "tid": 2379456, + "ts": 6197198106415.774, "dur": 65875.804, + "args": { + "External id": 31271,"Record function id": 0, "Sequence number": 479787, "Fwd thread id": 1, "Ev Idx": 4134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197198106417.085, "dur": 65865.811, + "args": { + "External id": 31272,"Sequence number": 479787, "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": 2338707, "tid": 2379456, "ts": 6197198106417.085, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.10)", "pid": 2338707, "tid": 2379456, + "ts": 6197198106446.642, "dur": 38.295, + "args": { + "External id": 31273,"Record function id": 0, "Ev Idx": 4136 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.10)", "pid": 2338707, "tid": 2379456, + "ts": 6197198106492.477, "dur": 70.116, + "args": { + "External id": 31274,"Record function id": 0, "Ev Idx": 4137 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.10)", "pid": 2338707, "tid": 2379456, + "ts": 6197198106567.766, "dur": 65706.337, + "args": { + "External id": 31275,"Record function id": 0, "Ev Idx": 4138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197198106655.822, "dur": 6.802, + "args": { + "External id": 31276,"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": 2338707, "tid": 2379456, + "ts": 6197198106672.021, "dur": 4.404, + "args": { + "External id": 31277,"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": 2338707, "tid": 2379456, + "ts": 6197198106691.087, "dur": 64652.010, + "args": { + "External id": 31278,"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": 2338707, "tid": 2379456, + "ts": 6197198106722.011, "dur": 64607.984, + "args": { + "External id": 31279,"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": 2338707, "tid": 2379456, + "ts": 6197198106816.272, "dur": 18.316, + "args": { + "External id": 31280,"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": 2338707, "tid": 2379456, + "ts": 6197198106858.872, "dur": 64422.941, + "args": { + "External id": 31281,"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": 2338707, "tid": 2379456, + "ts": 6197198106862.046, "dur": 64418.839, + "args": { + "External id": 31282,"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": 2338707, "tid": 2379456, + "ts": 6197198106867.032, "dur": 10.319, + "args": { + "External id": 31283,"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": 2338707, "tid": 2379456, + "ts": 6197198106879.508, "dur": 64396.019, + "args": { + "External id": 31284,"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": 2338707, "tid": 2379456, + "ts": 6197198171453.921, "dur": 11.864, + "args": { + "External id": 31285,"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": 2338707, "tid": 2379456, + "ts": 6197198171457.515, "dur": 7.852, + "args": { + "External id": 31286,"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": 2338707, "tid": 2379456, + "ts": 6197198171496.095, "dur": 435.276, + "args": { + "External id": 31287,"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": 2338707, "tid": 2379456, + "ts": 6197198171526.917, "dur": 398.649, + "args": { + "External id": 31288,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197198171538.397, "dur": 380.606, + "args": { + "External id": 31289,"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": 2338707, "tid": 2379456, + "ts": 6197198171954.689, "dur": 2.644, + "args": { + "External id": 31290,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2379456, + "ts": 6197198172020.282, "dur": 8.143, + "args": { + "External id": 31291,"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": 2338707, "tid": 2379456, + "ts": 6197198172116.431, "dur": 2.655, + "args": { + "External id": 31292,"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": 2338707, "tid": 2379456, + "ts": 6197198172136.534, "dur": 1.484, + "args": { + "External id": 31293,"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": 2338707, "tid": 2379456, + "ts": 6197198172150.170, "dur": 1.286, + "args": { + "External id": 31294,"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": 2338707, "tid": 2379456, + "ts": 6197198172161.824, "dur": 3.028, + "args": { + "External id": 31295,"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": 2338707, "tid": 2379456, + "ts": 6197198172174.871, "dur": 0.988, + "args": { + "External id": 31296,"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": 2338707, "tid": 2379456, + "ts": 6197198172185.913, "dur": 1.027, + "args": { + "External id": 31297,"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": 2338707, "tid": 2379456, + "ts": 6197198172198.228, "dur": 2.356, + "args": { + "External id": 31298,"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": 2338707, "tid": 2379456, + "ts": 6197198172210.494, "dur": 3.326, + "args": { + "External id": 31299,"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": 2338707, "tid": 2379456, + "ts": 6197198172307.629, "dur": 3012.072, + "args": { + "External id": 31300,"Record function id": 0, "Ev Idx": 4163 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.9)", "pid": 2338707, "tid": 2379456, + "ts": 6197198172328.680, "dur": 1100.060, + "args": { + "External id": 31301,"Record function id": 0, "Ev Idx": 4164 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.9)", "pid": 2338707, "tid": 2379456, + "ts": 6197198172344.096, "dur": 346.111, + "args": { + "External id": 31302,"Record function id": 0, "Ev Idx": 4165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6197198172436.925, "dur": 4.041, + "args": { + "External id": 31303,"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": 2338707, "tid": 2379456, + "ts": 6197198172444.414, "dur": 1.182, + "args": { + "External id": 31304,"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": 2338707, "tid": 2379456, + "ts": 6197198172447.708, "dur": 0.836, + "args": { + "External id": 31305,"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": 2338707, "tid": 2379456, + "ts": 6197198172450.355, "dur": 1.071, + "args": { + "External id": 31306,"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": 2338707, "tid": 2379456, + "ts": 6197198172452.968, "dur": 0.722, + "args": { + "External id": 31307,"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": 2338707, "tid": 2379456, + "ts": 6197198172455.089, "dur": 0.539, + "args": { + "External id": 31308,"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": 2338707, "tid": 2379456, + "ts": 6197198172457.240, "dur": 4.085, + "args": { + "External id": 31309,"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": 2338707, "tid": 2379456, + "ts": 6197198172462.993, "dur": 0.827, + "args": { + "External id": 31310,"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": 2338707, "tid": 2379456, + "ts": 6197198172468.244, "dur": 0.701, + "args": { + "External id": 31311,"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": 2338707, "tid": 2379456, + "ts": 6197198172470.303, "dur": 0.575, + "args": { + "External id": 31312,"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": 2338707, "tid": 2379456, + "ts": 6197198172487.993, "dur": 171.892, + "args": { + "External id": 31313,"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": 2338707, "tid": 2379456, + "ts": 6197198172504.040, "dur": 151.407, + "args": { + "External id": 31314,"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": 2338707, "tid": 2379456, + "ts": 6197198172529.624, "dur": 15.227, + "args": { + "External id": 31315,"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": 2338707, "tid": 2379456, + "ts": 6197198172550.578, "dur": 71.416, + "args": { + "External id": 31316,"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": 2338707, "tid": 2379456, + "ts": 6197198172553.579, "dur": 67.960, + "args": { + "External id": 31317,"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": 2338707, "tid": 2379456, + "ts": 6197198172557.973, "dur": 9.536, + "args": { + "External id": 31318,"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": 2338707, "tid": 2379456, + "ts": 6197198172569.140, "dur": 51.594, + "args": { + "External id": 31319,"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": 2338707, "tid": 2379456, + "ts": 6197198172802.848, "dur": 617.846, + "args": { + "External id": 31320,"Record function id": 0, "Ev Idx": 4183 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.8)", "pid": 2338707, "tid": 2379456, + "ts": 6197198172821.798, "dur": 586.610, + "args": { + "External id": 31321,"Record function id": 0, "Ev Idx": 4184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197198172886.292, "dur": 5.744, + "args": { + "External id": 31322,"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": 2338707, "tid": 2379456, + "ts": 6197198172907.191, "dur": 29.800, + "args": { + "External id": 31323,"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": 2338707, "tid": 2379456, + "ts": 6197198172912.354, "dur": 1.766, + "args": { + "External id": 31324,"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": 2338707, "tid": 2379456, + "ts": 6197198172916.829, "dur": 2.356, + "args": { + "External id": 31325,"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": 2338707, "tid": 2379456, + "ts": 6197198172920.862, "dur": 0.407, + "args": { + "External id": 31326,"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": 2338707, "tid": 2379456, + "ts": 6197198172922.452, "dur": 0.490, + "args": { + "External id": 31327,"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": 2338707, "tid": 2379456, + "ts": 6197198172924.847, "dur": 0.369, + "args": { + "External id": 31328,"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": 2338707, "tid": 2379456, + "ts": 6197198172926.798, "dur": 0.277, + "args": { + "External id": 31329,"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": 2338707, "tid": 2379456, + "ts": 6197198172928.009, "dur": 0.409, + "args": { + "External id": 31330,"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": 2338707, "tid": 2379456, + "ts": 6197198172929.921, "dur": 0.414, + "args": { + "External id": 31331,"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": 2338707, "tid": 2379456, + "ts": 6197198172931.995, "dur": 0.305, + "args": { + "External id": 31332,"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": 2338707, "tid": 2379456, + "ts": 6197198172948.446, "dur": 43.405, + "args": { + "External id": 31333,"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": 2338707, "tid": 2379456, + "ts": 6197198173020.883, "dur": 153.247, + "args": { + "External id": 31334,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2379456, + "ts": 6197198173030.780, "dur": 4.906, + "args": { + "External id": 31335,"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": 2338707, "tid": 2379456, + "ts": 6197198173040.822, "dur": 10.079, + "args": { + "External id": 31336,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2379456, + "ts": 6197198173045.249, "dur": 5.252, + "args": { + "External id": 31337,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2379456, + "ts": 6197198173048.482, "dur": 0.881, + "args": { + "External id": 31338,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197198173097.190, "dur": 24.197, + "args": { + "External id": 31339,"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": 2338707, "tid": 2379456, + "ts": 6197198173099.750, "dur": 0.709, + "args": { + "External id": 31340,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197198173102.593, "dur": 0.411, + "args": { + "External id": 31341,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2379456, + "ts": 6197198173104.445, "dur": 0.443, + "args": { + "External id": 31342,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2379456, + "ts": 6197198173105.885, "dur": 0.562, + "args": { + "External id": 31343,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2379456, + "ts": 6197198173107.720, "dur": 0.436, + "args": { + "External id": 31344,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2379456, + "ts": 6197198173109.736, "dur": 0.274, + "args": { + "External id": 31345,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2379456, + "ts": 6197198173110.970, "dur": 2.518, + "args": { + "External id": 31346,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2379456, + "ts": 6197198173115.036, "dur": 0.364, + "args": { + "External id": 31347,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2379456, + "ts": 6197198173116.787, "dur": 0.723, + "args": { + "External id": 31348,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2379456, + "ts": 6197198173134.018, "dur": 31.721, + "args": { + "External id": 31349,"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": 2338707, "tid": 2379456, + "ts": 6197198173221.750, "dur": 116.141, + "args": { + "External id": 31350,"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": 2338707, "tid": 2379456, + "ts": 6197198173245.657, "dur": 88.575, + "args": { + "External id": 31351,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197198173258.917, "dur": 70.809, + "args": { + "External id": 31352,"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": 2338707, "tid": 2379456, + "ts": 6197198173356.332, "dur": 1.794, + "args": { + "External id": 31353,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197198173436.118, "dur": 1860.241, + "args": { + "External id": 31354,"Sequence number": 479786, "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": 2338707, "tid": 2379456, "ts": 6197198173436.118, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6197198173546.803, "dur": 108.658, + "args": { + "External id": 31355,"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": 2338707, "tid": 2379456, + "ts": 6197198173717.881, "dur": 49.415, + "args": { + "External id": 31356,"kernel_hash": "cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/u7/cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs.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": 2338707, "tid": 2379456, + "ts": 6197198173788.996, "dur": 58.057, + "args": { + "External id": 31357,"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": 2338707, "tid": 2379456, + "ts": 6197198173856.443, "dur": 32.191, + "args": { + "External id": 31358,"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": 2338707, "tid": 2379456, + "ts": 6197198173895.345, "dur": 37.041, + "args": { + "External id": 31359,"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": 2338707, "tid": 2379456, + "ts": 6197198173941.507, "dur": 29.499, + "args": { + "External id": 31360,"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": 2338707, "tid": 2379456, + "ts": 6197198173978.068, "dur": 32.453, + "args": { + "External id": 31361,"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": 2338707, "tid": 2379456, + "ts": 6197198174034.669, "dur": 66.661, + "args": { + "External id": 31362,"kernel_hash": "cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/wm/cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s.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": 2338707, "tid": 2379456, + "ts": 6197198174122.463, "dur": 31.627, + "args": { + "External id": 31363,"kernel_hash": "cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql", "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/qt/cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql.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": 2338707, "tid": 2379456, + "ts": 6197198174178.814, "dur": 21.455, + "args": { + "External id": 31364,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197198174213.860, "dur": 17.266, + "args": { + "External id": 31365,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197198174242.335, "dur": 43.586, + "args": { + "External id": 31366,"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": 2338707, "tid": 2379456, + "ts": 6197198174289.775, "dur": 37.792, + "args": { + "External id": 31367,"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": 2338707, "tid": 2379456, + "ts": 6197198174359.902, "dur": 242.874, + "args": { + "External id": 31368,"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": 2338707, "tid": 2379456, + "ts": 6197198174438.577, "dur": 6.847, + "args": { + "External id": 31369,"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": 2338707, "tid": 2379456, + "ts": 6197198174447.808, "dur": 4.909, + "args": { + "External id": 31370,"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": 2338707, "tid": 2379456, + "ts": 6197198174453.996, "dur": 2.353, + "args": { + "External id": 31371,"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": 2338707, "tid": 2379456, + "ts": 6197198174457.655, "dur": 2.342, + "args": { + "External id": 31372,"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": 2338707, "tid": 2379456, + "ts": 6197198174502.735, "dur": 5.083, + "args": { + "External id": 31373,"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": 2338707, "tid": 2379456, + "ts": 6197198174504.604, "dur": 2.983, + "args": { + "External id": 31374,"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": 2338707, "tid": 2379456, + "ts": 6197198174509.884, "dur": 32.087, + "args": { + "External id": 31375,"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": 2338707, "tid": 2379456, + "ts": 6197198174515.238, "dur": 1.826, + "args": { + "External id": 31376,"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": 2338707, "tid": 2379456, + "ts": 6197198174543.404, "dur": 2.058, + "args": { + "External id": 31377,"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": 2338707, "tid": 2379456, + "ts": 6197198174544.492, "dur": 0.888, + "args": { + "External id": 31378,"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": 2338707, "tid": 2379456, + "ts": 6197198174546.591, "dur": 14.269, + "args": { + "External id": 31379,"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": 2338707, "tid": 2379456, + "ts": 6197198174548.918, "dur": 0.695, + "args": { + "External id": 31380,"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": 2338707, "tid": 2379456, + "ts": 6197198174636.029, "dur": 29.947, + "args": { + "External id": 31381,"kernel_hash": "cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4", "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/yk/cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4.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": 2338707, "tid": 2379456, + "ts": 6197198174682.302, "dur": 16.572, + "args": { + "External id": 31382,"kernel_hash": "ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg", "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/eu/ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg.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": 2338707, "tid": 2379456, + "ts": 6197198174729.808, "dur": 48.838, + "args": { + "External id": 31383,"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": 2338707, "tid": 2379456, + "ts": 6197198174786.618, "dur": 40.260, + "args": { + "External id": 31384,"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": 2338707, "tid": 2379456, + "ts": 6197198174838.295, "dur": 21.237, + "args": { + "External id": 31385,"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": 2338707, "tid": 2379456, + "ts": 6197198174865.886, "dur": 31.092, + "args": { + "External id": 31386,"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": 2338707, "tid": 2379456, + "ts": 6197198174905.241, "dur": 42.235, + "args": { + "External id": 31387,"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": 2338707, "tid": 2379456, + "ts": 6197198174962.159, "dur": 39.650, + "args": { + "External id": 31388,"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": 2338707, "tid": 2379456, + "ts": 6197198175022.942, "dur": 24.747, + "args": { + "External id": 31389,"kernel_hash": "c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/6w/c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7.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": 2338707, "tid": 2379456, + "ts": 6197198175117.102, "dur": 32.699, + "args": { + "External id": 31390,"kernel_hash": "ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx", "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/kj/ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx.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": 2338707, "tid": 2379456, + "ts": 6197198175165.944, "dur": 17.851, + "args": { + "External id": 31391,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197198175217.265, "dur": 14.829, + "args": { + "External id": 31392,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197198175247.220, "dur": 15.678, + "args": { + "External id": 31393,"kernel_hash": "cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/eb/cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b.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": 2338707, "tid": 2379456, + "ts": 6197198175345.034, "dur": 16.049, + "args": { + "External id": 31394,"Record function id": 0, "Ev Idx": 4257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198175348.449, "dur": 11.613, + "args": { + "External id": 31395,"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": 2338707, "tid": 2379456, + "ts": 6197198175352.711, "dur": 6.303, + "args": { + "External id": 31396,"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": 2338707, "tid": 2379456, + "ts": 6197198175354.882, "dur": 4.017, + "args": { + "External id": 31397,"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": 2338707, "tid": 2379456, + "ts": 6197198175365.119, "dur": 4.908, + "args": { + "External id": 31398,"Record function id": 0, "Ev Idx": 4261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198175366.442, "dur": 3.087, + "args": { + "External id": 31399,"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": 2338707, "tid": 2379456, + "ts": 6197198175367.036, "dur": 1.980, + "args": { + "External id": 31400,"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": 2338707, "tid": 2379456, + "ts": 6197198175367.831, "dur": 1.091, + "args": { + "External id": 31401,"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": 2338707, "tid": 2379456, + "ts": 6197198175373.328, "dur": 4.588, + "args": { + "External id": 31402,"Record function id": 0, "Ev Idx": 4265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198175374.545, "dur": 2.937, + "args": { + "External id": 31403,"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": 2338707, "tid": 2379456, + "ts": 6197198175375.040, "dur": 1.796, + "args": { + "External id": 31404,"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": 2338707, "tid": 2379456, + "ts": 6197198175375.581, "dur": 1.192, + "args": { + "External id": 31405,"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": 2338707, "tid": 2379456, + "ts": 6197198175381.094, "dur": 4.091, + "args": { + "External id": 31406,"Record function id": 0, "Ev Idx": 4269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198175382.588, "dur": 2.183, + "args": { + "External id": 31407,"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": 2338707, "tid": 2379456, + "ts": 6197198175383.299, "dur": 0.943, + "args": { + "External id": 31408,"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": 2338707, "tid": 2379456, + "ts": 6197198175383.579, "dur": 0.592, + "args": { + "External id": 31409,"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": 2338707, "tid": 2379456, + "ts": 6197198175388.320, "dur": 6.912, + "args": { + "External id": 31410,"Record function id": 0, "Ev Idx": 4273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198175389.796, "dur": 5.027, + "args": { + "External id": 31411,"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": 2338707, "tid": 2379456, + "ts": 6197198175393.289, "dur": 1.133, + "args": { + "External id": 31412,"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": 2338707, "tid": 2379456, + "ts": 6197198175393.589, "dur": 0.647, + "args": { + "External id": 31413,"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": 2338707, "tid": 2379456, + "ts": 6197198175398.422, "dur": 5.726, + "args": { + "External id": 31414,"Record function id": 0, "Ev Idx": 4277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198175399.682, "dur": 4.032, + "args": { + "External id": 31415,"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": 2338707, "tid": 2379456, + "ts": 6197198175400.200, "dur": 3.100, + "args": { + "External id": 31416,"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": 2338707, "tid": 2379456, + "ts": 6197198175400.584, "dur": 2.626, + "args": { + "External id": 31417,"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": 2338707, "tid": 2379456, + "ts": 6197198175407.939, "dur": 3.671, + "args": { + "External id": 31418,"Record function id": 0, "Ev Idx": 4281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198175409.027, "dur": 2.152, + "args": { + "External id": 31419,"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": 2338707, "tid": 2379456, + "ts": 6197198175409.503, "dur": 1.280, + "args": { + "External id": 31420,"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": 2338707, "tid": 2379456, + "ts": 6197198175409.806, "dur": 0.902, + "args": { + "External id": 31421,"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": 2338707, "tid": 2379456, + "ts": 6197198175415.088, "dur": 3.735, + "args": { + "External id": 31422,"Record function id": 0, "Ev Idx": 4285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198175416.200, "dur": 2.232, + "args": { + "External id": 31423,"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": 2338707, "tid": 2379456, + "ts": 6197198175416.875, "dur": 0.930, + "args": { + "External id": 31424,"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": 2338707, "tid": 2379456, + "ts": 6197198175417.158, "dur": 0.570, + "args": { + "External id": 31425,"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": 2338707, "tid": 2379456, + "ts": 6197198175422.275, "dur": 3.872, + "args": { + "External id": 31426,"Record function id": 0, "Ev Idx": 4289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198175423.478, "dur": 2.185, + "args": { + "External id": 31427,"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": 2338707, "tid": 2379456, + "ts": 6197198175423.950, "dur": 1.294, + "args": { + "External id": 31428,"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": 2338707, "tid": 2379456, + "ts": 6197198175424.433, "dur": 0.700, + "args": { + "External id": 31429,"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": 2338707, "tid": 2379456, + "ts": 6197198175430.304, "dur": 63466.518, + "args": { + "External id": 31430,"Record function id": 0, "Sequence number": 479785, "Fwd thread id": 1, "Ev Idx": 4293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197198175431.637, "dur": 63455.165, + "args": { + "External id": 31431,"Sequence number": 479785, "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": 2338707, "tid": 2379456, "ts": 6197198175431.637, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.9)", "pid": 2338707, "tid": 2379456, + "ts": 6197198175461.836, "dur": 38.636, + "args": { + "External id": 31432,"Record function id": 0, "Ev Idx": 4295 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.9)", "pid": 2338707, "tid": 2379456, + "ts": 6197198175508.181, "dur": 62.504, + "args": { + "External id": 31433,"Record function id": 0, "Ev Idx": 4296 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.9)", "pid": 2338707, "tid": 2379456, + "ts": 6197198175576.520, "dur": 63302.489, + "args": { + "External id": 31434,"Record function id": 0, "Ev Idx": 4297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197198175664.610, "dur": 6.712, + "args": { + "External id": 31435,"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": 2338707, "tid": 2379456, + "ts": 6197198175681.087, "dur": 4.662, + "args": { + "External id": 31436,"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": 2338707, "tid": 2379456, + "ts": 6197198175716.842, "dur": 62292.873, + "args": { + "External id": 31437,"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": 2338707, "tid": 2379456, + "ts": 6197198175732.343, "dur": 62264.509, + "args": { + "External id": 31438,"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": 2338707, "tid": 2379456, + "ts": 6197198175821.230, "dur": 19.106, + "args": { + "External id": 31439,"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": 2338707, "tid": 2379456, + "ts": 6197198175863.490, "dur": 62089.949, + "args": { + "External id": 31440,"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": 2338707, "tid": 2379456, + "ts": 6197198175866.374, "dur": 62085.825, + "args": { + "External id": 31441,"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": 2338707, "tid": 2379456, + "ts": 6197198175871.165, "dur": 10.740, + "args": { + "External id": 31442,"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": 2338707, "tid": 2379456, + "ts": 6197198175883.767, "dur": 62063.270, + "args": { + "External id": 31443,"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": 2338707, "tid": 2379456, + "ts": 6197198238157.127, "dur": 12.080, + "args": { + "External id": 31444,"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": 2338707, "tid": 2379456, + "ts": 6197198238160.580, "dur": 8.020, + "args": { + "External id": 31445,"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": 2338707, "tid": 2379456, + "ts": 6197198238200.472, "dur": 370.864, + "args": { + "External id": 31446,"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": 2338707, "tid": 2379456, + "ts": 6197198238234.487, "dur": 331.706, + "args": { + "External id": 31447,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197198238246.918, "dur": 313.504, + "args": { + "External id": 31448,"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": 2338707, "tid": 2379456, + "ts": 6197198238591.356, "dur": 2.504, + "args": { + "External id": 31449,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2379456, + "ts": 6197198238652.374, "dur": 8.403, + "args": { + "External id": 31450,"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": 2338707, "tid": 2379456, + "ts": 6197198238722.776, "dur": 2.163, + "args": { + "External id": 31451,"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": 2338707, "tid": 2379456, + "ts": 6197198238744.116, "dur": 0.834, + "args": { + "External id": 31452,"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": 2338707, "tid": 2379456, + "ts": 6197198238756.500, "dur": 1.030, + "args": { + "External id": 31453,"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": 2338707, "tid": 2379456, + "ts": 6197198238768.102, "dur": 2.779, + "args": { + "External id": 31454,"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": 2338707, "tid": 2379456, + "ts": 6197198238780.801, "dur": 1.062, + "args": { + "External id": 31455,"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": 2338707, "tid": 2379456, + "ts": 6197198238792.751, "dur": 0.982, + "args": { + "External id": 31456,"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": 2338707, "tid": 2379456, + "ts": 6197198238804.318, "dur": 2.839, + "args": { + "External id": 31457,"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": 2338707, "tid": 2379456, + "ts": 6197198238816.664, "dur": 2.842, + "args": { + "External id": 31458,"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": 2338707, "tid": 2379456, + "ts": 6197198238912.036, "dur": 2947.276, + "args": { + "External id": 31459,"Record function id": 0, "Ev Idx": 4322 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.8)", "pid": 2338707, "tid": 2379456, + "ts": 6197198238932.144, "dur": 1101.876, + "args": { + "External id": 31460,"Record function id": 0, "Ev Idx": 4323 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.8)", "pid": 2338707, "tid": 2379456, + "ts": 6197198238946.991, "dur": 382.056, + "args": { + "External id": 31461,"Record function id": 0, "Ev Idx": 4324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6197198239035.481, "dur": 4.251, + "args": { + "External id": 31462,"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": 2338707, "tid": 2379456, + "ts": 6197198239043.657, "dur": 1.145, + "args": { + "External id": 31463,"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": 2338707, "tid": 2379456, + "ts": 6197198239046.466, "dur": 1.050, + "args": { + "External id": 31464,"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": 2338707, "tid": 2379456, + "ts": 6197198239049.285, "dur": 0.727, + "args": { + "External id": 31465,"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": 2338707, "tid": 2379456, + "ts": 6197198239051.380, "dur": 34.480, + "args": { + "External id": 31466,"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": 2338707, "tid": 2379456, + "ts": 6197198239090.415, "dur": 1.379, + "args": { + "External id": 31467,"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": 2338707, "tid": 2379456, + "ts": 6197198239093.753, "dur": 4.153, + "args": { + "External id": 31468,"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": 2338707, "tid": 2379456, + "ts": 6197198239099.635, "dur": 0.548, + "args": { + "External id": 31469,"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": 2338707, "tid": 2379456, + "ts": 6197198239103.273, "dur": 0.585, + "args": { + "External id": 31470,"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": 2338707, "tid": 2379456, + "ts": 6197198239105.845, "dur": 0.600, + "args": { + "External id": 31471,"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": 2338707, "tid": 2379456, + "ts": 6197198239125.009, "dur": 168.391, + "args": { + "External id": 31472,"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": 2338707, "tid": 2379456, + "ts": 6197198239142.019, "dur": 146.544, + "args": { + "External id": 31473,"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": 2338707, "tid": 2379456, + "ts": 6197198239167.789, "dur": 14.817, + "args": { + "External id": 31474,"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": 2338707, "tid": 2379456, + "ts": 6197198239186.539, "dur": 72.687, + "args": { + "External id": 31475,"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": 2338707, "tid": 2379456, + "ts": 6197198239189.419, "dur": 69.503, + "args": { + "External id": 31476,"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": 2338707, "tid": 2379456, + "ts": 6197198239193.843, "dur": 5.765, + "args": { + "External id": 31477,"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": 2338707, "tid": 2379456, + "ts": 6197198239201.492, "dur": 56.628, + "args": { + "External id": 31478,"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": 2338707, "tid": 2379456, + "ts": 6197198239424.167, "dur": 602.596, + "args": { + "External id": 31479,"Record function id": 0, "Ev Idx": 4342 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.7)", "pid": 2338707, "tid": 2379456, + "ts": 6197198239442.816, "dur": 571.858, + "args": { + "External id": 31480,"Record function id": 0, "Ev Idx": 4343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197198239507.482, "dur": 5.135, + "args": { + "External id": 31481,"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": 2338707, "tid": 2379456, + "ts": 6197198239527.165, "dur": 30.192, + "args": { + "External id": 31482,"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": 2338707, "tid": 2379456, + "ts": 6197198239532.922, "dur": 1.787, + "args": { + "External id": 31483,"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": 2338707, "tid": 2379456, + "ts": 6197198239536.111, "dur": 2.901, + "args": { + "External id": 31484,"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": 2338707, "tid": 2379456, + "ts": 6197198239540.934, "dur": 0.450, + "args": { + "External id": 31485,"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": 2338707, "tid": 2379456, + "ts": 6197198239543.381, "dur": 0.705, + "args": { + "External id": 31486,"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": 2338707, "tid": 2379456, + "ts": 6197198239545.182, "dur": 0.480, + "args": { + "External id": 31487,"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": 2338707, "tid": 2379456, + "ts": 6197198239547.125, "dur": 0.432, + "args": { + "External id": 31488,"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": 2338707, "tid": 2379456, + "ts": 6197198239549.043, "dur": 0.409, + "args": { + "External id": 31489,"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": 2338707, "tid": 2379456, + "ts": 6197198239550.355, "dur": 0.446, + "args": { + "External id": 31490,"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": 2338707, "tid": 2379456, + "ts": 6197198239552.268, "dur": 0.373, + "args": { + "External id": 31491,"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": 2338707, "tid": 2379456, + "ts": 6197198239567.334, "dur": 40.944, + "args": { + "External id": 31492,"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": 2338707, "tid": 2379456, + "ts": 6197198239638.075, "dur": 136.293, + "args": { + "External id": 31493,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2379456, + "ts": 6197198239647.717, "dur": 4.230, + "args": { + "External id": 31494,"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": 2338707, "tid": 2379456, + "ts": 6197198239656.835, "dur": 9.972, + "args": { + "External id": 31495,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2379456, + "ts": 6197198239661.245, "dur": 5.144, + "args": { + "External id": 31496,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2379456, + "ts": 6197198239664.462, "dur": 0.728, + "args": { + "External id": 31497,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197198239673.298, "dur": 48.172, + "args": { + "External id": 31498,"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": 2338707, "tid": 2379456, + "ts": 6197198239675.296, "dur": 0.642, + "args": { + "External id": 31499,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197198239677.773, "dur": 0.371, + "args": { + "External id": 31500,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2379456, + "ts": 6197198239683.422, "dur": 0.530, + "args": { + "External id": 31501,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2379456, + "ts": 6197198239685.319, "dur": 0.446, + "args": { + "External id": 31502,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2379456, + "ts": 6197198239687.027, "dur": 0.476, + "args": { + "External id": 31503,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2379456, + "ts": 6197198239689.139, "dur": 0.405, + "args": { + "External id": 31504,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2379456, + "ts": 6197198239690.929, "dur": 2.713, + "args": { + "External id": 31505,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2379456, + "ts": 6197198239694.669, "dur": 0.378, + "args": { + "External id": 31506,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2379456, + "ts": 6197198239696.816, "dur": 0.366, + "args": { + "External id": 31507,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2379456, + "ts": 6197198239734.635, "dur": 32.056, + "args": { + "External id": 31508,"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": 2338707, "tid": 2379456, + "ts": 6197198239819.798, "dur": 126.989, + "args": { + "External id": 31509,"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": 2338707, "tid": 2379456, + "ts": 6197198239849.711, "dur": 93.354, + "args": { + "External id": 31510,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197198239860.077, "dur": 78.300, + "args": { + "External id": 31511,"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": 2338707, "tid": 2379456, + "ts": 6197198239961.999, "dur": 1.792, + "args": { + "External id": 31512,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197198240042.534, "dur": 1795.491, + "args": { + "External id": 31513,"Sequence number": 479784, "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": 2338707, "tid": 2379456, "ts": 6197198240042.534, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6197198240194.726, "dur": 110.252, + "args": { + "External id": 31514,"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": 2338707, "tid": 2379456, + "ts": 6197198240351.027, "dur": 38.743, + "args": { + "External id": 31515,"kernel_hash": "cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/u7/cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs.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": 2338707, "tid": 2379456, + "ts": 6197198240408.316, "dur": 49.843, + "args": { + "External id": 31516,"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": 2338707, "tid": 2379456, + "ts": 6197198240466.796, "dur": 32.349, + "args": { + "External id": 31517,"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": 2338707, "tid": 2379456, + "ts": 6197198240505.628, "dur": 32.929, + "args": { + "External id": 31518,"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": 2338707, "tid": 2379456, + "ts": 6197198240547.122, "dur": 28.196, + "args": { + "External id": 31519,"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": 2338707, "tid": 2379456, + "ts": 6197198240582.373, "dur": 29.334, + "args": { + "External id": 31520,"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": 2338707, "tid": 2379456, + "ts": 6197198240638.295, "dur": 22.906, + "args": { + "External id": 31521,"kernel_hash": "cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/wm/cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s.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": 2338707, "tid": 2379456, + "ts": 6197198240681.217, "dur": 46.120, + "args": { + "External id": 31522,"kernel_hash": "cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql", "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/qt/cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql.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": 2338707, "tid": 2379456, + "ts": 6197198240752.952, "dur": 20.598, + "args": { + "External id": 31523,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197198240786.821, "dur": 21.471, + "args": { + "External id": 31524,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197198240819.800, "dur": 41.962, + "args": { + "External id": 31525,"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": 2338707, "tid": 2379456, + "ts": 6197198240865.702, "dur": 37.487, + "args": { + "External id": 31526,"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": 2338707, "tid": 2379456, + "ts": 6197198240935.379, "dur": 289.673, + "args": { + "External id": 31527,"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": 2338707, "tid": 2379456, + "ts": 6197198241013.573, "dur": 6.048, + "args": { + "External id": 31528,"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": 2338707, "tid": 2379456, + "ts": 6197198241021.728, "dur": 4.758, + "args": { + "External id": 31529,"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": 2338707, "tid": 2379456, + "ts": 6197198241027.756, "dur": 2.414, + "args": { + "External id": 31530,"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": 2338707, "tid": 2379456, + "ts": 6197198241031.770, "dur": 2.206, + "args": { + "External id": 31531,"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": 2338707, "tid": 2379456, + "ts": 6197198241115.257, "dur": 5.283, + "args": { + "External id": 31532,"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": 2338707, "tid": 2379456, + "ts": 6197198241117.156, "dur": 2.980, + "args": { + "External id": 31533,"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": 2338707, "tid": 2379456, + "ts": 6197198241122.461, "dur": 32.187, + "args": { + "External id": 31534,"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": 2338707, "tid": 2379456, + "ts": 6197198241128.050, "dur": 1.880, + "args": { + "External id": 31535,"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": 2338707, "tid": 2379456, + "ts": 6197198241156.236, "dur": 2.566, + "args": { + "External id": 31536,"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": 2338707, "tid": 2379456, + "ts": 6197198241158.082, "dur": 0.637, + "args": { + "External id": 31537,"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": 2338707, "tid": 2379456, + "ts": 6197198241159.885, "dur": 15.499, + "args": { + "External id": 31538,"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": 2338707, "tid": 2379456, + "ts": 6197198241162.436, "dur": 0.927, + "args": { + "External id": 31539,"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": 2338707, "tid": 2379456, + "ts": 6197198241262.488, "dur": 31.088, + "args": { + "External id": 31540,"kernel_hash": "cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4", "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/yk/cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4.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": 2338707, "tid": 2379456, + "ts": 6197198241309.732, "dur": 16.692, + "args": { + "External id": 31541,"kernel_hash": "ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg", "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/eu/ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg.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": 2338707, "tid": 2379456, + "ts": 6197198241334.485, "dur": 47.358, + "args": { + "External id": 31542,"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": 2338707, "tid": 2379456, + "ts": 6197198241389.240, "dur": 40.307, + "args": { + "External id": 31543,"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": 2338707, "tid": 2379456, + "ts": 6197198241440.806, "dur": 24.980, + "args": { + "External id": 31544,"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": 2338707, "tid": 2379456, + "ts": 6197198241472.099, "dur": 35.113, + "args": { + "External id": 31545,"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": 2338707, "tid": 2379456, + "ts": 6197198241515.067, "dur": 28.648, + "args": { + "External id": 31546,"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": 2338707, "tid": 2379456, + "ts": 6197198241551.611, "dur": 31.208, + "args": { + "External id": 31547,"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": 2338707, "tid": 2379456, + "ts": 6197198241600.249, "dur": 24.450, + "args": { + "External id": 31548,"kernel_hash": "c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/6w/c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7.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": 2338707, "tid": 2379456, + "ts": 6197198241639.413, "dur": 26.134, + "args": { + "External id": 31549,"kernel_hash": "ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx", "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/kj/ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx.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": 2338707, "tid": 2379456, + "ts": 6197198241679.027, "dur": 17.671, + "args": { + "External id": 31550,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197198241741.460, "dur": 27.248, + "args": { + "External id": 31551,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197198241788.438, "dur": 16.569, + "args": { + "External id": 31552,"kernel_hash": "cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/eb/cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b.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": 2338707, "tid": 2379456, + "ts": 6197198241885.371, "dur": 15.088, + "args": { + "External id": 31553,"Record function id": 0, "Ev Idx": 4416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198241888.690, "dur": 10.752, + "args": { + "External id": 31554,"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": 2338707, "tid": 2379456, + "ts": 6197198241892.829, "dur": 5.777, + "args": { + "External id": 31555,"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": 2338707, "tid": 2379456, + "ts": 6197198241894.152, "dur": 4.358, + "args": { + "External id": 31556,"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": 2338707, "tid": 2379456, + "ts": 6197198241905.432, "dur": 4.176, + "args": { + "External id": 31557,"Record function id": 0, "Ev Idx": 4420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198241906.700, "dur": 2.447, + "args": { + "External id": 31558,"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": 2338707, "tid": 2379456, + "ts": 6197198241907.455, "dur": 1.274, + "args": { + "External id": 31559,"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": 2338707, "tid": 2379456, + "ts": 6197198241907.791, "dur": 0.835, + "args": { + "External id": 31560,"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": 2338707, "tid": 2379456, + "ts": 6197198241912.907, "dur": 4.128, + "args": { + "External id": 31561,"Record function id": 0, "Ev Idx": 4424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198241914.484, "dur": 2.137, + "args": { + "External id": 31562,"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": 2338707, "tid": 2379456, + "ts": 6197198241915.122, "dur": 1.118, + "args": { + "External id": 31563,"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": 2338707, "tid": 2379456, + "ts": 6197198241915.505, "dur": 0.670, + "args": { + "External id": 31564,"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": 2338707, "tid": 2379456, + "ts": 6197198241920.168, "dur": 8.663, + "args": { + "External id": 31565,"Record function id": 0, "Ev Idx": 4428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198241924.909, "dur": 3.464, + "args": { + "External id": 31566,"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": 2338707, "tid": 2379456, + "ts": 6197198241925.474, "dur": 2.453, + "args": { + "External id": 31567,"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": 2338707, "tid": 2379456, + "ts": 6197198241926.844, "dur": 0.987, + "args": { + "External id": 31568,"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": 2338707, "tid": 2379456, + "ts": 6197198241932.111, "dur": 6.450, + "args": { + "External id": 31569,"Record function id": 0, "Ev Idx": 4432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198241933.321, "dur": 4.801, + "args": { + "External id": 31570,"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": 2338707, "tid": 2379456, + "ts": 6197198241934.075, "dur": 3.562, + "args": { + "External id": 31571,"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": 2338707, "tid": 2379456, + "ts": 6197198241934.415, "dur": 3.158, + "args": { + "External id": 31572,"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": 2338707, "tid": 2379456, + "ts": 6197198241941.774, "dur": 3.767, + "args": { + "External id": 31573,"Record function id": 0, "Ev Idx": 4436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198241942.917, "dur": 2.204, + "args": { + "External id": 31574,"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": 2338707, "tid": 2379456, + "ts": 6197198241943.563, "dur": 1.113, + "args": { + "External id": 31575,"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": 2338707, "tid": 2379456, + "ts": 6197198241943.873, "dur": 0.732, + "args": { + "External id": 31576,"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": 2338707, "tid": 2379456, + "ts": 6197198241948.722, "dur": 5.465, + "args": { + "External id": 31577,"Record function id": 0, "Ev Idx": 4440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198241950.138, "dur": 3.618, + "args": { + "External id": 31578,"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": 2338707, "tid": 2379456, + "ts": 6197198241951.147, "dur": 1.991, + "args": { + "External id": 31579,"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": 2338707, "tid": 2379456, + "ts": 6197198241952.062, "dur": 0.970, + "args": { + "External id": 31580,"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": 2338707, "tid": 2379456, + "ts": 6197198241957.388, "dur": 4.227, + "args": { + "External id": 31581,"Record function id": 0, "Ev Idx": 4444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198241958.915, "dur": 2.283, + "args": { + "External id": 31582,"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": 2338707, "tid": 2379456, + "ts": 6197198241959.553, "dur": 1.242, + "args": { + "External id": 31583,"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": 2338707, "tid": 2379456, + "ts": 6197198241959.851, "dur": 0.860, + "args": { + "External id": 31584,"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": 2338707, "tid": 2379456, + "ts": 6197198241964.781, "dur": 3.523, + "args": { + "External id": 31585,"Record function id": 0, "Ev Idx": 4448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198241966.056, "dur": 1.825, + "args": { + "External id": 31586,"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": 2338707, "tid": 2379456, + "ts": 6197198241966.502, "dur": 0.978, + "args": { + "External id": 31587,"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": 2338707, "tid": 2379456, + "ts": 6197198241966.762, "dur": 0.636, + "args": { + "External id": 31588,"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": 2338707, "tid": 2379456, + "ts": 6197198241972.228, "dur": 65298.675, + "args": { + "External id": 31589,"Record function id": 0, "Sequence number": 479783, "Fwd thread id": 1, "Ev Idx": 4452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197198241973.860, "dur": 65287.653, + "args": { + "External id": 31590,"Sequence number": 479783, "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": 2338707, "tid": 2379456, "ts": 6197198241973.860, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.8)", "pid": 2338707, "tid": 2379456, + "ts": 6197198242002.772, "dur": 36.482, + "args": { + "External id": 31591,"Record function id": 0, "Ev Idx": 4454 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.8)", "pid": 2338707, "tid": 2379456, + "ts": 6197198242046.958, "dur": 103.418, + "args": { + "External id": 31592,"Record function id": 0, "Ev Idx": 4455 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.8)", "pid": 2338707, "tid": 2379456, + "ts": 6197198242158.226, "dur": 65095.578, + "args": { + "External id": 31593,"Record function id": 0, "Ev Idx": 4456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197198242247.903, "dur": 7.905, + "args": { + "External id": 31594,"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": 2338707, "tid": 2379456, + "ts": 6197198242266.599, "dur": 4.894, + "args": { + "External id": 31595,"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": 2338707, "tid": 2379456, + "ts": 6197198242286.844, "dur": 64082.974, + "args": { + "External id": 31596,"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": 2338707, "tid": 2379456, + "ts": 6197198242301.158, "dur": 64055.397, + "args": { + "External id": 31597,"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": 2338707, "tid": 2379456, + "ts": 6197198242398.307, "dur": 16.955, + "args": { + "External id": 31598,"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": 2338707, "tid": 2379456, + "ts": 6197198242439.431, "dur": 63874.143, + "args": { + "External id": 31599,"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": 2338707, "tid": 2379456, + "ts": 6197198242442.268, "dur": 63870.322, + "args": { + "External id": 31600,"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": 2338707, "tid": 2379456, + "ts": 6197198242446.718, "dur": 10.009, + "args": { + "External id": 31601,"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": 2338707, "tid": 2379456, + "ts": 6197198242458.526, "dur": 63848.856, + "args": { + "External id": 31602,"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": 2338707, "tid": 2379456, + "ts": 6197198306473.785, "dur": 12.102, + "args": { + "External id": 31603,"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": 2338707, "tid": 2379456, + "ts": 6197198306477.429, "dur": 8.080, + "args": { + "External id": 31604,"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": 2338707, "tid": 2379456, + "ts": 6197198306516.659, "dur": 396.691, + "args": { + "External id": 31605,"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": 2338707, "tid": 2379456, + "ts": 6197198306549.170, "dur": 359.095, + "args": { + "External id": 31606,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197198306560.690, "dur": 341.162, + "args": { + "External id": 31607,"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": 2338707, "tid": 2379456, + "ts": 6197198306936.398, "dur": 2.487, + "args": { + "External id": 31608,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2379456, + "ts": 6197198306998.268, "dur": 6.348, + "args": { + "External id": 31609,"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": 2338707, "tid": 2379456, + "ts": 6197198307050.623, "dur": 1.372, + "args": { + "External id": 31610,"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": 2338707, "tid": 2379456, + "ts": 6197198307116.702, "dur": 1.421, + "args": { + "External id": 31611,"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": 2338707, "tid": 2379456, + "ts": 6197198307130.111, "dur": 1.147, + "args": { + "External id": 31612,"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": 2338707, "tid": 2379456, + "ts": 6197198307142.612, "dur": 0.946, + "args": { + "External id": 31613,"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": 2338707, "tid": 2379456, + "ts": 6197198307155.747, "dur": 1.219, + "args": { + "External id": 31614,"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": 2338707, "tid": 2379456, + "ts": 6197198307166.982, "dur": 0.778, + "args": { + "External id": 31615,"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": 2338707, "tid": 2379456, + "ts": 6197198307178.115, "dur": 2.465, + "args": { + "External id": 31616,"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": 2338707, "tid": 2379456, + "ts": 6197198307189.830, "dur": 1.220, + "args": { + "External id": 31617,"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": 2338707, "tid": 2379456, + "ts": 6197198307287.781, "dur": 3016.030, + "args": { + "External id": 31618,"Record function id": 0, "Ev Idx": 4481 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.7)", "pid": 2338707, "tid": 2379456, + "ts": 6197198307308.577, "dur": 1103.181, + "args": { + "External id": 31619,"Record function id": 0, "Ev Idx": 4482 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.7)", "pid": 2338707, "tid": 2379456, + "ts": 6197198307323.408, "dur": 335.118, + "args": { + "External id": 31620,"Record function id": 0, "Ev Idx": 4483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6197198307417.148, "dur": 4.296, + "args": { + "External id": 31621,"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": 2338707, "tid": 2379456, + "ts": 6197198307425.103, "dur": 1.193, + "args": { + "External id": 31622,"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": 2338707, "tid": 2379456, + "ts": 6197198307428.095, "dur": 0.779, + "args": { + "External id": 31623,"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": 2338707, "tid": 2379456, + "ts": 6197198307430.761, "dur": 1.054, + "args": { + "External id": 31624,"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": 2338707, "tid": 2379456, + "ts": 6197198307433.406, "dur": 0.909, + "args": { + "External id": 31625,"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": 2338707, "tid": 2379456, + "ts": 6197198307435.552, "dur": 0.811, + "args": { + "External id": 31626,"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": 2338707, "tid": 2379456, + "ts": 6197198307438.171, "dur": 2.216, + "args": { + "External id": 31627,"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": 2338707, "tid": 2379456, + "ts": 6197198307442.110, "dur": 3.043, + "args": { + "External id": 31628,"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": 2338707, "tid": 2379456, + "ts": 6197198307446.651, "dur": 0.861, + "args": { + "External id": 31629,"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": 2338707, "tid": 2379456, + "ts": 6197198307449.141, "dur": 0.887, + "args": { + "External id": 31630,"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": 2338707, "tid": 2379456, + "ts": 6197198307469.388, "dur": 161.009, + "args": { + "External id": 31631,"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": 2338707, "tid": 2379456, + "ts": 6197198307485.766, "dur": 140.084, + "args": { + "External id": 31632,"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": 2338707, "tid": 2379456, + "ts": 6197198307511.859, "dur": 15.280, + "args": { + "External id": 31633,"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": 2338707, "tid": 2379456, + "ts": 6197198307530.957, "dur": 65.814, + "args": { + "External id": 31634,"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": 2338707, "tid": 2379456, + "ts": 6197198307533.689, "dur": 62.723, + "args": { + "External id": 31635,"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": 2338707, "tid": 2379456, + "ts": 6197198307537.856, "dur": 5.772, + "args": { + "External id": 31636,"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": 2338707, "tid": 2379456, + "ts": 6197198307545.478, "dur": 50.290, + "args": { + "External id": 31637,"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": 2338707, "tid": 2379456, + "ts": 6197198307769.948, "dur": 634.005, + "args": { + "External id": 31638,"Record function id": 0, "Ev Idx": 4501 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.6)", "pid": 2338707, "tid": 2379456, + "ts": 6197198307788.101, "dur": 603.469, + "args": { + "External id": 31639,"Record function id": 0, "Ev Idx": 4502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197198307855.081, "dur": 5.749, + "args": { + "External id": 31640,"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": 2338707, "tid": 2379456, + "ts": 6197198307876.312, "dur": 30.356, + "args": { + "External id": 31641,"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": 2338707, "tid": 2379456, + "ts": 6197198307881.608, "dur": 1.851, + "args": { + "External id": 31642,"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": 2338707, "tid": 2379456, + "ts": 6197198307885.444, "dur": 0.452, + "args": { + "External id": 31643,"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": 2338707, "tid": 2379456, + "ts": 6197198307887.639, "dur": 2.122, + "args": { + "External id": 31644,"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": 2338707, "tid": 2379456, + "ts": 6197198307891.306, "dur": 0.306, + "args": { + "External id": 31645,"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": 2338707, "tid": 2379456, + "ts": 6197198307892.668, "dur": 0.736, + "args": { + "External id": 31646,"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": 2338707, "tid": 2379456, + "ts": 6197198307895.066, "dur": 0.431, + "args": { + "External id": 31647,"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": 2338707, "tid": 2379456, + "ts": 6197198307896.876, "dur": 0.312, + "args": { + "External id": 31648,"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": 2338707, "tid": 2379456, + "ts": 6197198307898.473, "dur": 0.543, + "args": { + "External id": 31649,"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": 2338707, "tid": 2379456, + "ts": 6197198307900.668, "dur": 0.328, + "args": { + "External id": 31650,"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": 2338707, "tid": 2379456, + "ts": 6197198307917.895, "dur": 41.730, + "args": { + "External id": 31651,"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": 2338707, "tid": 2379456, + "ts": 6197198307988.734, "dur": 167.418, + "args": { + "External id": 31652,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2379456, + "ts": 6197198307999.729, "dur": 2.866, + "args": { + "External id": 31653,"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": 2338707, "tid": 2379456, + "ts": 6197198308007.590, "dur": 12.750, + "args": { + "External id": 31654,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2379456, + "ts": 6197198308012.134, "dur": 7.791, + "args": { + "External id": 31655,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2379456, + "ts": 6197198308015.801, "dur": 2.850, + "args": { + "External id": 31656,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197198308027.239, "dur": 71.192, + "args": { + "External id": 31657,"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": 2338707, "tid": 2379456, + "ts": 6197198308029.069, "dur": 0.544, + "args": { + "External id": 31658,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197198308031.716, "dur": 0.387, + "args": { + "External id": 31659,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2379456, + "ts": 6197198308033.752, "dur": 0.383, + "args": { + "External id": 31660,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2379456, + "ts": 6197198308035.501, "dur": 0.463, + "args": { + "External id": 31661,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2379456, + "ts": 6197198308037.226, "dur": 0.437, + "args": { + "External id": 31662,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2379456, + "ts": 6197198308039.216, "dur": 0.295, + "args": { + "External id": 31663,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2379456, + "ts": 6197198308040.600, "dur": 0.471, + "args": { + "External id": 31664,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2379456, + "ts": 6197198308042.944, "dur": 2.413, + "args": { + "External id": 31665,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2379456, + "ts": 6197198308046.916, "dur": 0.336, + "args": { + "External id": 31666,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2379456, + "ts": 6197198308112.901, "dur": 35.178, + "args": { + "External id": 31667,"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": 2338707, "tid": 2379456, + "ts": 6197198308203.655, "dur": 115.468, + "args": { + "External id": 31668,"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": 2338707, "tid": 2379456, + "ts": 6197198308226.065, "dur": 89.379, + "args": { + "External id": 31669,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197198308237.827, "dur": 73.696, + "args": { + "External id": 31670,"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": 2338707, "tid": 2379456, + "ts": 6197198308337.031, "dur": 1.900, + "args": { + "External id": 31671,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197198308419.833, "dur": 1857.124, + "args": { + "External id": 31672,"Sequence number": 479782, "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": 2338707, "tid": 2379456, "ts": 6197198308419.833, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6197198308533.314, "dur": 105.663, + "args": { + "External id": 31673,"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": 2338707, "tid": 2379456, + "ts": 6197198308679.195, "dur": 60.807, + "args": { + "External id": 31674,"kernel_hash": "cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/u7/cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs.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": 2338707, "tid": 2379456, + "ts": 6197198308766.319, "dur": 58.070, + "args": { + "External id": 31675,"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": 2338707, "tid": 2379456, + "ts": 6197198308834.202, "dur": 32.274, + "args": { + "External id": 31676,"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": 2338707, "tid": 2379456, + "ts": 6197198308872.856, "dur": 33.000, + "args": { + "External id": 31677,"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": 2338707, "tid": 2379456, + "ts": 6197198308912.610, "dur": 28.306, + "args": { + "External id": 31678,"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": 2338707, "tid": 2379456, + "ts": 6197198308950.216, "dur": 29.257, + "args": { + "External id": 31679,"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": 2338707, "tid": 2379456, + "ts": 6197198309008.562, "dur": 26.720, + "args": { + "External id": 31680,"kernel_hash": "cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/wm/cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s.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": 2338707, "tid": 2379456, + "ts": 6197198309092.920, "dur": 34.961, + "args": { + "External id": 31681,"kernel_hash": "cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql", "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/qt/cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql.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": 2338707, "tid": 2379456, + "ts": 6197198309154.136, "dur": 22.075, + "args": { + "External id": 31682,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197198309190.945, "dur": 17.012, + "args": { + "External id": 31683,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197198309219.309, "dur": 46.016, + "args": { + "External id": 31684,"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": 2338707, "tid": 2379456, + "ts": 6197198309269.509, "dur": 34.583, + "args": { + "External id": 31685,"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": 2338707, "tid": 2379456, + "ts": 6197198309333.852, "dur": 273.806, + "args": { + "External id": 31686,"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": 2338707, "tid": 2379456, + "ts": 6197198309416.937, "dur": 6.205, + "args": { + "External id": 31687,"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": 2338707, "tid": 2379456, + "ts": 6197198309425.506, "dur": 2.832, + "args": { + "External id": 31688,"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": 2338707, "tid": 2379456, + "ts": 6197198309429.690, "dur": 4.555, + "args": { + "External id": 31689,"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": 2338707, "tid": 2379456, + "ts": 6197198309435.786, "dur": 2.095, + "args": { + "External id": 31690,"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": 2338707, "tid": 2379456, + "ts": 6197198309497.826, "dur": 10.246, + "args": { + "External id": 31691,"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": 2338707, "tid": 2379456, + "ts": 6197198309504.992, "dur": 2.854, + "args": { + "External id": 31692,"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": 2338707, "tid": 2379456, + "ts": 6197198309510.036, "dur": 32.747, + "args": { + "External id": 31693,"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": 2338707, "tid": 2379456, + "ts": 6197198309515.402, "dur": 1.813, + "args": { + "External id": 31694,"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": 2338707, "tid": 2379456, + "ts": 6197198309544.473, "dur": 1.925, + "args": { + "External id": 31695,"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": 2338707, "tid": 2379456, + "ts": 6197198309545.696, "dur": 0.609, + "args": { + "External id": 31696,"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": 2338707, "tid": 2379456, + "ts": 6197198309547.445, "dur": 17.075, + "args": { + "External id": 31697,"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": 2338707, "tid": 2379456, + "ts": 6197198309549.940, "dur": 0.455, + "args": { + "External id": 31698,"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": 2338707, "tid": 2379456, + "ts": 6197198309641.305, "dur": 28.138, + "args": { + "External id": 31699,"kernel_hash": "cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4", "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/yk/cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4.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": 2338707, "tid": 2379456, + "ts": 6197198309688.513, "dur": 36.709, + "args": { + "External id": 31700,"kernel_hash": "ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg", "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/eu/ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg.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": 2338707, "tid": 2379456, + "ts": 6197198309736.621, "dur": 53.350, + "args": { + "External id": 31701,"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": 2338707, "tid": 2379456, + "ts": 6197198309796.739, "dur": 43.935, + "args": { + "External id": 31702,"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": 2338707, "tid": 2379456, + "ts": 6197198309849.313, "dur": 23.488, + "args": { + "External id": 31703,"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": 2338707, "tid": 2379456, + "ts": 6197198309881.879, "dur": 35.505, + "args": { + "External id": 31704,"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": 2338707, "tid": 2379456, + "ts": 6197198309925.025, "dur": 28.514, + "args": { + "External id": 31705,"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": 2338707, "tid": 2379456, + "ts": 6197198309961.285, "dur": 30.964, + "args": { + "External id": 31706,"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": 2338707, "tid": 2379456, + "ts": 6197198310011.635, "dur": 77.609, + "args": { + "External id": 31707,"kernel_hash": "c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/6w/c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7.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": 2338707, "tid": 2379456, + "ts": 6197198310117.228, "dur": 27.072, + "args": { + "External id": 31708,"kernel_hash": "ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx", "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/kj/ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx.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": 2338707, "tid": 2379456, + "ts": 6197198310160.075, "dur": 17.858, + "args": { + "External id": 31709,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197198310195.625, "dur": 14.831, + "args": { + "External id": 31710,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197198310223.764, "dur": 19.356, + "args": { + "External id": 31711,"kernel_hash": "cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/eb/cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b.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": 2338707, "tid": 2379456, + "ts": 6197198310326.284, "dur": 16.664, + "args": { + "External id": 31712,"Record function id": 0, "Ev Idx": 4575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198310330.324, "dur": 11.429, + "args": { + "External id": 31713,"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": 2338707, "tid": 2379456, + "ts": 6197198310334.573, "dur": 6.215, + "args": { + "External id": 31714,"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": 2338707, "tid": 2379456, + "ts": 6197198310336.518, "dur": 4.127, + "args": { + "External id": 31715,"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": 2338707, "tid": 2379456, + "ts": 6197198310346.777, "dur": 5.140, + "args": { + "External id": 31716,"Record function id": 0, "Ev Idx": 4579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198310348.585, "dur": 2.869, + "args": { + "External id": 31717,"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": 2338707, "tid": 2379456, + "ts": 6197198310349.492, "dur": 1.521, + "args": { + "External id": 31718,"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": 2338707, "tid": 2379456, + "ts": 6197198310350.209, "dur": 0.701, + "args": { + "External id": 31719,"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": 2338707, "tid": 2379456, + "ts": 6197198310355.274, "dur": 4.448, + "args": { + "External id": 31720,"Record function id": 0, "Ev Idx": 4583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198310356.720, "dur": 2.567, + "args": { + "External id": 31721,"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": 2338707, "tid": 2379456, + "ts": 6197198310357.471, "dur": 1.421, + "args": { + "External id": 31722,"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": 2338707, "tid": 2379456, + "ts": 6197198310357.901, "dur": 0.923, + "args": { + "External id": 31723,"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": 2338707, "tid": 2379456, + "ts": 6197198310362.981, "dur": 4.471, + "args": { + "External id": 31724,"Record function id": 0, "Ev Idx": 4587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198310364.361, "dur": 2.619, + "args": { + "External id": 31725,"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": 2338707, "tid": 2379456, + "ts": 6197198310365.103, "dur": 1.461, + "args": { + "External id": 31726,"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": 2338707, "tid": 2379456, + "ts": 6197198310365.884, "dur": 0.566, + "args": { + "External id": 31727,"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": 2338707, "tid": 2379456, + "ts": 6197198310370.591, "dur": 3.630, + "args": { + "External id": 31728,"Record function id": 0, "Ev Idx": 4591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198310371.754, "dur": 2.037, + "args": { + "External id": 31729,"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": 2338707, "tid": 2379456, + "ts": 6197198310372.265, "dur": 1.018, + "args": { + "External id": 31730,"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": 2338707, "tid": 2379456, + "ts": 6197198310372.585, "dur": 0.636, + "args": { + "External id": 31731,"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": 2338707, "tid": 2379456, + "ts": 6197198310377.318, "dur": 5.830, + "args": { + "External id": 31732,"Record function id": 0, "Ev Idx": 4595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198310378.330, "dur": 4.387, + "args": { + "External id": 31733,"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": 2338707, "tid": 2379456, + "ts": 6197198310379.212, "dur": 3.056, + "args": { + "External id": 31734,"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": 2338707, "tid": 2379456, + "ts": 6197198310379.490, "dur": 2.704, + "args": { + "External id": 31735,"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": 2338707, "tid": 2379456, + "ts": 6197198310386.916, "dur": 4.190, + "args": { + "External id": 31736,"Record function id": 0, "Ev Idx": 4599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198310388.102, "dur": 2.609, + "args": { + "External id": 31737,"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": 2338707, "tid": 2379456, + "ts": 6197198310388.729, "dur": 1.423, + "args": { + "External id": 31738,"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": 2338707, "tid": 2379456, + "ts": 6197198310389.354, "dur": 0.698, + "args": { + "External id": 31739,"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": 2338707, "tid": 2379456, + "ts": 6197198310394.490, "dur": 3.499, + "args": { + "External id": 31740,"Record function id": 0, "Ev Idx": 4603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198310395.746, "dur": 1.801, + "args": { + "External id": 31741,"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": 2338707, "tid": 2379456, + "ts": 6197198310396.203, "dur": 0.944, + "args": { + "External id": 31742,"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": 2338707, "tid": 2379456, + "ts": 6197198310396.457, "dur": 0.599, + "args": { + "External id": 31743,"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": 2338707, "tid": 2379456, + "ts": 6197198310401.411, "dur": 33.073, + "args": { + "External id": 31744,"Record function id": 0, "Ev Idx": 4607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198310431.712, "dur": 2.309, + "args": { + "External id": 31745,"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": 2338707, "tid": 2379456, + "ts": 6197198310432.334, "dur": 1.127, + "args": { + "External id": 31746,"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": 2338707, "tid": 2379456, + "ts": 6197198310432.682, "dur": 0.706, + "args": { + "External id": 31747,"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": 2338707, "tid": 2379456, + "ts": 6197198310446.850, "dur": 65298.762, + "args": { + "External id": 31748,"Record function id": 0, "Sequence number": 479781, "Fwd thread id": 1, "Ev Idx": 4611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197198310448.374, "dur": 65287.164, + "args": { + "External id": 31749,"Sequence number": 479781, "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": 2338707, "tid": 2379456, "ts": 6197198310448.374, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.7)", "pid": 2338707, "tid": 2379456, + "ts": 6197198310480.272, "dur": 38.081, + "args": { + "External id": 31750,"Record function id": 0, "Ev Idx": 4613 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.7)", "pid": 2338707, "tid": 2379456, + "ts": 6197198310525.796, "dur": 66.792, + "args": { + "External id": 31751,"Record function id": 0, "Ev Idx": 4614 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.7)", "pid": 2338707, "tid": 2379456, + "ts": 6197198310598.561, "dur": 65127.862, + "args": { + "External id": 31752,"Record function id": 0, "Ev Idx": 4615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197198310687.692, "dur": 6.981, + "args": { + "External id": 31753,"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": 2338707, "tid": 2379456, + "ts": 6197198310722.763, "dur": 5.133, + "args": { + "External id": 31754,"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": 2338707, "tid": 2379456, + "ts": 6197198310745.739, "dur": 64083.095, + "args": { + "External id": 31755,"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": 2338707, "tid": 2379456, + "ts": 6197198310759.720, "dur": 64055.761, + "args": { + "External id": 31756,"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": 2338707, "tid": 2379456, + "ts": 6197198310846.690, "dur": 18.029, + "args": { + "External id": 31757,"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": 2338707, "tid": 2379456, + "ts": 6197198310884.617, "dur": 63885.031, + "args": { + "External id": 31758,"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": 2338707, "tid": 2379456, + "ts": 6197198310887.677, "dur": 63880.922, + "args": { + "External id": 31759,"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": 2338707, "tid": 2379456, + "ts": 6197198310892.215, "dur": 10.526, + "args": { + "External id": 31760,"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": 2338707, "tid": 2379456, + "ts": 6197198310904.683, "dur": 63858.725, + "args": { + "External id": 31761,"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": 2338707, "tid": 2379456, + "ts": 6197198374931.346, "dur": 12.251, + "args": { + "External id": 31762,"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": 2338707, "tid": 2379456, + "ts": 6197198374934.765, "dur": 8.427, + "args": { + "External id": 31763,"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": 2338707, "tid": 2379456, + "ts": 6197198374975.597, "dur": 441.078, + "args": { + "External id": 31764,"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": 2338707, "tid": 2379456, + "ts": 6197198375007.621, "dur": 403.127, + "args": { + "External id": 31765,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197198375018.801, "dur": 386.043, + "args": { + "External id": 31766,"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": 2338707, "tid": 2379456, + "ts": 6197198375440.239, "dur": 2.689, + "args": { + "External id": 31767,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2379456, + "ts": 6197198375504.886, "dur": 6.576, + "args": { + "External id": 31768,"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": 2338707, "tid": 2379456, + "ts": 6197198375557.051, "dur": 1.468, + "args": { + "External id": 31769,"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": 2338707, "tid": 2379456, + "ts": 6197198375573.492, "dur": 1.178, + "args": { + "External id": 31770,"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": 2338707, "tid": 2379456, + "ts": 6197198375585.456, "dur": 1.240, + "args": { + "External id": 31771,"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": 2338707, "tid": 2379456, + "ts": 6197198375597.741, "dur": 0.810, + "args": { + "External id": 31772,"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": 2338707, "tid": 2379456, + "ts": 6197198375610.398, "dur": 1.157, + "args": { + "External id": 31773,"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": 2338707, "tid": 2379456, + "ts": 6197198375622.731, "dur": 1.192, + "args": { + "External id": 31774,"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": 2338707, "tid": 2379456, + "ts": 6197198375634.870, "dur": 2.758, + "args": { + "External id": 31775,"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": 2338707, "tid": 2379456, + "ts": 6197198375646.941, "dur": 0.741, + "args": { + "External id": 31776,"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": 2338707, "tid": 2379456, + "ts": 6197198375762.826, "dur": 2956.665, + "args": { + "External id": 31777,"Record function id": 0, "Ev Idx": 4640 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.6)", "pid": 2338707, "tid": 2379456, + "ts": 6197198375785.986, "dur": 1088.830, + "args": { + "External id": 31778,"Record function id": 0, "Ev Idx": 4641 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.6)", "pid": 2338707, "tid": 2379456, + "ts": 6197198375801.117, "dur": 384.229, + "args": { + "External id": 31779,"Record function id": 0, "Ev Idx": 4642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6197198375894.291, "dur": 5.002, + "args": { + "External id": 31780,"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": 2338707, "tid": 2379456, + "ts": 6197198375902.744, "dur": 1.487, + "args": { + "External id": 31781,"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": 2338707, "tid": 2379456, + "ts": 6197198375906.107, "dur": 1.035, + "args": { + "External id": 31782,"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": 2338707, "tid": 2379456, + "ts": 6197198375909.271, "dur": 0.826, + "args": { + "External id": 31783,"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": 2338707, "tid": 2379456, + "ts": 6197198375911.511, "dur": 0.757, + "args": { + "External id": 31784,"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": 2338707, "tid": 2379456, + "ts": 6197198375913.415, "dur": 0.941, + "args": { + "External id": 31785,"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": 2338707, "tid": 2379456, + "ts": 6197198375916.193, "dur": 2.402, + "args": { + "External id": 31786,"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": 2338707, "tid": 2379456, + "ts": 6197198375920.273, "dur": 2.405, + "args": { + "External id": 31787,"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": 2338707, "tid": 2379456, + "ts": 6197198375924.171, "dur": 0.847, + "args": { + "External id": 31788,"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": 2338707, "tid": 2379456, + "ts": 6197198375928.537, "dur": 0.618, + "args": { + "External id": 31789,"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": 2338707, "tid": 2379456, + "ts": 6197198375949.924, "dur": 199.688, + "args": { + "External id": 31790,"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": 2338707, "tid": 2379456, + "ts": 6197198375966.626, "dur": 177.611, + "args": { + "External id": 31791,"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": 2338707, "tid": 2379456, + "ts": 6197198375991.291, "dur": 18.948, + "args": { + "External id": 31792,"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": 2338707, "tid": 2379456, + "ts": 6197198376014.025, "dur": 101.459, + "args": { + "External id": 31793,"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": 2338707, "tid": 2379456, + "ts": 6197198376016.795, "dur": 98.221, + "args": { + "External id": 31794,"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": 2338707, "tid": 2379456, + "ts": 6197198376021.118, "dur": 5.060, + "args": { + "External id": 31795,"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": 2338707, "tid": 2379456, + "ts": 6197198376027.920, "dur": 85.940, + "args": { + "External id": 31796,"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": 2338707, "tid": 2379456, + "ts": 6197198376279.472, "dur": 587.773, + "args": { + "External id": 31797,"Record function id": 0, "Ev Idx": 4660 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.5)", "pid": 2338707, "tid": 2379456, + "ts": 6197198376301.433, "dur": 553.181, + "args": { + "External id": 31798,"Record function id": 0, "Ev Idx": 4661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197198376367.634, "dur": 6.066, + "args": { + "External id": 31799,"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": 2338707, "tid": 2379456, + "ts": 6197198376387.943, "dur": 30.776, + "args": { + "External id": 31800,"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": 2338707, "tid": 2379456, + "ts": 6197198376393.587, "dur": 1.654, + "args": { + "External id": 31801,"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": 2338707, "tid": 2379456, + "ts": 6197198376396.942, "dur": 0.421, + "args": { + "External id": 31802,"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": 2338707, "tid": 2379456, + "ts": 6197198376399.275, "dur": 2.473, + "args": { + "External id": 31803,"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": 2338707, "tid": 2379456, + "ts": 6197198376403.374, "dur": 0.413, + "args": { + "External id": 31804,"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": 2338707, "tid": 2379456, + "ts": 6197198376404.911, "dur": 0.498, + "args": { + "External id": 31805,"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": 2338707, "tid": 2379456, + "ts": 6197198376407.074, "dur": 0.418, + "args": { + "External id": 31806,"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": 2338707, "tid": 2379456, + "ts": 6197198376409.214, "dur": 0.368, + "args": { + "External id": 31807,"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": 2338707, "tid": 2379456, + "ts": 6197198376410.788, "dur": 0.354, + "args": { + "External id": 31808,"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": 2338707, "tid": 2379456, + "ts": 6197198376412.541, "dur": 0.430, + "args": { + "External id": 31809,"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": 2338707, "tid": 2379456, + "ts": 6197198376428.604, "dur": 42.897, + "args": { + "External id": 31810,"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": 2338707, "tid": 2379456, + "ts": 6197198376500.818, "dur": 105.195, + "args": { + "External id": 31811,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2379456, + "ts": 6197198376510.955, "dur": 2.963, + "args": { + "External id": 31812,"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": 2338707, "tid": 2379456, + "ts": 6197198376519.036, "dur": 12.059, + "args": { + "External id": 31813,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2379456, + "ts": 6197198376523.505, "dur": 7.173, + "args": { + "External id": 31814,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2379456, + "ts": 6197198376526.814, "dur": 2.565, + "args": { + "External id": 31815,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197198376537.634, "dur": 23.749, + "args": { + "External id": 31816,"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": 2338707, "tid": 2379456, + "ts": 6197198376539.306, "dur": 0.693, + "args": { + "External id": 31817,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197198376541.834, "dur": 0.402, + "args": { + "External id": 31818,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2379456, + "ts": 6197198376544.186, "dur": 0.416, + "args": { + "External id": 31819,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2379456, + "ts": 6197198376545.620, "dur": 0.551, + "args": { + "External id": 31820,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2379456, + "ts": 6197198376547.742, "dur": 0.511, + "args": { + "External id": 31821,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2379456, + "ts": 6197198376549.827, "dur": 0.404, + "args": { + "External id": 31822,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2379456, + "ts": 6197198376551.094, "dur": 0.359, + "args": { + "External id": 31823,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2379456, + "ts": 6197198376552.841, "dur": 2.345, + "args": { + "External id": 31824,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2379456, + "ts": 6197198376556.601, "dur": 0.455, + "args": { + "External id": 31825,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2379456, + "ts": 6197198376571.135, "dur": 27.587, + "args": { + "External id": 31826,"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": 2338707, "tid": 2379456, + "ts": 6197198376647.733, "dur": 133.779, + "args": { + "External id": 31827,"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": 2338707, "tid": 2379456, + "ts": 6197198376671.499, "dur": 106.150, + "args": { + "External id": 31828,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197198376681.094, "dur": 91.481, + "args": { + "External id": 31829,"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": 2338707, "tid": 2379456, + "ts": 6197198376801.189, "dur": 1.855, + "args": { + "External id": 31830,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197198376883.001, "dur": 1797.391, + "args": { + "External id": 31831,"Sequence number": 479780, "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": 2338707, "tid": 2379456, "ts": 6197198376883.001, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6197198376993.777, "dur": 147.348, + "args": { + "External id": 31832,"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": 2338707, "tid": 2379456, + "ts": 6197198377184.907, "dur": 40.223, + "args": { + "External id": 31833,"kernel_hash": "cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/u7/cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs.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": 2338707, "tid": 2379456, + "ts": 6197198377244.825, "dur": 57.787, + "args": { + "External id": 31834,"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": 2338707, "tid": 2379456, + "ts": 6197198377312.097, "dur": 32.048, + "args": { + "External id": 31835,"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": 2338707, "tid": 2379456, + "ts": 6197198377354.674, "dur": 33.219, + "args": { + "External id": 31836,"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": 2338707, "tid": 2379456, + "ts": 6197198377395.030, "dur": 27.253, + "args": { + "External id": 31837,"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": 2338707, "tid": 2379456, + "ts": 6197198377431.902, "dur": 29.523, + "args": { + "External id": 31838,"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": 2338707, "tid": 2379456, + "ts": 6197198377490.586, "dur": 26.279, + "args": { + "External id": 31839,"kernel_hash": "cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/wm/cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s.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": 2338707, "tid": 2379456, + "ts": 6197198377544.446, "dur": 30.756, + "args": { + "External id": 31840,"kernel_hash": "cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql", "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/qt/cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql.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": 2338707, "tid": 2379456, + "ts": 6197198377600.002, "dur": 19.185, + "args": { + "External id": 31841,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197198377632.801, "dur": 18.213, + "args": { + "External id": 31842,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197198377662.255, "dur": 56.924, + "args": { + "External id": 31843,"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": 2338707, "tid": 2379456, + "ts": 6197198377724.768, "dur": 38.894, + "args": { + "External id": 31844,"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": 2338707, "tid": 2379456, + "ts": 6197198377794.694, "dur": 291.623, + "args": { + "External id": 31845,"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": 2338707, "tid": 2379456, + "ts": 6197198377874.771, "dur": 6.514, + "args": { + "External id": 31846,"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": 2338707, "tid": 2379456, + "ts": 6197198377883.529, "dur": 2.395, + "args": { + "External id": 31847,"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": 2338707, "tid": 2379456, + "ts": 6197198377887.180, "dur": 3.537, + "args": { + "External id": 31848,"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": 2338707, "tid": 2379456, + "ts": 6197198377891.914, "dur": 2.294, + "args": { + "External id": 31849,"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": 2338707, "tid": 2379456, + "ts": 6197198377945.057, "dur": 5.038, + "args": { + "External id": 31850,"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": 2338707, "tid": 2379456, + "ts": 6197198377947.072, "dur": 2.825, + "args": { + "External id": 31851,"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": 2338707, "tid": 2379456, + "ts": 6197198377951.786, "dur": 34.006, + "args": { + "External id": 31852,"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": 2338707, "tid": 2379456, + "ts": 6197198377957.360, "dur": 1.760, + "args": { + "External id": 31853,"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": 2338707, "tid": 2379456, + "ts": 6197198377987.269, "dur": 1.687, + "args": { + "External id": 31854,"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": 2338707, "tid": 2379456, + "ts": 6197198377988.285, "dur": 0.593, + "args": { + "External id": 31855,"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": 2338707, "tid": 2379456, + "ts": 6197198377990.216, "dur": 19.437, + "args": { + "External id": 31856,"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": 2338707, "tid": 2379456, + "ts": 6197198377991.936, "dur": 0.553, + "args": { + "External id": 31857,"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": 2338707, "tid": 2379456, + "ts": 6197198378126.808, "dur": 31.762, + "args": { + "External id": 31858,"kernel_hash": "cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4", "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/yk/cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4.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": 2338707, "tid": 2379456, + "ts": 6197198378175.146, "dur": 17.924, + "args": { + "External id": 31859,"kernel_hash": "ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg", "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/eu/ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg.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": 2338707, "tid": 2379456, + "ts": 6197198378201.197, "dur": 49.874, + "args": { + "External id": 31860,"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": 2338707, "tid": 2379456, + "ts": 6197198378257.884, "dur": 41.531, + "args": { + "External id": 31861,"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": 2338707, "tid": 2379456, + "ts": 6197198378308.364, "dur": 21.602, + "args": { + "External id": 31862,"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": 2338707, "tid": 2379456, + "ts": 6197198378338.430, "dur": 31.504, + "args": { + "External id": 31863,"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": 2338707, "tid": 2379456, + "ts": 6197198378377.784, "dur": 28.182, + "args": { + "External id": 31864,"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": 2338707, "tid": 2379456, + "ts": 6197198378413.838, "dur": 45.702, + "args": { + "External id": 31865,"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": 2338707, "tid": 2379456, + "ts": 6197198378484.050, "dur": 27.872, + "args": { + "External id": 31866,"kernel_hash": "c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/6w/c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7.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": 2338707, "tid": 2379456, + "ts": 6197198378528.922, "dur": 25.833, + "args": { + "External id": 31867,"kernel_hash": "ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx", "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/kj/ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx.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": 2338707, "tid": 2379456, + "ts": 6197198378566.608, "dur": 21.329, + "args": { + "External id": 31868,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197198378601.607, "dur": 16.507, + "args": { + "External id": 31869,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197198378633.002, "dur": 17.046, + "args": { + "External id": 31870,"kernel_hash": "cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/eb/cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b.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": 2338707, "tid": 2379456, + "ts": 6197198378743.122, "dur": 15.331, + "args": { + "External id": 31871,"Record function id": 0, "Ev Idx": 4734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198378746.448, "dur": 11.149, + "args": { + "External id": 31872,"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": 2338707, "tid": 2379456, + "ts": 6197198378750.489, "dur": 5.736, + "args": { + "External id": 31873,"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": 2338707, "tid": 2379456, + "ts": 6197198378751.866, "dur": 4.256, + "args": { + "External id": 31874,"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": 2338707, "tid": 2379456, + "ts": 6197198378762.542, "dur": 5.089, + "args": { + "External id": 31875,"Record function id": 0, "Ev Idx": 4738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198378764.060, "dur": 3.115, + "args": { + "External id": 31876,"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": 2338707, "tid": 2379456, + "ts": 6197198378764.891, "dur": 1.504, + "args": { + "External id": 31877,"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": 2338707, "tid": 2379456, + "ts": 6197198378765.514, "dur": 0.799, + "args": { + "External id": 31878,"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": 2338707, "tid": 2379456, + "ts": 6197198378770.995, "dur": 10.135, + "args": { + "External id": 31879,"Record function id": 0, "Ev Idx": 4742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198378772.574, "dur": 8.126, + "args": { + "External id": 31880,"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": 2338707, "tid": 2379456, + "ts": 6197198378778.854, "dur": 1.300, + "args": { + "External id": 31881,"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": 2338707, "tid": 2379456, + "ts": 6197198378779.311, "dur": 0.781, + "args": { + "External id": 31882,"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": 2338707, "tid": 2379456, + "ts": 6197198378784.342, "dur": 4.924, + "args": { + "External id": 31883,"Record function id": 0, "Ev Idx": 4746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198378785.733, "dur": 3.124, + "args": { + "External id": 31884,"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": 2338707, "tid": 2379456, + "ts": 6197198378786.674, "dur": 1.615, + "args": { + "External id": 31885,"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": 2338707, "tid": 2379456, + "ts": 6197198378787.344, "dur": 0.848, + "args": { + "External id": 31886,"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": 2338707, "tid": 2379456, + "ts": 6197198378792.446, "dur": 3.955, + "args": { + "External id": 31887,"Record function id": 0, "Ev Idx": 4750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198378793.622, "dur": 2.386, + "args": { + "External id": 31888,"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": 2338707, "tid": 2379456, + "ts": 6197198378794.252, "dur": 1.296, + "args": { + "External id": 31889,"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": 2338707, "tid": 2379456, + "ts": 6197198378794.707, "dur": 0.764, + "args": { + "External id": 31890,"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": 2338707, "tid": 2379456, + "ts": 6197198378799.453, "dur": 4.787, + "args": { + "External id": 31891,"Record function id": 0, "Ev Idx": 4754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198378800.713, "dur": 3.098, + "args": { + "External id": 31892,"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": 2338707, "tid": 2379456, + "ts": 6197198378801.875, "dur": 1.235, + "args": { + "External id": 31893,"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": 2338707, "tid": 2379456, + "ts": 6197198378802.145, "dur": 0.851, + "args": { + "External id": 31894,"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": 2338707, "tid": 2379456, + "ts": 6197198378807.631, "dur": 6.164, + "args": { + "External id": 31895,"Record function id": 0, "Ev Idx": 4758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198378808.942, "dur": 4.438, + "args": { + "External id": 31896,"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": 2338707, "tid": 2379456, + "ts": 6197198378809.474, "dur": 3.513, + "args": { + "External id": 31897,"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": 2338707, "tid": 2379456, + "ts": 6197198378810.251, "dur": 2.631, + "args": { + "External id": 31898,"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": 2338707, "tid": 2379456, + "ts": 6197198378817.195, "dur": 4.236, + "args": { + "External id": 31899,"Record function id": 0, "Ev Idx": 4762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198378818.688, "dur": 2.310, + "args": { + "External id": 31900,"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": 2338707, "tid": 2379456, + "ts": 6197198378819.203, "dur": 1.392, + "args": { + "External id": 31901,"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": 2338707, "tid": 2379456, + "ts": 6197198378819.570, "dur": 0.963, + "args": { + "External id": 31902,"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": 2338707, "tid": 2379456, + "ts": 6197198378824.641, "dur": 3.361, + "args": { + "External id": 31903,"Record function id": 0, "Ev Idx": 4766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198378825.639, "dur": 1.931, + "args": { + "External id": 31904,"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": 2338707, "tid": 2379456, + "ts": 6197198378826.076, "dur": 0.966, + "args": { + "External id": 31905,"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": 2338707, "tid": 2379456, + "ts": 6197198378826.331, "dur": 0.647, + "args": { + "External id": 31906,"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": 2338707, "tid": 2379456, + "ts": 6197198378831.908, "dur": 63094.806, + "args": { + "External id": 31907,"Record function id": 0, "Sequence number": 479779, "Fwd thread id": 1, "Ev Idx": 4770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197198378832.998, "dur": 63084.956, + "args": { + "External id": 31908,"Sequence number": 479779, "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": 2338707, "tid": 2379456, "ts": 6197198378832.998, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.6)", "pid": 2338707, "tid": 2379456, + "ts": 6197198378863.192, "dur": 38.128, + "args": { + "External id": 31909,"Record function id": 0, "Ev Idx": 4772 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.6)", "pid": 2338707, "tid": 2379456, + "ts": 6197198378908.772, "dur": 67.175, + "args": { + "External id": 31910,"Record function id": 0, "Ev Idx": 4773 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.6)", "pid": 2338707, "tid": 2379456, + "ts": 6197198378981.498, "dur": 62929.208, + "args": { + "External id": 31911,"Record function id": 0, "Ev Idx": 4774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197198379116.296, "dur": 8.280, + "args": { + "External id": 31912,"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": 2338707, "tid": 2379456, + "ts": 6197198379135.706, "dur": 4.924, + "args": { + "External id": 31913,"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": 2338707, "tid": 2379456, + "ts": 6197198379163.471, "dur": 61997.740, + "args": { + "External id": 31914,"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": 2338707, "tid": 2379456, + "ts": 6197198379177.449, "dur": 61971.049, + "args": { + "External id": 31915,"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": 2338707, "tid": 2379456, + "ts": 6197198379268.346, "dur": 17.607, + "args": { + "External id": 31916,"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": 2338707, "tid": 2379456, + "ts": 6197198379309.310, "dur": 61791.019, + "args": { + "External id": 31917,"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": 2338707, "tid": 2379456, + "ts": 6197198379312.024, "dur": 61787.175, + "args": { + "External id": 31918,"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": 2338707, "tid": 2379456, + "ts": 6197198379317.149, "dur": 9.798, + "args": { + "External id": 31919,"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": 2338707, "tid": 2379456, + "ts": 6197198379329.105, "dur": 61765.169, + "args": { + "External id": 31920,"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": 2338707, "tid": 2379456, + "ts": 6197198441265.617, "dur": 11.768, + "args": { + "External id": 31921,"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": 2338707, "tid": 2379456, + "ts": 6197198441269.089, "dur": 7.856, + "args": { + "External id": 31922,"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": 2338707, "tid": 2379456, + "ts": 6197198441308.678, "dur": 295.452, + "args": { + "External id": 31923,"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": 2338707, "tid": 2379456, + "ts": 6197198441340.344, "dur": 258.793, + "args": { + "External id": 31924,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197198441351.738, "dur": 241.006, + "args": { + "External id": 31925,"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": 2338707, "tid": 2379456, + "ts": 6197198441626.329, "dur": 1.962, + "args": { + "External id": 31926,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2379456, + "ts": 6197198441683.484, "dur": 6.291, + "args": { + "External id": 31927,"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": 2338707, "tid": 2379456, + "ts": 6197198441755.046, "dur": 2.171, + "args": { + "External id": 31928,"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": 2338707, "tid": 2379456, + "ts": 6197198441773.328, "dur": 1.482, + "args": { + "External id": 31929,"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": 2338707, "tid": 2379456, + "ts": 6197198441786.842, "dur": 0.912, + "args": { + "External id": 31930,"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": 2338707, "tid": 2379456, + "ts": 6197198441799.248, "dur": 0.918, + "args": { + "External id": 31931,"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": 2338707, "tid": 2379456, + "ts": 6197198441812.113, "dur": 1.091, + "args": { + "External id": 31932,"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": 2338707, "tid": 2379456, + "ts": 6197198441822.951, "dur": 1.200, + "args": { + "External id": 31933,"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": 2338707, "tid": 2379456, + "ts": 6197198441834.102, "dur": 2.725, + "args": { + "External id": 31934,"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": 2338707, "tid": 2379456, + "ts": 6197198441846.687, "dur": 1.054, + "args": { + "External id": 31935,"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": 2338707, "tid": 2379456, + "ts": 6197198441942.294, "dur": 2934.102, + "args": { + "External id": 31936,"Record function id": 0, "Ev Idx": 4799 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.5)", "pid": 2338707, "tid": 2379456, + "ts": 6197198441962.547, "dur": 1085.892, + "args": { + "External id": 31937,"Record function id": 0, "Ev Idx": 4800 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.5)", "pid": 2338707, "tid": 2379456, + "ts": 6197198441977.158, "dur": 383.685, + "args": { + "External id": 31938,"Record function id": 0, "Ev Idx": 4801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6197198442104.941, "dur": 5.448, + "args": { + "External id": 31939,"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": 2338707, "tid": 2379456, + "ts": 6197198442114.488, "dur": 0.995, + "args": { + "External id": 31940,"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": 2338707, "tid": 2379456, + "ts": 6197198442117.355, "dur": 0.997, + "args": { + "External id": 31941,"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": 2338707, "tid": 2379456, + "ts": 6197198442120.131, "dur": 0.942, + "args": { + "External id": 31942,"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": 2338707, "tid": 2379456, + "ts": 6197198442122.535, "dur": 0.733, + "args": { + "External id": 31943,"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": 2338707, "tid": 2379456, + "ts": 6197198442124.591, "dur": 0.834, + "args": { + "External id": 31944,"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": 2338707, "tid": 2379456, + "ts": 6197198442127.075, "dur": 2.079, + "args": { + "External id": 31945,"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": 2338707, "tid": 2379456, + "ts": 6197198442130.829, "dur": 2.341, + "args": { + "External id": 31946,"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": 2338707, "tid": 2379456, + "ts": 6197198442134.446, "dur": 0.662, + "args": { + "External id": 31947,"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": 2338707, "tid": 2379456, + "ts": 6197198442138.553, "dur": 0.637, + "args": { + "External id": 31948,"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": 2338707, "tid": 2379456, + "ts": 6197198442157.997, "dur": 165.859, + "args": { + "External id": 31949,"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": 2338707, "tid": 2379456, + "ts": 6197198442174.856, "dur": 144.382, + "args": { + "External id": 31950,"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": 2338707, "tid": 2379456, + "ts": 6197198442199.740, "dur": 16.131, + "args": { + "External id": 31951,"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": 2338707, "tid": 2379456, + "ts": 6197198442219.702, "dur": 68.931, + "args": { + "External id": 31952,"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": 2338707, "tid": 2379456, + "ts": 6197198442222.459, "dur": 65.775, + "args": { + "External id": 31953,"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": 2338707, "tid": 2379456, + "ts": 6197198442226.863, "dur": 5.484, + "args": { + "External id": 31954,"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": 2338707, "tid": 2379456, + "ts": 6197198442234.034, "dur": 53.431, + "args": { + "External id": 31955,"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": 2338707, "tid": 2379456, + "ts": 6197198442455.733, "dur": 584.996, + "args": { + "External id": 31956,"Record function id": 0, "Ev Idx": 4819 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.4)", "pid": 2338707, "tid": 2379456, + "ts": 6197198442474.017, "dur": 554.150, + "args": { + "External id": 31957,"Record function id": 0, "Ev Idx": 4820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197198442540.564, "dur": 4.875, + "args": { + "External id": 31958,"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": 2338707, "tid": 2379456, + "ts": 6197198442559.644, "dur": 28.591, + "args": { + "External id": 31959,"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": 2338707, "tid": 2379456, + "ts": 6197198442564.942, "dur": 1.591, + "args": { + "External id": 31960,"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": 2338707, "tid": 2379456, + "ts": 6197198442568.151, "dur": 0.498, + "args": { + "External id": 31961,"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": 2338707, "tid": 2379456, + "ts": 6197198442570.052, "dur": 2.207, + "args": { + "External id": 31962,"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": 2338707, "tid": 2379456, + "ts": 6197198442573.742, "dur": 0.404, + "args": { + "External id": 31963,"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": 2338707, "tid": 2379456, + "ts": 6197198442575.419, "dur": 0.583, + "args": { + "External id": 31964,"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": 2338707, "tid": 2379456, + "ts": 6197198442578.190, "dur": 0.459, + "args": { + "External id": 31965,"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": 2338707, "tid": 2379456, + "ts": 6197198442579.874, "dur": 0.437, + "args": { + "External id": 31966,"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": 2338707, "tid": 2379456, + "ts": 6197198442581.454, "dur": 0.478, + "args": { + "External id": 31967,"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": 2338707, "tid": 2379456, + "ts": 6197198442583.224, "dur": 0.531, + "args": { + "External id": 31968,"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": 2338707, "tid": 2379456, + "ts": 6197198442597.914, "dur": 39.788, + "args": { + "External id": 31969,"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": 2338707, "tid": 2379456, + "ts": 6197198442665.222, "dur": 128.536, + "args": { + "External id": 31970,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2379456, + "ts": 6197198442674.791, "dur": 3.027, + "args": { + "External id": 31971,"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": 2338707, "tid": 2379456, + "ts": 6197198442682.709, "dur": 11.984, + "args": { + "External id": 31972,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2379456, + "ts": 6197198442687.249, "dur": 7.046, + "args": { + "External id": 31973,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2379456, + "ts": 6197198442690.637, "dur": 2.371, + "args": { + "External id": 31974,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197198442719.154, "dur": 23.924, + "args": { + "External id": 31975,"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": 2338707, "tid": 2379456, + "ts": 6197198442721.396, "dur": 0.627, + "args": { + "External id": 31976,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197198442723.934, "dur": 0.419, + "args": { + "External id": 31977,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2379456, + "ts": 6197198442725.871, "dur": 0.313, + "args": { + "External id": 31978,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2379456, + "ts": 6197198442727.286, "dur": 0.365, + "args": { + "External id": 31979,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2379456, + "ts": 6197198442729.186, "dur": 0.500, + "args": { + "External id": 31980,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2379456, + "ts": 6197198442731.129, "dur": 0.402, + "args": { + "External id": 31981,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2379456, + "ts": 6197198442732.352, "dur": 0.442, + "args": { + "External id": 31982,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2379456, + "ts": 6197198442734.340, "dur": 2.460, + "args": { + "External id": 31983,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2379456, + "ts": 6197198442738.438, "dur": 0.306, + "args": { + "External id": 31984,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2379456, + "ts": 6197198442754.818, "dur": 30.961, + "args": { + "External id": 31985,"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": 2338707, "tid": 2379456, + "ts": 6197198442838.517, "dur": 118.723, + "args": { + "External id": 31986,"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": 2338707, "tid": 2379456, + "ts": 6197198442862.482, "dur": 91.165, + "args": { + "External id": 31987,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197198442872.179, "dur": 73.715, + "args": { + "External id": 31988,"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": 2338707, "tid": 2379456, + "ts": 6197198442974.218, "dur": 1.954, + "args": { + "External id": 31989,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197198443093.004, "dur": 1749.131, + "args": { + "External id": 31990,"Sequence number": 479778, "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": 2338707, "tid": 2379456, "ts": 6197198443093.004, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6197198443206.616, "dur": 112.282, + "args": { + "External id": 31991,"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": 2338707, "tid": 2379456, + "ts": 6197198443372.245, "dur": 40.973, + "args": { + "External id": 31992,"kernel_hash": "cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/u7/cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs.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": 2338707, "tid": 2379456, + "ts": 6197198443432.235, "dur": 51.201, + "args": { + "External id": 31993,"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": 2338707, "tid": 2379456, + "ts": 6197198443492.956, "dur": 32.013, + "args": { + "External id": 31994,"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": 2338707, "tid": 2379456, + "ts": 6197198443531.164, "dur": 32.772, + "args": { + "External id": 31995,"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": 2338707, "tid": 2379456, + "ts": 6197198443571.211, "dur": 28.787, + "args": { + "External id": 31996,"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": 2338707, "tid": 2379456, + "ts": 6197198443611.980, "dur": 29.546, + "args": { + "External id": 31997,"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": 2338707, "tid": 2379456, + "ts": 6197198443669.025, "dur": 25.105, + "args": { + "External id": 31998,"kernel_hash": "cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/wm/cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s.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": 2338707, "tid": 2379456, + "ts": 6197198443729.363, "dur": 33.607, + "args": { + "External id": 31999,"kernel_hash": "cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql", "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/qt/cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql.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": 2338707, "tid": 2379456, + "ts": 6197198443788.580, "dur": 19.812, + "args": { + "External id": 32000,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197198443821.756, "dur": 15.047, + "args": { + "External id": 32001,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197198443847.500, "dur": 42.298, + "args": { + "External id": 32002,"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": 2338707, "tid": 2379456, + "ts": 6197198443893.681, "dur": 34.324, + "args": { + "External id": 32003,"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": 2338707, "tid": 2379456, + "ts": 6197198443959.812, "dur": 307.196, + "args": { + "External id": 32004,"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": 2338707, "tid": 2379456, + "ts": 6197198444041.834, "dur": 6.671, + "args": { + "External id": 32005,"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": 2338707, "tid": 2379456, + "ts": 6197198444050.636, "dur": 50.824, + "args": { + "External id": 32006,"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": 2338707, "tid": 2379456, + "ts": 6197198444104.063, "dur": 2.443, + "args": { + "External id": 32007,"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": 2338707, "tid": 2379456, + "ts": 6197198444107.772, "dur": 4.180, + "args": { + "External id": 32008,"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": 2338707, "tid": 2379456, + "ts": 6197198444160.616, "dur": 5.237, + "args": { + "External id": 32009,"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": 2338707, "tid": 2379456, + "ts": 6197198444162.666, "dur": 2.954, + "args": { + "External id": 32010,"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": 2338707, "tid": 2379456, + "ts": 6197198444167.739, "dur": 32.332, + "args": { + "External id": 32011,"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": 2338707, "tid": 2379456, + "ts": 6197198444173.726, "dur": 2.013, + "args": { + "External id": 32012,"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": 2338707, "tid": 2379456, + "ts": 6197198444201.633, "dur": 1.678, + "args": { + "External id": 32013,"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": 2338707, "tid": 2379456, + "ts": 6197198444202.618, "dur": 0.612, + "args": { + "External id": 32014,"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": 2338707, "tid": 2379456, + "ts": 6197198444204.453, "dur": 14.413, + "args": { + "External id": 32015,"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": 2338707, "tid": 2379456, + "ts": 6197198444206.156, "dur": 0.461, + "args": { + "External id": 32016,"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": 2338707, "tid": 2379456, + "ts": 6197198444303.707, "dur": 28.444, + "args": { + "External id": 32017,"kernel_hash": "cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4", "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/yk/cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4.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": 2338707, "tid": 2379456, + "ts": 6197198444348.060, "dur": 16.854, + "args": { + "External id": 32018,"kernel_hash": "ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg", "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/eu/ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg.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": 2338707, "tid": 2379456, + "ts": 6197198444373.714, "dur": 46.992, + "args": { + "External id": 32019,"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": 2338707, "tid": 2379456, + "ts": 6197198444428.221, "dur": 39.752, + "args": { + "External id": 32020,"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": 2338707, "tid": 2379456, + "ts": 6197198444477.536, "dur": 21.252, + "args": { + "External id": 32021,"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": 2338707, "tid": 2379456, + "ts": 6197198444507.451, "dur": 32.127, + "args": { + "External id": 32022,"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": 2338707, "tid": 2379456, + "ts": 6197198444547.083, "dur": 28.039, + "args": { + "External id": 32023,"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": 2338707, "tid": 2379456, + "ts": 6197198444581.826, "dur": 31.085, + "args": { + "External id": 32024,"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": 2338707, "tid": 2379456, + "ts": 6197198444633.095, "dur": 21.346, + "args": { + "External id": 32025,"kernel_hash": "c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/6w/c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7.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": 2338707, "tid": 2379456, + "ts": 6197198444669.777, "dur": 27.186, + "args": { + "External id": 32026,"kernel_hash": "ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx", "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/kj/ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx.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": 2338707, "tid": 2379456, + "ts": 6197198444728.520, "dur": 20.939, + "args": { + "External id": 32027,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197198444765.879, "dur": 15.478, + "args": { + "External id": 32028,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197198444793.769, "dur": 16.703, + "args": { + "External id": 32029,"kernel_hash": "cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/eb/cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b.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": 2338707, "tid": 2379456, + "ts": 6197198444901.237, "dur": 17.251, + "args": { + "External id": 32030,"Record function id": 0, "Ev Idx": 4893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198444904.676, "dur": 12.792, + "args": { + "External id": 32031,"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": 2338707, "tid": 2379456, + "ts": 6197198444908.855, "dur": 6.784, + "args": { + "External id": 32032,"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": 2338707, "tid": 2379456, + "ts": 6197198444911.154, "dur": 4.363, + "args": { + "External id": 32033,"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": 2338707, "tid": 2379456, + "ts": 6197198444922.231, "dur": 5.751, + "args": { + "External id": 32034,"Record function id": 0, "Ev Idx": 4897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198444923.771, "dur": 3.790, + "args": { + "External id": 32035,"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": 2338707, "tid": 2379456, + "ts": 6197198444924.779, "dur": 2.013, + "args": { + "External id": 32036,"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": 2338707, "tid": 2379456, + "ts": 6197198444925.485, "dur": 1.219, + "args": { + "External id": 32037,"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": 2338707, "tid": 2379456, + "ts": 6197198444931.195, "dur": 3.877, + "args": { + "External id": 32038,"Record function id": 0, "Ev Idx": 4901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198444932.423, "dur": 2.253, + "args": { + "External id": 32039,"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": 2338707, "tid": 2379456, + "ts": 6197198444932.950, "dur": 1.205, + "args": { + "External id": 32040,"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": 2338707, "tid": 2379456, + "ts": 6197198444933.308, "dur": 0.785, + "args": { + "External id": 32041,"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": 2338707, "tid": 2379456, + "ts": 6197198444938.220, "dur": 4.052, + "args": { + "External id": 32042,"Record function id": 0, "Ev Idx": 4905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198444939.284, "dur": 2.549, + "args": { + "External id": 32043,"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": 2338707, "tid": 2379456, + "ts": 6197198444939.823, "dur": 1.422, + "args": { + "External id": 32044,"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": 2338707, "tid": 2379456, + "ts": 6197198444940.465, "dur": 0.661, + "args": { + "External id": 32045,"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": 2338707, "tid": 2379456, + "ts": 6197198444945.194, "dur": 4.036, + "args": { + "External id": 32046,"Record function id": 0, "Ev Idx": 4909 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198444946.504, "dur": 2.342, + "args": { + "External id": 32047,"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": 2338707, "tid": 2379456, + "ts": 6197198444947.377, "dur": 0.986, + "args": { + "External id": 32048,"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": 2338707, "tid": 2379456, + "ts": 6197198444947.709, "dur": 0.572, + "args": { + "External id": 32049,"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": 2338707, "tid": 2379456, + "ts": 6197198444952.237, "dur": 5.874, + "args": { + "External id": 32050,"Record function id": 0, "Ev Idx": 4913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198444953.444, "dur": 4.274, + "args": { + "External id": 32051,"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": 2338707, "tid": 2379456, + "ts": 6197198444953.988, "dur": 3.316, + "args": { + "External id": 32052,"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": 2338707, "tid": 2379456, + "ts": 6197198444954.291, "dur": 2.940, + "args": { + "External id": 32053,"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": 2338707, "tid": 2379456, + "ts": 6197198444961.243, "dur": 4.145, + "args": { + "External id": 32054,"Record function id": 0, "Ev Idx": 4917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198444962.462, "dur": 2.529, + "args": { + "External id": 32055,"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": 2338707, "tid": 2379456, + "ts": 6197198444962.936, "dur": 1.525, + "args": { + "External id": 32056,"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": 2338707, "tid": 2379456, + "ts": 6197198444963.705, "dur": 0.639, + "args": { + "External id": 32057,"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": 2338707, "tid": 2379456, + "ts": 6197198444968.398, "dur": 3.606, + "args": { + "External id": 32058,"Record function id": 0, "Ev Idx": 4921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198444969.471, "dur": 2.148, + "args": { + "External id": 32059,"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": 2338707, "tid": 2379456, + "ts": 6197198444970.092, "dur": 0.912, + "args": { + "External id": 32060,"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": 2338707, "tid": 2379456, + "ts": 6197198444970.382, "dur": 0.542, + "args": { + "External id": 32061,"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": 2338707, "tid": 2379456, + "ts": 6197198444974.815, "dur": 3.327, + "args": { + "External id": 32062,"Record function id": 0, "Ev Idx": 4925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198444975.823, "dur": 1.909, + "args": { + "External id": 32063,"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": 2338707, "tid": 2379456, + "ts": 6197198444976.328, "dur": 1.003, + "args": { + "External id": 32064,"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": 2338707, "tid": 2379456, + "ts": 6197198444976.592, "dur": 0.643, + "args": { + "External id": 32065,"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": 2338707, "tid": 2379456, + "ts": 6197198444982.148, "dur": 65401.352, + "args": { + "External id": 32066,"Record function id": 0, "Sequence number": 479777, "Fwd thread id": 1, "Ev Idx": 4929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197198444983.473, "dur": 65390.607, + "args": { + "External id": 32067,"Sequence number": 479777, "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": 2338707, "tid": 2379456, "ts": 6197198444983.473, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.5)", "pid": 2338707, "tid": 2379456, + "ts": 6197198445018.023, "dur": 76.630, + "args": { + "External id": 32068,"Record function id": 0, "Ev Idx": 4931 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.5)", "pid": 2338707, "tid": 2379456, + "ts": 6197198445104.061, "dur": 65.532, + "args": { + "External id": 32069,"Record function id": 0, "Ev Idx": 4932 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.5)", "pid": 2338707, "tid": 2379456, + "ts": 6197198445175.692, "dur": 65190.769, + "args": { + "External id": 32070,"Record function id": 0, "Ev Idx": 4933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197198445264.099, "dur": 7.822, + "args": { + "External id": 32071,"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": 2338707, "tid": 2379456, + "ts": 6197198445282.293, "dur": 5.040, + "args": { + "External id": 32072,"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": 2338707, "tid": 2379456, + "ts": 6197198445302.321, "dur": 64152.782, + "args": { + "External id": 32073,"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": 2338707, "tid": 2379456, + "ts": 6197198445316.444, "dur": 64126.111, + "args": { + "External id": 32074,"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": 2338707, "tid": 2379456, + "ts": 6197198445412.113, "dur": 16.962, + "args": { + "External id": 32075,"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": 2338707, "tid": 2379456, + "ts": 6197198445451.113, "dur": 63949.396, + "args": { + "External id": 32076,"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": 2338707, "tid": 2379456, + "ts": 6197198445453.633, "dur": 63945.929, + "args": { + "External id": 32077,"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": 2338707, "tid": 2379456, + "ts": 6197198445458.575, "dur": 10.630, + "args": { + "External id": 32078,"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": 2338707, "tid": 2379456, + "ts": 6197198445471.367, "dur": 63923.123, + "args": { + "External id": 32079,"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": 2338707, "tid": 2379456, + "ts": 6197198509558.714, "dur": 11.898, + "args": { + "External id": 32080,"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": 2338707, "tid": 2379456, + "ts": 6197198509562.250, "dur": 7.933, + "args": { + "External id": 32081,"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": 2338707, "tid": 2379456, + "ts": 6197198509599.627, "dur": 436.640, + "args": { + "External id": 32082,"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": 2338707, "tid": 2379456, + "ts": 6197198509631.153, "dur": 399.297, + "args": { + "External id": 32083,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197198509642.444, "dur": 381.858, + "args": { + "External id": 32084,"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": 2338707, "tid": 2379456, + "ts": 6197198510090.811, "dur": 3.697, + "args": { + "External id": 32085,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2379456, + "ts": 6197198510161.404, "dur": 6.865, + "args": { + "External id": 32086,"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": 2338707, "tid": 2379456, + "ts": 6197198510214.822, "dur": 1.170, + "args": { + "External id": 32087,"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": 2338707, "tid": 2379456, + "ts": 6197198510231.352, "dur": 0.852, + "args": { + "External id": 32088,"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": 2338707, "tid": 2379456, + "ts": 6197198510243.175, "dur": 0.993, + "args": { + "External id": 32089,"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": 2338707, "tid": 2379456, + "ts": 6197198510255.987, "dur": 0.937, + "args": { + "External id": 32090,"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": 2338707, "tid": 2379456, + "ts": 6197198510268.547, "dur": 1.362, + "args": { + "External id": 32091,"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": 2338707, "tid": 2379456, + "ts": 6197198510279.607, "dur": 1.069, + "args": { + "External id": 32092,"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": 2338707, "tid": 2379456, + "ts": 6197198510290.912, "dur": 2.395, + "args": { + "External id": 32093,"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": 2338707, "tid": 2379456, + "ts": 6197198510302.905, "dur": 1.093, + "args": { + "External id": 32094,"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": 2338707, "tid": 2379456, + "ts": 6197198510399.430, "dur": 2933.871, + "args": { + "External id": 32095,"Record function id": 0, "Ev Idx": 4958 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.4)", "pid": 2338707, "tid": 2379456, + "ts": 6197198510419.169, "dur": 1076.817, + "args": { + "External id": 32096,"Record function id": 0, "Ev Idx": 4959 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.4)", "pid": 2338707, "tid": 2379456, + "ts": 6197198510435.604, "dur": 365.281, + "args": { + "External id": 32097,"Record function id": 0, "Ev Idx": 4960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6197198510526.763, "dur": 7.664, + "args": { + "External id": 32098,"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": 2338707, "tid": 2379456, + "ts": 6197198510537.501, "dur": 1.228, + "args": { + "External id": 32099,"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": 2338707, "tid": 2379456, + "ts": 6197198510540.451, "dur": 0.853, + "args": { + "External id": 32100,"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": 2338707, "tid": 2379456, + "ts": 6197198510543.095, "dur": 0.814, + "args": { + "External id": 32101,"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": 2338707, "tid": 2379456, + "ts": 6197198510545.700, "dur": 0.581, + "args": { + "External id": 32102,"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": 2338707, "tid": 2379456, + "ts": 6197198510547.641, "dur": 0.728, + "args": { + "External id": 32103,"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": 2338707, "tid": 2379456, + "ts": 6197198510550.141, "dur": 1.762, + "args": { + "External id": 32104,"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": 2338707, "tid": 2379456, + "ts": 6197198510553.488, "dur": 2.410, + "args": { + "External id": 32105,"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": 2338707, "tid": 2379456, + "ts": 6197198510559.363, "dur": 1.161, + "args": { + "External id": 32106,"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": 2338707, "tid": 2379456, + "ts": 6197198510562.002, "dur": 0.861, + "args": { + "External id": 32107,"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": 2338707, "tid": 2379456, + "ts": 6197198510579.702, "dur": 189.279, + "args": { + "External id": 32108,"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": 2338707, "tid": 2379456, + "ts": 6197198510598.874, "dur": 164.633, + "args": { + "External id": 32109,"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": 2338707, "tid": 2379456, + "ts": 6197198510625.860, "dur": 15.103, + "args": { + "External id": 32110,"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": 2338707, "tid": 2379456, + "ts": 6197198510644.720, "dur": 86.668, + "args": { + "External id": 32111,"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": 2338707, "tid": 2379456, + "ts": 6197198510647.694, "dur": 83.385, + "args": { + "External id": 32112,"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": 2338707, "tid": 2379456, + "ts": 6197198510652.024, "dur": 5.746, + "args": { + "External id": 32113,"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": 2338707, "tid": 2379456, + "ts": 6197198510659.447, "dur": 70.359, + "args": { + "External id": 32114,"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": 2338707, "tid": 2379456, + "ts": 6197198510890.042, "dur": 598.283, + "args": { + "External id": 32115,"Record function id": 0, "Ev Idx": 4978 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.3)", "pid": 2338707, "tid": 2379456, + "ts": 6197198510907.597, "dur": 568.224, + "args": { + "External id": 32116,"Record function id": 0, "Ev Idx": 4979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197198510973.260, "dur": 5.869, + "args": { + "External id": 32117,"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": 2338707, "tid": 2379456, + "ts": 6197198510994.228, "dur": 28.153, + "args": { + "External id": 32118,"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": 2338707, "tid": 2379456, + "ts": 6197198510999.140, "dur": 1.850, + "args": { + "External id": 32119,"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": 2338707, "tid": 2379456, + "ts": 6197198511003.469, "dur": 0.521, + "args": { + "External id": 32120,"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": 2338707, "tid": 2379456, + "ts": 6197198511005.460, "dur": 2.040, + "args": { + "External id": 32121,"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": 2338707, "tid": 2379456, + "ts": 6197198511008.357, "dur": 0.477, + "args": { + "External id": 32122,"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": 2338707, "tid": 2379456, + "ts": 6197198511010.520, "dur": 0.280, + "args": { + "External id": 32123,"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": 2338707, "tid": 2379456, + "ts": 6197198511012.557, "dur": 0.337, + "args": { + "External id": 32124,"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": 2338707, "tid": 2379456, + "ts": 6197198511013.723, "dur": 0.463, + "args": { + "External id": 32125,"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": 2338707, "tid": 2379456, + "ts": 6197198511016.200, "dur": 0.478, + "args": { + "External id": 32126,"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": 2338707, "tid": 2379456, + "ts": 6197198511017.674, "dur": 0.255, + "args": { + "External id": 32127,"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": 2338707, "tid": 2379456, + "ts": 6197198511033.050, "dur": 77.849, + "args": { + "External id": 32128,"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": 2338707, "tid": 2379456, + "ts": 6197198511144.470, "dur": 108.269, + "args": { + "External id": 32129,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2379456, + "ts": 6197198511155.339, "dur": 3.821, + "args": { + "External id": 32130,"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": 2338707, "tid": 2379456, + "ts": 6197198511164.460, "dur": 12.569, + "args": { + "External id": 32131,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2379456, + "ts": 6197198511168.596, "dur": 7.987, + "args": { + "External id": 32132,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2379456, + "ts": 6197198511172.094, "dur": 2.829, + "args": { + "External id": 32133,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197198511184.292, "dur": 22.052, + "args": { + "External id": 32134,"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": 2338707, "tid": 2379456, + "ts": 6197198511186.378, "dur": 0.475, + "args": { + "External id": 32135,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197198511188.389, "dur": 0.547, + "args": { + "External id": 32136,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2379456, + "ts": 6197198511190.545, "dur": 0.561, + "args": { + "External id": 32137,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2379456, + "ts": 6197198511192.628, "dur": 0.288, + "args": { + "External id": 32138,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2379456, + "ts": 6197198511193.847, "dur": 0.438, + "args": { + "External id": 32139,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2379456, + "ts": 6197198511195.715, "dur": 0.453, + "args": { + "External id": 32140,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2379456, + "ts": 6197198511197.414, "dur": 0.329, + "args": { + "External id": 32141,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2379456, + "ts": 6197198511198.829, "dur": 1.959, + "args": { + "External id": 32142,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2379456, + "ts": 6197198511202.176, "dur": 0.468, + "args": { + "External id": 32143,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2379456, + "ts": 6197198511217.107, "dur": 28.472, + "args": { + "External id": 32144,"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": 2338707, "tid": 2379456, + "ts": 6197198511296.651, "dur": 112.857, + "args": { + "External id": 32145,"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": 2338707, "tid": 2379456, + "ts": 6197198511319.743, "dur": 86.251, + "args": { + "External id": 32146,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197198511329.719, "dur": 72.127, + "args": { + "External id": 32147,"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": 2338707, "tid": 2379456, + "ts": 6197198511426.683, "dur": 1.745, + "args": { + "External id": 32148,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197198511504.366, "dur": 1804.935, + "args": { + "External id": 32149,"Sequence number": 479776, "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": 2338707, "tid": 2379456, "ts": 6197198511504.366, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6197198511620.579, "dur": 128.264, + "args": { + "External id": 32150,"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": 2338707, "tid": 2379456, + "ts": 6197198511793.106, "dur": 41.926, + "args": { + "External id": 32151,"kernel_hash": "cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/u7/cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs.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": 2338707, "tid": 2379456, + "ts": 6197198511854.238, "dur": 55.712, + "args": { + "External id": 32152,"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": 2338707, "tid": 2379456, + "ts": 6197198511919.320, "dur": 31.328, + "args": { + "External id": 32153,"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": 2338707, "tid": 2379456, + "ts": 6197198511956.766, "dur": 31.631, + "args": { + "External id": 32154,"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": 2338707, "tid": 2379456, + "ts": 6197198511994.873, "dur": 27.213, + "args": { + "External id": 32155,"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": 2338707, "tid": 2379456, + "ts": 6197198512030.779, "dur": 69.660, + "args": { + "External id": 32156,"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": 2338707, "tid": 2379456, + "ts": 6197198512136.485, "dur": 26.313, + "args": { + "External id": 32157,"kernel_hash": "cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/wm/cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s.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": 2338707, "tid": 2379456, + "ts": 6197198512184.506, "dur": 30.234, + "args": { + "External id": 32158,"kernel_hash": "cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql", "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/qt/cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql.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": 2338707, "tid": 2379456, + "ts": 6197198512236.759, "dur": 20.437, + "args": { + "External id": 32159,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197198512271.391, "dur": 16.805, + "args": { + "External id": 32160,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197198512298.931, "dur": 47.421, + "args": { + "External id": 32161,"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": 2338707, "tid": 2379456, + "ts": 6197198512350.608, "dur": 38.681, + "args": { + "External id": 32162,"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": 2338707, "tid": 2379456, + "ts": 6197198512418.410, "dur": 254.278, + "args": { + "External id": 32163,"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": 2338707, "tid": 2379456, + "ts": 6197198512498.404, "dur": 7.326, + "args": { + "External id": 32164,"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": 2338707, "tid": 2379456, + "ts": 6197198512507.987, "dur": 2.627, + "args": { + "External id": 32165,"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": 2338707, "tid": 2379456, + "ts": 6197198512511.840, "dur": 2.775, + "args": { + "External id": 32166,"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": 2338707, "tid": 2379456, + "ts": 6197198512515.819, "dur": 4.321, + "args": { + "External id": 32167,"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": 2338707, "tid": 2379456, + "ts": 6197198512568.168, "dur": 5.561, + "args": { + "External id": 32168,"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": 2338707, "tid": 2379456, + "ts": 6197198512570.530, "dur": 2.977, + "args": { + "External id": 32169,"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": 2338707, "tid": 2379456, + "ts": 6197198512575.589, "dur": 33.892, + "args": { + "External id": 32170,"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": 2338707, "tid": 2379456, + "ts": 6197198512580.796, "dur": 1.810, + "args": { + "External id": 32171,"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": 2338707, "tid": 2379456, + "ts": 6197198512610.858, "dur": 2.052, + "args": { + "External id": 32172,"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": 2338707, "tid": 2379456, + "ts": 6197198512612.044, "dur": 0.799, + "args": { + "External id": 32173,"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": 2338707, "tid": 2379456, + "ts": 6197198512614.062, "dur": 16.828, + "args": { + "External id": 32174,"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": 2338707, "tid": 2379456, + "ts": 6197198512615.769, "dur": 0.462, + "args": { + "External id": 32175,"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": 2338707, "tid": 2379456, + "ts": 6197198512723.993, "dur": 30.143, + "args": { + "External id": 32176,"kernel_hash": "cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4", "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/yk/cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4.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": 2338707, "tid": 2379456, + "ts": 6197198512771.582, "dur": 18.788, + "args": { + "External id": 32177,"kernel_hash": "ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg", "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/eu/ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg.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": 2338707, "tid": 2379456, + "ts": 6197198512799.956, "dur": 45.255, + "args": { + "External id": 32178,"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": 2338707, "tid": 2379456, + "ts": 6197198512852.799, "dur": 39.272, + "args": { + "External id": 32179,"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": 2338707, "tid": 2379456, + "ts": 6197198512900.491, "dur": 20.898, + "args": { + "External id": 32180,"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": 2338707, "tid": 2379456, + "ts": 6197198512928.984, "dur": 32.872, + "args": { + "External id": 32181,"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": 2338707, "tid": 2379456, + "ts": 6197198512969.513, "dur": 27.599, + "args": { + "External id": 32182,"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": 2338707, "tid": 2379456, + "ts": 6197198513004.903, "dur": 31.176, + "args": { + "External id": 32183,"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": 2338707, "tid": 2379456, + "ts": 6197198513088.365, "dur": 26.714, + "args": { + "External id": 32184,"kernel_hash": "c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/6w/c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7.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": 2338707, "tid": 2379456, + "ts": 6197198513143.846, "dur": 33.519, + "args": { + "External id": 32185,"kernel_hash": "ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx", "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/kj/ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx.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": 2338707, "tid": 2379456, + "ts": 6197198513194.816, "dur": 20.460, + "args": { + "External id": 32186,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197198513231.488, "dur": 14.597, + "args": { + "External id": 32187,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197198513258.838, "dur": 18.356, + "args": { + "External id": 32188,"kernel_hash": "cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/eb/cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b.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": 2338707, "tid": 2379456, + "ts": 6197198513355.777, "dur": 15.164, + "args": { + "External id": 32189,"Record function id": 0, "Ev Idx": 5052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198513358.993, "dur": 10.937, + "args": { + "External id": 32190,"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": 2338707, "tid": 2379456, + "ts": 6197198513363.311, "dur": 5.570, + "args": { + "External id": 32191,"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": 2338707, "tid": 2379456, + "ts": 6197198513364.790, "dur": 4.000, + "args": { + "External id": 32192,"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": 2338707, "tid": 2379456, + "ts": 6197198513374.789, "dur": 4.546, + "args": { + "External id": 32193,"Record function id": 0, "Ev Idx": 5056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198513375.935, "dur": 2.903, + "args": { + "External id": 32194,"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": 2338707, "tid": 2379456, + "ts": 6197198513376.795, "dur": 1.480, + "args": { + "External id": 32195,"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": 2338707, "tid": 2379456, + "ts": 6197198513377.212, "dur": 0.947, + "args": { + "External id": 32196,"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": 2338707, "tid": 2379456, + "ts": 6197198513385.923, "dur": 3.982, + "args": { + "External id": 32197,"Record function id": 0, "Ev Idx": 5060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198513387.240, "dur": 2.169, + "args": { + "External id": 32198,"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": 2338707, "tid": 2379456, + "ts": 6197198513387.798, "dur": 1.154, + "args": { + "External id": 32199,"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": 2338707, "tid": 2379456, + "ts": 6197198513388.095, "dur": 0.795, + "args": { + "External id": 32200,"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": 2338707, "tid": 2379456, + "ts": 6197198513393.262, "dur": 4.860, + "args": { + "External id": 32201,"Record function id": 0, "Ev Idx": 5064 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198513394.617, "dur": 3.030, + "args": { + "External id": 32202,"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": 2338707, "tid": 2379456, + "ts": 6197198513395.680, "dur": 1.476, + "args": { + "External id": 32203,"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": 2338707, "tid": 2379456, + "ts": 6197198513396.386, "dur": 0.661, + "args": { + "External id": 32204,"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": 2338707, "tid": 2379456, + "ts": 6197198513401.485, "dur": 3.771, + "args": { + "External id": 32205,"Record function id": 0, "Ev Idx": 5068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198513402.645, "dur": 2.161, + "args": { + "External id": 32206,"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": 2338707, "tid": 2379456, + "ts": 6197198513403.276, "dur": 1.112, + "args": { + "External id": 32207,"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": 2338707, "tid": 2379456, + "ts": 6197198513403.572, "dur": 0.750, + "args": { + "External id": 32208,"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": 2338707, "tid": 2379456, + "ts": 6197198513408.423, "dur": 3.386, + "args": { + "External id": 32209,"Record function id": 0, "Ev Idx": 5072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198513409.525, "dur": 1.820, + "args": { + "External id": 32210,"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": 2338707, "tid": 2379456, + "ts": 6197198513410.061, "dur": 0.808, + "args": { + "External id": 32211,"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": 2338707, "tid": 2379456, + "ts": 6197198513410.323, "dur": 0.453, + "args": { + "External id": 32212,"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": 2338707, "tid": 2379456, + "ts": 6197198513415.046, "dur": 5.779, + "args": { + "External id": 32213,"Record function id": 0, "Ev Idx": 5076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198513416.239, "dur": 4.135, + "args": { + "External id": 32214,"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": 2338707, "tid": 2379456, + "ts": 6197198513416.700, "dur": 3.254, + "args": { + "External id": 32215,"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": 2338707, "tid": 2379456, + "ts": 6197198513417.522, "dur": 2.294, + "args": { + "External id": 32216,"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": 2338707, "tid": 2379456, + "ts": 6197198513423.938, "dur": 4.247, + "args": { + "External id": 32217,"Record function id": 0, "Ev Idx": 5080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198513425.314, "dur": 2.448, + "args": { + "External id": 32218,"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": 2338707, "tid": 2379456, + "ts": 6197198513425.811, "dur": 1.525, + "args": { + "External id": 32219,"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": 2338707, "tid": 2379456, + "ts": 6197198513426.503, "dur": 0.769, + "args": { + "External id": 32220,"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": 2338707, "tid": 2379456, + "ts": 6197198513431.697, "dur": 3.359, + "args": { + "External id": 32221,"Record function id": 0, "Ev Idx": 5084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198513432.801, "dur": 1.805, + "args": { + "External id": 32222,"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": 2338707, "tid": 2379456, + "ts": 6197198513433.260, "dur": 0.949, + "args": { + "External id": 32223,"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": 2338707, "tid": 2379456, + "ts": 6197198513433.573, "dur": 0.572, + "args": { + "External id": 32224,"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": 2338707, "tid": 2379456, + "ts": 6197198513439.267, "dur": 63527.243, + "args": { + "External id": 32225,"Record function id": 0, "Sequence number": 479775, "Fwd thread id": 1, "Ev Idx": 5088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197198513440.763, "dur": 63516.481, + "args": { + "External id": 32226,"Sequence number": 479775, "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": 2338707, "tid": 2379456, "ts": 6197198513440.763, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.4)", "pid": 2338707, "tid": 2379456, + "ts": 6197198513470.479, "dur": 38.908, + "args": { + "External id": 32227,"Record function id": 0, "Ev Idx": 5090 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.4)", "pid": 2338707, "tid": 2379456, + "ts": 6197198513517.248, "dur": 64.287, + "args": { + "External id": 32228,"Record function id": 0, "Ev Idx": 5091 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.4)", "pid": 2338707, "tid": 2379456, + "ts": 6197198513587.774, "dur": 63361.143, + "args": { + "External id": 32229,"Record function id": 0, "Ev Idx": 5092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197198513673.771, "dur": 6.644, + "args": { + "External id": 32230,"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": 2338707, "tid": 2379456, + "ts": 6197198513690.034, "dur": 4.288, + "args": { + "External id": 32231,"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": 2338707, "tid": 2379456, + "ts": 6197198513726.682, "dur": 62403.930, + "args": { + "External id": 32232,"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": 2338707, "tid": 2379456, + "ts": 6197198513741.621, "dur": 62375.709, + "args": { + "External id": 32233,"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": 2338707, "tid": 2379456, + "ts": 6197198513844.226, "dur": 18.045, + "args": { + "External id": 32234,"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": 2338707, "tid": 2379456, + "ts": 6197198513885.723, "dur": 62163.929, + "args": { + "External id": 32235,"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": 2338707, "tid": 2379456, + "ts": 6197198513888.647, "dur": 62159.983, + "args": { + "External id": 32236,"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": 2338707, "tid": 2379456, + "ts": 6197198513893.294, "dur": 11.122, + "args": { + "External id": 32237,"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": 2338707, "tid": 2379456, + "ts": 6197198513906.236, "dur": 62137.359, + "args": { + "External id": 32238,"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": 2338707, "tid": 2379456, + "ts": 6197198576237.053, "dur": 12.263, + "args": { + "External id": 32239,"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": 2338707, "tid": 2379456, + "ts": 6197198576240.842, "dur": 7.986, + "args": { + "External id": 32240,"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": 2338707, "tid": 2379456, + "ts": 6197198576278.716, "dur": 366.418, + "args": { + "External id": 32241,"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": 2338707, "tid": 2379456, + "ts": 6197198576311.250, "dur": 328.866, + "args": { + "External id": 32242,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197198576323.024, "dur": 311.367, + "args": { + "External id": 32243,"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": 2338707, "tid": 2379456, + "ts": 6197198576664.607, "dur": 2.187, + "args": { + "External id": 32244,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2379456, + "ts": 6197198576745.425, "dur": 6.801, + "args": { + "External id": 32245,"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": 2338707, "tid": 2379456, + "ts": 6197198576796.789, "dur": 3.076, + "args": { + "External id": 32246,"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": 2338707, "tid": 2379456, + "ts": 6197198576814.363, "dur": 0.974, + "args": { + "External id": 32247,"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": 2338707, "tid": 2379456, + "ts": 6197198576826.998, "dur": 1.051, + "args": { + "External id": 32248,"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": 2338707, "tid": 2379456, + "ts": 6197198576839.773, "dur": 1.268, + "args": { + "External id": 32249,"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": 2338707, "tid": 2379456, + "ts": 6197198576851.289, "dur": 3.071, + "args": { + "External id": 32250,"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": 2338707, "tid": 2379456, + "ts": 6197198576864.322, "dur": 1.071, + "args": { + "External id": 32251,"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": 2338707, "tid": 2379456, + "ts": 6197198576876.486, "dur": 2.514, + "args": { + "External id": 32252,"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": 2338707, "tid": 2379456, + "ts": 6197198576888.250, "dur": 0.849, + "args": { + "External id": 32253,"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": 2338707, "tid": 2379456, + "ts": 6197198576981.589, "dur": 2994.007, + "args": { + "External id": 32254,"Record function id": 0, "Ev Idx": 5117 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.3)", "pid": 2338707, "tid": 2379456, + "ts": 6197198577002.272, "dur": 1185.340, + "args": { + "External id": 32255,"Record function id": 0, "Ev Idx": 5118 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.3)", "pid": 2338707, "tid": 2379456, + "ts": 6197198577018.224, "dur": 419.105, + "args": { + "External id": 32256,"Record function id": 0, "Ev Idx": 5119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6197198577181.764, "dur": 8.213, + "args": { + "External id": 32257,"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": 2338707, "tid": 2379456, + "ts": 6197198577193.959, "dur": 1.141, + "args": { + "External id": 32258,"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": 2338707, "tid": 2379456, + "ts": 6197198577196.839, "dur": 0.795, + "args": { + "External id": 32259,"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": 2338707, "tid": 2379456, + "ts": 6197198577199.123, "dur": 0.615, + "args": { + "External id": 32260,"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": 2338707, "tid": 2379456, + "ts": 6197198577201.206, "dur": 1.058, + "args": { + "External id": 32261,"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": 2338707, "tid": 2379456, + "ts": 6197198577205.613, "dur": 0.841, + "args": { + "External id": 32262,"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": 2338707, "tid": 2379456, + "ts": 6197198577207.964, "dur": 1.809, + "args": { + "External id": 32263,"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": 2338707, "tid": 2379456, + "ts": 6197198577211.067, "dur": 0.848, + "args": { + "External id": 32264,"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": 2338707, "tid": 2379456, + "ts": 6197198577213.375, "dur": 2.162, + "args": { + "External id": 32265,"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": 2338707, "tid": 2379456, + "ts": 6197198577216.817, "dur": 0.586, + "args": { + "External id": 32266,"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": 2338707, "tid": 2379456, + "ts": 6197198577240.260, "dur": 165.513, + "args": { + "External id": 32267,"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": 2338707, "tid": 2379456, + "ts": 6197198577257.369, "dur": 143.457, + "args": { + "External id": 32268,"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": 2338707, "tid": 2379456, + "ts": 6197198577283.163, "dur": 14.845, + "args": { + "External id": 32269,"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": 2338707, "tid": 2379456, + "ts": 6197198577304.096, "dur": 67.380, + "args": { + "External id": 32270,"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": 2338707, "tid": 2379456, + "ts": 6197198577306.983, "dur": 64.108, + "args": { + "External id": 32271,"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": 2338707, "tid": 2379456, + "ts": 6197198577310.887, "dur": 5.701, + "args": { + "External id": 32272,"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": 2338707, "tid": 2379456, + "ts": 6197198577318.236, "dur": 52.338, + "args": { + "External id": 32273,"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": 2338707, "tid": 2379456, + "ts": 6197198577531.669, "dur": 647.973, + "args": { + "External id": 32274,"Record function id": 0, "Ev Idx": 5137 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.2)", "pid": 2338707, "tid": 2379456, + "ts": 6197198577548.682, "dur": 617.876, + "args": { + "External id": 32275,"Record function id": 0, "Ev Idx": 5138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197198577612.884, "dur": 4.992, + "args": { + "External id": 32276,"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": 2338707, "tid": 2379456, + "ts": 6197198577632.999, "dur": 28.786, + "args": { + "External id": 32277,"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": 2338707, "tid": 2379456, + "ts": 6197198577638.218, "dur": 1.725, + "args": { + "External id": 32278,"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": 2338707, "tid": 2379456, + "ts": 6197198577641.833, "dur": 0.590, + "args": { + "External id": 32279,"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": 2338707, "tid": 2379456, + "ts": 6197198577644.067, "dur": 0.552, + "args": { + "External id": 32280,"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": 2338707, "tid": 2379456, + "ts": 6197198577646.447, "dur": 2.091, + "args": { + "External id": 32281,"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": 2338707, "tid": 2379456, + "ts": 6197198577649.505, "dur": 0.453, + "args": { + "External id": 32282,"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": 2338707, "tid": 2379456, + "ts": 6197198577651.951, "dur": 0.333, + "args": { + "External id": 32283,"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": 2338707, "tid": 2379456, + "ts": 6197198577653.583, "dur": 0.322, + "args": { + "External id": 32284,"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": 2338707, "tid": 2379456, + "ts": 6197198577654.918, "dur": 0.370, + "args": { + "External id": 32285,"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": 2338707, "tid": 2379456, + "ts": 6197198577656.741, "dur": 0.539, + "args": { + "External id": 32286,"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": 2338707, "tid": 2379456, + "ts": 6197198577671.307, "dur": 63.185, + "args": { + "External id": 32287,"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": 2338707, "tid": 2379456, + "ts": 6197198577767.167, "dur": 119.471, + "args": { + "External id": 32288,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2379456, + "ts": 6197198577778.093, "dur": 4.169, + "args": { + "External id": 32289,"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": 2338707, "tid": 2379456, + "ts": 6197198577787.487, "dur": 13.373, + "args": { + "External id": 32290,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2379456, + "ts": 6197198577795.184, "dur": 5.267, + "args": { + "External id": 32291,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2379456, + "ts": 6197198577798.226, "dur": 0.715, + "args": { + "External id": 32292,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197198577807.585, "dur": 25.223, + "args": { + "External id": 32293,"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": 2338707, "tid": 2379456, + "ts": 6197198577809.287, "dur": 2.387, + "args": { + "External id": 32294,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197198577813.583, "dur": 0.518, + "args": { + "External id": 32295,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2379456, + "ts": 6197198577815.858, "dur": 0.396, + "args": { + "External id": 32296,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2379456, + "ts": 6197198577817.201, "dur": 0.571, + "args": { + "External id": 32297,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2379456, + "ts": 6197198577819.161, "dur": 0.456, + "args": { + "External id": 32298,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2379456, + "ts": 6197198577821.077, "dur": 0.690, + "args": { + "External id": 32299,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2379456, + "ts": 6197198577822.698, "dur": 0.381, + "args": { + "External id": 32300,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2379456, + "ts": 6197198577824.498, "dur": 0.314, + "args": { + "External id": 32301,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2379456, + "ts": 6197198577826.351, "dur": 1.770, + "args": { + "External id": 32302,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2379456, + "ts": 6197198577846.560, "dur": 32.298, + "args": { + "External id": 32303,"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": 2338707, "tid": 2379456, + "ts": 6197198577931.635, "dur": 118.596, + "args": { + "External id": 32304,"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": 2338707, "tid": 2379456, + "ts": 6197198577959.397, "dur": 87.448, + "args": { + "External id": 32305,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197198577969.360, "dur": 73.145, + "args": { + "External id": 32306,"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": 2338707, "tid": 2379456, + "ts": 6197198578107.514, "dur": 3.307, + "args": { + "External id": 32307,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197198578195.682, "dur": 1758.047, + "args": { + "External id": 32308,"Sequence number": 479774, "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": 2338707, "tid": 2379456, "ts": 6197198578195.682, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6197198578304.628, "dur": 111.657, + "args": { + "External id": 32309,"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": 2338707, "tid": 2379456, + "ts": 6197198578457.114, "dur": 40.240, + "args": { + "External id": 32310,"kernel_hash": "cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/u7/cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs.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": 2338707, "tid": 2379456, + "ts": 6197198578516.177, "dur": 50.825, + "args": { + "External id": 32311,"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": 2338707, "tid": 2379456, + "ts": 6197198578576.761, "dur": 32.278, + "args": { + "External id": 32312,"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": 2338707, "tid": 2379456, + "ts": 6197198578615.299, "dur": 32.720, + "args": { + "External id": 32313,"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": 2338707, "tid": 2379456, + "ts": 6197198578654.875, "dur": 28.572, + "args": { + "External id": 32314,"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": 2338707, "tid": 2379456, + "ts": 6197198578692.048, "dur": 50.851, + "args": { + "External id": 32315,"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": 2338707, "tid": 2379456, + "ts": 6197198578774.044, "dur": 28.093, + "args": { + "External id": 32316,"kernel_hash": "cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/wm/cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s.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": 2338707, "tid": 2379456, + "ts": 6197198578821.370, "dur": 30.255, + "args": { + "External id": 32317,"kernel_hash": "cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql", "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/qt/cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql.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": 2338707, "tid": 2379456, + "ts": 6197198578876.562, "dur": 19.451, + "args": { + "External id": 32318,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197198578909.522, "dur": 19.569, + "args": { + "External id": 32319,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197198578944.106, "dur": 43.387, + "args": { + "External id": 32320,"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": 2338707, "tid": 2379456, + "ts": 6197198578991.807, "dur": 34.276, + "args": { + "External id": 32321,"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": 2338707, "tid": 2379456, + "ts": 6197198579088.381, "dur": 247.188, + "args": { + "External id": 32322,"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": 2338707, "tid": 2379456, + "ts": 6197198579169.355, "dur": 6.487, + "args": { + "External id": 32323,"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": 2338707, "tid": 2379456, + "ts": 6197198579178.090, "dur": 2.500, + "args": { + "External id": 32324,"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": 2338707, "tid": 2379456, + "ts": 6197198579182.021, "dur": 2.227, + "args": { + "External id": 32325,"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": 2338707, "tid": 2379456, + "ts": 6197198579185.486, "dur": 3.158, + "args": { + "External id": 32326,"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": 2338707, "tid": 2379456, + "ts": 6197198579235.186, "dur": 4.729, + "args": { + "External id": 32327,"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": 2338707, "tid": 2379456, + "ts": 6197198579236.875, "dur": 2.838, + "args": { + "External id": 32328,"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": 2338707, "tid": 2379456, + "ts": 6197198579241.823, "dur": 31.639, + "args": { + "External id": 32329,"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": 2338707, "tid": 2379456, + "ts": 6197198579247.378, "dur": 1.756, + "args": { + "External id": 32330,"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": 2338707, "tid": 2379456, + "ts": 6197198579274.693, "dur": 2.281, + "args": { + "External id": 32331,"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": 2338707, "tid": 2379456, + "ts": 6197198579276.115, "dur": 0.762, + "args": { + "External id": 32332,"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": 2338707, "tid": 2379456, + "ts": 6197198579278.224, "dur": 14.560, + "args": { + "External id": 32333,"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": 2338707, "tid": 2379456, + "ts": 6197198579280.282, "dur": 0.657, + "args": { + "External id": 32334,"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": 2338707, "tid": 2379456, + "ts": 6197198579377.650, "dur": 28.852, + "args": { + "External id": 32335,"kernel_hash": "cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4", "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/yk/cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4.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": 2338707, "tid": 2379456, + "ts": 6197198579426.268, "dur": 16.745, + "args": { + "External id": 32336,"kernel_hash": "ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg", "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/eu/ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg.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": 2338707, "tid": 2379456, + "ts": 6197198579451.724, "dur": 48.891, + "args": { + "External id": 32337,"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": 2338707, "tid": 2379456, + "ts": 6197198579507.395, "dur": 40.540, + "args": { + "External id": 32338,"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": 2338707, "tid": 2379456, + "ts": 6197198579557.008, "dur": 21.183, + "args": { + "External id": 32339,"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": 2338707, "tid": 2379456, + "ts": 6197198579586.791, "dur": 32.793, + "args": { + "External id": 32340,"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": 2338707, "tid": 2379456, + "ts": 6197198579627.683, "dur": 28.542, + "args": { + "External id": 32341,"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": 2338707, "tid": 2379456, + "ts": 6197198579663.813, "dur": 30.789, + "args": { + "External id": 32342,"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": 2338707, "tid": 2379456, + "ts": 6197198579747.089, "dur": 34.502, + "args": { + "External id": 32343,"kernel_hash": "c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/6w/c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7.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": 2338707, "tid": 2379456, + "ts": 6197198579800.537, "dur": 24.716, + "args": { + "External id": 32344,"kernel_hash": "ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx", "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/kj/ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx.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": 2338707, "tid": 2379456, + "ts": 6197198579839.513, "dur": 20.185, + "args": { + "External id": 32345,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197198579876.332, "dur": 14.192, + "args": { + "External id": 32346,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197198579903.120, "dur": 18.655, + "args": { + "External id": 32347,"kernel_hash": "cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/eb/cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b.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": 2338707, "tid": 2379456, + "ts": 6197198579998.189, "dur": 14.857, + "args": { + "External id": 32348,"Record function id": 0, "Ev Idx": 5211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198580001.362, "dur": 10.611, + "args": { + "External id": 32349,"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": 2338707, "tid": 2379456, + "ts": 6197198580005.369, "dur": 5.696, + "args": { + "External id": 32350,"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": 2338707, "tid": 2379456, + "ts": 6197198580006.957, "dur": 3.991, + "args": { + "External id": 32351,"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": 2338707, "tid": 2379456, + "ts": 6197198580017.158, "dur": 4.881, + "args": { + "External id": 32352,"Record function id": 0, "Ev Idx": 5215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198580018.834, "dur": 2.735, + "args": { + "External id": 32353,"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": 2338707, "tid": 2379456, + "ts": 6197198580019.426, "dur": 1.605, + "args": { + "External id": 32354,"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": 2338707, "tid": 2379456, + "ts": 6197198580020.109, "dur": 0.857, + "args": { + "External id": 32355,"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": 2338707, "tid": 2379456, + "ts": 6197198580025.306, "dur": 3.809, + "args": { + "External id": 32356,"Record function id": 0, "Ev Idx": 5219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198580026.257, "dur": 2.429, + "args": { + "External id": 32357,"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": 2338707, "tid": 2379456, + "ts": 6197198580027.057, "dur": 1.209, + "args": { + "External id": 32358,"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": 2338707, "tid": 2379456, + "ts": 6197198580027.453, "dur": 0.731, + "args": { + "External id": 32359,"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": 2338707, "tid": 2379456, + "ts": 6197198580032.291, "dur": 4.400, + "args": { + "External id": 32360,"Record function id": 0, "Ev Idx": 5223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198580033.462, "dur": 2.789, + "args": { + "External id": 32361,"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": 2338707, "tid": 2379456, + "ts": 6197198580034.182, "dur": 1.596, + "args": { + "External id": 32362,"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": 2338707, "tid": 2379456, + "ts": 6197198580034.951, "dur": 0.720, + "args": { + "External id": 32363,"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": 2338707, "tid": 2379456, + "ts": 6197198580039.895, "dur": 3.630, + "args": { + "External id": 32364,"Record function id": 0, "Ev Idx": 5227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198580041.069, "dur": 2.033, + "args": { + "External id": 32365,"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": 2338707, "tid": 2379456, + "ts": 6197198580041.553, "dur": 1.106, + "args": { + "External id": 32366,"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": 2338707, "tid": 2379456, + "ts": 6197198580041.990, "dur": 0.590, + "args": { + "External id": 32367,"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": 2338707, "tid": 2379456, + "ts": 6197198580046.642, "dur": 39.789, + "args": { + "External id": 32368,"Record function id": 0, "Ev Idx": 5231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198580047.664, "dur": 36.827, + "args": { + "External id": 32369,"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": 2338707, "tid": 2379456, + "ts": 6197198580048.371, "dur": 2.856, + "args": { + "External id": 32370,"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": 2338707, "tid": 2379456, + "ts": 6197198580048.706, "dur": 2.443, + "args": { + "External id": 32371,"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": 2338707, "tid": 2379456, + "ts": 6197198580092.650, "dur": 5.849, + "args": { + "External id": 32372,"Record function id": 0, "Ev Idx": 5235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198580094.314, "dur": 3.686, + "args": { + "External id": 32373,"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": 2338707, "tid": 2379456, + "ts": 6197198580095.280, "dur": 1.934, + "args": { + "External id": 32374,"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": 2338707, "tid": 2379456, + "ts": 6197198580096.010, "dur": 1.084, + "args": { + "External id": 32375,"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": 2338707, "tid": 2379456, + "ts": 6197198580101.588, "dur": 4.786, + "args": { + "External id": 32376,"Record function id": 0, "Ev Idx": 5239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198580102.944, "dur": 2.996, + "args": { + "External id": 32377,"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": 2338707, "tid": 2379456, + "ts": 6197198580103.978, "dur": 1.516, + "args": { + "External id": 32378,"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": 2338707, "tid": 2379456, + "ts": 6197198580104.665, "dur": 0.733, + "args": { + "External id": 32379,"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": 2338707, "tid": 2379456, + "ts": 6197198580110.107, "dur": 3.882, + "args": { + "External id": 32380,"Record function id": 0, "Ev Idx": 5243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198580111.266, "dur": 2.241, + "args": { + "External id": 32381,"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": 2338707, "tid": 2379456, + "ts": 6197198580111.966, "dur": 1.084, + "args": { + "External id": 32382,"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": 2338707, "tid": 2379456, + "ts": 6197198580112.302, "dur": 0.668, + "args": { + "External id": 32383,"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": 2338707, "tid": 2379456, + "ts": 6197198580118.246, "dur": 62710.925, + "args": { + "External id": 32384,"Record function id": 0, "Sequence number": 479773, "Fwd thread id": 1, "Ev Idx": 5247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197198580119.511, "dur": 62700.560, + "args": { + "External id": 32385,"Sequence number": 479773, "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": 2338707, "tid": 2379456, "ts": 6197198580119.511, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.3)", "pid": 2338707, "tid": 2379456, + "ts": 6197198580150.125, "dur": 39.460, + "args": { + "External id": 32386,"Record function id": 0, "Ev Idx": 5249 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.3)", "pid": 2338707, "tid": 2379456, + "ts": 6197198580197.526, "dur": 65.465, + "args": { + "External id": 32387,"Record function id": 0, "Ev Idx": 5250 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.3)", "pid": 2338707, "tid": 2379456, + "ts": 6197198580268.947, "dur": 62543.344, + "args": { + "External id": 32388,"Record function id": 0, "Ev Idx": 5251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197198580358.766, "dur": 7.056, + "args": { + "External id": 32389,"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": 2338707, "tid": 2379456, + "ts": 6197198580375.473, "dur": 4.721, + "args": { + "External id": 32390,"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": 2338707, "tid": 2379456, + "ts": 6197198580393.934, "dur": 61551.976, + "args": { + "External id": 32391,"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": 2338707, "tid": 2379456, + "ts": 6197198580408.792, "dur": 61524.188, + "args": { + "External id": 32392,"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": 2338707, "tid": 2379456, + "ts": 6197198580503.903, "dur": 16.971, + "args": { + "External id": 32393,"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": 2338707, "tid": 2379456, + "ts": 6197198580540.765, "dur": 61349.687, + "args": { + "External id": 32394,"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": 2338707, "tid": 2379456, + "ts": 6197198580543.289, "dur": 61345.857, + "args": { + "External id": 32395,"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": 2338707, "tid": 2379456, + "ts": 6197198580547.683, "dur": 9.306, + "args": { + "External id": 32396,"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": 2338707, "tid": 2379456, + "ts": 6197198580559.087, "dur": 61325.192, + "args": { + "External id": 32397,"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": 2338707, "tid": 2379456, + "ts": 6197198642050.555, "dur": 52.228, + "args": { + "External id": 32398,"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": 2338707, "tid": 2379456, + "ts": 6197198642092.519, "dur": 9.453, + "args": { + "External id": 32399,"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": 2338707, "tid": 2379456, + "ts": 6197198642134.294, "dur": 372.687, + "args": { + "External id": 32400,"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": 2338707, "tid": 2379456, + "ts": 6197198642166.705, "dur": 335.274, + "args": { + "External id": 32401,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197198642179.586, "dur": 317.213, + "args": { + "External id": 32402,"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": 2338707, "tid": 2379456, + "ts": 6197198642527.114, "dur": 2.249, + "args": { + "External id": 32403,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2379456, + "ts": 6197198642589.839, "dur": 6.411, + "args": { + "External id": 32404,"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": 2338707, "tid": 2379456, + "ts": 6197198642638.129, "dur": 3.128, + "args": { + "External id": 32405,"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": 2338707, "tid": 2379456, + "ts": 6197198642656.392, "dur": 1.005, + "args": { + "External id": 32406,"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": 2338707, "tid": 2379456, + "ts": 6197198642668.495, "dur": 0.760, + "args": { + "External id": 32407,"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": 2338707, "tid": 2379456, + "ts": 6197198642681.864, "dur": 1.088, + "args": { + "External id": 32408,"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": 2338707, "tid": 2379456, + "ts": 6197198642693.139, "dur": 2.958, + "args": { + "External id": 32409,"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": 2338707, "tid": 2379456, + "ts": 6197198642726.601, "dur": 1.663, + "args": { + "External id": 32410,"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": 2338707, "tid": 2379456, + "ts": 6197198642738.852, "dur": 2.727, + "args": { + "External id": 32411,"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": 2338707, "tid": 2379456, + "ts": 6197198642751.424, "dur": 0.740, + "args": { + "External id": 32412,"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": 2338707, "tid": 2379456, + "ts": 6197198642844.816, "dur": 3009.117, + "args": { + "External id": 32413,"Record function id": 0, "Ev Idx": 5276 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.2)", "pid": 2338707, "tid": 2379456, + "ts": 6197198642867.591, "dur": 1109.937, + "args": { + "External id": 32414,"Record function id": 0, "Ev Idx": 5277 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.2)", "pid": 2338707, "tid": 2379456, + "ts": 6197198642881.720, "dur": 386.134, + "args": { + "External id": 32415,"Record function id": 0, "Ev Idx": 5278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6197198642972.489, "dur": 5.905, + "args": { + "External id": 32416,"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": 2338707, "tid": 2379456, + "ts": 6197198642981.788, "dur": 1.148, + "args": { + "External id": 32417,"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": 2338707, "tid": 2379456, + "ts": 6197198642984.660, "dur": 0.812, + "args": { + "External id": 32418,"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": 2338707, "tid": 2379456, + "ts": 6197198642987.421, "dur": 0.536, + "args": { + "External id": 32419,"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": 2338707, "tid": 2379456, + "ts": 6197198642989.457, "dur": 0.946, + "args": { + "External id": 32420,"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": 2338707, "tid": 2379456, + "ts": 6197198642991.536, "dur": 0.701, + "args": { + "External id": 32421,"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": 2338707, "tid": 2379456, + "ts": 6197198642993.871, "dur": 2.212, + "args": { + "External id": 32422,"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": 2338707, "tid": 2379456, + "ts": 6197198642997.544, "dur": 0.776, + "args": { + "External id": 32423,"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": 2338707, "tid": 2379456, + "ts": 6197198643001.921, "dur": 2.166, + "args": { + "External id": 32424,"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": 2338707, "tid": 2379456, + "ts": 6197198643005.742, "dur": 1.144, + "args": { + "External id": 32425,"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": 2338707, "tid": 2379456, + "ts": 6197198643023.179, "dur": 209.208, + "args": { + "External id": 32426,"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": 2338707, "tid": 2379456, + "ts": 6197198643042.801, "dur": 183.254, + "args": { + "External id": 32427,"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": 2338707, "tid": 2379456, + "ts": 6197198643107.059, "dur": 16.637, + "args": { + "External id": 32428,"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": 2338707, "tid": 2379456, + "ts": 6197198643127.890, "dur": 67.999, + "args": { + "External id": 32429,"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": 2338707, "tid": 2379456, + "ts": 6197198643130.786, "dur": 64.769, + "args": { + "External id": 32430,"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": 2338707, "tid": 2379456, + "ts": 6197198643135.137, "dur": 5.734, + "args": { + "External id": 32431,"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": 2338707, "tid": 2379456, + "ts": 6197198643142.908, "dur": 51.915, + "args": { + "External id": 32432,"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": 2338707, "tid": 2379456, + "ts": 6197198643365.240, "dur": 604.150, + "args": { + "External id": 32433,"Record function id": 0, "Ev Idx": 5296 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.1)", "pid": 2338707, "tid": 2379456, + "ts": 6197198643382.350, "dur": 574.961, + "args": { + "External id": 32434,"Record function id": 0, "Ev Idx": 5297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197198643449.055, "dur": 4.958, + "args": { + "External id": 32435,"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": 2338707, "tid": 2379456, + "ts": 6197198643468.739, "dur": 33.463, + "args": { + "External id": 32436,"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": 2338707, "tid": 2379456, + "ts": 6197198643473.940, "dur": 1.906, + "args": { + "External id": 32437,"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": 2338707, "tid": 2379456, + "ts": 6197198643483.041, "dur": 0.595, + "args": { + "External id": 32438,"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": 2338707, "tid": 2379456, + "ts": 6197198643485.046, "dur": 0.483, + "args": { + "External id": 32439,"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": 2338707, "tid": 2379456, + "ts": 6197198643487.083, "dur": 1.870, + "args": { + "External id": 32440,"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": 2338707, "tid": 2379456, + "ts": 6197198643489.795, "dur": 0.411, + "args": { + "External id": 32441,"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": 2338707, "tid": 2379456, + "ts": 6197198643491.640, "dur": 0.358, + "args": { + "External id": 32442,"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": 2338707, "tid": 2379456, + "ts": 6197198643493.548, "dur": 0.345, + "args": { + "External id": 32443,"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": 2338707, "tid": 2379456, + "ts": 6197198643494.877, "dur": 0.321, + "args": { + "External id": 32444,"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": 2338707, "tid": 2379456, + "ts": 6197198643496.523, "dur": 0.450, + "args": { + "External id": 32445,"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": 2338707, "tid": 2379456, + "ts": 6197198643512.208, "dur": 46.130, + "args": { + "External id": 32446,"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": 2338707, "tid": 2379456, + "ts": 6197198643587.209, "dur": 107.479, + "args": { + "External id": 32447,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2379456, + "ts": 6197198643597.115, "dur": 3.218, + "args": { + "External id": 32448,"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": 2338707, "tid": 2379456, + "ts": 6197198643604.951, "dur": 9.413, + "args": { + "External id": 32449,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2379456, + "ts": 6197198643608.951, "dur": 5.002, + "args": { + "External id": 32450,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2379456, + "ts": 6197198643612.249, "dur": 0.575, + "args": { + "External id": 32451,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197198643620.632, "dur": 27.335, + "args": { + "External id": 32452,"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": 2338707, "tid": 2379456, + "ts": 6197198643622.373, "dur": 2.772, + "args": { + "External id": 32453,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197198643626.668, "dur": 0.440, + "args": { + "External id": 32454,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2379456, + "ts": 6197198643629.076, "dur": 0.369, + "args": { + "External id": 32455,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2379456, + "ts": 6197198643631.017, "dur": 0.424, + "args": { + "External id": 32456,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2379456, + "ts": 6197198643632.418, "dur": 0.404, + "args": { + "External id": 32457,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2379456, + "ts": 6197198643634.249, "dur": 0.390, + "args": { + "External id": 32458,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2379456, + "ts": 6197198643636.629, "dur": 0.183, + "args": { + "External id": 32459,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2379456, + "ts": 6197198643638.334, "dur": 0.630, + "args": { + "External id": 32460,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2379456, + "ts": 6197198643640.676, "dur": 2.520, + "args": { + "External id": 32461,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2379456, + "ts": 6197198643658.106, "dur": 29.690, + "args": { + "External id": 32462,"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": 2338707, "tid": 2379456, + "ts": 6197198643760.370, "dur": 121.563, + "args": { + "External id": 32463,"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": 2338707, "tid": 2379456, + "ts": 6197198643787.274, "dur": 91.116, + "args": { + "External id": 32464,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197198643797.249, "dur": 76.736, + "args": { + "External id": 32465,"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": 2338707, "tid": 2379456, + "ts": 6197198643902.148, "dur": 1.518, + "args": { + "External id": 32466,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197198643985.528, "dur": 1845.778, + "args": { + "External id": 32467,"Sequence number": 479772, "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": 2338707, "tid": 2379456, "ts": 6197198643985.528, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6197198644135.493, "dur": 109.576, + "args": { + "External id": 32468,"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": 2338707, "tid": 2379456, + "ts": 6197198644288.813, "dur": 41.331, + "args": { + "External id": 32469,"kernel_hash": "cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/u7/cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs.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": 2338707, "tid": 2379456, + "ts": 6197198644350.240, "dur": 51.453, + "args": { + "External id": 32470,"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": 2338707, "tid": 2379456, + "ts": 6197198644411.388, "dur": 31.352, + "args": { + "External id": 32471,"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": 2338707, "tid": 2379456, + "ts": 6197198644449.340, "dur": 34.082, + "args": { + "External id": 32472,"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": 2338707, "tid": 2379456, + "ts": 6197198644489.923, "dur": 27.793, + "args": { + "External id": 32473,"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": 2338707, "tid": 2379456, + "ts": 6197198644526.272, "dur": 31.693, + "args": { + "External id": 32474,"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": 2338707, "tid": 2379456, + "ts": 6197198644583.121, "dur": 26.196, + "args": { + "External id": 32475,"kernel_hash": "cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/wm/cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s.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": 2338707, "tid": 2379456, + "ts": 6197198644631.718, "dur": 29.185, + "args": { + "External id": 32476,"kernel_hash": "cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql", "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/qt/cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql.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": 2338707, "tid": 2379456, + "ts": 6197198644682.714, "dur": 41.628, + "args": { + "External id": 32477,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197198644742.447, "dur": 19.463, + "args": { + "External id": 32478,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197198644773.431, "dur": 43.225, + "args": { + "External id": 32479,"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": 2338707, "tid": 2379456, + "ts": 6197198644820.510, "dur": 35.209, + "args": { + "External id": 32480,"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": 2338707, "tid": 2379456, + "ts": 6197198644890.016, "dur": 307.915, + "args": { + "External id": 32481,"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": 2338707, "tid": 2379456, + "ts": 6197198644966.886, "dur": 6.669, + "args": { + "External id": 32482,"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": 2338707, "tid": 2379456, + "ts": 6197198644975.923, "dur": 2.947, + "args": { + "External id": 32483,"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": 2338707, "tid": 2379456, + "ts": 6197198644980.332, "dur": 2.388, + "args": { + "External id": 32484,"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": 2338707, "tid": 2379456, + "ts": 6197198644984.247, "dur": 4.623, + "args": { + "External id": 32485,"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": 2338707, "tid": 2379456, + "ts": 6197198645037.037, "dur": 4.599, + "args": { + "External id": 32486,"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": 2338707, "tid": 2379456, + "ts": 6197198645038.770, "dur": 2.674, + "args": { + "External id": 32487,"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": 2338707, "tid": 2379456, + "ts": 6197198645043.285, "dur": 83.087, + "args": { + "External id": 32488,"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": 2338707, "tid": 2379456, + "ts": 6197198645048.944, "dur": 1.740, + "args": { + "External id": 32489,"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": 2338707, "tid": 2379456, + "ts": 6197198645129.297, "dur": 2.443, + "args": { + "External id": 32490,"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": 2338707, "tid": 2379456, + "ts": 6197198645130.620, "dur": 1.032, + "args": { + "External id": 32491,"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": 2338707, "tid": 2379456, + "ts": 6197198645132.803, "dur": 16.931, + "args": { + "External id": 32492,"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": 2338707, "tid": 2379456, + "ts": 6197198645135.465, "dur": 0.606, + "args": { + "External id": 32493,"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": 2338707, "tid": 2379456, + "ts": 6197198645239.025, "dur": 27.912, + "args": { + "External id": 32494,"kernel_hash": "cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4", "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/yk/cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4.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": 2338707, "tid": 2379456, + "ts": 6197198645285.572, "dur": 19.674, + "args": { + "External id": 32495,"kernel_hash": "ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg", "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/eu/ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg.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": 2338707, "tid": 2379456, + "ts": 6197198645314.381, "dur": 51.166, + "args": { + "External id": 32496,"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": 2338707, "tid": 2379456, + "ts": 6197198645373.406, "dur": 42.313, + "args": { + "External id": 32497,"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": 2338707, "tid": 2379456, + "ts": 6197198645425.096, "dur": 22.627, + "args": { + "External id": 32498,"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": 2338707, "tid": 2379456, + "ts": 6197198645456.550, "dur": 33.039, + "args": { + "External id": 32499,"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": 2338707, "tid": 2379456, + "ts": 6197198645497.639, "dur": 28.849, + "args": { + "External id": 32500,"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": 2338707, "tid": 2379456, + "ts": 6197198645534.082, "dur": 34.134, + "args": { + "External id": 32501,"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": 2338707, "tid": 2379456, + "ts": 6197198645586.810, "dur": 23.836, + "args": { + "External id": 32502,"kernel_hash": "c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/6w/c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7.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": 2338707, "tid": 2379456, + "ts": 6197198645647.200, "dur": 31.904, + "args": { + "External id": 32503,"kernel_hash": "ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx", "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/kj/ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx.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": 2338707, "tid": 2379456, + "ts": 6197198645693.948, "dur": 34.350, + "args": { + "External id": 32504,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197198645749.081, "dur": 15.946, + "args": { + "External id": 32505,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197198645778.566, "dur": 16.738, + "args": { + "External id": 32506,"kernel_hash": "cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/eb/cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b.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": 2338707, "tid": 2379456, + "ts": 6197198645879.359, "dur": 15.611, + "args": { + "External id": 32507,"Record function id": 0, "Ev Idx": 5370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198645882.839, "dur": 11.256, + "args": { + "External id": 32508,"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": 2338707, "tid": 2379456, + "ts": 6197198645886.756, "dur": 6.146, + "args": { + "External id": 32509,"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": 2338707, "tid": 2379456, + "ts": 6197198645888.704, "dur": 4.068, + "args": { + "External id": 32510,"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": 2338707, "tid": 2379456, + "ts": 6197198645899.191, "dur": 5.273, + "args": { + "External id": 32511,"Record function id": 0, "Ev Idx": 5374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198645900.622, "dur": 3.426, + "args": { + "External id": 32512,"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": 2338707, "tid": 2379456, + "ts": 6197198645901.255, "dur": 2.327, + "args": { + "External id": 32513,"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": 2338707, "tid": 2379456, + "ts": 6197198645902.142, "dur": 1.335, + "args": { + "External id": 32514,"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": 2338707, "tid": 2379456, + "ts": 6197198645907.828, "dur": 4.782, + "args": { + "External id": 32515,"Record function id": 0, "Ev Idx": 5378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198645909.268, "dur": 2.929, + "args": { + "External id": 32516,"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": 2338707, "tid": 2379456, + "ts": 6197198645910.087, "dur": 1.707, + "args": { + "External id": 32517,"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": 2338707, "tid": 2379456, + "ts": 6197198645910.610, "dur": 1.117, + "args": { + "External id": 32518,"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": 2338707, "tid": 2379456, + "ts": 6197198645915.843, "dur": 4.143, + "args": { + "External id": 32519,"Record function id": 0, "Ev Idx": 5382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198645917.164, "dur": 2.384, + "args": { + "External id": 32520,"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": 2338707, "tid": 2379456, + "ts": 6197198645917.638, "dur": 1.522, + "args": { + "External id": 32521,"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": 2338707, "tid": 2379456, + "ts": 6197198645918.163, "dur": 0.931, + "args": { + "External id": 32522,"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": 2338707, "tid": 2379456, + "ts": 6197198645923.095, "dur": 4.468, + "args": { + "External id": 32523,"Record function id": 0, "Ev Idx": 5386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198645924.423, "dur": 2.733, + "args": { + "External id": 32524,"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": 2338707, "tid": 2379456, + "ts": 6197198645925.264, "dur": 1.385, + "args": { + "External id": 32525,"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": 2338707, "tid": 2379456, + "ts": 6197198645925.707, "dur": 0.876, + "args": { + "External id": 32526,"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": 2338707, "tid": 2379456, + "ts": 6197198645930.792, "dur": 7.291, + "args": { + "External id": 32527,"Record function id": 0, "Ev Idx": 5390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198645932.502, "dur": 5.160, + "args": { + "External id": 32528,"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": 2338707, "tid": 2379456, + "ts": 6197198645933.409, "dur": 3.830, + "args": { + "External id": 32529,"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": 2338707, "tid": 2379456, + "ts": 6197198645934.071, "dur": 3.072, + "args": { + "External id": 32530,"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": 2338707, "tid": 2379456, + "ts": 6197198645941.386, "dur": 4.888, + "args": { + "External id": 32531,"Record function id": 0, "Ev Idx": 5394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198645942.912, "dur": 2.922, + "args": { + "External id": 32532,"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": 2338707, "tid": 2379456, + "ts": 6197198645943.715, "dur": 1.697, + "args": { + "External id": 32533,"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": 2338707, "tid": 2379456, + "ts": 6197198645944.202, "dur": 1.131, + "args": { + "External id": 32534,"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": 2338707, "tid": 2379456, + "ts": 6197198645949.580, "dur": 4.328, + "args": { + "External id": 32535,"Record function id": 0, "Ev Idx": 5398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198645950.819, "dur": 2.670, + "args": { + "External id": 32536,"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": 2338707, "tid": 2379456, + "ts": 6197198645951.775, "dur": 1.274, + "args": { + "External id": 32537,"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": 2338707, "tid": 2379456, + "ts": 6197198645952.235, "dur": 0.735, + "args": { + "External id": 32538,"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": 2338707, "tid": 2379456, + "ts": 6197198645956.975, "dur": 4.612, + "args": { + "External id": 32539,"Record function id": 0, "Ev Idx": 5402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198645958.461, "dur": 2.707, + "args": { + "External id": 32540,"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": 2338707, "tid": 2379456, + "ts": 6197198645959.108, "dur": 1.640, + "args": { + "External id": 32541,"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": 2338707, "tid": 2379456, + "ts": 6197198645959.598, "dur": 1.037, + "args": { + "External id": 32542,"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": 2338707, "tid": 2379456, + "ts": 6197198645965.690, "dur": 66156.355, + "args": { + "External id": 32543,"Record function id": 0, "Sequence number": 479771, "Fwd thread id": 1, "Ev Idx": 5406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197198645967.293, "dur": 66144.026, + "args": { + "External id": 32544,"Sequence number": 479771, "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": 2338707, "tid": 2379456, "ts": 6197198645967.293, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.2)", "pid": 2338707, "tid": 2379456, + "ts": 6197198645996.997, "dur": 35.746, + "args": { + "External id": 32545,"Record function id": 0, "Ev Idx": 5408 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.2)", "pid": 2338707, "tid": 2379456, + "ts": 6197198646041.097, "dur": 104.446, + "args": { + "External id": 32546,"Record function id": 0, "Ev Idx": 5409 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.2)", "pid": 2338707, "tid": 2379456, + "ts": 6197198646153.590, "dur": 65948.674, + "args": { + "External id": 32547,"Record function id": 0, "Ev Idx": 5410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197198646243.088, "dur": 7.433, + "args": { + "External id": 32548,"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": 2338707, "tid": 2379456, + "ts": 6197198646260.370, "dur": 5.020, + "args": { + "External id": 32549,"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": 2338707, "tid": 2379456, + "ts": 6197198646279.977, "dur": 64899.469, + "args": { + "External id": 32550,"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": 2338707, "tid": 2379456, + "ts": 6197198646294.644, "dur": 64871.854, + "args": { + "External id": 32551,"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": 2338707, "tid": 2379456, + "ts": 6197198646389.666, "dur": 16.993, + "args": { + "External id": 32552,"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": 2338707, "tid": 2379456, + "ts": 6197198646426.962, "dur": 64693.517, + "args": { + "External id": 32553,"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": 2338707, "tid": 2379456, + "ts": 6197198646429.686, "dur": 64689.751, + "args": { + "External id": 32554,"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": 2338707, "tid": 2379456, + "ts": 6197198646435.198, "dur": 13.486, + "args": { + "External id": 32555,"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": 2338707, "tid": 2379456, + "ts": 6197198646450.871, "dur": 64663.515, + "args": { + "External id": 32556,"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": 2338707, "tid": 2379456, + "ts": 6197198711281.328, "dur": 11.707, + "args": { + "External id": 32557,"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": 2338707, "tid": 2379456, + "ts": 6197198711284.798, "dur": 7.841, + "args": { + "External id": 32558,"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": 2338707, "tid": 2379456, + "ts": 6197198711325.913, "dur": 441.791, + "args": { + "External id": 32559,"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": 2338707, "tid": 2379456, + "ts": 6197198711357.907, "dur": 403.961, + "args": { + "External id": 32560,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197198711369.505, "dur": 384.735, + "args": { + "External id": 32561,"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": 2338707, "tid": 2379456, + "ts": 6197198711790.578, "dur": 2.453, + "args": { + "External id": 32562,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2379456, + "ts": 6197198711855.746, "dur": 6.559, + "args": { + "External id": 32563,"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": 2338707, "tid": 2379456, + "ts": 6197198711907.967, "dur": 1.324, + "args": { + "External id": 32564,"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": 2338707, "tid": 2379456, + "ts": 6197198711923.878, "dur": 0.980, + "args": { + "External id": 32565,"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": 2338707, "tid": 2379456, + "ts": 6197198711936.768, "dur": 0.937, + "args": { + "External id": 32566,"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": 2338707, "tid": 2379456, + "ts": 6197198711947.731, "dur": 1.156, + "args": { + "External id": 32567,"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": 2338707, "tid": 2379456, + "ts": 6197198711960.978, "dur": 1.160, + "args": { + "External id": 32568,"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": 2338707, "tid": 2379456, + "ts": 6197198711972.473, "dur": 0.984, + "args": { + "External id": 32569,"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": 2338707, "tid": 2379456, + "ts": 6197198711983.731, "dur": 2.215, + "args": { + "External id": 32570,"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": 2338707, "tid": 2379456, + "ts": 6197198711995.038, "dur": 1.007, + "args": { + "External id": 32571,"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": 2338707, "tid": 2379456, + "ts": 6197198712139.221, "dur": 3001.242, + "args": { + "External id": 32572,"Record function id": 0, "Ev Idx": 5435 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.1)", "pid": 2338707, "tid": 2379456, + "ts": 6197198712160.971, "dur": 1105.406, + "args": { + "External id": 32573,"Record function id": 0, "Ev Idx": 5436 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.1)", "pid": 2338707, "tid": 2379456, + "ts": 6197198712174.889, "dur": 347.554, + "args": { + "External id": 32574,"Record function id": 0, "Ev Idx": 5437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6197198712269.549, "dur": 4.709, + "args": { + "External id": 32575,"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": 2338707, "tid": 2379456, + "ts": 6197198712278.122, "dur": 1.261, + "args": { + "External id": 32576,"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": 2338707, "tid": 2379456, + "ts": 6197198712281.241, "dur": 1.043, + "args": { + "External id": 32577,"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": 2338707, "tid": 2379456, + "ts": 6197198712284.869, "dur": 1.258, + "args": { + "External id": 32578,"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": 2338707, "tid": 2379456, + "ts": 6197198712287.482, "dur": 1.317, + "args": { + "External id": 32579,"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": 2338707, "tid": 2379456, + "ts": 6197198712289.977, "dur": 1.097, + "args": { + "External id": 32580,"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": 2338707, "tid": 2379456, + "ts": 6197198712292.526, "dur": 2.200, + "args": { + "External id": 32581,"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": 2338707, "tid": 2379456, + "ts": 6197198712296.815, "dur": 3.464, + "args": { + "External id": 32582,"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": 2338707, "tid": 2379456, + "ts": 6197198712304.201, "dur": 0.957, + "args": { + "External id": 32583,"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": 2338707, "tid": 2379456, + "ts": 6197198712306.522, "dur": 0.755, + "args": { + "External id": 32584,"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": 2338707, "tid": 2379456, + "ts": 6197198712324.420, "dur": 168.056, + "args": { + "External id": 32585,"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": 2338707, "tid": 2379456, + "ts": 6197198712349.908, "dur": 138.290, + "args": { + "External id": 32586,"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": 2338707, "tid": 2379456, + "ts": 6197198712373.934, "dur": 14.844, + "args": { + "External id": 32587,"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": 2338707, "tid": 2379456, + "ts": 6197198712392.541, "dur": 66.794, + "args": { + "External id": 32588,"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": 2338707, "tid": 2379456, + "ts": 6197198712395.474, "dur": 63.558, + "args": { + "External id": 32589,"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": 2338707, "tid": 2379456, + "ts": 6197198712399.553, "dur": 5.871, + "args": { + "External id": 32590,"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": 2338707, "tid": 2379456, + "ts": 6197198712407.267, "dur": 51.059, + "args": { + "External id": 32591,"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": 2338707, "tid": 2379456, + "ts": 6197198712613.967, "dur": 644.240, + "args": { + "External id": 32592,"Record function id": 0, "Ev Idx": 5455 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.0)", "pid": 2338707, "tid": 2379456, + "ts": 6197198712631.208, "dur": 615.037, + "args": { + "External id": 32593,"Record function id": 0, "Ev Idx": 5456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197198712693.604, "dur": 4.628, + "args": { + "External id": 32594,"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": 2338707, "tid": 2379456, + "ts": 6197198712729.679, "dur": 32.881, + "args": { + "External id": 32595,"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": 2338707, "tid": 2379456, + "ts": 6197198712735.283, "dur": 2.106, + "args": { + "External id": 32596,"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": 2338707, "tid": 2379456, + "ts": 6197198712739.703, "dur": 0.833, + "args": { + "External id": 32597,"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": 2338707, "tid": 2379456, + "ts": 6197198712742.896, "dur": 2.653, + "args": { + "External id": 32598,"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": 2338707, "tid": 2379456, + "ts": 6197198712746.748, "dur": 0.546, + "args": { + "External id": 32599,"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": 2338707, "tid": 2379456, + "ts": 6197198712749.131, "dur": 0.429, + "args": { + "External id": 32600,"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": 2338707, "tid": 2379456, + "ts": 6197198712751.290, "dur": 0.307, + "args": { + "External id": 32601,"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": 2338707, "tid": 2379456, + "ts": 6197198712752.626, "dur": 0.446, + "args": { + "External id": 32602,"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": 2338707, "tid": 2379456, + "ts": 6197198712754.860, "dur": 0.553, + "args": { + "External id": 32603,"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": 2338707, "tid": 2379456, + "ts": 6197198712756.931, "dur": 0.467, + "args": { + "External id": 32604,"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": 2338707, "tid": 2379456, + "ts": 6197198712774.004, "dur": 47.971, + "args": { + "External id": 32605,"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": 2338707, "tid": 2379456, + "ts": 6197198712851.482, "dur": 111.929, + "args": { + "External id": 32606,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2379456, + "ts": 6197198712861.695, "dur": 3.891, + "args": { + "External id": 32607,"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": 2338707, "tid": 2379456, + "ts": 6197198712870.642, "dur": 12.726, + "args": { + "External id": 32608,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2379456, + "ts": 6197198712875.048, "dur": 7.908, + "args": { + "External id": 32609,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2379456, + "ts": 6197198712878.649, "dur": 2.992, + "args": { + "External id": 32610,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197198712889.964, "dur": 23.857, + "args": { + "External id": 32611,"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": 2338707, "tid": 2379456, + "ts": 6197198712891.937, "dur": 0.471, + "args": { + "External id": 32612,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197198712894.059, "dur": 0.476, + "args": { + "External id": 32613,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2379456, + "ts": 6197198712896.372, "dur": 0.530, + "args": { + "External id": 32614,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2379456, + "ts": 6197198712898.624, "dur": 0.457, + "args": { + "External id": 32615,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2379456, + "ts": 6197198712900.302, "dur": 0.469, + "args": { + "External id": 32616,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2379456, + "ts": 6197198712902.489, "dur": 0.354, + "args": { + "External id": 32617,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2379456, + "ts": 6197198712904.503, "dur": 0.360, + "args": { + "External id": 32618,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2379456, + "ts": 6197198712905.913, "dur": 2.297, + "args": { + "External id": 32619,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2379456, + "ts": 6197198712909.832, "dur": 0.340, + "args": { + "External id": 32620,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2379456, + "ts": 6197198712923.992, "dur": 31.920, + "args": { + "External id": 32621,"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": 2338707, "tid": 2379456, + "ts": 6197198713006.742, "dur": 165.659, + "args": { + "External id": 32622,"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": 2338707, "tid": 2379456, + "ts": 6197198713033.281, "dur": 135.204, + "args": { + "External id": 32623,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197198713043.258, "dur": 120.220, + "args": { + "External id": 32624,"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": 2338707, "tid": 2379456, + "ts": 6197198713191.630, "dur": 2.063, + "args": { + "External id": 32625,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197198713273.825, "dur": 1844.389, + "args": { + "External id": 32626,"Sequence number": 479770, "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": 2338707, "tid": 2379456, "ts": 6197198713273.825, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6197198713386.548, "dur": 105.375, + "args": { + "External id": 32627,"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": 2338707, "tid": 2379456, + "ts": 6197198713531.407, "dur": 41.568, + "args": { + "External id": 32628,"kernel_hash": "cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/u7/cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs.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": 2338707, "tid": 2379456, + "ts": 6197198713595.855, "dur": 53.896, + "args": { + "External id": 32629,"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": 2338707, "tid": 2379456, + "ts": 6197198713659.182, "dur": 30.968, + "args": { + "External id": 32630,"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": 2338707, "tid": 2379456, + "ts": 6197198713696.504, "dur": 56.357, + "args": { + "External id": 32631,"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": 2338707, "tid": 2379456, + "ts": 6197198713763.232, "dur": 29.265, + "args": { + "External id": 32632,"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": 2338707, "tid": 2379456, + "ts": 6197198713801.629, "dur": 30.045, + "args": { + "External id": 32633,"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": 2338707, "tid": 2379456, + "ts": 6197198713861.546, "dur": 28.329, + "args": { + "External id": 32634,"kernel_hash": "cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/wm/cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s.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": 2338707, "tid": 2379456, + "ts": 6197198713910.658, "dur": 30.244, + "args": { + "External id": 32635,"kernel_hash": "cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql", "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/qt/cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql.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": 2338707, "tid": 2379456, + "ts": 6197198713964.974, "dur": 20.707, + "args": { + "External id": 32636,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197198714000.131, "dur": 16.577, + "args": { + "External id": 32637,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197198714027.557, "dur": 80.107, + "args": { + "External id": 32638,"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": 2338707, "tid": 2379456, + "ts": 6197198714113.434, "dur": 40.523, + "args": { + "External id": 32639,"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": 2338707, "tid": 2379456, + "ts": 6197198714191.026, "dur": 253.500, + "args": { + "External id": 32640,"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": 2338707, "tid": 2379456, + "ts": 6197198714271.147, "dur": 6.916, + "args": { + "External id": 32641,"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": 2338707, "tid": 2379456, + "ts": 6197198714280.324, "dur": 3.247, + "args": { + "External id": 32642,"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": 2338707, "tid": 2379456, + "ts": 6197198714284.724, "dur": 2.660, + "args": { + "External id": 32643,"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": 2338707, "tid": 2379456, + "ts": 6197198714288.443, "dur": 4.184, + "args": { + "External id": 32644,"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": 2338707, "tid": 2379456, + "ts": 6197198714341.082, "dur": 4.693, + "args": { + "External id": 32645,"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": 2338707, "tid": 2379456, + "ts": 6197198714342.669, "dur": 2.916, + "args": { + "External id": 32646,"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": 2338707, "tid": 2379456, + "ts": 6197198714347.410, "dur": 33.508, + "args": { + "External id": 32647,"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": 2338707, "tid": 2379456, + "ts": 6197198714352.947, "dur": 1.691, + "args": { + "External id": 32648,"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": 2338707, "tid": 2379456, + "ts": 6197198714382.627, "dur": 1.566, + "args": { + "External id": 32649,"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": 2338707, "tid": 2379456, + "ts": 6197198714383.431, "dur": 0.680, + "args": { + "External id": 32650,"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": 2338707, "tid": 2379456, + "ts": 6197198714385.177, "dur": 16.339, + "args": { + "External id": 32651,"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": 2338707, "tid": 2379456, + "ts": 6197198714387.201, "dur": 0.816, + "args": { + "External id": 32652,"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": 2338707, "tid": 2379456, + "ts": 6197198714480.764, "dur": 30.695, + "args": { + "External id": 32653,"kernel_hash": "cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4", "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/yk/cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4.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": 2338707, "tid": 2379456, + "ts": 6197198714527.167, "dur": 17.891, + "args": { + "External id": 32654,"kernel_hash": "ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg", "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/eu/ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg.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": 2338707, "tid": 2379456, + "ts": 6197198714553.838, "dur": 45.915, + "args": { + "External id": 32655,"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": 2338707, "tid": 2379456, + "ts": 6197198714607.479, "dur": 39.993, + "args": { + "External id": 32656,"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": 2338707, "tid": 2379456, + "ts": 6197198714662.340, "dur": 22.036, + "args": { + "External id": 32657,"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": 2338707, "tid": 2379456, + "ts": 6197198714690.900, "dur": 73.377, + "args": { + "External id": 32658,"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": 2338707, "tid": 2379456, + "ts": 6197198714791.372, "dur": 40.536, + "args": { + "External id": 32659,"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": 2338707, "tid": 2379456, + "ts": 6197198714840.092, "dur": 32.312, + "args": { + "External id": 32660,"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": 2338707, "tid": 2379456, + "ts": 6197198714896.836, "dur": 25.299, + "args": { + "External id": 32661,"kernel_hash": "c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/6w/c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7.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": 2338707, "tid": 2379456, + "ts": 6197198714941.429, "dur": 24.009, + "args": { + "External id": 32662,"kernel_hash": "ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx", "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/kj/ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx.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": 2338707, "tid": 2379456, + "ts": 6197198714979.568, "dur": 17.087, + "args": { + "External id": 32663,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197198715009.428, "dur": 14.254, + "args": { + "External id": 32664,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197198715035.558, "dur": 15.941, + "args": { + "External id": 32665,"kernel_hash": "cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/eb/cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b.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": 2338707, "tid": 2379456, + "ts": 6197198715162.643, "dur": 15.850, + "args": { + "External id": 32666,"Record function id": 0, "Ev Idx": 5529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198715166.252, "dur": 11.199, + "args": { + "External id": 32667,"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": 2338707, "tid": 2379456, + "ts": 6197198715170.348, "dur": 6.181, + "args": { + "External id": 32668,"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": 2338707, "tid": 2379456, + "ts": 6197198715172.131, "dur": 4.277, + "args": { + "External id": 32669,"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": 2338707, "tid": 2379456, + "ts": 6197198715182.424, "dur": 5.390, + "args": { + "External id": 32670,"Record function id": 0, "Ev Idx": 5533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198715183.620, "dur": 3.722, + "args": { + "External id": 32671,"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": 2338707, "tid": 2379456, + "ts": 6197198715184.545, "dur": 2.259, + "args": { + "External id": 32672,"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": 2338707, "tid": 2379456, + "ts": 6197198715185.223, "dur": 1.513, + "args": { + "External id": 32673,"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": 2338707, "tid": 2379456, + "ts": 6197198715191.085, "dur": 4.779, + "args": { + "External id": 32674,"Record function id": 0, "Ev Idx": 5537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198715192.179, "dur": 3.250, + "args": { + "External id": 32675,"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": 2338707, "tid": 2379456, + "ts": 6197198715193.045, "dur": 1.970, + "args": { + "External id": 32676,"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": 2338707, "tid": 2379456, + "ts": 6197198715193.559, "dur": 1.386, + "args": { + "External id": 32677,"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": 2338707, "tid": 2379456, + "ts": 6197198715199.016, "dur": 3.759, + "args": { + "External id": 32678,"Record function id": 0, "Ev Idx": 5541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198715199.999, "dur": 2.299, + "args": { + "External id": 32679,"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": 2338707, "tid": 2379456, + "ts": 6197198715200.564, "dur": 1.334, + "args": { + "External id": 32680,"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": 2338707, "tid": 2379456, + "ts": 6197198715201.038, "dur": 0.796, + "args": { + "External id": 32681,"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": 2338707, "tid": 2379456, + "ts": 6197198715205.852, "dur": 3.775, + "args": { + "External id": 32682,"Record function id": 0, "Ev Idx": 5545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198715206.960, "dur": 2.269, + "args": { + "External id": 32683,"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": 2338707, "tid": 2379456, + "ts": 6197198715207.409, "dur": 1.140, + "args": { + "External id": 32684,"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": 2338707, "tid": 2379456, + "ts": 6197198715207.728, "dur": 0.727, + "args": { + "External id": 32685,"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": 2338707, "tid": 2379456, + "ts": 6197198715212.772, "dur": 6.253, + "args": { + "External id": 32686,"Record function id": 0, "Ev Idx": 5549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198715213.948, "dur": 4.642, + "args": { + "External id": 32687,"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": 2338707, "tid": 2379456, + "ts": 6197198715214.428, "dur": 3.740, + "args": { + "External id": 32688,"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": 2338707, "tid": 2379456, + "ts": 6197198715215.135, "dur": 2.930, + "args": { + "External id": 32689,"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": 2338707, "tid": 2379456, + "ts": 6197198715222.185, "dur": 3.594, + "args": { + "External id": 32690,"Record function id": 0, "Ev Idx": 5553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198715223.214, "dur": 2.154, + "args": { + "External id": 32691,"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": 2338707, "tid": 2379456, + "ts": 6197198715223.677, "dur": 1.280, + "args": { + "External id": 32692,"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": 2338707, "tid": 2379456, + "ts": 6197198715223.956, "dur": 0.939, + "args": { + "External id": 32693,"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": 2338707, "tid": 2379456, + "ts": 6197198715232.478, "dur": 3.824, + "args": { + "External id": 32694,"Record function id": 0, "Ev Idx": 5557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198715233.969, "dur": 1.874, + "args": { + "External id": 32695,"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": 2338707, "tid": 2379456, + "ts": 6197198715234.537, "dur": 0.866, + "args": { + "External id": 32696,"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": 2338707, "tid": 2379456, + "ts": 6197198715234.800, "dur": 0.530, + "args": { + "External id": 32697,"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": 2338707, "tid": 2379456, + "ts": 6197198715239.503, "dur": 4.097, + "args": { + "External id": 32698,"Record function id": 0, "Ev Idx": 5561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198715241.034, "dur": 2.098, + "args": { + "External id": 32699,"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": 2338707, "tid": 2379456, + "ts": 6197198715241.488, "dur": 1.130, + "args": { + "External id": 32700,"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": 2338707, "tid": 2379456, + "ts": 6197198715241.923, "dur": 0.584, + "args": { + "External id": 32701,"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": 2338707, "tid": 2379456, + "ts": 6197198715247.637, "dur": 64584.725, + "args": { + "External id": 32702,"Record function id": 0, "Sequence number": 479769, "Fwd thread id": 1, "Ev Idx": 5565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197198715248.842, "dur": 64574.617, + "args": { + "External id": 32703,"Sequence number": 479769, "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": 2338707, "tid": 2379456, "ts": 6197198715248.842, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.1)", "pid": 2338707, "tid": 2379456, + "ts": 6197198715280.128, "dur": 42.765, + "args": { + "External id": 32704,"Record function id": 0, "Ev Idx": 5567 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.1)", "pid": 2338707, "tid": 2379456, + "ts": 6197198715330.914, "dur": 70.537, + "args": { + "External id": 32705,"Record function id": 0, "Ev Idx": 5568 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.1)", "pid": 2338707, "tid": 2379456, + "ts": 6197198715408.236, "dur": 64407.632, + "args": { + "External id": 32706,"Record function id": 0, "Ev Idx": 5569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197198715495.245, "dur": 7.125, + "args": { + "External id": 32707,"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": 2338707, "tid": 2379456, + "ts": 6197198715512.160, "dur": 4.517, + "args": { + "External id": 32708,"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": 2338707, "tid": 2379456, + "ts": 6197198715530.977, "dur": 63422.148, + "args": { + "External id": 32709,"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": 2338707, "tid": 2379456, + "ts": 6197198715544.744, "dur": 63395.573, + "args": { + "External id": 32710,"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": 2338707, "tid": 2379456, + "ts": 6197198715642.768, "dur": 16.917, + "args": { + "External id": 32711,"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": 2338707, "tid": 2379456, + "ts": 6197198715684.284, "dur": 63212.219, + "args": { + "External id": 32712,"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": 2338707, "tid": 2379456, + "ts": 6197198715686.918, "dur": 63208.574, + "args": { + "External id": 32713,"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": 2338707, "tid": 2379456, + "ts": 6197198715691.966, "dur": 28.471, + "args": { + "External id": 32714,"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": 2338707, "tid": 2379456, + "ts": 6197198715723.861, "dur": 63166.574, + "args": { + "External id": 32715,"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": 2338707, "tid": 2379456, + "ts": 6197198779080.812, "dur": 14.082, + "args": { + "External id": 32716,"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": 2338707, "tid": 2379456, + "ts": 6197198779085.254, "dur": 8.922, + "args": { + "External id": 32717,"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": 2338707, "tid": 2379456, + "ts": 6197198779126.534, "dur": 375.507, + "args": { + "External id": 32718,"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": 2338707, "tid": 2379456, + "ts": 6197198779159.561, "dur": 337.628, + "args": { + "External id": 32719,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197198779172.034, "dur": 319.644, + "args": { + "External id": 32720,"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": 2338707, "tid": 2379456, + "ts": 6197198779522.907, "dur": 2.358, + "args": { + "External id": 32721,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2379456, + "ts": 6197198779586.987, "dur": 6.616, + "args": { + "External id": 32722,"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": 2338707, "tid": 2379456, + "ts": 6197198779638.456, "dur": 1.371, + "args": { + "External id": 32723,"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": 2338707, "tid": 2379456, + "ts": 6197198779655.160, "dur": 2.902, + "args": { + "External id": 32724,"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": 2338707, "tid": 2379456, + "ts": 6197198779671.017, "dur": 1.120, + "args": { + "External id": 32725,"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": 2338707, "tid": 2379456, + "ts": 6197198779682.349, "dur": 1.239, + "args": { + "External id": 32726,"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": 2338707, "tid": 2379456, + "ts": 6197198779694.133, "dur": 0.922, + "args": { + "External id": 32727,"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": 2338707, "tid": 2379456, + "ts": 6197198779726.630, "dur": 3.334, + "args": { + "External id": 32728,"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": 2338707, "tid": 2379456, + "ts": 6197198779741.525, "dur": 2.255, + "args": { + "External id": 32729,"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": 2338707, "tid": 2379456, + "ts": 6197198779753.622, "dur": 0.857, + "args": { + "External id": 32730,"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": 2338707, "tid": 2379456, + "ts": 6197198779848.133, "dur": 2383.152, + "args": { + "External id": 32731,"Record function id": 0, "Ev Idx": 5594 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.0)", "pid": 2338707, "tid": 2379456, + "ts": 6197198779868.421, "dur": 511.185, + "args": { + "External id": 32732,"Record function id": 0, "Ev Idx": 5595 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.0)", "pid": 2338707, "tid": 2379456, + "ts": 6197198779883.870, "dur": 390.350, + "args": { + "External id": 32733,"Record function id": 0, "Ev Idx": 5596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6197198779977.175, "dur": 4.150, + "args": { + "External id": 32734,"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": 2338707, "tid": 2379456, + "ts": 6197198779984.631, "dur": 1.121, + "args": { + "External id": 32735,"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": 2338707, "tid": 2379456, + "ts": 6197198779987.761, "dur": 2.888, + "args": { + "External id": 32736,"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": 2338707, "tid": 2379456, + "ts": 6197198779992.762, "dur": 0.896, + "args": { + "External id": 32737,"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": 2338707, "tid": 2379456, + "ts": 6197198779995.299, "dur": 0.972, + "args": { + "External id": 32738,"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": 2338707, "tid": 2379456, + "ts": 6197198779997.812, "dur": 0.996, + "args": { + "External id": 32739,"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": 2338707, "tid": 2379456, + "ts": 6197198780000.334, "dur": 1.778, + "args": { + "External id": 32740,"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": 2338707, "tid": 2379456, + "ts": 6197198780003.656, "dur": 1.426, + "args": { + "External id": 32741,"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": 2338707, "tid": 2379456, + "ts": 6197198780008.498, "dur": 1.316, + "args": { + "External id": 32742,"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": 2338707, "tid": 2379456, + "ts": 6197198780011.478, "dur": 1.076, + "args": { + "External id": 32743,"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": 2338707, "tid": 2379456, + "ts": 6197198780029.973, "dur": 210.704, + "args": { + "External id": 32744,"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": 2338707, "tid": 2379456, + "ts": 6197198780045.935, "dur": 189.218, + "args": { + "External id": 32745,"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": 2338707, "tid": 2379456, + "ts": 6197198780109.715, "dur": 21.933, + "args": { + "External id": 32746,"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": 2338707, "tid": 2379456, + "ts": 6197198780135.913, "dur": 70.018, + "args": { + "External id": 32747,"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": 2338707, "tid": 2379456, + "ts": 6197198780138.587, "dur": 66.897, + "args": { + "External id": 32748,"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": 2338707, "tid": 2379456, + "ts": 6197198780142.666, "dur": 7.595, + "args": { + "External id": 32749,"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": 2338707, "tid": 2379456, + "ts": 6197198780151.920, "dur": 53.013, + "args": { + "External id": 32750,"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": 2338707, "tid": 2379456, + "ts": 6197198780387.538, "dur": 1819.782, + "args": { + "External id": 32751,"Sequence number": 479768, "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": 2338707, "tid": 2379456, "ts": 6197198780387.538, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6197198780493.736, "dur": 104.542, + "args": { + "External id": 32752,"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": 2338707, "tid": 2379456, + "ts": 6197198780639.618, "dur": 42.039, + "args": { + "External id": 32753,"kernel_hash": "cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/u7/cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs.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": 2338707, "tid": 2379456, + "ts": 6197198780718.971, "dur": 58.925, + "args": { + "External id": 32754,"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": 2338707, "tid": 2379456, + "ts": 6197198780790.788, "dur": 32.856, + "args": { + "External id": 32755,"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": 2338707, "tid": 2379456, + "ts": 6197198780831.721, "dur": 33.788, + "args": { + "External id": 32756,"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": 2338707, "tid": 2379456, + "ts": 6197198780873.516, "dur": 28.010, + "args": { + "External id": 32757,"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": 2338707, "tid": 2379456, + "ts": 6197198780910.886, "dur": 30.296, + "args": { + "External id": 32758,"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": 2338707, "tid": 2379456, + "ts": 6197198780965.620, "dur": 25.106, + "args": { + "External id": 32759,"kernel_hash": "cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/wm/cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s.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": 2338707, "tid": 2379456, + "ts": 6197198781007.599, "dur": 34.401, + "args": { + "External id": 32760,"kernel_hash": "cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql", "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/qt/cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql.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": 2338707, "tid": 2379456, + "ts": 6197198781101.216, "dur": 22.489, + "args": { + "External id": 32761,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197198781137.642, "dur": 15.103, + "args": { + "External id": 32762,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197198781163.546, "dur": 43.624, + "args": { + "External id": 32763,"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": 2338707, "tid": 2379456, + "ts": 6197198781211.087, "dur": 33.980, + "args": { + "External id": 32764,"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": 2338707, "tid": 2379456, + "ts": 6197198781275.074, "dur": 294.005, + "args": { + "External id": 32765,"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": 2338707, "tid": 2379456, + "ts": 6197198781352.663, "dur": 6.175, + "args": { + "External id": 32766,"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": 2338707, "tid": 2379456, + "ts": 6197198781361.263, "dur": 2.967, + "args": { + "External id": 32767,"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": 2338707, "tid": 2379456, + "ts": 6197198781365.673, "dur": 2.821, + "args": { + "External id": 32768,"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": 2338707, "tid": 2379456, + "ts": 6197198781411.073, "dur": 11.207, + "args": { + "External id": 32769,"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": 2338707, "tid": 2379456, + "ts": 6197198781466.347, "dur": 4.901, + "args": { + "External id": 32770,"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": 2338707, "tid": 2379456, + "ts": 6197198781468.216, "dur": 2.786, + "args": { + "External id": 32771,"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": 2338707, "tid": 2379456, + "ts": 6197198781473.035, "dur": 31.612, + "args": { + "External id": 32772,"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": 2338707, "tid": 2379456, + "ts": 6197198781478.587, "dur": 1.742, + "args": { + "External id": 32773,"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": 2338707, "tid": 2379456, + "ts": 6197198781506.048, "dur": 1.641, + "args": { + "External id": 32774,"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": 2338707, "tid": 2379456, + "ts": 6197198781506.858, "dur": 0.716, + "args": { + "External id": 32775,"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": 2338707, "tid": 2379456, + "ts": 6197198781508.989, "dur": 14.551, + "args": { + "External id": 32776,"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": 2338707, "tid": 2379456, + "ts": 6197198781511.364, "dur": 0.543, + "args": { + "External id": 32777,"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": 2338707, "tid": 2379456, + "ts": 6197198781605.117, "dur": 28.311, + "args": { + "External id": 32778,"kernel_hash": "cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4", "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/yk/cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4.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": 2338707, "tid": 2379456, + "ts": 6197198781652.912, "dur": 15.690, + "args": { + "External id": 32779,"kernel_hash": "ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg", "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/eu/ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg.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": 2338707, "tid": 2379456, + "ts": 6197198781680.013, "dur": 65.169, + "args": { + "External id": 32780,"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": 2338707, "tid": 2379456, + "ts": 6197198781754.858, "dur": 46.204, + "args": { + "External id": 32781,"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": 2338707, "tid": 2379456, + "ts": 6197198781811.753, "dur": 25.013, + "args": { + "External id": 32782,"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": 2338707, "tid": 2379456, + "ts": 6197198781842.962, "dur": 31.867, + "args": { + "External id": 32783,"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": 2338707, "tid": 2379456, + "ts": 6197198781882.254, "dur": 29.443, + "args": { + "External id": 32784,"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": 2338707, "tid": 2379456, + "ts": 6197198781919.244, "dur": 33.594, + "args": { + "External id": 32785,"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": 2338707, "tid": 2379456, + "ts": 6197198781971.512, "dur": 27.781, + "args": { + "External id": 32786,"kernel_hash": "c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/6w/c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7.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": 2338707, "tid": 2379456, + "ts": 6197198782014.499, "dur": 23.204, + "args": { + "External id": 32787,"kernel_hash": "ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx", "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/kj/ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx.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": 2338707, "tid": 2379456, + "ts": 6197198782051.117, "dur": 52.840, + "args": { + "External id": 32788,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197198782124.809, "dur": 17.388, + "args": { + "External id": 32789,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197198782154.949, "dur": 19.744, + "args": { + "External id": 32790,"kernel_hash": "cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/eb/cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b.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": 2338707, "tid": 2379456, + "ts": 6197198782253.804, "dur": 15.388, + "args": { + "External id": 32791,"Record function id": 0, "Ev Idx": 5654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198782257.321, "dur": 10.901, + "args": { + "External id": 32792,"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": 2338707, "tid": 2379456, + "ts": 6197198782261.397, "dur": 5.912, + "args": { + "External id": 32793,"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": 2338707, "tid": 2379456, + "ts": 6197198782263.192, "dur": 4.003, + "args": { + "External id": 32794,"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": 2338707, "tid": 2379456, + "ts": 6197198782273.078, "dur": 5.603, + "args": { + "External id": 32795,"Record function id": 0, "Ev Idx": 5658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198782274.548, "dur": 3.655, + "args": { + "External id": 32796,"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": 2338707, "tid": 2379456, + "ts": 6197198782275.587, "dur": 2.120, + "args": { + "External id": 32797,"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": 2338707, "tid": 2379456, + "ts": 6197198782276.529, "dur": 1.069, + "args": { + "External id": 32798,"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": 2338707, "tid": 2379456, + "ts": 6197198782281.961, "dur": 4.454, + "args": { + "External id": 32799,"Record function id": 0, "Ev Idx": 5662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198782283.243, "dur": 2.738, + "args": { + "External id": 32800,"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": 2338707, "tid": 2379456, + "ts": 6197198782283.857, "dur": 1.662, + "args": { + "External id": 32801,"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": 2338707, "tid": 2379456, + "ts": 6197198782284.524, "dur": 0.928, + "args": { + "External id": 32802,"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": 2338707, "tid": 2379456, + "ts": 6197198782289.626, "dur": 3.763, + "args": { + "External id": 32803,"Record function id": 0, "Ev Idx": 5666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198782290.987, "dur": 2.008, + "args": { + "External id": 32804,"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": 2338707, "tid": 2379456, + "ts": 6197198782291.481, "dur": 1.077, + "args": { + "External id": 32805,"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": 2338707, "tid": 2379456, + "ts": 6197198782291.957, "dur": 0.536, + "args": { + "External id": 32806,"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": 2338707, "tid": 2379456, + "ts": 6197198782296.481, "dur": 4.085, + "args": { + "External id": 32807,"Record function id": 0, "Ev Idx": 5670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198782297.910, "dur": 2.251, + "args": { + "External id": 32808,"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": 2338707, "tid": 2379456, + "ts": 6197198782298.708, "dur": 1.063, + "args": { + "External id": 32809,"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": 2338707, "tid": 2379456, + "ts": 6197198782299.027, "dur": 0.678, + "args": { + "External id": 32810,"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": 2338707, "tid": 2379456, + "ts": 6197198782303.607, "dur": 4.561, + "args": { + "External id": 32811,"Record function id": 0, "Ev Idx": 5674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198782305.312, "dur": 2.395, + "args": { + "External id": 32812,"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": 2338707, "tid": 2379456, + "ts": 6197198782305.934, "dur": 1.324, + "args": { + "External id": 32813,"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": 2338707, "tid": 2379456, + "ts": 6197198782306.458, "dur": 0.698, + "args": { + "External id": 32814,"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": 2338707, "tid": 2379456, + "ts": 6197198782311.247, "dur": 5.826, + "args": { + "External id": 32815,"Record function id": 0, "Ev Idx": 5678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198782312.603, "dur": 4.055, + "args": { + "External id": 32816,"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": 2338707, "tid": 2379456, + "ts": 6197198782313.410, "dur": 2.800, + "args": { + "External id": 32817,"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": 2338707, "tid": 2379456, + "ts": 6197198782313.898, "dur": 2.219, + "args": { + "External id": 32818,"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": 2338707, "tid": 2379456, + "ts": 6197198782320.325, "dur": 4.834, + "args": { + "External id": 32819,"Record function id": 0, "Ev Idx": 5682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198782322.007, "dur": 2.705, + "args": { + "External id": 32820,"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": 2338707, "tid": 2379456, + "ts": 6197198782322.978, "dur": 1.325, + "args": { + "External id": 32821,"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": 2338707, "tid": 2379456, + "ts": 6197198782323.594, "dur": 0.618, + "args": { + "External id": 32822,"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": 2338707, "tid": 2379456, + "ts": 6197198782328.574, "dur": 4.260, + "args": { + "External id": 32823,"Record function id": 0, "Ev Idx": 5686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198782330.117, "dur": 2.294, + "args": { + "External id": 32824,"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": 2338707, "tid": 2379456, + "ts": 6197198782330.651, "dur": 1.362, + "args": { + "External id": 32825,"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": 2338707, "tid": 2379456, + "ts": 6197198782331.210, "dur": 0.693, + "args": { + "External id": 32826,"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": 2338707, "tid": 2379456, + "ts": 6197198782337.149, "dur": 65805.463, + "args": { + "External id": 32827,"Record function id": 0, "Sequence number": 479767, "Fwd thread id": 1, "Ev Idx": 5690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197198782338.417, "dur": 65793.892, + "args": { + "External id": 32828,"Sequence number": 479767, "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": 2338707, "tid": 2379456, "ts": 6197198782338.417, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.0)", "pid": 2338707, "tid": 2379456, + "ts": 6197198782367.799, "dur": 34.308, + "args": { + "External id": 32829,"Record function id": 0, "Ev Idx": 5692 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.0)", "pid": 2338707, "tid": 2379456, + "ts": 6197198782408.841, "dur": 70.196, + "args": { + "External id": 32830,"Record function id": 0, "Ev Idx": 5693 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.0)", "pid": 2338707, "tid": 2379456, + "ts": 6197198782484.547, "dur": 65639.204, + "args": { + "External id": 32831,"Record function id": 0, "Ev Idx": 5694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197198782571.820, "dur": 6.312, + "args": { + "External id": 32832,"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": 2338707, "tid": 2379456, + "ts": 6197198782587.702, "dur": 4.558, + "args": { + "External id": 32833,"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": 2338707, "tid": 2379456, + "ts": 6197198782605.442, "dur": 64657.864, + "args": { + "External id": 32834,"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": 2338707, "tid": 2379456, + "ts": 6197198782618.378, "dur": 64633.013, + "args": { + "External id": 32835,"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": 2338707, "tid": 2379456, + "ts": 6197198782745.643, "dur": 22.470, + "args": { + "External id": 32836,"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": 2338707, "tid": 2379456, + "ts": 6197198782788.731, "dur": 64416.135, + "args": { + "External id": 32837,"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": 2338707, "tid": 2379456, + "ts": 6197198782791.788, "dur": 64412.032, + "args": { + "External id": 32838,"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": 2338707, "tid": 2379456, + "ts": 6197198782796.697, "dur": 15.996, + "args": { + "External id": 32839,"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": 2338707, "tid": 2379456, + "ts": 6197198782815.112, "dur": 64384.081, + "args": { + "External id": 32840,"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": 2338707, "tid": 2379456, + "ts": 6197198847368.202, "dur": 14.650, + "args": { + "External id": 32841,"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": 2338707, "tid": 2379456, + "ts": 6197198847371.734, "dur": 10.735, + "args": { + "External id": 32842,"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": 2338707, "tid": 2379456, + "ts": 6197198847414.929, "dur": 389.753, + "args": { + "External id": 32843,"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": 2338707, "tid": 2379456, + "ts": 6197198847448.090, "dur": 351.030, + "args": { + "External id": 32844,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197198847459.889, "dur": 332.997, + "args": { + "External id": 32845,"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": 2338707, "tid": 2379456, + "ts": 6197198847827.112, "dur": 2.337, + "args": { + "External id": 32846,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2379456, + "ts": 6197198847888.153, "dur": 6.573, + "args": { + "External id": 32847,"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": 2338707, "tid": 2379456, + "ts": 6197198847938.654, "dur": 1.466, + "args": { + "External id": 32848,"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": 2338707, "tid": 2379456, + "ts": 6197198847954.850, "dur": 1.211, + "args": { + "External id": 32849,"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": 2338707, "tid": 2379456, + "ts": 6197198847968.829, "dur": 0.864, + "args": { + "External id": 32850,"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": 2338707, "tid": 2379456, + "ts": 6197198847980.144, "dur": 1.127, + "args": { + "External id": 32851,"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": 2338707, "tid": 2379456, + "ts": 6197198847992.514, "dur": 1.101, + "args": { + "External id": 32852,"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": 2338707, "tid": 2379456, + "ts": 6197198848003.355, "dur": 1.074, + "args": { + "External id": 32853,"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": 2338707, "tid": 2379456, + "ts": 6197198848015.778, "dur": 2.649, + "args": { + "External id": 32854,"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": 2338707, "tid": 2379456, + "ts": 6197198848029.060, "dur": 0.882, + "args": { + "External id": 32855,"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": 2338707, "tid": 2379456, + "ts": 6197198848159.558, "dur": 290.984, + "args": { + "External id": 32856,"Record function id": 0, "Sequence number": 479766, "Fwd thread id": 1, "Ev Idx": 5719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197198848162.530, "dur": 279.040, + "args": { + "External id": 32857,"Sequence number": 479766, "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": 2338707, "tid": 2379456, "ts": 6197198848162.530, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_embedding_dense_backward_0", "pid": 2338707, "tid": 2379456, + "ts": 6197198848286.234, "dur": 51.756, + "args": { + "External id": 32858,"kernel_hash": "cylhmuu3q4lld7ngapzsx2q3nsghgiylz3hysdrztph5rn33kr3r", "grid": "grid(131072000,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "131072000"], "kernel_file": "/tmp/torchinductor_cvm/yl/cylhmuu3q4lld7ngapzsx2q3nsghgiylz3hysdrztph5rn33kr3r.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": 2338707, "tid": 2379456, + "ts": 6197198848355.805, "dur": 27.283, + "args": { + "External id": 32859,"kernel_hash": "cqovkpvfazf4uawh526mshntxf6zr2towc3gbwazqnfjbhqiu3u5", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qo/cqovkpvfazf4uawh526mshntxf6zr2towc3gbwazqnfjbhqiu3u5.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": 2338707, "tid": 2379456, + "ts": 6197198848402.525, "dur": 23.035, + "args": { + "External id": 32860,"kernel_hash": "cxsh2jiwiopwz5eatuiwkxhwp4pcrm5kca3w7qyj3ojcu3sw473n", "grid": "grid(131072000,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "131072000"], "kernel_file": "/tmp/torchinductor_cvm/xs/cxsh2jiwiopwz5eatuiwkxhwp4pcrm5kca3w7qyj3ojcu3sw473n.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": 2338707, "tid": 2379456, + "ts": 6197198848460.561, "dur": 14.833, + "args": { + "External id": 32861,"Record function id": 0, "Ev Idx": 5724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197198848463.667, "dur": 10.848, + "args": { + "External id": 32862,"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": 2338707, "tid": 2379456, + "ts": 6197198848467.271, "dur": 6.554, + "args": { + "External id": 32863,"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": 2338707, "tid": 2379456, + "ts": 6197198848468.914, "dur": 4.814, + "args": { + "External id": 32864,"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": 2338707, "tid": 2379456, + "ts": 6197198848497.455, "dur": 17080.168, + "args": { + "External id": 32865,"Record function id": 0, "Ev Idx": 5728 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate", "pid": 2338707, "tid": 2379456, + "ts": 6197198848515.178, "dur": 41.056, + "args": { + "External id": 32866,"Record function id": 0, "Ev Idx": 5729 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard", "pid": 2338707, "tid": 2379456, + "ts": 6197198848562.650, "dur": 310.043, + "args": { + "External id": 32867,"Record function id": 0, "Ev Idx": 5730 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce", "pid": 2338707, "tid": 2379456, + "ts": 6197198848881.243, "dur": 16446.411, + "args": { + "External id": 32868,"Record function id": 0, "Ev Idx": 5731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197198849008.516, "dur": 7.427, + "args": { + "External id": 32869,"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": 2338707, "tid": 2379456, + "ts": 6197198849026.497, "dur": 5.385, + "args": { + "External id": 32870,"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": 2338707, "tid": 2379456, + "ts": 6197198849086.798, "dur": 14949.100, + "args": { + "External id": 32871,"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": 2338707, "tid": 2379456, + "ts": 6197198849107.392, "dur": 14914.146, + "args": { + "External id": 32872,"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": 2338707, "tid": 2379456, + "ts": 6197198849840.286, "dur": 25.657, + "args": { + "External id": 32873,"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": 2338707, "tid": 2379456, + "ts": 6197198850132.428, "dur": 13837.352, + "args": { + "External id": 32874,"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": 2338707, "tid": 2379456, + "ts": 6197198850136.915, "dur": 13831.579, + "args": { + "External id": 32875,"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": 2338707, "tid": 2379456, + "ts": 6197198850145.011, "dur": 15.155, + "args": { + "External id": 32876,"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": 2338707, "tid": 2379456, + "ts": 6197198850163.483, "dur": 13798.318, + "args": { + "External id": 32877,"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": 2338707, "tid": 2379456, + "ts": 6197198864214.696, "dur": 12.637, + "args": { + "External id": 32878,"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": 2338707, "tid": 2379456, + "ts": 6197198864219.341, "dur": 7.337, + "args": { + "External id": 32879,"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": 2338707, "tid": 2379456, + "ts": 6197198864258.863, "dur": 356.346, + "args": { + "External id": 32880,"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": 2338707, "tid": 2379456, + "ts": 6197198864284.507, "dur": 326.007, + "args": { + "External id": 32881,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197198864295.092, "dur": 310.646, + "args": { + "External id": 32882,"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": 2338707, "tid": 2379456, + "ts": 6197198864634.361, "dur": 2.019, + "args": { + "External id": 32883,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2379456, + "ts": 6197198864691.540, "dur": 6.180, + "args": { + "External id": 32884,"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": 2338707, "tid": 2379456, + "ts": 6197198864760.501, "dur": 2.185, + "args": { + "External id": 32885,"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": 2338707, "tid": 2379456, + "ts": 6197198864777.497, "dur": 1.462, + "args": { + "External id": 32886,"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": 2338707, "tid": 2379456, + "ts": 6197198864792.838, "dur": 1.164, + "args": { + "External id": 32887,"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": 2338707, "tid": 2379456, + "ts": 6197198864805.270, "dur": 1.007, + "args": { + "External id": 32888,"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": 2338707, "tid": 2379456, + "ts": 6197198864819.759, "dur": 0.825, + "args": { + "External id": 32889,"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": 2338707, "tid": 2379456, + "ts": 6197198864831.393, "dur": 2.749, + "args": { + "External id": 32890,"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": 2338707, "tid": 2379456, + "ts": 6197198864845.749, "dur": 1.070, + "args": { + "External id": 32891,"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": 2338707, "tid": 2379456, + "ts": 6197198864857.998, "dur": 1.155, + "args": { + "External id": 32892,"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": 2338707, "tid": 2379456, + "ts": 6197198864871.047, "dur": 0.867, + "args": { + "External id": 32893,"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": 2338707, "tid": 2379456, + "ts": 6197198864883.212, "dur": 1.116, + "args": { + "External id": 32894,"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": 2338707, "tid": 2379456, + "ts": 6197198864895.560, "dur": 0.982, + "args": { + "External id": 32895,"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": 2338707, "tid": 2379456, + "ts": 6197198864907.226, "dur": 0.936, + "args": { + "External id": 32896,"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": 2338707, "tid": 2379456, + "ts": 6197198864919.837, "dur": 0.999, + "args": { + "External id": 32897,"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": 2338707, "tid": 2379456, + "ts": 6197198864931.254, "dur": 2.207, + "args": { + "External id": 32898,"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": 2338707, "tid": 2379456, + "ts": 6197198864943.526, "dur": 1.108, + "args": { + "External id": 32899,"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": 2338707, "tid": 2379456, + "ts": 6197198864954.924, "dur": 0.968, + "args": { + "External id": 32900,"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": 2338707, "tid": 2379456, + "ts": 6197198864966.183, "dur": 0.860, + "args": { + "External id": 32901,"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": 2338707, "tid": 2379456, + "ts": 6197198864977.559, "dur": 0.781, + "args": { + "External id": 32902,"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": 2338707, "tid": 2379456, + "ts": 6197198864990.841, "dur": 0.925, + "args": { + "External id": 32903,"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": 2338707, "tid": 2379456, + "ts": 6197198865002.203, "dur": 0.825, + "args": { + "External id": 32904,"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": 2338707, "tid": 2379456, + "ts": 6197198865014.059, "dur": 1.058, + "args": { + "External id": 32905,"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": 2338707, "tid": 2379456, + "ts": 6197198865025.698, "dur": 2.382, + "args": { + "External id": 32906,"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": 2338707, "tid": 2379456, + "ts": 6197198865048.233, "dur": 0.915, + "args": { + "External id": 32907,"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": 2338707, "tid": 2379456, + "ts": 6197198865097.281, "dur": 1.490, + "args": { + "External id": 32908,"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": 2338707, "tid": 2379456, + "ts": 6197198865110.506, "dur": 0.881, + "args": { + "External id": 32909,"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": 2338707, "tid": 2379456, + "ts": 6197198865122.210, "dur": 1.080, + "args": { + "External id": 32910,"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": 2338707, "tid": 2379456, + "ts": 6197198865133.479, "dur": 1.020, + "args": { + "External id": 32911,"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": 2338707, "tid": 2379456, + "ts": 6197198865145.722, "dur": 0.907, + "args": { + "External id": 32912,"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": 2338707, "tid": 2379456, + "ts": 6197198865156.615, "dur": 1.086, + "args": { + "External id": 32913,"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": 2338707, "tid": 2379456, + "ts": 6197198865167.429, "dur": 2.120, + "args": { + "External id": 32914,"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": 2338707, "tid": 2379456, + "ts": 6197198865179.421, "dur": 0.940, + "args": { + "External id": 32915,"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": 2338707, "tid": 2379456, + "ts": 6197198865190.626, "dur": 1.090, + "args": { + "External id": 32916,"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": 2338707, "tid": 2379456, + "ts": 6197198865201.583, "dur": 0.860, + "args": { + "External id": 32917,"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": 2338707, "tid": 2379456, + "ts": 6197198865212.219, "dur": 0.794, + "args": { + "External id": 32918,"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": 2338707, "tid": 2379456, + "ts": 6197198865226.617, "dur": 1.253, + "args": { + "External id": 32919,"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": 2338707, "tid": 2379456, + "ts": 6197198865238.588, "dur": 1.067, + "args": { + "External id": 32920,"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": 2338707, "tid": 2379456, + "ts": 6197198865250.680, "dur": 0.997, + "args": { + "External id": 32921,"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": 2338707, "tid": 2379456, + "ts": 6197198865261.952, "dur": 1.900, + "args": { + "External id": 32922,"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": 2338707, "tid": 2379456, + "ts": 6197200036770.675, "dur": 98.245, + "args": { + "External id": 32923,"Record function id": 0, "Sequence number": 480221, "Fwd thread id": 1, "Ev Idx": 5786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "DivBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200036779.164, "dur": 81.703, + "args": { + "External id": 32924,"Sequence number": 480221, "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": 2338707, "tid": 2379456, "ts": 6197200036779.164, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::div", "pid": 2338707, "tid": 2379456, + "ts": 6197200036786.238, "dur": 72.870, + "args": { + "External id": 32925,"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": 2338707, "tid": 2379456, + "ts": 6197200036889.419, "dur": 261.666, + "args": { + "External id": 32926,"Record function id": 0, "Ev Idx": 5789 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward", "pid": 2338707, "tid": 2379456, + "ts": 6197200036945.548, "dur": 88.655, + "args": { + "External id": 32927,"Record function id": 0, "Ev Idx": 5790 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.25", "pid": 2338707, "tid": 2379456, + "ts": 6197200036975.027, "dur": 47.641, + "args": { + "External id": 32928,"Record function id": 0, "Ev Idx": 5791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200037039.414, "dur": 1.716, + "args": { + "External id": 32929,"Sequence number": 480220, "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": 2338707, "tid": 2379456, "ts": 6197200037039.414, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338707, "tid": 2379456, + "ts": 6197200037044.931, "dur": 100.281, + "args": { + "External id": 32930,"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": 2338707, "tid": 2379456, + "ts": 6197200037050.141, "dur": 94.405, + "args": { + "External id": 32931,"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": 2338707, "tid": 2379456, + "ts": 6197200037105.686, "dur": 2.578, + "args": { + "External id": 32932,"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": 2338707, "tid": 2379456, + "ts": 6197200037162.090, "dur": 39469.341, + "args": { + "External id": 32933,"Record function id": 0, "Sequence number": 480218, "Fwd thread id": 1, "Ev Idx": 5796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197200037164.135, "dur": 39452.146, + "args": { + "External id": 32934,"Sequence number": 480218, "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": 2338707, "tid": 2379456, "ts": 6197200037164.135, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197200037203.386, "dur": 3.812, + "args": { + "External id": 32935,"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": 2338707, "tid": 2379456, + "ts": 6197200037210.504, "dur": 39129.328, + "args": { + "External id": 32936,"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": 2338707, "tid": 2379456, + "ts": 6197200037214.854, "dur": 39124.599, + "args": { + "External id": 32937,"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": 2338707, "tid": 2379456, + "ts": 6197200037218.017, "dur": 5.673, + "args": { + "External id": 32938,"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": 2338707, "tid": 2379456, + "ts": 6197200037225.606, "dur": 39111.426, + "args": { + "External id": 32939,"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": 2338707, "tid": 2379456, + "ts": 6197200076346.659, "dur": 0.600, + "args": { + "External id": 32940,"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": 2338707, "tid": 2379456, + "ts": 6197200076349.465, "dur": 3.432, + "args": { + "External id": 32941,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 5804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach_", "pid": 2338707, "tid": 2379456, + "ts": 6197200076351.277, "dur": 1.447, + "args": { + "External id": 32942,"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": 2338707, "tid": 2379456, + "ts": 6197200076359.901, "dur": 33.902, + "args": { + "External id": 32943,"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": 2338707, "tid": 2379456, + "ts": 6197200076402.106, "dur": 48.414, + "args": { + "External id": 32944,"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": 2338707, "tid": 2379456, + "ts": 6197200076403.579, "dur": 46.696, + "args": { + "External id": 32945,"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": 2338707, "tid": 2379456, + "ts": 6197200076405.526, "dur": 44.452, + "args": { + "External id": 32946,"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": 2338707, "tid": 2379456, + "ts": 6197200076647.283, "dur": 18.874, + "args": { + "External id": 32947,"Record function id": 0, "Sequence number": 480217, "Fwd thread id": 1, "Ev Idx": 5810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200076649.369, "dur": 14.141, + "args": { + "External id": 32948,"Sequence number": 480217, "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": 2338707, "tid": 2379456, "ts": 6197200076649.369, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200076655.154, "dur": 8.082, + "args": { + "External id": 32949,"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": 2338707, "tid": 2379456, + "ts": 6197200076657.572, "dur": 5.456, + "args": { + "External id": 32950,"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": 2338707, "tid": 2379456, + "ts": 6197200076670.090, "dur": 119.487, + "args": { + "External id": 32951,"Record function id": 0, "Sequence number": 480216, "Fwd thread id": 1, "Ev Idx": 5814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200076671.221, "dur": 110.870, + "args": { + "External id": 32952,"Sequence number": 480216, "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": 2338707, "tid": 2379456, "ts": 6197200076671.221, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338707, "tid": 2379456, + "ts": 6197200076674.718, "dur": 106.703, + "args": { + "External id": 32953,"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": 2338707, "tid": 2379456, + "ts": 6197200076680.096, "dur": 50.550, + "args": { + "External id": 32954,"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": 2338707, "tid": 2379456, + "ts": 6197200076685.619, "dur": 5.754, + "args": { + "External id": 32955,"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": 2338707, "tid": 2379456, + "ts": 6197200076692.901, "dur": 37.452, + "args": { + "External id": 32956,"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": 2338707, "tid": 2379456, + "ts": 6197200076696.872, "dur": 32.831, + "args": { + "External id": 32957,"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": 2338707, "tid": 2379456, + "ts": 6197200076733.794, "dur": 6.401, + "args": { + "External id": 32958,"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": 2338707, "tid": 2379456, + "ts": 6197200076737.552, "dur": 2.071, + "args": { + "External id": 32959,"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": 2338707, "tid": 2379456, + "ts": 6197200076741.927, "dur": 38.422, + "args": { + "External id": 32960,"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": 2338707, "tid": 2379456, + "ts": 6197200076796.107, "dur": 58.660, + "args": { + "External id": 32961,"Record function id": 0, "Sequence number": 480215, "Fwd thread id": 1, "Ev Idx": 5824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SelectBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200076797.574, "dur": 53.630, + "args": { + "External id": 32962,"Sequence number": 480215, "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": 2338707, "tid": 2379456, "ts": 6197200076797.574, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select_backward", "pid": 2338707, "tid": 2379456, + "ts": 6197200076800.957, "dur": 49.951, + "args": { + "External id": 32963,"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": 2338707, "tid": 2379456, + "ts": 6197200076803.723, "dur": 21.766, + "args": { + "External id": 32964,"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": 2338707, "tid": 2379456, + "ts": 6197200076805.328, "dur": 3.433, + "args": { + "External id": 32965,"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": 2338707, "tid": 2379456, + "ts": 6197200076809.697, "dur": 15.540, + "args": { + "External id": 32966,"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": 2338707, "tid": 2379456, + "ts": 6197200076814.376, "dur": 10.254, + "args": { + "External id": 32967,"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": 2338707, "tid": 2379456, + "ts": 6197200076826.801, "dur": 6.827, + "args": { + "External id": 32968,"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": 2338707, "tid": 2379456, + "ts": 6197200076831.535, "dur": 1.391, + "args": { + "External id": 32969,"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": 2338707, "tid": 2379456, + "ts": 6197200076834.771, "dur": 15.624, + "args": { + "External id": 32970,"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": 2338707, "tid": 2379456, + "ts": 6197200076859.079, "dur": 192.194, + "args": { + "External id": 32971,"Record function id": 0, "Sequence number": 480214, "Fwd thread id": 1, "Ev Idx": 5834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200076860.172, "dur": 187.478, + "args": { + "External id": 32972,"Sequence number": 480214, "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": 2338707, "tid": 2379456, "ts": 6197200076860.172, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338707, "tid": 2379456, + "ts": 6197200076861.828, "dur": 185.433, + "args": { + "External id": 32973,"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": 2338707, "tid": 2379456, + "ts": 6197200076864.474, "dur": 19.136, + "args": { + "External id": 32974,"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": 2338707, "tid": 2379456, + "ts": 6197200076865.495, "dur": 2.824, + "args": { + "External id": 32975,"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": 2338707, "tid": 2379456, + "ts": 6197200076869.341, "dur": 14.005, + "args": { + "External id": 32976,"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": 2338707, "tid": 2379456, + "ts": 6197200076872.709, "dur": 10.199, + "args": { + "External id": 32977,"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": 2338707, "tid": 2379456, + "ts": 6197200076884.903, "dur": 3.359, + "args": { + "External id": 32978,"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": 2338707, "tid": 2379456, + "ts": 6197200076887.096, "dur": 0.919, + "args": { + "External id": 32979,"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": 2338707, "tid": 2379456, + "ts": 6197200076889.042, "dur": 156.868, + "args": { + "External id": 32980,"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": 2338707, "tid": 2379456, + "ts": 6197200077090.189, "dur": 96.844, + "args": { + "External id": 32981,"Record function id": 0, "Sequence number": 480213, "Fwd thread id": 1, "Ev Idx": 5844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200077092.199, "dur": 90.932, + "args": { + "External id": 32982,"Sequence number": 480213, "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": 2338707, "tid": 2379456, "ts": 6197200077092.199, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338707, "tid": 2379456, + "ts": 6197200077094.269, "dur": 88.511, + "args": { + "External id": 32983,"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": 2338707, "tid": 2379456, + "ts": 6197200077095.968, "dur": 21.562, + "args": { + "External id": 32984,"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": 2338707, "tid": 2379456, + "ts": 6197200077097.315, "dur": 3.487, + "args": { + "External id": 32985,"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": 2338707, "tid": 2379456, + "ts": 6197200077101.923, "dur": 15.355, + "args": { + "External id": 32986,"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": 2338707, "tid": 2379456, + "ts": 6197200077103.632, "dur": 13.110, + "args": { + "External id": 32987,"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": 2338707, "tid": 2379456, + "ts": 6197200077120.345, "dur": 3.730, + "args": { + "External id": 32988,"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": 2338707, "tid": 2379456, + "ts": 6197200077122.797, "dur": 0.893, + "args": { + "External id": 32989,"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": 2338707, "tid": 2379456, + "ts": 6197200077127.266, "dur": 54.604, + "args": { + "External id": 32990,"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": 2338707, "tid": 2379456, + "ts": 6197200077192.172, "dur": 39.192, + "args": { + "External id": 32991,"Record function id": 0, "Sequence number": 480212, "Fwd thread id": 1, "Ev Idx": 5854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200077193.663, "dur": 0.945, + "args": { + "External id": 32992,"Sequence number": 480212, "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": 2338707, "tid": 2379456, "ts": 6197200077193.663, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338707, "tid": 2379456, + "ts": 6197200077197.459, "dur": 30.383, + "args": { + "External id": 32993,"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": 2338707, "tid": 2379456, + "ts": 6197200077200.573, "dur": 26.868, + "args": { + "External id": 32994,"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": 2338707, "tid": 2379456, + "ts": 6197200077206.845, "dur": 1.007, + "args": { + "External id": 32995,"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": 2338707, "tid": 2379456, + "ts": 6197200077236.757, "dur": 2496.367, + "args": { + "External id": 32996,"Record function id": 0, "Sequence number": 480210, "Fwd thread id": 1, "Ev Idx": 5859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197200077238.788, "dur": 2441.808, + "args": { + "External id": 32997,"Sequence number": 480210, "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": 2338707, "tid": 2379456, "ts": 6197200077238.788, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197200077276.578, "dur": 3.309, + "args": { + "External id": 32998,"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": 2338707, "tid": 2379456, + "ts": 6197200077282.894, "dur": 2168.978, + "args": { + "External id": 32999,"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": 2338707, "tid": 2379456, + "ts": 6197200077284.942, "dur": 2166.600, + "args": { + "External id": 33000,"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": 2338707, "tid": 2379456, + "ts": 6197200077288.138, "dur": 4.221, + "args": { + "External id": 33001,"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": 2338707, "tid": 2379456, + "ts": 6197200077293.508, "dur": 2156.924, + "args": { + "External id": 33002,"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": 2338707, "tid": 2379456, + "ts": 6197200079455.437, "dur": 0.415, + "args": { + "External id": 33003,"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": 2338707, "tid": 2379456, + "ts": 6197200079457.402, "dur": 5.561, + "args": { + "External id": 33004,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 5867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach_", "pid": 2338707, "tid": 2379456, + "ts": 6197200079461.836, "dur": 1.013, + "args": { + "External id": 33005,"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": 2338707, "tid": 2379456, + "ts": 6197200079468.292, "dur": 25.600, + "args": { + "External id": 33006,"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": 2338707, "tid": 2379456, + "ts": 6197200079500.143, "dur": 43.767, + "args": { + "External id": 33007,"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": 2338707, "tid": 2379456, + "ts": 6197200079501.432, "dur": 42.232, + "args": { + "External id": 33008,"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": 2338707, "tid": 2379456, + "ts": 6197200079503.285, "dur": 40.138, + "args": { + "External id": 33009,"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": 2338707, "tid": 2379456, + "ts": 6197200079692.720, "dur": 34.984, + "args": { + "External id": 33010,"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": 2338707, "tid": 2379456, + "ts": 6197200079745.267, "dur": 15.554, + "args": { + "External id": 33011,"Record function id": 0, "Sequence number": 480209, "Fwd thread id": 1, "Ev Idx": 5874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200079747.419, "dur": 10.727, + "args": { + "External id": 33012,"Sequence number": 480209, "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": 2338707, "tid": 2379456, "ts": 6197200079747.419, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200079751.079, "dur": 6.855, + "args": { + "External id": 33013,"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": 2338707, "tid": 2379456, + "ts": 6197200079753.221, "dur": 4.467, + "args": { + "External id": 33014,"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": 2338707, "tid": 2379456, + "ts": 6197200079764.962, "dur": 81.030, + "args": { + "External id": 33015,"Record function id": 0, "Sequence number": 480208, "Fwd thread id": 1, "Ev Idx": 5878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200079765.843, "dur": 75.231, + "args": { + "External id": 33016,"Sequence number": 480208, "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": 2338707, "tid": 2379456, "ts": 6197200079765.843, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338707, "tid": 2379456, + "ts": 6197200079768.688, "dur": 72.073, + "args": { + "External id": 33017,"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": 2338707, "tid": 2379456, + "ts": 6197200079771.917, "dur": 27.011, + "args": { + "External id": 33018,"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": 2338707, "tid": 2379456, + "ts": 6197200079776.612, "dur": 4.081, + "args": { + "External id": 33019,"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": 2338707, "tid": 2379456, + "ts": 6197200079781.898, "dur": 16.736, + "args": { + "External id": 33020,"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": 2338707, "tid": 2379456, + "ts": 6197200079783.352, "dur": 14.726, + "args": { + "External id": 33021,"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": 2338707, "tid": 2379456, + "ts": 6197200079800.729, "dur": 5.028, + "args": { + "External id": 33022,"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": 2338707, "tid": 2379456, + "ts": 6197200079803.841, "dur": 1.627, + "args": { + "External id": 33023,"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": 2338707, "tid": 2379456, + "ts": 6197200079807.138, "dur": 32.723, + "args": { + "External id": 33024,"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": 2338707, "tid": 2379456, + "ts": 6197200079850.271, "dur": 59.843, + "args": { + "External id": 33025,"Record function id": 0, "Sequence number": 480207, "Fwd thread id": 1, "Ev Idx": 5888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SelectBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200079851.680, "dur": 55.710, + "args": { + "External id": 33026,"Sequence number": 480207, "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": 2338707, "tid": 2379456, "ts": 6197200079851.680, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select_backward", "pid": 2338707, "tid": 2379456, + "ts": 6197200079854.104, "dur": 52.957, + "args": { + "External id": 33027,"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": 2338707, "tid": 2379456, + "ts": 6197200079856.273, "dur": 18.095, + "args": { + "External id": 33028,"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": 2338707, "tid": 2379456, + "ts": 6197200079857.831, "dur": 2.624, + "args": { + "External id": 33029,"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": 2338707, "tid": 2379456, + "ts": 6197200079861.071, "dur": 13.040, + "args": { + "External id": 33030,"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": 2338707, "tid": 2379456, + "ts": 6197200079862.240, "dur": 11.477, + "args": { + "External id": 33031,"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": 2338707, "tid": 2379456, + "ts": 6197200079882.967, "dur": 6.231, + "args": { + "External id": 33032,"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": 2338707, "tid": 2379456, + "ts": 6197200079887.071, "dur": 1.550, + "args": { + "External id": 33033,"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": 2338707, "tid": 2379456, + "ts": 6197200079889.879, "dur": 16.560, + "args": { + "External id": 33034,"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": 2338707, "tid": 2379456, + "ts": 6197200079913.878, "dur": 120.404, + "args": { + "External id": 33035,"Record function id": 0, "Sequence number": 480206, "Fwd thread id": 1, "Ev Idx": 5898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200079914.996, "dur": 116.376, + "args": { + "External id": 33036,"Sequence number": 480206, "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": 2338707, "tid": 2379456, "ts": 6197200079914.996, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338707, "tid": 2379456, + "ts": 6197200079917.185, "dur": 113.751, + "args": { + "External id": 33037,"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": 2338707, "tid": 2379456, + "ts": 6197200079918.583, "dur": 17.434, + "args": { + "External id": 33038,"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": 2338707, "tid": 2379456, + "ts": 6197200079919.639, "dur": 2.158, + "args": { + "External id": 33039,"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": 2338707, "tid": 2379456, + "ts": 6197200079922.379, "dur": 13.369, + "args": { + "External id": 33040,"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": 2338707, "tid": 2379456, + "ts": 6197200079923.572, "dur": 11.789, + "args": { + "External id": 33041,"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": 2338707, "tid": 2379456, + "ts": 6197200079936.984, "dur": 3.338, + "args": { + "External id": 33042,"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": 2338707, "tid": 2379456, + "ts": 6197200079939.070, "dur": 1.007, + "args": { + "External id": 33043,"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": 2338707, "tid": 2379456, + "ts": 6197200079941.218, "dur": 88.846, + "args": { + "External id": 33044,"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": 2338707, "tid": 2379456, + "ts": 6197200080039.033, "dur": 146.853, + "args": { + "External id": 33045,"Record function id": 0, "Sequence number": 480205, "Fwd thread id": 1, "Ev Idx": 5908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200080040.037, "dur": 124.524, + "args": { + "External id": 33046,"Sequence number": 480205, "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": 2338707, "tid": 2379456, "ts": 6197200080040.037, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338707, "tid": 2379456, + "ts": 6197200080041.862, "dur": 122.185, + "args": { + "External id": 33047,"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": 2338707, "tid": 2379456, + "ts": 6197200080042.993, "dur": 60.931, + "args": { + "External id": 33048,"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": 2338707, "tid": 2379456, + "ts": 6197200080043.993, "dur": 2.521, + "args": { + "External id": 33049,"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": 2338707, "tid": 2379456, + "ts": 6197200080047.442, "dur": 56.218, + "args": { + "External id": 33050,"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": 2338707, "tid": 2379456, + "ts": 6197200080050.939, "dur": 52.030, + "args": { + "External id": 33051,"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": 2338707, "tid": 2379456, + "ts": 6197200080105.762, "dur": 3.688, + "args": { + "External id": 33052,"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": 2338707, "tid": 2379456, + "ts": 6197200080108.031, "dur": 1.143, + "args": { + "External id": 33053,"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": 2338707, "tid": 2379456, + "ts": 6197200080110.184, "dur": 53.138, + "args": { + "External id": 33054,"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": 2338707, "tid": 2379456, + "ts": 6197200080169.941, "dur": 14.420, + "args": { + "External id": 33055,"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": 2338707, "tid": 2379456, + "ts": 6197200080192.258, "dur": 34.088, + "args": { + "External id": 33056,"Record function id": 0, "Sequence number": 480204, "Fwd thread id": 1, "Ev Idx": 5919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200080193.741, "dur": 0.942, + "args": { + "External id": 33057,"Sequence number": 480204, "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": 2338707, "tid": 2379456, "ts": 6197200080193.741, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338707, "tid": 2379456, + "ts": 6197200080197.293, "dur": 25.894, + "args": { + "External id": 33058,"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": 2338707, "tid": 2379456, + "ts": 6197200080200.074, "dur": 22.732, + "args": { + "External id": 33059,"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": 2338707, "tid": 2379456, + "ts": 6197200080205.706, "dur": 0.878, + "args": { + "External id": 33060,"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": 2338707, "tid": 2379456, + "ts": 6197200080231.424, "dur": 3452.436, + "args": { + "External id": 33061,"Record function id": 0, "Sequence number": 480202, "Fwd thread id": 1, "Ev Idx": 5924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197200080232.842, "dur": 3421.808, + "args": { + "External id": 33062,"Sequence number": 480202, "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": 2338707, "tid": 2379456, "ts": 6197200080232.842, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197200080266.770, "dur": 3.376, + "args": { + "External id": 33063,"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": 2338707, "tid": 2379456, + "ts": 6197200080272.957, "dur": 3170.271, + "args": { + "External id": 33064,"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": 2338707, "tid": 2379456, + "ts": 6197200080274.570, "dur": 3168.415, + "args": { + "External id": 33065,"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": 2338707, "tid": 2379456, + "ts": 6197200080277.717, "dur": 3.843, + "args": { + "External id": 33066,"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": 2338707, "tid": 2379456, + "ts": 6197200080282.838, "dur": 3159.033, + "args": { + "External id": 33067,"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": 2338707, "tid": 2379456, + "ts": 6197200083446.925, "dur": 0.532, + "args": { + "External id": 33068,"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": 2338707, "tid": 2379456, + "ts": 6197200083448.831, "dur": 2.323, + "args": { + "External id": 33069,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 5932 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach_", "pid": 2338707, "tid": 2379456, + "ts": 6197200083450.132, "dur": 0.908, + "args": { + "External id": 33070,"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": 2338707, "tid": 2379456, + "ts": 6197200083456.129, "dur": 21.348, + "args": { + "External id": 33071,"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": 2338707, "tid": 2379456, + "ts": 6197200083482.971, "dur": 46.616, + "args": { + "External id": 33072,"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": 2338707, "tid": 2379456, + "ts": 6197200083484.348, "dur": 44.962, + "args": { + "External id": 33073,"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": 2338707, "tid": 2379456, + "ts": 6197200083485.866, "dur": 43.085, + "args": { + "External id": 33074,"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": 2338707, "tid": 2379456, + "ts": 6197200083664.940, "dur": 15.221, + "args": { + "External id": 33075,"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": 2338707, "tid": 2379456, + "ts": 6197200083694.779, "dur": 25.557, + "args": { + "External id": 33076,"Record function id": 0, "Sequence number": 480201, "Fwd thread id": 1, "Ev Idx": 5939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200083696.211, "dur": 21.024, + "args": { + "External id": 33077,"Sequence number": 480201, "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": 2338707, "tid": 2379456, "ts": 6197200083696.211, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200083699.366, "dur": 17.620, + "args": { + "External id": 33078,"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": 2338707, "tid": 2379456, + "ts": 6197200083712.065, "dur": 4.566, + "args": { + "External id": 33079,"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": 2338707, "tid": 2379456, + "ts": 6197200083725.540, "dur": 70.771, + "args": { + "External id": 33080,"Record function id": 0, "Sequence number": 480200, "Fwd thread id": 1, "Ev Idx": 5943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200083726.639, "dur": 64.201, + "args": { + "External id": 33081,"Sequence number": 480200, "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": 2338707, "tid": 2379456, "ts": 6197200083726.639, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338707, "tid": 2379456, + "ts": 6197200083728.746, "dur": 61.661, + "args": { + "External id": 33082,"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": 2338707, "tid": 2379456, + "ts": 6197200083731.924, "dur": 25.969, + "args": { + "External id": 33083,"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": 2338707, "tid": 2379456, + "ts": 6197200083734.136, "dur": 4.121, + "args": { + "External id": 33084,"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": 2338707, "tid": 2379456, + "ts": 6197200083739.440, "dur": 18.193, + "args": { + "External id": 33085,"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": 2338707, "tid": 2379456, + "ts": 6197200083741.467, "dur": 15.695, + "args": { + "External id": 33086,"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": 2338707, "tid": 2379456, + "ts": 6197200083759.591, "dur": 3.944, + "args": { + "External id": 33087,"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": 2338707, "tid": 2379456, + "ts": 6197200083762.069, "dur": 1.191, + "args": { + "External id": 33088,"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": 2338707, "tid": 2379456, + "ts": 6197200083764.722, "dur": 24.950, + "args": { + "External id": 33089,"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": 2338707, "tid": 2379456, + "ts": 6197200083800.783, "dur": 49.704, + "args": { + "External id": 33090,"Record function id": 0, "Sequence number": 480199, "Fwd thread id": 1, "Ev Idx": 5953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SelectBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200083801.907, "dur": 46.192, + "args": { + "External id": 33091,"Sequence number": 480199, "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": 2338707, "tid": 2379456, "ts": 6197200083801.907, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select_backward", "pid": 2338707, "tid": 2379456, + "ts": 6197200083803.673, "dur": 44.111, + "args": { + "External id": 33092,"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": 2338707, "tid": 2379456, + "ts": 6197200083805.571, "dur": 20.400, + "args": { + "External id": 33093,"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": 2338707, "tid": 2379456, + "ts": 6197200083806.607, "dur": 3.056, + "args": { + "External id": 33094,"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": 2338707, "tid": 2379456, + "ts": 6197200083811.128, "dur": 14.587, + "args": { + "External id": 33095,"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": 2338707, "tid": 2379456, + "ts": 6197200083812.268, "dur": 13.103, + "args": { + "External id": 33096,"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": 2338707, "tid": 2379456, + "ts": 6197200083827.260, "dur": 5.269, + "args": { + "External id": 33097,"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": 2338707, "tid": 2379456, + "ts": 6197200083830.762, "dur": 1.253, + "args": { + "External id": 33098,"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": 2338707, "tid": 2379456, + "ts": 6197200083833.264, "dur": 13.993, + "args": { + "External id": 33099,"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": 2338707, "tid": 2379456, + "ts": 6197200083854.429, "dur": 113.833, + "args": { + "External id": 33100,"Record function id": 0, "Sequence number": 480198, "Fwd thread id": 1, "Ev Idx": 5963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200083855.796, "dur": 109.726, + "args": { + "External id": 33101,"Sequence number": 480198, "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": 2338707, "tid": 2379456, "ts": 6197200083855.796, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338707, "tid": 2379456, + "ts": 6197200083857.430, "dur": 107.705, + "args": { + "External id": 33102,"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": 2338707, "tid": 2379456, + "ts": 6197200083859.053, "dur": 17.251, + "args": { + "External id": 33103,"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": 2338707, "tid": 2379456, + "ts": 6197200083860.083, "dur": 2.210, + "args": { + "External id": 33104,"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": 2338707, "tid": 2379456, + "ts": 6197200083863.152, "dur": 12.915, + "args": { + "External id": 33105,"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": 2338707, "tid": 2379456, + "ts": 6197200083864.139, "dur": 11.560, + "args": { + "External id": 33106,"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": 2338707, "tid": 2379456, + "ts": 6197200083877.071, "dur": 2.142, + "args": { + "External id": 33107,"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": 2338707, "tid": 2379456, + "ts": 6197200083878.441, "dur": 0.590, + "args": { + "External id": 33108,"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": 2338707, "tid": 2379456, + "ts": 6197200083879.832, "dur": 84.170, + "args": { + "External id": 33109,"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": 2338707, "tid": 2379456, + "ts": 6197200083973.026, "dur": 146.594, + "args": { + "External id": 33110,"Record function id": 0, "Sequence number": 480197, "Fwd thread id": 1, "Ev Idx": 5973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200083973.988, "dur": 120.629, + "args": { + "External id": 33111,"Sequence number": 480197, "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": 2338707, "tid": 2379456, "ts": 6197200083973.988, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338707, "tid": 2379456, + "ts": 6197200083975.822, "dur": 118.385, + "args": { + "External id": 33112,"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": 2338707, "tid": 2379456, + "ts": 6197200083977.193, "dur": 19.228, + "args": { + "External id": 33113,"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": 2338707, "tid": 2379456, + "ts": 6197200083977.892, "dur": 2.170, + "args": { + "External id": 33114,"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": 2338707, "tid": 2379456, + "ts": 6197200083981.167, "dur": 15.001, + "args": { + "External id": 33115,"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": 2338707, "tid": 2379456, + "ts": 6197200083982.371, "dur": 13.466, + "args": { + "External id": 33116,"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": 2338707, "tid": 2379456, + "ts": 6197200083997.447, "dur": 2.006, + "args": { + "External id": 33117,"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": 2338707, "tid": 2379456, + "ts": 6197200083998.757, "dur": 0.564, + "args": { + "External id": 33118,"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": 2338707, "tid": 2379456, + "ts": 6197200084000.096, "dur": 92.577, + "args": { + "External id": 33119,"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": 2338707, "tid": 2379456, + "ts": 6197200084100.367, "dur": 18.003, + "args": { + "External id": 33120,"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": 2338707, "tid": 2379456, + "ts": 6197200084126.243, "dur": 38.022, + "args": { + "External id": 33121,"Record function id": 0, "Sequence number": 480196, "Fwd thread id": 1, "Ev Idx": 5984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200084127.885, "dur": 1.157, + "args": { + "External id": 33122,"Sequence number": 480196, "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": 2338707, "tid": 2379456, "ts": 6197200084127.885, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338707, "tid": 2379456, + "ts": 6197200084131.046, "dur": 28.486, + "args": { + "External id": 33123,"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": 2338707, "tid": 2379456, + "ts": 6197200084133.097, "dur": 26.114, + "args": { + "External id": 33124,"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": 2338707, "tid": 2379456, + "ts": 6197200084139.019, "dur": 0.841, + "args": { + "External id": 33125,"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": 2338707, "tid": 2379456, + "ts": 6197200084168.675, "dur": 3490.224, + "args": { + "External id": 33126,"Record function id": 0, "Sequence number": 480195, "Fwd thread id": 1, "Ev Idx": 5989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197200084181.002, "dur": 3447.689, + "args": { + "External id": 33127,"Sequence number": 480195, "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": 2338707, "tid": 2379456, "ts": 6197200084181.002, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197200084210.869, "dur": 2.620, + "args": { + "External id": 33128,"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": 2338707, "tid": 2379456, + "ts": 6197200084216.085, "dur": 3204.849, + "args": { + "External id": 33129,"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": 2338707, "tid": 2379456, + "ts": 6197200084217.936, "dur": 3202.778, + "args": { + "External id": 33130,"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": 2338707, "tid": 2379456, + "ts": 6197200084220.782, "dur": 3.351, + "args": { + "External id": 33131,"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": 2338707, "tid": 2379456, + "ts": 6197200084224.996, "dur": 3194.666, + "args": { + "External id": 33132,"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": 2338707, "tid": 2379456, + "ts": 6197200087424.287, "dur": 0.352, + "args": { + "External id": 33133,"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": 2338707, "tid": 2379456, + "ts": 6197200087425.919, "dur": 2.202, + "args": { + "External id": 33134,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 5997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach_", "pid": 2338707, "tid": 2379456, + "ts": 6197200087427.155, "dur": 0.852, + "args": { + "External id": 33135,"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": 2338707, "tid": 2379456, + "ts": 6197200087432.644, "dur": 22.455, + "args": { + "External id": 33136,"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": 2338707, "tid": 2379456, + "ts": 6197200087460.178, "dur": 43.900, + "args": { + "External id": 33137,"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": 2338707, "tid": 2379456, + "ts": 6197200087461.247, "dur": 42.620, + "args": { + "External id": 33138,"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": 2338707, "tid": 2379456, + "ts": 6197200087462.650, "dur": 40.898, + "args": { + "External id": 33139,"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": 2338707, "tid": 2379456, + "ts": 6197200087640.209, "dur": 14.684, + "args": { + "External id": 33140,"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": 2338707, "tid": 2379456, + "ts": 6197200087671.949, "dur": 12.640, + "args": { + "External id": 33141,"Record function id": 0, "Ev Idx": 6004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200087674.507, "dur": 8.365, + "args": { + "External id": 33142,"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": 2338707, "tid": 2379456, + "ts": 6197200087677.422, "dur": 4.577, + "args": { + "External id": 33143,"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": 2338707, "tid": 2379456, + "ts": 6197200087678.231, "dur": 3.663, + "args": { + "External id": 33144,"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": 2338707, "tid": 2379456, + "ts": 6197200087688.455, "dur": 24.787, + "args": { + "External id": 33145,"Record function id": 0, "Sequence number": 480194, "Fwd thread id": 1, "Ev Idx": 6008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200087689.581, "dur": 8.584, + "args": { + "External id": 33146,"Sequence number": 480194, "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": 2338707, "tid": 2379456, "ts": 6197200087689.581, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200087692.402, "dur": 5.481, + "args": { + "External id": 33147,"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": 2338707, "tid": 2379456, + "ts": 6197200087694.220, "dur": 3.418, + "args": { + "External id": 33148,"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": 2338707, "tid": 2379456, + "ts": 6197200087719.062, "dur": 75.086, + "args": { + "External id": 33149,"Record function id": 0, "Sequence number": 480193, "Fwd thread id": 1, "Ev Idx": 6012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200087719.969, "dur": 68.476, + "args": { + "External id": 33150,"Sequence number": 480193, "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": 2338707, "tid": 2379456, "ts": 6197200087719.969, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338707, "tid": 2379456, + "ts": 6197200087722.633, "dur": 65.354, + "args": { + "External id": 33151,"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": 2338707, "tid": 2379456, + "ts": 6197200087726.697, "dur": 26.353, + "args": { + "External id": 33152,"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": 2338707, "tid": 2379456, + "ts": 6197200087728.340, "dur": 4.356, + "args": { + "External id": 33153,"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": 2338707, "tid": 2379456, + "ts": 6197200087733.920, "dur": 18.852, + "args": { + "External id": 33154,"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": 2338707, "tid": 2379456, + "ts": 6197200087735.594, "dur": 16.677, + "args": { + "External id": 33155,"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": 2338707, "tid": 2379456, + "ts": 6197200087754.862, "dur": 5.465, + "args": { + "External id": 33156,"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": 2338707, "tid": 2379456, + "ts": 6197200087758.581, "dur": 1.373, + "args": { + "External id": 33157,"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": 2338707, "tid": 2379456, + "ts": 6197200087761.357, "dur": 25.799, + "args": { + "External id": 33158,"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": 2338707, "tid": 2379456, + "ts": 6197200087798.547, "dur": 50.023, + "args": { + "External id": 33159,"Record function id": 0, "Sequence number": 480192, "Fwd thread id": 1, "Ev Idx": 6022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SelectBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200087799.538, "dur": 46.109, + "args": { + "External id": 33160,"Sequence number": 480192, "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": 2338707, "tid": 2379456, "ts": 6197200087799.538, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select_backward", "pid": 2338707, "tid": 2379456, + "ts": 6197200087801.998, "dur": 43.383, + "args": { + "External id": 33161,"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": 2338707, "tid": 2379456, + "ts": 6197200087804.318, "dur": 16.742, + "args": { + "External id": 33162,"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": 2338707, "tid": 2379456, + "ts": 6197200087805.629, "dur": 3.135, + "args": { + "External id": 33163,"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": 2338707, "tid": 2379456, + "ts": 6197200087809.411, "dur": 11.351, + "args": { + "External id": 33164,"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": 2338707, "tid": 2379456, + "ts": 6197200087810.195, "dur": 10.172, + "args": { + "External id": 33165,"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": 2338707, "tid": 2379456, + "ts": 6197200087823.389, "dur": 5.742, + "args": { + "External id": 33166,"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": 2338707, "tid": 2379456, + "ts": 6197200087826.828, "dur": 1.616, + "args": { + "External id": 33167,"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": 2338707, "tid": 2379456, + "ts": 6197200087830.014, "dur": 14.837, + "args": { + "External id": 33168,"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": 2338707, "tid": 2379456, + "ts": 6197200087852.431, "dur": 121.665, + "args": { + "External id": 33169,"Record function id": 0, "Sequence number": 480191, "Fwd thread id": 1, "Ev Idx": 6032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200087853.660, "dur": 117.054, + "args": { + "External id": 33170,"Sequence number": 480191, "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": 2338707, "tid": 2379456, "ts": 6197200087853.660, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338707, "tid": 2379456, + "ts": 6197200087855.846, "dur": 114.513, + "args": { + "External id": 33171,"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": 2338707, "tid": 2379456, + "ts": 6197200087857.188, "dur": 19.990, + "args": { + "External id": 33172,"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": 2338707, "tid": 2379456, + "ts": 6197200087858.398, "dur": 2.013, + "args": { + "External id": 33173,"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": 2338707, "tid": 2379456, + "ts": 6197200087865.524, "dur": 11.406, + "args": { + "External id": 33174,"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": 2338707, "tid": 2379456, + "ts": 6197200087866.790, "dur": 9.770, + "args": { + "External id": 33175,"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": 2338707, "tid": 2379456, + "ts": 6197200087880.243, "dur": 2.973, + "args": { + "External id": 33176,"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": 2338707, "tid": 2379456, + "ts": 6197200087882.113, "dur": 0.854, + "args": { + "External id": 33177,"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": 2338707, "tid": 2379456, + "ts": 6197200087884.053, "dur": 85.350, + "args": { + "External id": 33178,"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": 2338707, "tid": 2379456, + "ts": 6197200087978.737, "dur": 130.066, + "args": { + "External id": 33179,"Record function id": 0, "Sequence number": 480190, "Fwd thread id": 1, "Ev Idx": 6042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200087980.204, "dur": 104.600, + "args": { + "External id": 33180,"Sequence number": 480190, "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": 2338707, "tid": 2379456, "ts": 6197200087980.204, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338707, "tid": 2379456, + "ts": 6197200087982.389, "dur": 101.882, + "args": { + "External id": 33181,"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": 2338707, "tid": 2379456, + "ts": 6197200087983.673, "dur": 15.280, + "args": { + "External id": 33182,"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": 2338707, "tid": 2379456, + "ts": 6197200087984.504, "dur": 2.293, + "args": { + "External id": 33183,"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": 2338707, "tid": 2379456, + "ts": 6197200087987.456, "dur": 11.254, + "args": { + "External id": 33184,"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": 2338707, "tid": 2379456, + "ts": 6197200087988.437, "dur": 9.937, + "args": { + "External id": 33185,"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": 2338707, "tid": 2379456, + "ts": 6197200088002.116, "dur": 3.580, + "args": { + "External id": 33186,"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": 2338707, "tid": 2379456, + "ts": 6197200088004.665, "dur": 0.789, + "args": { + "External id": 33187,"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": 2338707, "tid": 2379456, + "ts": 6197200088006.410, "dur": 76.590, + "args": { + "External id": 33188,"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": 2338707, "tid": 2379456, + "ts": 6197200088091.458, "dur": 14.925, + "args": { + "External id": 33189,"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": 2338707, "tid": 2379456, + "ts": 6197200088117.887, "dur": 329.929, + "args": { + "External id": 33190,"Record function id": 0, "Sequence number": 480189, "Fwd thread id": 1, "Ev Idx": 6053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197200088119.538, "dur": 320.581, + "args": { + "External id": 33191,"Sequence number": 480189, "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": 2338707, "tid": 2379456, "ts": 6197200088119.538, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338707, "tid": 2379456, + "ts": 6197200088278.445, "dur": 40.567, + "args": { + "External id": 33192,"kernel_hash": "cze4nwoznzp5ccj3536wygl2i2ykkdyt3hdmkvx2y6tl7tevwkdm", "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/ze/cze4nwoznzp5ccj3536wygl2i2ykkdyt3hdmkvx2y6tl7tevwkdm.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": 2338707, "tid": 2379456, + "ts": 6197200088351.280, "dur": 27.194, + "args": { + "External id": 33193,"kernel_hash": "ccswrdngzi6jo4g2p2v6rs3fdbvr7wkgz5izdhrj3lqu7uzzy4ad", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/cs/ccswrdngzi6jo4g2p2v6rs3fdbvr7wkgz5izdhrj3lqu7uzzy4ad.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": 2338707, "tid": 2379456, + "ts": 6197200088396.802, "dur": 19.604, + "args": { + "External id": 33194,"kernel_hash": "cddm6binnqpaq4idvznth7jqun5cvp5pc6dr7dh3ezznaxoowmjo", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/dd/cddm6binnqpaq4idvznth7jqun5cvp5pc6dr7dh3ezznaxoowmjo.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": 2338707, "tid": 2379456, + "ts": 6197200088456.817, "dur": 15.792, + "args": { + "External id": 33195,"Record function id": 0, "Ev Idx": 6058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200088458.940, "dur": 9.023, + "args": { + "External id": 33196,"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": 2338707, "tid": 2379456, + "ts": 6197200088461.840, "dur": 5.365, + "args": { + "External id": 33197,"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": 2338707, "tid": 2379456, + "ts": 6197200088463.608, "dur": 3.472, + "args": { + "External id": 33198,"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": 2338707, "tid": 2379456, + "ts": 6197200088477.006, "dur": 33.926, + "args": { + "External id": 33199,"Record function id": 0, "Sequence number": 480188, "Fwd thread id": 1, "Ev Idx": 6062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "StackBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200088478.167, "dur": 25.453, + "args": { + "External id": 33200,"Sequence number": 480188, "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": 2338707, "tid": 2379456, "ts": 6197200088478.167, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 2338707, "tid": 2379456, + "ts": 6197200088480.004, "dur": 9.444, + "args": { + "External id": 33201,"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": 2338707, "tid": 2379456, + "ts": 6197200088486.209, "dur": 1.304, + "args": { + "External id": 33202,"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": 2338707, "tid": 2379456, + "ts": 6197200088490.134, "dur": 4.340, + "args": { + "External id": 33203,"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": 2338707, "tid": 2379456, + "ts": 6197200088492.575, "dur": 0.858, + "args": { + "External id": 33204,"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": 2338707, "tid": 2379456, + "ts": 6197200088495.019, "dur": 3.527, + "args": { + "External id": 33205,"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": 2338707, "tid": 2379456, + "ts": 6197200088496.709, "dur": 0.938, + "args": { + "External id": 33206,"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": 2338707, "tid": 2379456, + "ts": 6197200088499.094, "dur": 3.746, + "args": { + "External id": 33207,"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": 2338707, "tid": 2379456, + "ts": 6197200088501.560, "dur": 0.607, + "args": { + "External id": 33208,"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": 2338707, "tid": 2379456, + "ts": 6197200088514.520, "dur": 5.821, + "args": { + "External id": 33209,"Record function id": 0, "Sequence number": 480187, "Fwd thread id": 1, "Ev Idx": 6072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200088515.362, "dur": 1.304, + "args": { + "External id": 33210,"Sequence number": 480187, "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": 2338707, "tid": 2379456, "ts": 6197200088515.362, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SwiGLULinearFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197200088524.760, "dur": 508.699, + "args": { + "External id": 33211,"Record function id": 0, "Sequence number": 480186, "Fwd thread id": 1, "Ev Idx": 6074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197200088526.191, "dur": 492.168, + "args": { + "External id": 33212,"Sequence number": 480186, "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": 2338707, "tid": 2379456, "ts": 6197200088526.191, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200088563.499, "dur": 9.155, + "args": { + "External id": 33213,"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": 2338707, "tid": 2379456, + "ts": 6197200088568.413, "dur": 3.941, + "args": { + "External id": 33214,"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": 2338707, "tid": 2379456, + "ts": 6197200088576.567, "dur": 6.911, + "args": { + "External id": 33215,"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": 2338707, "tid": 2379456, + "ts": 6197200088579.099, "dur": 3.541, + "args": { + "External id": 33216,"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": 2338707, "tid": 2379456, + "ts": 6197200088581.171, "dur": 1.220, + "args": { + "External id": 33217,"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": 2338707, "tid": 2379456, + "ts": 6197200088589.615, "dur": 139.787, + "args": { + "External id": 33218,"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": 2338707, "tid": 2379456, + "ts": 6197200088590.912, "dur": 3.629, + "args": { + "External id": 33219,"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": 2338707, "tid": 2379456, + "ts": 6197200088591.666, "dur": 2.100, + "args": { + "External id": 33220,"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": 2338707, "tid": 2379456, + "ts": 6197200088592.824, "dur": 0.779, + "args": { + "External id": 33221,"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": 2338707, "tid": 2379456, + "ts": 6197200088598.706, "dur": 129.689, + "args": { + "External id": 33222,"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": 2338707, "tid": 2379456, + "ts": 6197200088600.518, "dur": 126.489, + "args": { + "External id": 33223,"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": 2338707, "tid": 2379456, + "ts": 6197200088736.590, "dur": 7.986, + "args": { + "External id": 33224,"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": 2338707, "tid": 2379456, + "ts": 6197200088740.998, "dur": 3.371, + "args": { + "External id": 33225,"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": 2338707, "tid": 2379456, + "ts": 6197200088782.240, "dur": 6.144, + "args": { + "External id": 33226,"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": 2338707, "tid": 2379456, + "ts": 6197200088790.014, "dur": 2.194, + "args": { + "External id": 33227,"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": 2338707, "tid": 2379456, + "ts": 6197200088793.494, "dur": 2.539, + "args": { + "External id": 33228,"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": 2338707, "tid": 2379456, + "ts": 6197200088830.343, "dur": 3.643, + "args": { + "External id": 33229,"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": 2338707, "tid": 2379456, + "ts": 6197200088831.856, "dur": 1.950, + "args": { + "External id": 33230,"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": 2338707, "tid": 2379456, + "ts": 6197200088860.336, "dur": 135.239, + "args": { + "External id": 33231,"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": 2338707, "tid": 2379456, + "ts": 6197200088867.109, "dur": 7.347, + "args": { + "External id": 33232,"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": 2338707, "tid": 2379456, + "ts": 6197200088871.265, "dur": 1.147, + "args": { + "External id": 33233,"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": 2338707, "tid": 2379456, + "ts": 6197200088876.424, "dur": 4.690, + "args": { + "External id": 33234,"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": 2338707, "tid": 2379456, + "ts": 6197200088879.759, "dur": 0.793, + "args": { + "External id": 33235,"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": 2338707, "tid": 2379456, + "ts": 6197200088882.610, "dur": 2.544, + "args": { + "External id": 33236,"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": 2338707, "tid": 2379456, + "ts": 6197200088884.261, "dur": 0.485, + "args": { + "External id": 33237,"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": 2338707, "tid": 2379456, + "ts": 6197200088886.039, "dur": 3.055, + "args": { + "External id": 33238,"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": 2338707, "tid": 2379456, + "ts": 6197200088887.907, "dur": 0.854, + "args": { + "External id": 33239,"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": 2338707, "tid": 2379456, + "ts": 6197200088893.182, "dur": 3.257, + "args": { + "External id": 33240,"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": 2338707, "tid": 2379456, + "ts": 6197200088895.440, "dur": 0.691, + "args": { + "External id": 33241,"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": 2338707, "tid": 2379456, + "ts": 6197200088899.471, "dur": 6.697, + "args": { + "External id": 33242,"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": 2338707, "tid": 2379456, + "ts": 6197200088903.846, "dur": 2.117, + "args": { + "External id": 33243,"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": 2338707, "tid": 2379456, + "ts": 6197200088906.909, "dur": 2.761, + "args": { + "External id": 33244,"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": 2338707, "tid": 2379456, + "ts": 6197200088908.901, "dur": 0.443, + "args": { + "External id": 33245,"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": 2338707, "tid": 2379456, + "ts": 6197200088910.636, "dur": 2.541, + "args": { + "External id": 33246,"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": 2338707, "tid": 2379456, + "ts": 6197200088911.462, "dur": 1.590, + "args": { + "External id": 33247,"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": 2338707, "tid": 2379456, + "ts": 6197200088914.461, "dur": 68.858, + "args": { + "External id": 33248,"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": 2338707, "tid": 2379456, + "ts": 6197200088985.326, "dur": 1.153, + "args": { + "External id": 33249,"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": 2338707, "tid": 2379456, + "ts": 6197200088987.928, "dur": 3.279, + "args": { + "External id": 33250,"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": 2338707, "tid": 2379456, + "ts": 6197200088989.850, "dur": 0.822, + "args": { + "External id": 33251,"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": 2338707, "tid": 2379456, + "ts": 6197200088993.346, "dur": 1.094, + "args": { + "External id": 33252,"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": 2338707, "tid": 2379456, + "ts": 6197200089046.395, "dur": 49.402, + "args": { + "External id": 33253,"Record function id": 0, "Ev Idx": 6116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200089048.352, "dur": 45.992, + "args": { + "External id": 33254,"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": 2338707, "tid": 2379456, + "ts": 6197200089050.838, "dur": 41.947, + "args": { + "External id": 33255,"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": 2338707, "tid": 2379456, + "ts": 6197200089088.523, "dur": 3.784, + "args": { + "External id": 33256,"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": 2338707, "tid": 2379456, + "ts": 6197200089102.416, "dur": 9.707, + "args": { + "External id": 33257,"Record function id": 0, "Sequence number": 480185, "Fwd thread id": 1, "Ev Idx": 6120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200089103.821, "dur": 5.260, + "args": { + "External id": 33258,"Sequence number": 480185, "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": 2338707, "tid": 2379456, "ts": 6197200089103.821, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200089106.258, "dur": 2.605, + "args": { + "External id": 33259,"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": 2338707, "tid": 2379456, + "ts": 6197200089107.147, "dur": 1.636, + "args": { + "External id": 33260,"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": 2338707, "tid": 2379456, + "ts": 6197200089115.857, "dur": 130.350, + "args": { + "External id": 33261,"Record function id": 0, "Sequence number": 480184, "Fwd thread id": 1, "Ev Idx": 6124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200089116.749, "dur": 121.642, + "args": { + "External id": 33262,"Sequence number": 480184, "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": 2338707, "tid": 2379456, "ts": 6197200089116.749, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197200089123.247, "dur": 5.382, + "args": { + "External id": 33263,"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": 2338707, "tid": 2379456, + "ts": 6197200089124.826, "dur": 3.217, + "args": { + "External id": 33264,"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": 2338707, "tid": 2379456, + "ts": 6197200089126.759, "dur": 1.112, + "args": { + "External id": 33265,"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": 2338707, "tid": 2379456, + "ts": 6197200089129.952, "dur": 54.666, + "args": { + "External id": 33266,"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": 2338707, "tid": 2379456, + "ts": 6197200089185.893, "dur": 6.702, + "args": { + "External id": 33267,"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": 2338707, "tid": 2379456, + "ts": 6197200089186.657, "dur": 5.314, + "args": { + "External id": 33268,"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": 2338707, "tid": 2379456, + "ts": 6197200089190.244, "dur": 1.595, + "args": { + "External id": 33269,"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": 2338707, "tid": 2379456, + "ts": 6197200089194.190, "dur": 4.151, + "args": { + "External id": 33270,"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": 2338707, "tid": 2379456, + "ts": 6197200089195.057, "dur": 2.643, + "args": { + "External id": 33271,"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": 2338707, "tid": 2379456, + "ts": 6197200089196.859, "dur": 0.706, + "args": { + "External id": 33272,"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": 2338707, "tid": 2379456, + "ts": 6197200089198.875, "dur": 38.622, + "args": { + "External id": 33273,"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": 2338707, "tid": 2379456, + "ts": 6197200089251.121, "dur": 7.620, + "args": { + "External id": 33274,"Record function id": 0, "Sequence number": 480183, "Fwd thread id": 1, "Ev Idx": 6137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200089252.217, "dur": 4.593, + "args": { + "External id": 33275,"Sequence number": 480183, "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": 2338707, "tid": 2379456, "ts": 6197200089252.217, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200089254.010, "dur": 2.653, + "args": { + "External id": 33276,"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": 2338707, "tid": 2379456, + "ts": 6197200089255.336, "dur": 1.188, + "args": { + "External id": 33277,"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": 2338707, "tid": 2379456, + "ts": 6197200089262.133, "dur": 72.438, + "args": { + "External id": 33278,"Record function id": 0, "Sequence number": 480182, "Fwd thread id": 1, "Ev Idx": 6141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200089265.233, "dur": 67.028, + "args": { + "External id": 33279,"Sequence number": 480182, "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": 2338707, "tid": 2379456, "ts": 6197200089265.233, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197200089266.357, "dur": 65.647, + "args": { + "External id": 33280,"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": 2338707, "tid": 2379456, + "ts": 6197200089328.870, "dur": 2.418, + "args": { + "External id": 37889,"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": 2338707, "tid": 2379456, + "ts": 6197200089330.433, "dur": 0.758, + "args": { + "External id": 37890,"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": 2338707, "tid": 2379456, + "ts": 6197200089339.275, "dur": 6.337, + "args": { + "External id": 37891,"Record function id": 0, "Ev Idx": 6146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200089340.947, "dur": 4.120, + "args": { + "External id": 37892,"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": 2338707, "tid": 2379456, + "ts": 6197200089342.425, "dur": 2.366, + "args": { + "External id": 37893,"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": 2338707, "tid": 2379456, + "ts": 6197200089343.128, "dur": 1.514, + "args": { + "External id": 37894,"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": 2338707, "tid": 2379456, + "ts": 6197200089348.966, "dur": 8.484, + "args": { + "External id": 37895,"Record function id": 0, "Sequence number": 480181, "Fwd thread id": 1, "Ev Idx": 6150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200089350.224, "dur": 4.905, + "args": { + "External id": 37896,"Sequence number": 480181, "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": 2338707, "tid": 2379456, "ts": 6197200089350.224, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200089351.308, "dur": 3.653, + "args": { + "External id": 37897,"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": 2338707, "tid": 2379456, + "ts": 6197200089354.100, "dur": 0.766, + "args": { + "External id": 37898,"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": 2338707, "tid": 2379456, + "ts": 6197200089360.406, "dur": 123.756, + "args": { + "External id": 37899,"Record function id": 0, "Sequence number": 480180, "Fwd thread id": 1, "Ev Idx": 6154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200089361.237, "dur": 113.629, + "args": { + "External id": 37900,"Sequence number": 480180, "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": 2338707, "tid": 2379456, "ts": 6197200089361.237, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197200089363.556, "dur": 3.461, + "args": { + "External id": 37901,"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": 2338707, "tid": 2379456, + "ts": 6197200089363.968, "dur": 2.634, + "args": { + "External id": 37902,"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": 2338707, "tid": 2379456, + "ts": 6197200089365.855, "dur": 0.657, + "args": { + "External id": 37903,"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": 2338707, "tid": 2379456, + "ts": 6197200089369.973, "dur": 48.934, + "args": { + "External id": 37904,"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": 2338707, "tid": 2379456, + "ts": 6197200089420.152, "dur": 3.813, + "args": { + "External id": 37905,"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": 2338707, "tid": 2379456, + "ts": 6197200089420.625, "dur": 2.851, + "args": { + "External id": 37906,"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": 2338707, "tid": 2379456, + "ts": 6197200089422.459, "dur": 0.887, + "args": { + "External id": 37907,"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": 2338707, "tid": 2379456, + "ts": 6197200089425.131, "dur": 5.727, + "args": { + "External id": 37908,"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": 2338707, "tid": 2379456, + "ts": 6197200089425.941, "dur": 4.216, + "args": { + "External id": 37909,"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": 2338707, "tid": 2379456, + "ts": 6197200089429.449, "dur": 0.642, + "args": { + "External id": 37910,"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": 2338707, "tid": 2379456, + "ts": 6197200089431.653, "dur": 42.518, + "args": { + "External id": 37911,"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": 2338707, "tid": 2379456, + "ts": 6197200089488.657, "dur": 34.114, + "args": { + "External id": 37912,"Record function id": 0, "Sequence number": 480179, "Fwd thread id": 1, "Ev Idx": 6167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200089489.511, "dur": 4.029, + "args": { + "External id": 37913,"Sequence number": 480179, "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": 2338707, "tid": 2379456, "ts": 6197200089489.511, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200089490.999, "dur": 2.400, + "args": { + "External id": 37914,"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": 2338707, "tid": 2379456, + "ts": 6197200089492.103, "dur": 1.152, + "args": { + "External id": 37915,"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": 2338707, "tid": 2379456, + "ts": 6197200089496.775, "dur": 23.307, + "args": { + "External id": 37916,"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": 2338707, "tid": 2379456, + "ts": 6197200089526.431, "dur": 10.097, + "args": { + "External id": 37917,"Record function id": 0, "Sequence number": 480178, "Fwd thread id": 1, "Ev Idx": 6172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200089527.633, "dur": 6.717, + "args": { + "External id": 37918,"Sequence number": 480178, "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": 2338707, "tid": 2379456, "ts": 6197200089527.633, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197200089528.365, "dur": 5.781, + "args": { + "External id": 37919,"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": 2338707, "tid": 2379456, + "ts": 6197200089529.359, "dur": 4.312, + "args": { + "External id": 37920,"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": 2338707, "tid": 2379456, + "ts": 6197200089532.979, "dur": 0.579, + "args": { + "External id": 37921,"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": 2338707, "tid": 2379456, + "ts": 6197200089540.592, "dur": 5.273, + "args": { + "External id": 37922,"Record function id": 0, "Ev Idx": 6177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200089541.890, "dur": 3.478, + "args": { + "External id": 37923,"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": 2338707, "tid": 2379456, + "ts": 6197200089543.113, "dur": 1.975, + "args": { + "External id": 37924,"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": 2338707, "tid": 2379456, + "ts": 6197200089543.704, "dur": 1.243, + "args": { + "External id": 37925,"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": 2338707, "tid": 2379456, + "ts": 6197200089550.659, "dur": 449.058, + "args": { + "External id": 37926,"Record function id": 0, "Sequence number": 480177, "Fwd thread id": 1, "Ev Idx": 6181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197200089552.188, "dur": 431.400, + "args": { + "External id": 37927,"Sequence number": 480177, "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": 2338707, "tid": 2379456, "ts": 6197200089552.188, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338707, "tid": 2379456, + "ts": 6197200089582.359, "dur": 33.470, + "args": { + "External id": 37928,"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": 2338707, "tid": 2379456, + "ts": 6197200089583.811, "dur": 31.820, + "args": { + "External id": 37929,"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": 2338707, "tid": 2379456, + "ts": 6197200089586.675, "dur": 6.430, + "args": { + "External id": 37930,"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": 2338707, "tid": 2379456, + "ts": 6197200089589.508, "dur": 3.027, + "args": { + "External id": 37931,"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": 2338707, "tid": 2379456, + "ts": 6197200089594.502, "dur": 20.551, + "args": { + "External id": 37932,"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": 2338707, "tid": 2379456, + "ts": 6197200089628.208, "dur": 4.429, + "args": { + "External id": 37933,"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": 2338707, "tid": 2379456, + "ts": 6197200089631.089, "dur": 1.401, + "args": { + "External id": 37934,"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": 2338707, "tid": 2379456, + "ts": 6197200089636.628, "dur": 1.674, + "args": { + "External id": 37935,"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": 2338707, "tid": 2379456, + "ts": 6197200089637.433, "dur": 0.773, + "args": { + "External id": 37936,"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": 2338707, "tid": 2379456, + "ts": 6197200089652.317, "dur": 2.244, + "args": { + "External id": 37937,"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": 2338707, "tid": 2379456, + "ts": 6197200089666.074, "dur": 2.719, + "args": { + "External id": 37938,"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": 2338707, "tid": 2379456, + "ts": 6197200089872.539, "dur": 3.020, + "args": { + "External id": 37939,"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": 2338707, "tid": 2379456, + "ts": 6197200089880.360, "dur": 37.367, + "args": { + "External id": 37940,"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": 2338707, "tid": 2379456, + "ts": 6197200089893.798, "dur": 1.135, + "args": { + "External id": 37941,"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": 2338707, "tid": 2379456, + "ts": 6197200089923.665, "dur": 27.720, + "args": { + "External id": 37942,"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": 2338707, "tid": 2379456, + "ts": 6197200089925.560, "dur": 25.597, + "args": { + "External id": 37943,"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": 2338707, "tid": 2379456, + "ts": 6197200089929.755, "dur": 4.832, + "args": { + "External id": 37944,"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": 2338707, "tid": 2379456, + "ts": 6197200089936.001, "dur": 14.548, + "args": { + "External id": 37945,"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": 2338707, "tid": 2379456, + "ts": 6197200089956.352, "dur": 4.811, + "args": { + "External id": 37946,"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": 2338707, "tid": 2379456, + "ts": 6197200089959.773, "dur": 1.248, + "args": { + "External id": 37947,"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": 2338707, "tid": 2379456, + "ts": 6197200089968.177, "dur": 1.833, + "args": { + "External id": 37948,"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": 2338707, "tid": 2379456, + "ts": 6197200089969.055, "dur": 0.853, + "args": { + "External id": 37949,"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": 2338707, "tid": 2379456, + "ts": 6197200089972.026, "dur": 2.329, + "args": { + "External id": 37950,"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": 2338707, "tid": 2379456, + "ts": 6197200089973.024, "dur": 1.218, + "args": { + "External id": 37951,"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": 2338707, "tid": 2379456, + "ts": 6197200090015.073, "dur": 8.402, + "args": { + "External id": 37952,"Record function id": 0, "Ev Idx": 6207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200090017.202, "dur": 5.556, + "args": { + "External id": 37953,"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": 2338707, "tid": 2379456, + "ts": 6197200090019.386, "dur": 2.538, + "args": { + "External id": 37954,"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": 2338707, "tid": 2379456, + "ts": 6197200090020.094, "dur": 1.724, + "args": { + "External id": 37955,"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": 2338707, "tid": 2379456, + "ts": 6197200090027.486, "dur": 8.749, + "args": { + "External id": 37956,"Record function id": 0, "Sequence number": 480176, "Fwd thread id": 1, "Ev Idx": 6211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200090028.616, "dur": 4.042, + "args": { + "External id": 37957,"Sequence number": 480176, "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": 2338707, "tid": 2379456, "ts": 6197200090028.616, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200090030.360, "dur": 2.093, + "args": { + "External id": 37958,"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": 2338707, "tid": 2379456, + "ts": 6197200090031.191, "dur": 1.101, + "args": { + "External id": 37959,"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": 2338707, "tid": 2379456, + "ts": 6197200090039.785, "dur": 225.774, + "args": { + "External id": 37960,"Record function id": 0, "Sequence number": 480175, "Fwd thread id": 1, "Ev Idx": 6215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200090040.531, "dur": 219.034, + "args": { + "External id": 37961,"Sequence number": 480175, "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": 2338707, "tid": 2379456, "ts": 6197200090040.531, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197200090044.604, "dur": 6.805, + "args": { + "External id": 37962,"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": 2338707, "tid": 2379456, + "ts": 6197200090048.287, "dur": 2.540, + "args": { + "External id": 37963,"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": 2338707, "tid": 2379456, + "ts": 6197200090049.818, "dur": 0.826, + "args": { + "External id": 37964,"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": 2338707, "tid": 2379456, + "ts": 6197200090101.676, "dur": 90.079, + "args": { + "External id": 37965,"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": 2338707, "tid": 2379456, + "ts": 6197200090193.344, "dur": 5.955, + "args": { + "External id": 37966,"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": 2338707, "tid": 2379456, + "ts": 6197200090194.673, "dur": 3.727, + "args": { + "External id": 37967,"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": 2338707, "tid": 2379456, + "ts": 6197200090196.929, "dur": 1.338, + "args": { + "External id": 37968,"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": 2338707, "tid": 2379456, + "ts": 6197200090201.316, "dur": 6.906, + "args": { + "External id": 37969,"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": 2338707, "tid": 2379456, + "ts": 6197200090205.338, "dur": 2.235, + "args": { + "External id": 37970,"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": 2338707, "tid": 2379456, + "ts": 6197200090206.736, "dur": 0.753, + "args": { + "External id": 37971,"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": 2338707, "tid": 2379456, + "ts": 6197200090208.740, "dur": 49.909, + "args": { + "External id": 37972,"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": 2338707, "tid": 2379456, + "ts": 6197200090272.716, "dur": 7.761, + "args": { + "External id": 37973,"Record function id": 0, "Sequence number": 480174, "Fwd thread id": 1, "Ev Idx": 6228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200090273.750, "dur": 4.689, + "args": { + "External id": 37974,"Sequence number": 480174, "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": 2338707, "tid": 2379456, "ts": 6197200090273.750, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200090275.676, "dur": 2.628, + "args": { + "External id": 37975,"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": 2338707, "tid": 2379456, + "ts": 6197200090276.697, "dur": 1.458, + "args": { + "External id": 37976,"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": 2338707, "tid": 2379456, + "ts": 6197200090284.187, "dur": 10.836, + "args": { + "External id": 37977,"Record function id": 0, "Sequence number": 480173, "Fwd thread id": 1, "Ev Idx": 6232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200090284.991, "dur": 7.771, + "args": { + "External id": 37978,"Sequence number": 480173, "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": 2338707, "tid": 2379456, "ts": 6197200090284.991, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197200090285.736, "dur": 6.788, + "args": { + "External id": 37979,"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": 2338707, "tid": 2379456, + "ts": 6197200090286.330, "dur": 5.630, + "args": { + "External id": 37980,"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": 2338707, "tid": 2379456, + "ts": 6197200090290.140, "dur": 1.664, + "args": { + "External id": 37981,"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": 2338707, "tid": 2379456, + "ts": 6197200090299.148, "dur": 6.840, + "args": { + "External id": 37982,"Record function id": 0, "Ev Idx": 6237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200090300.435, "dur": 4.933, + "args": { + "External id": 37983,"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": 2338707, "tid": 2379456, + "ts": 6197200090302.260, "dur": 2.842, + "args": { + "External id": 37984,"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": 2338707, "tid": 2379456, + "ts": 6197200090303.101, "dur": 1.879, + "args": { + "External id": 37985,"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": 2338707, "tid": 2379456, + "ts": 6197200090309.417, "dur": 6.302, + "args": { + "External id": 37986,"Record function id": 0, "Sequence number": 480172, "Fwd thread id": 1, "Ev Idx": 6241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200090310.197, "dur": 3.430, + "args": { + "External id": 37987,"Sequence number": 480172, "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": 2338707, "tid": 2379456, "ts": 6197200090310.197, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200090311.132, "dur": 2.343, + "args": { + "External id": 37988,"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": 2338707, "tid": 2379456, + "ts": 6197200090312.182, "dur": 1.196, + "args": { + "External id": 37989,"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": 2338707, "tid": 2379456, + "ts": 6197200090321.102, "dur": 430.480, + "args": { + "External id": 37990,"Record function id": 0, "Sequence number": 480171, "Fwd thread id": 1, "Ev Idx": 6245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFuncBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197200090322.657, "dur": 406.369, + "args": { + "External id": 37991,"Sequence number": 480171, "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": 2338707, "tid": 2379456, "ts": 6197200090322.657, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338707, "tid": 2379456, + "ts": 6197200090342.478, "dur": 8.775, + "args": { + "External id": 37992,"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": 2338707, "tid": 2379456, + "ts": 6197200090345.860, "dur": 4.966, + "args": { + "External id": 37993,"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": 2338707, "tid": 2379456, + "ts": 6197200090353.689, "dur": 4.675, + "args": { + "External id": 37994,"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": 2338707, "tid": 2379456, + "ts": 6197200090355.786, "dur": 2.364, + "args": { + "External id": 37995,"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": 2338707, "tid": 2379456, + "ts": 6197200090359.851, "dur": 4.093, + "args": { + "External id": 37996,"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": 2338707, "tid": 2379456, + "ts": 6197200090361.403, "dur": 2.373, + "args": { + "External id": 37997,"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": 2338707, "tid": 2379456, + "ts": 6197200090397.851, "dur": 285.498, + "args": { + "External id": 37998,"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": 2338707, "tid": 2379456, + "ts": 6197200090492.621, "dur": 3.473, + "args": { + "External id": 37999,"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": 2338707, "tid": 2379456, + "ts": 6197200090498.204, "dur": 2.981, + "args": { + "External id": 38000,"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": 2338707, "tid": 2379456, + "ts": 6197200090502.700, "dur": 2.260, + "args": { + "External id": 38001,"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": 2338707, "tid": 2379456, + "ts": 6197200090506.273, "dur": 2.413, + "args": { + "External id": 38002,"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": 2338707, "tid": 2379456, + "ts": 6197200090578.629, "dur": 3.261, + "args": { + "External id": 38003,"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": 2338707, "tid": 2379456, + "ts": 6197200090580.239, "dur": 1.551, + "args": { + "External id": 38004,"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": 2338707, "tid": 2379456, + "ts": 6197200090585.690, "dur": 30.507, + "args": { + "External id": 38005,"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": 2338707, "tid": 2379456, + "ts": 6197200090592.967, "dur": 1.532, + "args": { + "External id": 38006,"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": 2338707, "tid": 2379456, + "ts": 6197200090617.860, "dur": 2.593, + "args": { + "External id": 38007,"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": 2338707, "tid": 2379456, + "ts": 6197200090619.646, "dur": 0.727, + "args": { + "External id": 38008,"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": 2338707, "tid": 2379456, + "ts": 6197200090621.131, "dur": 16.550, + "args": { + "External id": 38009,"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": 2338707, "tid": 2379456, + "ts": 6197200090623.716, "dur": 0.989, + "args": { + "External id": 38010,"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": 2338707, "tid": 2379456, + "ts": 6197200090696.373, "dur": 19.763, + "args": { + "External id": 38011,"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": 2338707, "tid": 2379456, + "ts": 6197200090722.080, "dur": 1.298, + "args": { + "External id": 38012,"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": 2338707, "tid": 2379456, + "ts": 6197200090725.476, "dur": 0.723, + "args": { + "External id": 38013,"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": 2338707, "tid": 2379456, + "ts": 6197200090762.294, "dur": 242.875, + "args": { + "External id": 38014,"Record function id": 0, "Sequence number": 480170, "Fwd thread id": 1, "Ev Idx": 6269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197200090763.819, "dur": 234.743, + "args": { + "External id": 38015,"Sequence number": 480170, "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": 2338707, "tid": 2379456, "ts": 6197200090763.819, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338707, "tid": 2379456, + "ts": 6197200090790.259, "dur": 52.214, + "args": { + "External id": 38016,"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": 2338707, "tid": 2379456, + "ts": 6197200090793.979, "dur": 4.614, + "args": { + "External id": 38017,"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": 2338707, "tid": 2379456, + "ts": 6197200090800.164, "dur": 41.753, + "args": { + "External id": 38018,"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": 2338707, "tid": 2379456, + "ts": 6197200090853.353, "dur": 4.844, + "args": { + "External id": 38019,"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": 2338707, "tid": 2379456, + "ts": 6197200090855.503, "dur": 2.330, + "args": { + "External id": 38020,"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": 2338707, "tid": 2379456, + "ts": 6197200091012.807, "dur": 241.700, + "args": { + "External id": 38021,"Record function id": 0, "Sequence number": 480169, "Fwd thread id": 1, "Ev Idx": 6276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197200091014.713, "dur": 231.961, + "args": { + "External id": 38022,"Sequence number": 480169, "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": 2338707, "tid": 2379456, "ts": 6197200091014.713, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338707, "tid": 2379456, + "ts": 6197200091027.054, "dur": 100.384, + "args": { + "External id": 38023,"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": 2338707, "tid": 2379456, + "ts": 6197200091029.462, "dur": 2.919, + "args": { + "External id": 38024,"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": 2338707, "tid": 2379456, + "ts": 6197200091033.321, "dur": 93.058, + "args": { + "External id": 38025,"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": 2338707, "tid": 2379456, + "ts": 6197200091138.061, "dur": 8.050, + "args": { + "External id": 38026,"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": 2338707, "tid": 2379456, + "ts": 6197200091140.498, "dur": 5.314, + "args": { + "External id": 38027,"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": 2338707, "tid": 2379456, + "ts": 6197200091263.271, "dur": 15.023, + "args": { + "External id": 38028,"Record function id": 0, "Sequence number": 480168, "Fwd thread id": 1, "Ev Idx": 6283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200091264.903, "dur": 10.692, + "args": { + "External id": 38029,"Sequence number": 480168, "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": 2338707, "tid": 2379456, "ts": 6197200091264.903, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200091267.847, "dur": 7.499, + "args": { + "External id": 38030,"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": 2338707, "tid": 2379456, + "ts": 6197200091270.168, "dur": 4.962, + "args": { + "External id": 38031,"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": 2338707, "tid": 2379456, + "ts": 6197200091282.121, "dur": 8.055, + "args": { + "External id": 38032,"Record function id": 0, "Sequence number": 480167, "Fwd thread id": 1, "Ev Idx": 6287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200091283.525, "dur": 3.797, + "args": { + "External id": 38033,"Sequence number": 480167, "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": 2338707, "tid": 2379456, "ts": 6197200091283.525, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200091285.187, "dur": 1.978, + "args": { + "External id": 38034,"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": 2338707, "tid": 2379456, + "ts": 6197200091286.077, "dur": 0.972, + "args": { + "External id": 38035,"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": 2338707, "tid": 2379456, + "ts": 6197200091293.562, "dur": 13.330, + "args": { + "External id": 38036,"Record function id": 0, "Sequence number": 480166, "Fwd thread id": 1, "Ev Idx": 6291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200091299.042, "dur": 5.310, + "args": { + "External id": 38037,"Sequence number": 480166, "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": 2338707, "tid": 2379456, "ts": 6197200091299.042, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200091302.055, "dur": 2.146, + "args": { + "External id": 38038,"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": 2338707, "tid": 2379456, + "ts": 6197200091302.848, "dur": 1.213, + "args": { + "External id": 38039,"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": 2338707, "tid": 2379456, + "ts": 6197200091310.870, "dur": 7.539, + "args": { + "External id": 38040,"Record function id": 0, "Sequence number": 480165, "Fwd thread id": 1, "Ev Idx": 6295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200091311.849, "dur": 3.761, + "args": { + "External id": 38041,"Sequence number": 480165, "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": 2338707, "tid": 2379456, "ts": 6197200091311.849, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200091313.324, "dur": 2.143, + "args": { + "External id": 38042,"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": 2338707, "tid": 2379456, + "ts": 6197200091314.221, "dur": 1.141, + "args": { + "External id": 38043,"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": 2338707, "tid": 2379456, + "ts": 6197200091322.041, "dur": 166.851, + "args": { + "External id": 38044,"Record function id": 0, "Sequence number": 480164, "Fwd thread id": 1, "Ev Idx": 6299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200091322.821, "dur": 158.683, + "args": { + "External id": 38045,"Sequence number": 480164, "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": 2338707, "tid": 2379456, "ts": 6197200091322.821, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197200091327.142, "dur": 9.760, + "args": { + "External id": 38046,"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": 2338707, "tid": 2379456, + "ts": 6197200091331.710, "dur": 4.386, + "args": { + "External id": 38047,"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": 2338707, "tid": 2379456, + "ts": 6197200091334.032, "dur": 1.728, + "args": { + "External id": 38048,"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": 2338707, "tid": 2379456, + "ts": 6197200091338.547, "dur": 77.229, + "args": { + "External id": 38049,"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": 2338707, "tid": 2379456, + "ts": 6197200091416.983, "dur": 5.949, + "args": { + "External id": 38050,"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": 2338707, "tid": 2379456, + "ts": 6197200091417.672, "dur": 4.411, + "args": { + "External id": 38051,"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": 2338707, "tid": 2379456, + "ts": 6197200091419.777, "dur": 2.133, + "args": { + "External id": 38052,"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": 2338707, "tid": 2379456, + "ts": 6197200091427.192, "dur": 4.637, + "args": { + "External id": 38053,"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": 2338707, "tid": 2379456, + "ts": 6197200091428.654, "dur": 2.252, + "args": { + "External id": 38054,"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": 2338707, "tid": 2379456, + "ts": 6197200091430.224, "dur": 0.607, + "args": { + "External id": 38055,"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": 2338707, "tid": 2379456, + "ts": 6197200091432.480, "dur": 48.250, + "args": { + "External id": 38056,"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": 2338707, "tid": 2379456, + "ts": 6197200091494.306, "dur": 7.355, + "args": { + "External id": 38057,"Record function id": 0, "Sequence number": 480163, "Fwd thread id": 1, "Ev Idx": 6312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200091495.123, "dur": 4.270, + "args": { + "External id": 38058,"Sequence number": 480163, "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": 2338707, "tid": 2379456, "ts": 6197200091495.123, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200091497.078, "dur": 2.159, + "args": { + "External id": 38059,"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": 2338707, "tid": 2379456, + "ts": 6197200091498.034, "dur": 1.047, + "args": { + "External id": 38060,"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": 2338707, "tid": 2379456, + "ts": 6197200091505.261, "dur": 10.329, + "args": { + "External id": 38061,"Record function id": 0, "Sequence number": 480162, "Fwd thread id": 1, "Ev Idx": 6316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200091506.234, "dur": 7.050, + "args": { + "External id": 38062,"Sequence number": 480162, "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": 2338707, "tid": 2379456, "ts": 6197200091506.234, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197200091509.320, "dur": 3.805, + "args": { + "External id": 38063,"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": 2338707, "tid": 2379456, + "ts": 6197200091510.177, "dur": 2.468, + "args": { + "External id": 38064,"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": 2338707, "tid": 2379456, + "ts": 6197200091511.558, "dur": 0.964, + "args": { + "External id": 38065,"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": 2338707, "tid": 2379456, + "ts": 6197200091521.468, "dur": 10.070, + "args": { + "External id": 38066,"Record function id": 0, "Ev Idx": 6321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200091523.201, "dur": 7.548, + "args": { + "External id": 38067,"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": 2338707, "tid": 2379456, + "ts": 6197200091525.809, "dur": 4.553, + "args": { + "External id": 38068,"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": 2338707, "tid": 2379456, + "ts": 6197200091527.213, "dur": 3.045, + "args": { + "External id": 38069,"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": 2338707, "tid": 2379456, + "ts": 6197200091535.138, "dur": 6.118, + "args": { + "External id": 38070,"Record function id": 0, "Sequence number": 480161, "Fwd thread id": 1, "Ev Idx": 6325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200091536.138, "dur": 3.081, + "args": { + "External id": 38071,"Sequence number": 480161, "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": 2338707, "tid": 2379456, "ts": 6197200091536.138, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200091537.334, "dur": 1.734, + "args": { + "External id": 38072,"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": 2338707, "tid": 2379456, + "ts": 6197200091538.095, "dur": 0.843, + "args": { + "External id": 38073,"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": 2338707, "tid": 2379456, + "ts": 6197200091544.692, "dur": 95.752, + "args": { + "External id": 38074,"Record function id": 0, "Sequence number": 480160, "Fwd thread id": 1, "Ev Idx": 6329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200091547.512, "dur": 86.177, + "args": { + "External id": 38075,"Sequence number": 480160, "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": 2338707, "tid": 2379456, "ts": 6197200091547.512, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197200091550.060, "dur": 3.317, + "args": { + "External id": 38076,"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": 2338707, "tid": 2379456, + "ts": 6197200091550.881, "dur": 2.084, + "args": { + "External id": 38077,"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": 2338707, "tid": 2379456, + "ts": 6197200091552.150, "dur": 0.713, + "args": { + "External id": 38078,"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": 2338707, "tid": 2379456, + "ts": 6197200091553.908, "dur": 26.535, + "args": { + "External id": 38079,"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": 2338707, "tid": 2379456, + "ts": 6197200091581.417, "dur": 9.778, + "args": { + "External id": 38080,"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": 2338707, "tid": 2379456, + "ts": 6197200091582.426, "dur": 8.254, + "args": { + "External id": 38081,"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": 2338707, "tid": 2379456, + "ts": 6197200091588.337, "dur": 2.201, + "args": { + "External id": 38082,"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": 2338707, "tid": 2379456, + "ts": 6197200091592.291, "dur": 3.506, + "args": { + "External id": 38083,"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": 2338707, "tid": 2379456, + "ts": 6197200091593.464, "dur": 1.658, + "args": { + "External id": 38084,"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": 2338707, "tid": 2379456, + "ts": 6197200091594.544, "dur": 0.484, + "args": { + "External id": 38085,"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": 2338707, "tid": 2379456, + "ts": 6197200091596.172, "dur": 36.800, + "args": { + "External id": 38086,"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": 2338707, "tid": 2379456, + "ts": 6197200091645.024, "dur": 33.588, + "args": { + "External id": 38087,"Record function id": 0, "Sequence number": 480159, "Fwd thread id": 1, "Ev Idx": 6342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200091646.119, "dur": 4.198, + "args": { + "External id": 38088,"Sequence number": 480159, "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": 2338707, "tid": 2379456, "ts": 6197200091646.119, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200091647.483, "dur": 2.677, + "args": { + "External id": 38089,"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": 2338707, "tid": 2379456, + "ts": 6197200091648.674, "dur": 1.349, + "args": { + "External id": 38090,"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": 2338707, "tid": 2379456, + "ts": 6197200091653.243, "dur": 22.774, + "args": { + "External id": 38091,"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": 2338707, "tid": 2379456, + "ts": 6197200091684.741, "dur": 8.057, + "args": { + "External id": 38092,"Record function id": 0, "Sequence number": 480158, "Fwd thread id": 1, "Ev Idx": 6347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200091685.713, "dur": 4.670, + "args": { + "External id": 38093,"Sequence number": 480158, "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": 2338707, "tid": 2379456, "ts": 6197200091685.713, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197200091686.301, "dur": 3.856, + "args": { + "External id": 38094,"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": 2338707, "tid": 2379456, + "ts": 6197200091687.065, "dur": 2.526, + "args": { + "External id": 38095,"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": 2338707, "tid": 2379456, + "ts": 6197200091688.601, "dur": 0.885, + "args": { + "External id": 38096,"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": 2338707, "tid": 2379456, + "ts": 6197200091696.669, "dur": 22.117, + "args": { + "External id": 38097,"Record function id": 0, "Ev Idx": 6352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200091698.150, "dur": 19.442, + "args": { + "External id": 38098,"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": 2338707, "tid": 2379456, + "ts": 6197200091699.032, "dur": 17.978, + "args": { + "External id": 38099,"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": 2338707, "tid": 2379456, + "ts": 6197200091699.634, "dur": 16.936, + "args": { + "External id": 38100,"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": 2338707, "tid": 2379456, + "ts": 6197200091724.298, "dur": 10.553, + "args": { + "External id": 38101,"Record function id": 0, "Sequence number": 480157, "Fwd thread id": 1, "Ev Idx": 6356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200091726.129, "dur": 6.544, + "args": { + "External id": 38102,"Sequence number": 480157, "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": 2338707, "tid": 2379456, "ts": 6197200091726.129, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200091727.536, "dur": 4.967, + "args": { + "External id": 38103,"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": 2338707, "tid": 2379456, + "ts": 6197200091731.058, "dur": 1.313, + "args": { + "External id": 38104,"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": 2338707, "tid": 2379456, + "ts": 6197200091738.003, "dur": 106.155, + "args": { + "External id": 38105,"Record function id": 0, "Sequence number": 480156, "Fwd thread id": 1, "Ev Idx": 6360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200091738.711, "dur": 95.929, + "args": { + "External id": 38106,"Sequence number": 480156, "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": 2338707, "tid": 2379456, "ts": 6197200091738.711, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197200091740.805, "dur": 3.547, + "args": { + "External id": 38107,"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": 2338707, "tid": 2379456, + "ts": 6197200091741.394, "dur": 2.503, + "args": { + "External id": 38108,"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": 2338707, "tid": 2379456, + "ts": 6197200091743.021, "dur": 0.770, + "args": { + "External id": 38109,"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": 2338707, "tid": 2379456, + "ts": 6197200091747.238, "dur": 40.412, + "args": { + "External id": 38110,"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": 2338707, "tid": 2379456, + "ts": 6197200091788.679, "dur": 4.070, + "args": { + "External id": 38111,"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": 2338707, "tid": 2379456, + "ts": 6197200091789.229, "dur": 3.022, + "args": { + "External id": 38112,"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": 2338707, "tid": 2379456, + "ts": 6197200091790.913, "dur": 1.223, + "args": { + "External id": 38113,"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": 2338707, "tid": 2379456, + "ts": 6197200091794.066, "dur": 3.246, + "args": { + "External id": 38114,"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": 2338707, "tid": 2379456, + "ts": 6197200091795.188, "dur": 1.702, + "args": { + "External id": 38115,"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": 2338707, "tid": 2379456, + "ts": 6197200091796.065, "dur": 0.758, + "args": { + "External id": 38116,"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": 2338707, "tid": 2379456, + "ts": 6197200091799.969, "dur": 33.916, + "args": { + "External id": 38117,"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": 2338707, "tid": 2379456, + "ts": 6197200091848.645, "dur": 27.617, + "args": { + "External id": 38118,"Record function id": 0, "Sequence number": 480155, "Fwd thread id": 1, "Ev Idx": 6373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200091849.695, "dur": 4.137, + "args": { + "External id": 38119,"Sequence number": 480155, "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": 2338707, "tid": 2379456, "ts": 6197200091849.695, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200091851.541, "dur": 2.149, + "args": { + "External id": 38120,"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": 2338707, "tid": 2379456, + "ts": 6197200091852.459, "dur": 1.119, + "args": { + "External id": 38121,"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": 2338707, "tid": 2379456, + "ts": 6197200091856.719, "dur": 17.186, + "args": { + "External id": 38122,"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": 2338707, "tid": 2379456, + "ts": 6197200091879.968, "dur": 9.231, + "args": { + "External id": 38123,"Record function id": 0, "Sequence number": 480154, "Fwd thread id": 1, "Ev Idx": 6378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200091880.897, "dur": 6.369, + "args": { + "External id": 38124,"Sequence number": 480154, "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": 2338707, "tid": 2379456, "ts": 6197200091880.897, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197200091881.645, "dur": 5.412, + "args": { + "External id": 38125,"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": 2338707, "tid": 2379456, + "ts": 6197200091882.499, "dur": 4.060, + "args": { + "External id": 38126,"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": 2338707, "tid": 2379456, + "ts": 6197200091885.832, "dur": 0.620, + "args": { + "External id": 38127,"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": 2338707, "tid": 2379456, + "ts": 6197200091893.571, "dur": 5.688, + "args": { + "External id": 38128,"Record function id": 0, "Ev Idx": 6383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200091895.055, "dur": 3.708, + "args": { + "External id": 38129,"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": 2338707, "tid": 2379456, + "ts": 6197200091896.047, "dur": 2.401, + "args": { + "External id": 38130,"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": 2338707, "tid": 2379456, + "ts": 6197200091896.559, "dur": 1.806, + "args": { + "External id": 38131,"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": 2338707, "tid": 2379456, + "ts": 6197200091903.999, "dur": 418.727, + "args": { + "External id": 38132,"Record function id": 0, "Sequence number": 480153, "Fwd thread id": 1, "Ev Idx": 6387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197200091905.290, "dur": 379.351, + "args": { + "External id": 38133,"Sequence number": 480153, "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": 2338707, "tid": 2379456, "ts": 6197200091905.290, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200091939.516, "dur": 1.899, + "args": { + "External id": 38134,"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": 2338707, "tid": 2379456, + "ts": 6197200091940.183, "dur": 1.105, + "args": { + "External id": 38135,"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": 2338707, "tid": 2379456, + "ts": 6197200091958.201, "dur": 3.965, + "args": { + "External id": 38136,"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": 2338707, "tid": 2379456, + "ts": 6197200091971.439, "dur": 1.875, + "args": { + "External id": 38137,"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": 2338707, "tid": 2379456, + "ts": 6197200092176.312, "dur": 2.838, + "args": { + "External id": 38138,"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": 2338707, "tid": 2379456, + "ts": 6197200092183.815, "dur": 39.314, + "args": { + "External id": 38139,"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": 2338707, "tid": 2379456, + "ts": 6197200092195.532, "dur": 1.129, + "args": { + "External id": 38140,"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": 2338707, "tid": 2379456, + "ts": 6197200092229.061, "dur": 32.537, + "args": { + "External id": 38141,"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": 2338707, "tid": 2379456, + "ts": 6197200092230.973, "dur": 30.389, + "args": { + "External id": 38142,"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": 2338707, "tid": 2379456, + "ts": 6197200092237.341, "dur": 4.555, + "args": { + "External id": 38143,"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": 2338707, "tid": 2379456, + "ts": 6197200092243.599, "dur": 17.204, + "args": { + "External id": 38144,"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": 2338707, "tid": 2379456, + "ts": 6197200092266.081, "dur": 2.528, + "args": { + "External id": 38145,"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": 2338707, "tid": 2379456, + "ts": 6197200092267.126, "dur": 1.373, + "args": { + "External id": 38146,"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": 2338707, "tid": 2379456, + "ts": 6197200092275.593, "dur": 2.166, + "args": { + "External id": 38147,"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": 2338707, "tid": 2379456, + "ts": 6197200092276.603, "dur": 1.026, + "args": { + "External id": 38148,"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": 2338707, "tid": 2379456, + "ts": 6197200092297.670, "dur": 17.982, + "args": { + "External id": 38149,"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": 2338707, "tid": 2379456, + "ts": 6197200092335.731, "dur": 9.490, + "args": { + "External id": 38150,"Record function id": 0, "Ev Idx": 6405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200092338.395, "dur": 6.198, + "args": { + "External id": 38151,"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": 2338707, "tid": 2379456, + "ts": 6197200092340.363, "dur": 3.403, + "args": { + "External id": 38152,"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": 2338707, "tid": 2379456, + "ts": 6197200092341.311, "dur": 2.277, + "args": { + "External id": 38153,"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": 2338707, "tid": 2379456, + "ts": 6197200092348.842, "dur": 6.775, + "args": { + "External id": 38154,"Record function id": 0, "Sequence number": 480152, "Fwd thread id": 1, "Ev Idx": 6409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200092350.496, "dur": 1.376, + "args": { + "External id": 38155,"Sequence number": 480152, "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": 2338707, "tid": 2379456, "ts": 6197200092350.496, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SwiGLULinearFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197200092359.145, "dur": 432.026, + "args": { + "External id": 38156,"Record function id": 0, "Sequence number": 480151, "Fwd thread id": 1, "Ev Idx": 6411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197200092360.822, "dur": 417.418, + "args": { + "External id": 38157,"Sequence number": 480151, "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": 2338707, "tid": 2379456, "ts": 6197200092360.822, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200092393.306, "dur": 7.933, + "args": { + "External id": 38158,"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": 2338707, "tid": 2379456, + "ts": 6197200092397.801, "dur": 3.140, + "args": { + "External id": 38159,"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": 2338707, "tid": 2379456, + "ts": 6197200092404.800, "dur": 5.067, + "args": { + "External id": 38160,"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": 2338707, "tid": 2379456, + "ts": 6197200092406.212, "dur": 3.033, + "args": { + "External id": 38161,"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": 2338707, "tid": 2379456, + "ts": 6197200092408.166, "dur": 0.882, + "args": { + "External id": 38162,"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": 2338707, "tid": 2379456, + "ts": 6197200092415.203, "dur": 89.739, + "args": { + "External id": 38163,"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": 2338707, "tid": 2379456, + "ts": 6197200092415.958, "dur": 4.558, + "args": { + "External id": 38164,"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": 2338707, "tid": 2379456, + "ts": 6197200092416.559, "dur": 3.447, + "args": { + "External id": 38165,"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": 2338707, "tid": 2379456, + "ts": 6197200092417.559, "dur": 2.287, + "args": { + "External id": 38166,"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": 2338707, "tid": 2379456, + "ts": 6197200092421.672, "dur": 82.885, + "args": { + "External id": 38167,"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": 2338707, "tid": 2379456, + "ts": 6197200092423.150, "dur": 80.739, + "args": { + "External id": 38168,"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": 2338707, "tid": 2379456, + "ts": 6197200092508.798, "dur": 5.784, + "args": { + "External id": 38169,"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": 2338707, "tid": 2379456, + "ts": 6197200092512.794, "dur": 1.629, + "args": { + "External id": 38170,"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": 2338707, "tid": 2379456, + "ts": 6197200092546.689, "dur": 3.902, + "args": { + "External id": 38171,"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": 2338707, "tid": 2379456, + "ts": 6197200092552.215, "dur": 2.286, + "args": { + "External id": 38172,"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": 2338707, "tid": 2379456, + "ts": 6197200092555.994, "dur": 2.232, + "args": { + "External id": 38173,"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": 2338707, "tid": 2379456, + "ts": 6197200092588.971, "dur": 2.546, + "args": { + "External id": 38174,"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": 2338707, "tid": 2379456, + "ts": 6197200092589.972, "dur": 1.382, + "args": { + "External id": 38175,"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": 2338707, "tid": 2379456, + "ts": 6197200092616.019, "dur": 140.761, + "args": { + "External id": 38176,"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": 2338707, "tid": 2379456, + "ts": 6197200092622.414, "dur": 5.625, + "args": { + "External id": 38177,"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": 2338707, "tid": 2379456, + "ts": 6197200092626.365, "dur": 0.956, + "args": { + "External id": 38178,"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": 2338707, "tid": 2379456, + "ts": 6197200092629.396, "dur": 5.355, + "args": { + "External id": 38179,"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": 2338707, "tid": 2379456, + "ts": 6197200092633.270, "dur": 0.744, + "args": { + "External id": 38180,"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": 2338707, "tid": 2379456, + "ts": 6197200092635.935, "dur": 2.822, + "args": { + "External id": 38181,"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": 2338707, "tid": 2379456, + "ts": 6197200092637.826, "dur": 0.570, + "args": { + "External id": 38182,"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": 2338707, "tid": 2379456, + "ts": 6197200092639.380, "dur": 3.283, + "args": { + "External id": 38183,"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": 2338707, "tid": 2379456, + "ts": 6197200092641.113, "dur": 0.982, + "args": { + "External id": 38184,"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": 2338707, "tid": 2379456, + "ts": 6197200092646.428, "dur": 3.922, + "args": { + "External id": 38185,"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": 2338707, "tid": 2379456, + "ts": 6197200092649.353, "dur": 0.664, + "args": { + "External id": 38186,"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": 2338707, "tid": 2379456, + "ts": 6197200092653.895, "dur": 4.923, + "args": { + "External id": 38187,"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": 2338707, "tid": 2379456, + "ts": 6197200092656.890, "dur": 1.742, + "args": { + "External id": 38188,"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": 2338707, "tid": 2379456, + "ts": 6197200092659.705, "dur": 2.527, + "args": { + "External id": 38189,"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": 2338707, "tid": 2379456, + "ts": 6197200092661.426, "dur": 0.537, + "args": { + "External id": 38190,"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": 2338707, "tid": 2379456, + "ts": 6197200092663.110, "dur": 3.311, + "args": { + "External id": 38191,"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": 2338707, "tid": 2379456, + "ts": 6197200092663.867, "dur": 2.450, + "args": { + "External id": 38192,"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": 2338707, "tid": 2379456, + "ts": 6197200092667.554, "dur": 74.489, + "args": { + "External id": 38193,"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": 2338707, "tid": 2379456, + "ts": 6197200092745.439, "dur": 1.820, + "args": { + "External id": 38194,"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": 2338707, "tid": 2379456, + "ts": 6197200092748.370, "dur": 3.360, + "args": { + "External id": 38195,"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": 2338707, "tid": 2379456, + "ts": 6197200092750.369, "dur": 0.801, + "args": { + "External id": 38196,"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": 2338707, "tid": 2379456, + "ts": 6197200092754.759, "dur": 0.976, + "args": { + "External id": 38197,"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": 2338707, "tid": 2379456, + "ts": 6197200092803.034, "dur": 9.505, + "args": { + "External id": 38198,"Record function id": 0, "Ev Idx": 6453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200092805.302, "dur": 6.484, + "args": { + "External id": 38199,"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": 2338707, "tid": 2379456, + "ts": 6197200092807.495, "dur": 3.457, + "args": { + "External id": 38200,"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": 2338707, "tid": 2379456, + "ts": 6197200092808.469, "dur": 2.359, + "args": { + "External id": 38201,"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": 2338707, "tid": 2379456, + "ts": 6197200092816.217, "dur": 7.178, + "args": { + "External id": 38202,"Record function id": 0, "Sequence number": 480150, "Fwd thread id": 1, "Ev Idx": 6457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200092817.161, "dur": 3.732, + "args": { + "External id": 38203,"Sequence number": 480150, "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": 2338707, "tid": 2379456, "ts": 6197200092817.161, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200092818.938, "dur": 1.686, + "args": { + "External id": 38204,"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": 2338707, "tid": 2379456, + "ts": 6197200092819.709, "dur": 0.766, + "args": { + "External id": 38205,"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": 2338707, "tid": 2379456, + "ts": 6197200092826.765, "dur": 114.299, + "args": { + "External id": 38206,"Record function id": 0, "Sequence number": 480149, "Fwd thread id": 1, "Ev Idx": 6461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200092827.656, "dur": 107.342, + "args": { + "External id": 38207,"Sequence number": 480149, "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": 2338707, "tid": 2379456, "ts": 6197200092827.656, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197200092830.996, "dur": 6.637, + "args": { + "External id": 38208,"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": 2338707, "tid": 2379456, + "ts": 6197200092832.235, "dur": 4.737, + "args": { + "External id": 38209,"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": 2338707, "tid": 2379456, + "ts": 6197200092835.952, "dur": 0.844, + "args": { + "External id": 38210,"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": 2338707, "tid": 2379456, + "ts": 6197200092839.024, "dur": 48.629, + "args": { + "External id": 38211,"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": 2338707, "tid": 2379456, + "ts": 6197200092889.042, "dur": 4.028, + "args": { + "External id": 38212,"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": 2338707, "tid": 2379456, + "ts": 6197200092889.573, "dur": 2.759, + "args": { + "External id": 38213,"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": 2338707, "tid": 2379456, + "ts": 6197200092891.111, "dur": 1.051, + "args": { + "External id": 38214,"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": 2338707, "tid": 2379456, + "ts": 6197200092894.780, "dur": 5.431, + "args": { + "External id": 38215,"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": 2338707, "tid": 2379456, + "ts": 6197200092898.125, "dur": 1.566, + "args": { + "External id": 38216,"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": 2338707, "tid": 2379456, + "ts": 6197200092898.971, "dur": 0.654, + "args": { + "External id": 38217,"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": 2338707, "tid": 2379456, + "ts": 6197200092900.603, "dur": 33.670, + "args": { + "External id": 38218,"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": 2338707, "tid": 2379456, + "ts": 6197200092945.689, "dur": 6.574, + "args": { + "External id": 38219,"Record function id": 0, "Sequence number": 480148, "Fwd thread id": 1, "Ev Idx": 6474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200092946.813, "dur": 4.022, + "args": { + "External id": 38220,"Sequence number": 480148, "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": 2338707, "tid": 2379456, "ts": 6197200092946.813, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200092948.463, "dur": 2.202, + "args": { + "External id": 38221,"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": 2338707, "tid": 2379456, + "ts": 6197200092949.369, "dur": 1.150, + "args": { + "External id": 38222,"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": 2338707, "tid": 2379456, + "ts": 6197200092955.762, "dur": 9.444, + "args": { + "External id": 38223,"Record function id": 0, "Sequence number": 480147, "Fwd thread id": 1, "Ev Idx": 6478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200092956.798, "dur": 6.457, + "args": { + "External id": 38224,"Sequence number": 480147, "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": 2338707, "tid": 2379456, "ts": 6197200092956.798, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197200092957.534, "dur": 5.535, + "args": { + "External id": 38225,"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": 2338707, "tid": 2379456, + "ts": 6197200092960.308, "dur": 2.276, + "args": { + "External id": 38226,"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": 2338707, "tid": 2379456, + "ts": 6197200092961.751, "dur": 0.717, + "args": { + "External id": 38227,"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": 2338707, "tid": 2379456, + "ts": 6197200092969.012, "dur": 5.629, + "args": { + "External id": 38228,"Record function id": 0, "Ev Idx": 6483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200092970.809, "dur": 3.348, + "args": { + "External id": 38229,"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": 2338707, "tid": 2379456, + "ts": 6197200092971.885, "dur": 2.000, + "args": { + "External id": 38230,"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": 2338707, "tid": 2379456, + "ts": 6197200092972.293, "dur": 1.494, + "args": { + "External id": 38231,"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": 2338707, "tid": 2379456, + "ts": 6197200092978.149, "dur": 5.081, + "args": { + "External id": 38232,"Record function id": 0, "Sequence number": 480146, "Fwd thread id": 1, "Ev Idx": 6487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200092979.155, "dur": 2.310, + "args": { + "External id": 38233,"Sequence number": 480146, "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": 2338707, "tid": 2379456, "ts": 6197200092979.155, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200092980.129, "dur": 1.181, + "args": { + "External id": 38234,"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": 2338707, "tid": 2379456, + "ts": 6197200092980.602, "dur": 0.596, + "args": { + "External id": 38235,"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": 2338707, "tid": 2379456, + "ts": 6197200092986.413, "dur": 133.388, + "args": { + "External id": 38236,"Record function id": 0, "Sequence number": 480145, "Fwd thread id": 1, "Ev Idx": 6491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200092989.223, "dur": 120.503, + "args": { + "External id": 38237,"Sequence number": 480145, "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": 2338707, "tid": 2379456, "ts": 6197200092989.223, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197200092992.060, "dur": 3.179, + "args": { + "External id": 38238,"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": 2338707, "tid": 2379456, + "ts": 6197200092992.654, "dur": 2.119, + "args": { + "External id": 38239,"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": 2338707, "tid": 2379456, + "ts": 6197200092993.955, "dur": 0.718, + "args": { + "External id": 38240,"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": 2338707, "tid": 2379456, + "ts": 6197200092995.802, "dur": 32.530, + "args": { + "External id": 38241,"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": 2338707, "tid": 2379456, + "ts": 6197200093029.475, "dur": 5.959, + "args": { + "External id": 38242,"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": 2338707, "tid": 2379456, + "ts": 6197200093030.077, "dur": 4.822, + "args": { + "External id": 38243,"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": 2338707, "tid": 2379456, + "ts": 6197200093033.482, "dur": 1.284, + "args": { + "External id": 38244,"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": 2338707, "tid": 2379456, + "ts": 6197200093036.619, "dur": 4.147, + "args": { + "External id": 38245,"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": 2338707, "tid": 2379456, + "ts": 6197200093037.820, "dur": 2.319, + "args": { + "External id": 38246,"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": 2338707, "tid": 2379456, + "ts": 6197200093039.285, "dur": 0.763, + "args": { + "External id": 38247,"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": 2338707, "tid": 2379456, + "ts": 6197200093041.311, "dur": 67.159, + "args": { + "External id": 38248,"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": 2338707, "tid": 2379456, + "ts": 6197200093127.313, "dur": 31.860, + "args": { + "External id": 38249,"Record function id": 0, "Sequence number": 480144, "Fwd thread id": 1, "Ev Idx": 6504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200093128.453, "dur": 5.213, + "args": { + "External id": 38250,"Sequence number": 480144, "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": 2338707, "tid": 2379456, "ts": 6197200093128.453, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200093130.688, "dur": 2.838, + "args": { + "External id": 38251,"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": 2338707, "tid": 2379456, + "ts": 6197200093131.672, "dur": 1.750, + "args": { + "External id": 38252,"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": 2338707, "tid": 2379456, + "ts": 6197200093136.481, "dur": 19.700, + "args": { + "External id": 38253,"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": 2338707, "tid": 2379456, + "ts": 6197200093163.301, "dur": 10.071, + "args": { + "External id": 38254,"Record function id": 0, "Sequence number": 480143, "Fwd thread id": 1, "Ev Idx": 6509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200093164.206, "dur": 7.353, + "args": { + "External id": 38255,"Sequence number": 480143, "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": 2338707, "tid": 2379456, "ts": 6197200093164.206, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197200093167.494, "dur": 3.879, + "args": { + "External id": 38256,"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": 2338707, "tid": 2379456, + "ts": 6197200093168.147, "dur": 2.659, + "args": { + "External id": 38257,"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": 2338707, "tid": 2379456, + "ts": 6197200093169.899, "dur": 0.767, + "args": { + "External id": 38258,"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": 2338707, "tid": 2379456, + "ts": 6197200093177.406, "dur": 6.682, + "args": { + "External id": 38259,"Record function id": 0, "Ev Idx": 6514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200093178.846, "dur": 4.698, + "args": { + "External id": 38260,"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": 2338707, "tid": 2379456, + "ts": 6197200093180.162, "dur": 2.892, + "args": { + "External id": 38261,"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": 2338707, "tid": 2379456, + "ts": 6197200093180.863, "dur": 2.043, + "args": { + "External id": 38262,"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": 2338707, "tid": 2379456, + "ts": 6197200093188.362, "dur": 398.068, + "args": { + "External id": 38263,"Record function id": 0, "Sequence number": 480142, "Fwd thread id": 1, "Ev Idx": 6518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197200093190.010, "dur": 364.246, + "args": { + "External id": 38264,"Sequence number": 480142, "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": 2338707, "tid": 2379456, "ts": 6197200093190.010, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338707, "tid": 2379456, + "ts": 6197200093213.620, "dur": 32.982, + "args": { + "External id": 38265,"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": 2338707, "tid": 2379456, + "ts": 6197200093215.088, "dur": 31.232, + "args": { + "External id": 38266,"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": 2338707, "tid": 2379456, + "ts": 6197200093217.816, "dur": 5.997, + "args": { + "External id": 38267,"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": 2338707, "tid": 2379456, + "ts": 6197200093220.397, "dur": 2.874, + "args": { + "External id": 38268,"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": 2338707, "tid": 2379456, + "ts": 6197200093225.049, "dur": 20.746, + "args": { + "External id": 38269,"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": 2338707, "tid": 2379456, + "ts": 6197200093258.112, "dur": 5.061, + "args": { + "External id": 38270,"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": 2338707, "tid": 2379456, + "ts": 6197200093261.507, "dur": 1.484, + "args": { + "External id": 38271,"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": 2338707, "tid": 2379456, + "ts": 6197200093266.876, "dur": 1.893, + "args": { + "External id": 38272,"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": 2338707, "tid": 2379456, + "ts": 6197200093267.673, "dur": 0.959, + "args": { + "External id": 38273,"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": 2338707, "tid": 2379456, + "ts": 6197200093280.438, "dur": 2.827, + "args": { + "External id": 38274,"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": 2338707, "tid": 2379456, + "ts": 6197200093295.672, "dur": 2.222, + "args": { + "External id": 38275,"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": 2338707, "tid": 2379456, + "ts": 6197200093456.220, "dur": 3.017, + "args": { + "External id": 38276,"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": 2338707, "tid": 2379456, + "ts": 6197200093463.182, "dur": 29.305, + "args": { + "External id": 38277,"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": 2338707, "tid": 2379456, + "ts": 6197200093471.494, "dur": 1.200, + "args": { + "External id": 38278,"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": 2338707, "tid": 2379456, + "ts": 6197200093498.044, "dur": 27.405, + "args": { + "External id": 38279,"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": 2338707, "tid": 2379456, + "ts": 6197200093499.898, "dur": 25.361, + "args": { + "External id": 38280,"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": 2338707, "tid": 2379456, + "ts": 6197200093503.497, "dur": 3.968, + "args": { + "External id": 38281,"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": 2338707, "tid": 2379456, + "ts": 6197200093510.914, "dur": 13.759, + "args": { + "External id": 38282,"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": 2338707, "tid": 2379456, + "ts": 6197200093529.929, "dur": 2.546, + "args": { + "External id": 38283,"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": 2338707, "tid": 2379456, + "ts": 6197200093531.099, "dur": 1.236, + "args": { + "External id": 38284,"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": 2338707, "tid": 2379456, + "ts": 6197200093539.552, "dur": 2.587, + "args": { + "External id": 38285,"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": 2338707, "tid": 2379456, + "ts": 6197200093540.860, "dur": 1.170, + "args": { + "External id": 38286,"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": 2338707, "tid": 2379456, + "ts": 6197200093544.480, "dur": 1.938, + "args": { + "External id": 38287,"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": 2338707, "tid": 2379456, + "ts": 6197200093545.422, "dur": 0.905, + "args": { + "External id": 38288,"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": 2338707, "tid": 2379456, + "ts": 6197200093570.004, "dur": 14.896, + "args": { + "External id": 38289,"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": 2338707, "tid": 2379456, + "ts": 6197200093595.128, "dur": 7.124, + "args": { + "External id": 38290,"Record function id": 0, "Ev Idx": 6545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200093596.846, "dur": 4.858, + "args": { + "External id": 38291,"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": 2338707, "tid": 2379456, + "ts": 6197200093598.638, "dur": 2.185, + "args": { + "External id": 38292,"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": 2338707, "tid": 2379456, + "ts": 6197200093599.480, "dur": 1.213, + "args": { + "External id": 38293,"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": 2338707, "tid": 2379456, + "ts": 6197200093606.220, "dur": 7.398, + "args": { + "External id": 38294,"Record function id": 0, "Sequence number": 480141, "Fwd thread id": 1, "Ev Idx": 6549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200093607.179, "dur": 3.771, + "args": { + "External id": 38295,"Sequence number": 480141, "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": 2338707, "tid": 2379456, "ts": 6197200093607.179, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200093608.702, "dur": 2.076, + "args": { + "External id": 38296,"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": 2338707, "tid": 2379456, + "ts": 6197200093609.597, "dur": 1.073, + "args": { + "External id": 38297,"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": 2338707, "tid": 2379456, + "ts": 6197200093616.873, "dur": 161.585, + "args": { + "External id": 38298,"Record function id": 0, "Sequence number": 480140, "Fwd thread id": 1, "Ev Idx": 6553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200093617.727, "dur": 151.844, + "args": { + "External id": 38299,"Sequence number": 480140, "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": 2338707, "tid": 2379456, "ts": 6197200093617.727, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197200093623.664, "dur": 4.423, + "args": { + "External id": 38300,"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": 2338707, "tid": 2379456, + "ts": 6197200093624.699, "dur": 2.815, + "args": { + "External id": 38301,"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": 2338707, "tid": 2379456, + "ts": 6197200093626.402, "dur": 0.945, + "args": { + "External id": 38302,"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": 2338707, "tid": 2379456, + "ts": 6197200093629.258, "dur": 62.831, + "args": { + "External id": 38303,"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": 2338707, "tid": 2379456, + "ts": 6197200093693.249, "dur": 5.440, + "args": { + "External id": 38304,"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": 2338707, "tid": 2379456, + "ts": 6197200093694.018, "dur": 4.118, + "args": { + "External id": 38305,"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": 2338707, "tid": 2379456, + "ts": 6197200093695.697, "dur": 2.307, + "args": { + "External id": 38306,"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": 2338707, "tid": 2379456, + "ts": 6197200093720.490, "dur": 5.431, + "args": { + "External id": 38307,"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": 2338707, "tid": 2379456, + "ts": 6197200093722.561, "dur": 2.638, + "args": { + "External id": 38308,"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": 2338707, "tid": 2379456, + "ts": 6197200093724.176, "dur": 0.778, + "args": { + "External id": 38309,"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": 2338707, "tid": 2379456, + "ts": 6197200093726.556, "dur": 42.057, + "args": { + "External id": 38310,"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": 2338707, "tid": 2379456, + "ts": 6197200093785.023, "dur": 8.170, + "args": { + "External id": 38311,"Record function id": 0, "Sequence number": 480139, "Fwd thread id": 1, "Ev Idx": 6566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200093786.123, "dur": 4.365, + "args": { + "External id": 38312,"Sequence number": 480139, "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": 2338707, "tid": 2379456, "ts": 6197200093786.123, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200093787.840, "dur": 2.514, + "args": { + "External id": 38313,"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": 2338707, "tid": 2379456, + "ts": 6197200093788.780, "dur": 1.469, + "args": { + "External id": 38314,"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": 2338707, "tid": 2379456, + "ts": 6197200093796.788, "dur": 9.856, + "args": { + "External id": 38315,"Record function id": 0, "Sequence number": 480138, "Fwd thread id": 1, "Ev Idx": 6570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200093797.687, "dur": 6.665, + "args": { + "External id": 38316,"Sequence number": 480138, "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": 2338707, "tid": 2379456, "ts": 6197200093797.687, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197200093798.442, "dur": 5.689, + "args": { + "External id": 38317,"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": 2338707, "tid": 2379456, + "ts": 6197200093799.240, "dur": 4.390, + "args": { + "External id": 38318,"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": 2338707, "tid": 2379456, + "ts": 6197200093802.914, "dur": 0.580, + "args": { + "External id": 38319,"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": 2338707, "tid": 2379456, + "ts": 6197200093810.770, "dur": 5.873, + "args": { + "External id": 38320,"Record function id": 0, "Ev Idx": 6575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200093812.075, "dur": 4.025, + "args": { + "External id": 38321,"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": 2338707, "tid": 2379456, + "ts": 6197200093813.418, "dur": 2.366, + "args": { + "External id": 38322,"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": 2338707, "tid": 2379456, + "ts": 6197200093814.087, "dur": 1.570, + "args": { + "External id": 38323,"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": 2338707, "tid": 2379456, + "ts": 6197200093820.130, "dur": 7.186, + "args": { + "External id": 38324,"Record function id": 0, "Sequence number": 480137, "Fwd thread id": 1, "Ev Idx": 6579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200093820.910, "dur": 4.210, + "args": { + "External id": 38325,"Sequence number": 480137, "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": 2338707, "tid": 2379456, "ts": 6197200093820.910, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200093822.303, "dur": 2.654, + "args": { + "External id": 38326,"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": 2338707, "tid": 2379456, + "ts": 6197200093823.638, "dur": 1.188, + "args": { + "External id": 38327,"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": 2338707, "tid": 2379456, + "ts": 6197200093831.893, "dur": 393.554, + "args": { + "External id": 38328,"Record function id": 0, "Sequence number": 480136, "Fwd thread id": 1, "Ev Idx": 6583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFuncBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197200093833.350, "dur": 370.057, + "args": { + "External id": 38329,"Sequence number": 480136, "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": 2338707, "tid": 2379456, "ts": 6197200093833.350, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338707, "tid": 2379456, + "ts": 6197200093851.227, "dur": 7.777, + "args": { + "External id": 38330,"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": 2338707, "tid": 2379456, + "ts": 6197200093854.223, "dur": 4.305, + "args": { + "External id": 38331,"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": 2338707, "tid": 2379456, + "ts": 6197200093861.154, "dur": 3.357, + "args": { + "External id": 38332,"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": 2338707, "tid": 2379456, + "ts": 6197200093862.936, "dur": 1.411, + "args": { + "External id": 38333,"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": 2338707, "tid": 2379456, + "ts": 6197200093865.905, "dur": 3.744, + "args": { + "External id": 38334,"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": 2338707, "tid": 2379456, + "ts": 6197200093867.658, "dur": 1.813, + "args": { + "External id": 38335,"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": 2338707, "tid": 2379456, + "ts": 6197200093893.882, "dur": 283.134, + "args": { + "External id": 38336,"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": 2338707, "tid": 2379456, + "ts": 6197200093979.536, "dur": 4.022, + "args": { + "External id": 38337,"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": 2338707, "tid": 2379456, + "ts": 6197200093985.291, "dur": 2.739, + "args": { + "External id": 38338,"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": 2338707, "tid": 2379456, + "ts": 6197200093989.104, "dur": 2.008, + "args": { + "External id": 38339,"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": 2338707, "tid": 2379456, + "ts": 6197200093992.216, "dur": 2.267, + "args": { + "External id": 38340,"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": 2338707, "tid": 2379456, + "ts": 6197200094038.052, "dur": 2.484, + "args": { + "External id": 38341,"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": 2338707, "tid": 2379456, + "ts": 6197200094039.074, "dur": 1.341, + "args": { + "External id": 38342,"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": 2338707, "tid": 2379456, + "ts": 6197200094044.769, "dur": 65.582, + "args": { + "External id": 38343,"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": 2338707, "tid": 2379456, + "ts": 6197200094051.204, "dur": 1.159, + "args": { + "External id": 38344,"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": 2338707, "tid": 2379456, + "ts": 6197200094113.269, "dur": 2.185, + "args": { + "External id": 38345,"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": 2338707, "tid": 2379456, + "ts": 6197200094114.400, "dur": 0.985, + "args": { + "External id": 38346,"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": 2338707, "tid": 2379456, + "ts": 6197200094116.189, "dur": 15.276, + "args": { + "External id": 38347,"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": 2338707, "tid": 2379456, + "ts": 6197200094119.344, "dur": 0.767, + "args": { + "External id": 38348,"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": 2338707, "tid": 2379456, + "ts": 6197200094190.400, "dur": 3.978, + "args": { + "External id": 38349,"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": 2338707, "tid": 2379456, + "ts": 6197200094197.500, "dur": 0.712, + "args": { + "External id": 38350,"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": 2338707, "tid": 2379456, + "ts": 6197200094200.024, "dur": 0.535, + "args": { + "External id": 38351,"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": 2338707, "tid": 2379456, + "ts": 6197200094236.044, "dur": 219.843, + "args": { + "External id": 38352,"Record function id": 0, "Sequence number": 480135, "Fwd thread id": 1, "Ev Idx": 6607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197200094237.749, "dur": 211.813, + "args": { + "External id": 38353,"Sequence number": 480135, "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": 2338707, "tid": 2379456, "ts": 6197200094237.749, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338707, "tid": 2379456, + "ts": 6197200094257.201, "dur": 43.464, + "args": { + "External id": 38354,"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": 2338707, "tid": 2379456, + "ts": 6197200094260.992, "dur": 4.327, + "args": { + "External id": 38355,"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": 2338707, "tid": 2379456, + "ts": 6197200094266.645, "dur": 33.340, + "args": { + "External id": 38356,"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": 2338707, "tid": 2379456, + "ts": 6197200094310.881, "dur": 5.425, + "args": { + "External id": 38357,"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": 2338707, "tid": 2379456, + "ts": 6197200094313.207, "dur": 2.731, + "args": { + "External id": 38358,"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": 2338707, "tid": 2379456, + "ts": 6197200094463.228, "dur": 162.353, + "args": { + "External id": 38359,"Record function id": 0, "Sequence number": 480134, "Fwd thread id": 1, "Ev Idx": 6614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197200094464.676, "dur": 154.121, + "args": { + "External id": 38360,"Sequence number": 480134, "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": 2338707, "tid": 2379456, "ts": 6197200094464.676, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338707, "tid": 2379456, + "ts": 6197200094476.264, "dur": 48.775, + "args": { + "External id": 38361,"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": 2338707, "tid": 2379456, + "ts": 6197200094479.136, "dur": 3.400, + "args": { + "External id": 38362,"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": 2338707, "tid": 2379456, + "ts": 6197200094485.745, "dur": 38.805, + "args": { + "External id": 38363,"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": 2338707, "tid": 2379456, + "ts": 6197200094532.170, "dur": 5.609, + "args": { + "External id": 38364,"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": 2338707, "tid": 2379456, + "ts": 6197200094534.844, "dur": 2.639, + "args": { + "External id": 38365,"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": 2338707, "tid": 2379456, + "ts": 6197200094631.505, "dur": 11.983, + "args": { + "External id": 38366,"Record function id": 0, "Sequence number": 480133, "Fwd thread id": 1, "Ev Idx": 6621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200094632.762, "dur": 8.187, + "args": { + "External id": 38367,"Sequence number": 480133, "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": 2338707, "tid": 2379456, "ts": 6197200094632.762, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200094635.271, "dur": 5.417, + "args": { + "External id": 38368,"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": 2338707, "tid": 2379456, + "ts": 6197200094636.638, "dur": 3.893, + "args": { + "External id": 38369,"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": 2338707, "tid": 2379456, + "ts": 6197200094647.161, "dur": 6.347, + "args": { + "External id": 38370,"Record function id": 0, "Sequence number": 480132, "Fwd thread id": 1, "Ev Idx": 6625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200094648.114, "dur": 3.396, + "args": { + "External id": 38371,"Sequence number": 480132, "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": 2338707, "tid": 2379456, "ts": 6197200094648.114, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200094649.288, "dur": 2.065, + "args": { + "External id": 38372,"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": 2338707, "tid": 2379456, + "ts": 6197200094650.225, "dur": 1.023, + "args": { + "External id": 38373,"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": 2338707, "tid": 2379456, + "ts": 6197200094656.994, "dur": 10.180, + "args": { + "External id": 38374,"Record function id": 0, "Sequence number": 480131, "Fwd thread id": 1, "Ev Idx": 6629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200094657.822, "dur": 6.446, + "args": { + "External id": 38375,"Sequence number": 480131, "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": 2338707, "tid": 2379456, "ts": 6197200094657.822, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200094659.799, "dur": 4.342, + "args": { + "External id": 38376,"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": 2338707, "tid": 2379456, + "ts": 6197200094663.130, "dur": 0.906, + "args": { + "External id": 38377,"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": 2338707, "tid": 2379456, + "ts": 6197200094670.908, "dur": 6.133, + "args": { + "External id": 38378,"Record function id": 0, "Sequence number": 480130, "Fwd thread id": 1, "Ev Idx": 6633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200094672.072, "dur": 3.222, + "args": { + "External id": 38379,"Sequence number": 480130, "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": 2338707, "tid": 2379456, "ts": 6197200094672.072, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200094673.367, "dur": 1.779, + "args": { + "External id": 38380,"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": 2338707, "tid": 2379456, + "ts": 6197200094674.019, "dur": 0.969, + "args": { + "External id": 38381,"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": 2338707, "tid": 2379456, + "ts": 6197200094681.011, "dur": 187.543, + "args": { + "External id": 38382,"Record function id": 0, "Sequence number": 480129, "Fwd thread id": 1, "Ev Idx": 6637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200094681.861, "dur": 176.659, + "args": { + "External id": 38383,"Sequence number": 480129, "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": 2338707, "tid": 2379456, "ts": 6197200094681.861, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197200094685.499, "dur": 8.562, + "args": { + "External id": 38384,"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": 2338707, "tid": 2379456, + "ts": 6197200094689.327, "dur": 3.929, + "args": { + "External id": 38385,"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": 2338707, "tid": 2379456, + "ts": 6197200094691.392, "dur": 1.547, + "args": { + "External id": 38386,"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": 2338707, "tid": 2379456, + "ts": 6197200094695.817, "dur": 92.825, + "args": { + "External id": 38387,"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": 2338707, "tid": 2379456, + "ts": 6197200094790.815, "dur": 10.710, + "args": { + "External id": 38388,"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": 2338707, "tid": 2379456, + "ts": 6197200094791.901, "dur": 8.631, + "args": { + "External id": 38389,"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": 2338707, "tid": 2379456, + "ts": 6197200094797.825, "dur": 2.518, + "args": { + "External id": 38390,"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": 2338707, "tid": 2379456, + "ts": 6197200094805.818, "dur": 3.647, + "args": { + "External id": 38391,"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": 2338707, "tid": 2379456, + "ts": 6197200094806.880, "dur": 1.995, + "args": { + "External id": 38392,"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": 2338707, "tid": 2379456, + "ts": 6197200094808.036, "dur": 0.707, + "args": { + "External id": 38393,"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": 2338707, "tid": 2379456, + "ts": 6197200094810.135, "dur": 47.399, + "args": { + "External id": 38394,"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": 2338707, "tid": 2379456, + "ts": 6197200094876.136, "dur": 8.307, + "args": { + "External id": 38395,"Record function id": 0, "Sequence number": 480128, "Fwd thread id": 1, "Ev Idx": 6650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200094877.102, "dur": 5.216, + "args": { + "External id": 38396,"Sequence number": 480128, "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": 2338707, "tid": 2379456, "ts": 6197200094877.102, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200094879.178, "dur": 3.003, + "args": { + "External id": 38397,"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": 2338707, "tid": 2379456, + "ts": 6197200094880.418, "dur": 1.661, + "args": { + "External id": 38398,"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": 2338707, "tid": 2379456, + "ts": 6197200094887.832, "dur": 59.093, + "args": { + "External id": 38399,"Record function id": 0, "Sequence number": 480127, "Fwd thread id": 1, "Ev Idx": 6654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200094888.691, "dur": 56.017, + "args": { + "External id": 38400,"Sequence number": 480127, "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": 2338707, "tid": 2379456, "ts": 6197200094888.691, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197200094936.764, "dur": 7.732, + "args": { + "External id": 38401,"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": 2338707, "tid": 2379456, + "ts": 6197200094937.597, "dur": 6.313, + "args": { + "External id": 38402,"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": 2338707, "tid": 2379456, + "ts": 6197200094942.958, "dur": 0.833, + "args": { + "External id": 38403,"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": 2338707, "tid": 2379456, + "ts": 6197200094953.146, "dur": 9.446, + "args": { + "External id": 38404,"Record function id": 0, "Ev Idx": 6659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200094954.556, "dur": 7.290, + "args": { + "External id": 38405,"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": 2338707, "tid": 2379456, + "ts": 6197200094957.263, "dur": 4.189, + "args": { + "External id": 38406,"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": 2338707, "tid": 2379456, + "ts": 6197200094958.379, "dur": 2.964, + "args": { + "External id": 38407,"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": 2338707, "tid": 2379456, + "ts": 6197200094966.021, "dur": 6.042, + "args": { + "External id": 38408,"Record function id": 0, "Sequence number": 480126, "Fwd thread id": 1, "Ev Idx": 6663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200094967.296, "dur": 2.414, + "args": { + "External id": 38409,"Sequence number": 480126, "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": 2338707, "tid": 2379456, "ts": 6197200094967.296, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200094968.266, "dur": 1.283, + "args": { + "External id": 38410,"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": 2338707, "tid": 2379456, + "ts": 6197200094968.628, "dur": 0.802, + "args": { + "External id": 38411,"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": 2338707, "tid": 2379456, + "ts": 6197200094975.432, "dur": 135.712, + "args": { + "External id": 38412,"Record function id": 0, "Sequence number": 480125, "Fwd thread id": 1, "Ev Idx": 6667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200094978.359, "dur": 123.806, + "args": { + "External id": 38413,"Sequence number": 480125, "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": 2338707, "tid": 2379456, "ts": 6197200094978.359, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197200094981.261, "dur": 2.767, + "args": { + "External id": 38414,"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": 2338707, "tid": 2379456, + "ts": 6197200094981.687, "dur": 1.874, + "args": { + "External id": 38415,"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": 2338707, "tid": 2379456, + "ts": 6197200094982.768, "dur": 0.682, + "args": { + "External id": 38416,"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": 2338707, "tid": 2379456, + "ts": 6197200094984.653, "dur": 30.742, + "args": { + "External id": 38417,"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": 2338707, "tid": 2379456, + "ts": 6197200095016.362, "dur": 5.628, + "args": { + "External id": 38418,"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": 2338707, "tid": 2379456, + "ts": 6197200095016.858, "dur": 4.627, + "args": { + "External id": 38419,"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": 2338707, "tid": 2379456, + "ts": 6197200095020.741, "dur": 0.628, + "args": { + "External id": 38420,"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": 2338707, "tid": 2379456, + "ts": 6197200095023.219, "dur": 3.388, + "args": { + "External id": 38421,"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": 2338707, "tid": 2379456, + "ts": 6197200095024.276, "dur": 1.788, + "args": { + "External id": 38422,"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": 2338707, "tid": 2379456, + "ts": 6197200095025.385, "dur": 0.551, + "args": { + "External id": 38423,"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": 2338707, "tid": 2379456, + "ts": 6197200095027.029, "dur": 73.515, + "args": { + "External id": 38424,"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": 2338707, "tid": 2379456, + "ts": 6197200095118.881, "dur": 37.174, + "args": { + "External id": 38425,"Record function id": 0, "Sequence number": 480124, "Fwd thread id": 1, "Ev Idx": 6680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200095120.084, "dur": 5.526, + "args": { + "External id": 38426,"Sequence number": 480124, "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": 2338707, "tid": 2379456, "ts": 6197200095120.084, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200095121.737, "dur": 3.719, + "args": { + "External id": 38427,"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": 2338707, "tid": 2379456, + "ts": 6197200095122.480, "dur": 2.804, + "args": { + "External id": 38428,"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": 2338707, "tid": 2379456, + "ts": 6197200095129.064, "dur": 24.361, + "args": { + "External id": 38429,"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": 2338707, "tid": 2379456, + "ts": 6197200095159.860, "dur": 10.512, + "args": { + "External id": 38430,"Record function id": 0, "Sequence number": 480123, "Fwd thread id": 1, "Ev Idx": 6685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200095163.186, "dur": 5.032, + "args": { + "External id": 38431,"Sequence number": 480123, "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": 2338707, "tid": 2379456, "ts": 6197200095163.186, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197200095163.874, "dur": 4.150, + "args": { + "External id": 38432,"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": 2338707, "tid": 2379456, + "ts": 6197200095164.657, "dur": 2.711, + "args": { + "External id": 38433,"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": 2338707, "tid": 2379456, + "ts": 6197200095166.172, "dur": 1.059, + "args": { + "External id": 38434,"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": 2338707, "tid": 2379456, + "ts": 6197200095174.790, "dur": 6.887, + "args": { + "External id": 38435,"Record function id": 0, "Ev Idx": 6690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200095176.141, "dur": 4.886, + "args": { + "External id": 38436,"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": 2338707, "tid": 2379456, + "ts": 6197200095177.405, "dur": 3.041, + "args": { + "External id": 38437,"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": 2338707, "tid": 2379456, + "ts": 6197200095177.983, "dur": 2.341, + "args": { + "External id": 38438,"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": 2338707, "tid": 2379456, + "ts": 6197200095185.080, "dur": 9.493, + "args": { + "External id": 38439,"Record function id": 0, "Sequence number": 480122, "Fwd thread id": 1, "Ev Idx": 6694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200095186.777, "dur": 5.131, + "args": { + "External id": 38440,"Sequence number": 480122, "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": 2338707, "tid": 2379456, "ts": 6197200095186.777, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200095188.077, "dur": 3.687, + "args": { + "External id": 38441,"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": 2338707, "tid": 2379456, + "ts": 6197200095190.771, "dur": 0.887, + "args": { + "External id": 38442,"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": 2338707, "tid": 2379456, + "ts": 6197200095197.927, "dur": 105.000, + "args": { + "External id": 38443,"Record function id": 0, "Sequence number": 480121, "Fwd thread id": 1, "Ev Idx": 6698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200095198.717, "dur": 95.978, + "args": { + "External id": 38444,"Sequence number": 480121, "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": 2338707, "tid": 2379456, "ts": 6197200095198.717, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197200095201.703, "dur": 2.782, + "args": { + "External id": 38445,"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": 2338707, "tid": 2379456, + "ts": 6197200095202.144, "dur": 1.879, + "args": { + "External id": 38446,"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": 2338707, "tid": 2379456, + "ts": 6197200095203.232, "dur": 0.683, + "args": { + "External id": 38447,"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": 2338707, "tid": 2379456, + "ts": 6197200095205.125, "dur": 41.100, + "args": { + "External id": 38448,"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": 2338707, "tid": 2379456, + "ts": 6197200095249.774, "dur": 3.591, + "args": { + "External id": 38449,"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": 2338707, "tid": 2379456, + "ts": 6197200095250.207, "dur": 2.568, + "args": { + "External id": 38450,"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": 2338707, "tid": 2379456, + "ts": 6197200095251.558, "dur": 1.100, + "args": { + "External id": 38451,"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": 2338707, "tid": 2379456, + "ts": 6197200095254.701, "dur": 3.582, + "args": { + "External id": 38452,"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": 2338707, "tid": 2379456, + "ts": 6197200095255.669, "dur": 1.802, + "args": { + "External id": 38453,"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": 2338707, "tid": 2379456, + "ts": 6197200095256.871, "dur": 0.431, + "args": { + "External id": 38454,"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": 2338707, "tid": 2379456, + "ts": 6197200095260.891, "dur": 33.167, + "args": { + "External id": 38455,"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": 2338707, "tid": 2379456, + "ts": 6197200095308.198, "dur": 25.167, + "args": { + "External id": 38456,"Record function id": 0, "Sequence number": 480120, "Fwd thread id": 1, "Ev Idx": 6711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200095309.131, "dur": 3.364, + "args": { + "External id": 38457,"Sequence number": 480120, "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": 2338707, "tid": 2379456, "ts": 6197200095309.131, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200095310.280, "dur": 2.051, + "args": { + "External id": 38458,"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": 2338707, "tid": 2379456, + "ts": 6197200095311.015, "dur": 1.209, + "args": { + "External id": 38459,"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": 2338707, "tid": 2379456, + "ts": 6197200095315.022, "dur": 16.209, + "args": { + "External id": 38460,"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": 2338707, "tid": 2379456, + "ts": 6197200095337.265, "dur": 7.003, + "args": { + "External id": 38461,"Record function id": 0, "Sequence number": 480119, "Fwd thread id": 1, "Ev Idx": 6716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200095338.097, "dur": 4.100, + "args": { + "External id": 38462,"Sequence number": 480119, "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": 2338707, "tid": 2379456, "ts": 6197200095338.097, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197200095338.625, "dur": 3.381, + "args": { + "External id": 38463,"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": 2338707, "tid": 2379456, + "ts": 6197200095339.155, "dur": 2.329, + "args": { + "External id": 38464,"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": 2338707, "tid": 2379456, + "ts": 6197200095340.817, "dur": 0.545, + "args": { + "External id": 38465,"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": 2338707, "tid": 2379456, + "ts": 6197200095348.412, "dur": 5.229, + "args": { + "External id": 38466,"Record function id": 0, "Ev Idx": 6721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200095349.758, "dur": 3.398, + "args": { + "External id": 38467,"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": 2338707, "tid": 2379456, + "ts": 6197200095350.679, "dur": 1.978, + "args": { + "External id": 38468,"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": 2338707, "tid": 2379456, + "ts": 6197200095351.064, "dur": 1.506, + "args": { + "External id": 38469,"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": 2338707, "tid": 2379456, + "ts": 6197200095358.124, "dur": 376.280, + "args": { + "External id": 38470,"Record function id": 0, "Sequence number": 480118, "Fwd thread id": 1, "Ev Idx": 6725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197200095359.505, "dur": 320.806, + "args": { + "External id": 38471,"Sequence number": 480118, "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": 2338707, "tid": 2379456, "ts": 6197200095359.505, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200095396.165, "dur": 4.279, + "args": { + "External id": 38472,"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": 2338707, "tid": 2379456, + "ts": 6197200095399.489, "dur": 0.807, + "args": { + "External id": 38473,"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": 2338707, "tid": 2379456, + "ts": 6197200095416.201, "dur": 3.875, + "args": { + "External id": 38474,"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": 2338707, "tid": 2379456, + "ts": 6197200095429.001, "dur": 2.410, + "args": { + "External id": 38475,"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": 2338707, "tid": 2379456, + "ts": 6197200095583.307, "dur": 1.966, + "args": { + "External id": 38476,"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": 2338707, "tid": 2379456, + "ts": 6197200095589.487, "dur": 33.957, + "args": { + "External id": 38477,"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": 2338707, "tid": 2379456, + "ts": 6197200095599.583, "dur": 0.898, + "args": { + "External id": 38478,"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": 2338707, "tid": 2379456, + "ts": 6197200095628.893, "dur": 29.490, + "args": { + "External id": 38479,"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": 2338707, "tid": 2379456, + "ts": 6197200095630.881, "dur": 27.250, + "args": { + "External id": 38480,"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": 2338707, "tid": 2379456, + "ts": 6197200095637.101, "dur": 3.901, + "args": { + "External id": 38481,"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": 2338707, "tid": 2379456, + "ts": 6197200095642.489, "dur": 15.039, + "args": { + "External id": 38482,"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": 2338707, "tid": 2379456, + "ts": 6197200095662.507, "dur": 2.324, + "args": { + "External id": 38483,"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": 2338707, "tid": 2379456, + "ts": 6197200095663.581, "dur": 1.100, + "args": { + "External id": 38484,"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": 2338707, "tid": 2379456, + "ts": 6197200095671.540, "dur": 2.505, + "args": { + "External id": 38485,"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": 2338707, "tid": 2379456, + "ts": 6197200095672.792, "dur": 1.138, + "args": { + "External id": 38486,"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": 2338707, "tid": 2379456, + "ts": 6197200095692.268, "dur": 36.482, + "args": { + "External id": 38487,"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": 2338707, "tid": 2379456, + "ts": 6197200095746.967, "dur": 9.394, + "args": { + "External id": 38488,"Record function id": 0, "Ev Idx": 6743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200095749.500, "dur": 6.199, + "args": { + "External id": 38489,"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": 2338707, "tid": 2379456, + "ts": 6197200095751.587, "dur": 3.074, + "args": { + "External id": 38490,"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": 2338707, "tid": 2379456, + "ts": 6197200095752.493, "dur": 2.073, + "args": { + "External id": 38491,"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": 2338707, "tid": 2379456, + "ts": 6197200095760.488, "dur": 6.306, + "args": { + "External id": 38492,"Record function id": 0, "Sequence number": 480117, "Fwd thread id": 1, "Ev Idx": 6747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200095762.288, "dur": 1.396, + "args": { + "External id": 38493,"Sequence number": 480117, "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": 2338707, "tid": 2379456, "ts": 6197200095762.288, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SwiGLULinearFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197200095770.680, "dur": 459.802, + "args": { + "External id": 38494,"Record function id": 0, "Sequence number": 480116, "Fwd thread id": 1, "Ev Idx": 6749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197200095774.731, "dur": 443.299, + "args": { + "External id": 38495,"Sequence number": 480116, "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": 2338707, "tid": 2379456, "ts": 6197200095774.731, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200095807.655, "dur": 8.986, + "args": { + "External id": 38496,"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": 2338707, "tid": 2379456, + "ts": 6197200095812.590, "dur": 3.774, + "args": { + "External id": 38497,"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": 2338707, "tid": 2379456, + "ts": 6197200095819.973, "dur": 4.892, + "args": { + "External id": 38498,"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": 2338707, "tid": 2379456, + "ts": 6197200095821.525, "dur": 2.675, + "args": { + "External id": 38499,"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": 2338707, "tid": 2379456, + "ts": 6197200095823.148, "dur": 0.880, + "args": { + "External id": 38500,"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": 2338707, "tid": 2379456, + "ts": 6197200095828.287, "dur": 89.736, + "args": { + "External id": 38501,"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": 2338707, "tid": 2379456, + "ts": 6197200095831.146, "dur": 5.174, + "args": { + "External id": 38502,"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": 2338707, "tid": 2379456, + "ts": 6197200095831.904, "dur": 3.911, + "args": { + "External id": 38503,"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": 2338707, "tid": 2379456, + "ts": 6197200095833.515, "dur": 2.148, + "args": { + "External id": 38504,"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": 2338707, "tid": 2379456, + "ts": 6197200095837.457, "dur": 80.118, + "args": { + "External id": 38505,"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": 2338707, "tid": 2379456, + "ts": 6197200095838.721, "dur": 78.040, + "args": { + "External id": 38506,"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": 2338707, "tid": 2379456, + "ts": 6197200095921.851, "dur": 3.305, + "args": { + "External id": 38507,"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": 2338707, "tid": 2379456, + "ts": 6197200095923.476, "dur": 1.537, + "args": { + "External id": 38508,"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": 2338707, "tid": 2379456, + "ts": 6197200095958.486, "dur": 4.584, + "args": { + "External id": 38509,"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": 2338707, "tid": 2379456, + "ts": 6197200095964.420, "dur": 2.708, + "args": { + "External id": 38510,"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": 2338707, "tid": 2379456, + "ts": 6197200095968.597, "dur": 2.500, + "args": { + "External id": 38511,"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": 2338707, "tid": 2379456, + "ts": 6197200095999.705, "dur": 1.974, + "args": { + "External id": 38512,"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": 2338707, "tid": 2379456, + "ts": 6197200096000.319, "dur": 1.132, + "args": { + "External id": 38513,"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": 2338707, "tid": 2379456, + "ts": 6197200096024.867, "dur": 172.024, + "args": { + "External id": 38514,"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": 2338707, "tid": 2379456, + "ts": 6197200096031.466, "dur": 6.431, + "args": { + "External id": 38515,"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": 2338707, "tid": 2379456, + "ts": 6197200096035.260, "dur": 1.863, + "args": { + "External id": 38516,"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": 2338707, "tid": 2379456, + "ts": 6197200096039.296, "dur": 4.978, + "args": { + "External id": 38517,"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": 2338707, "tid": 2379456, + "ts": 6197200096042.761, "dur": 0.805, + "args": { + "External id": 38518,"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": 2338707, "tid": 2379456, + "ts": 6197200096045.507, "dur": 2.835, + "args": { + "External id": 38519,"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": 2338707, "tid": 2379456, + "ts": 6197200096047.331, "dur": 0.684, + "args": { + "External id": 38520,"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": 2338707, "tid": 2379456, + "ts": 6197200096049.498, "dur": 2.928, + "args": { + "External id": 38521,"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": 2338707, "tid": 2379456, + "ts": 6197200096051.279, "dur": 0.628, + "args": { + "External id": 38522,"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": 2338707, "tid": 2379456, + "ts": 6197200096093.011, "dur": 5.878, + "args": { + "External id": 38523,"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": 2338707, "tid": 2379456, + "ts": 6197200096097.075, "dur": 1.025, + "args": { + "External id": 38524,"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": 2338707, "tid": 2379456, + "ts": 6197200096100.311, "dur": 6.275, + "args": { + "External id": 38525,"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": 2338707, "tid": 2379456, + "ts": 6197200096104.185, "dur": 2.204, + "args": { + "External id": 38526,"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": 2338707, "tid": 2379456, + "ts": 6197200096109.969, "dur": 3.011, + "args": { + "External id": 38527,"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": 2338707, "tid": 2379456, + "ts": 6197200096112.129, "dur": 0.535, + "args": { + "External id": 38528,"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": 2338707, "tid": 2379456, + "ts": 6197200096113.740, "dur": 3.962, + "args": { + "External id": 38529,"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": 2338707, "tid": 2379456, + "ts": 6197200096114.777, "dur": 2.805, + "args": { + "External id": 38530,"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": 2338707, "tid": 2379456, + "ts": 6197200096119.025, "dur": 66.004, + "args": { + "External id": 38531,"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": 2338707, "tid": 2379456, + "ts": 6197200096186.830, "dur": 1.172, + "args": { + "External id": 38532,"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": 2338707, "tid": 2379456, + "ts": 6197200096189.036, "dur": 3.340, + "args": { + "External id": 38533,"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": 2338707, "tid": 2379456, + "ts": 6197200096191.063, "dur": 0.800, + "args": { + "External id": 38534,"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": 2338707, "tid": 2379456, + "ts": 6197200096194.543, "dur": 1.324, + "args": { + "External id": 38535,"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": 2338707, "tid": 2379456, + "ts": 6197200096242.288, "dur": 9.462, + "args": { + "External id": 38536,"Record function id": 0, "Ev Idx": 6791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200096244.403, "dur": 6.697, + "args": { + "External id": 38537,"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": 2338707, "tid": 2379456, + "ts": 6197200096246.569, "dur": 3.683, + "args": { + "External id": 38538,"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": 2338707, "tid": 2379456, + "ts": 6197200096247.599, "dur": 2.529, + "args": { + "External id": 38539,"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": 2338707, "tid": 2379456, + "ts": 6197200096255.580, "dur": 6.646, + "args": { + "External id": 38540,"Record function id": 0, "Sequence number": 480115, "Fwd thread id": 1, "Ev Idx": 6795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200096256.628, "dur": 3.691, + "args": { + "External id": 38541,"Sequence number": 480115, "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": 2338707, "tid": 2379456, "ts": 6197200096256.628, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200096258.570, "dur": 1.536, + "args": { + "External id": 38542,"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": 2338707, "tid": 2379456, + "ts": 6197200096259.088, "dur": 0.937, + "args": { + "External id": 38543,"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": 2338707, "tid": 2379456, + "ts": 6197200096265.777, "dur": 110.345, + "args": { + "External id": 38544,"Record function id": 0, "Sequence number": 480114, "Fwd thread id": 1, "Ev Idx": 6799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200096266.790, "dur": 102.453, + "args": { + "External id": 38545,"Sequence number": 480114, "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": 2338707, "tid": 2379456, "ts": 6197200096266.790, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197200096269.917, "dur": 7.140, + "args": { + "External id": 38546,"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": 2338707, "tid": 2379456, + "ts": 6197200096271.283, "dur": 5.181, + "args": { + "External id": 38547,"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": 2338707, "tid": 2379456, + "ts": 6197200096275.373, "dur": 0.952, + "args": { + "External id": 38548,"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": 2338707, "tid": 2379456, + "ts": 6197200096278.324, "dur": 42.541, + "args": { + "External id": 38549,"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": 2338707, "tid": 2379456, + "ts": 6197200096322.373, "dur": 4.441, + "args": { + "External id": 38550,"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": 2338707, "tid": 2379456, + "ts": 6197200096323.037, "dur": 3.216, + "args": { + "External id": 38551,"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": 2338707, "tid": 2379456, + "ts": 6197200096324.589, "dur": 1.490, + "args": { + "External id": 38552,"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": 2338707, "tid": 2379456, + "ts": 6197200096328.457, "dur": 5.820, + "args": { + "External id": 38553,"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": 2338707, "tid": 2379456, + "ts": 6197200096331.902, "dur": 1.739, + "args": { + "External id": 38554,"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": 2338707, "tid": 2379456, + "ts": 6197200096333.103, "dur": 0.437, + "args": { + "External id": 38555,"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": 2338707, "tid": 2379456, + "ts": 6197200096334.825, "dur": 33.632, + "args": { + "External id": 38556,"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": 2338707, "tid": 2379456, + "ts": 6197200096380.920, "dur": 6.918, + "args": { + "External id": 38557,"Record function id": 0, "Sequence number": 480113, "Fwd thread id": 1, "Ev Idx": 6812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200096381.957, "dur": 4.135, + "args": { + "External id": 38558,"Sequence number": 480113, "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": 2338707, "tid": 2379456, "ts": 6197200096381.957, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200096383.511, "dur": 2.418, + "args": { + "External id": 38559,"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": 2338707, "tid": 2379456, + "ts": 6197200096384.549, "dur": 1.222, + "args": { + "External id": 38560,"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": 2338707, "tid": 2379456, + "ts": 6197200096391.237, "dur": 9.542, + "args": { + "External id": 38561,"Record function id": 0, "Sequence number": 480112, "Fwd thread id": 1, "Ev Idx": 6816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200096392.272, "dur": 6.514, + "args": { + "External id": 38562,"Sequence number": 480112, "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": 2338707, "tid": 2379456, "ts": 6197200096392.272, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197200096392.929, "dur": 5.655, + "args": { + "External id": 38563,"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": 2338707, "tid": 2379456, + "ts": 6197200096395.880, "dur": 2.218, + "args": { + "External id": 38564,"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": 2338707, "tid": 2379456, + "ts": 6197200096397.395, "dur": 0.543, + "args": { + "External id": 38565,"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": 2338707, "tid": 2379456, + "ts": 6197200096404.982, "dur": 5.676, + "args": { + "External id": 38566,"Record function id": 0, "Ev Idx": 6821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200096406.287, "dur": 3.857, + "args": { + "External id": 38567,"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": 2338707, "tid": 2379456, + "ts": 6197200096407.224, "dur": 2.588, + "args": { + "External id": 38568,"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": 2338707, "tid": 2379456, + "ts": 6197200096408.047, "dur": 1.674, + "args": { + "External id": 38569,"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": 2338707, "tid": 2379456, + "ts": 6197200096413.882, "dur": 5.922, + "args": { + "External id": 38570,"Record function id": 0, "Sequence number": 480111, "Fwd thread id": 1, "Ev Idx": 6825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200096415.035, "dur": 2.921, + "args": { + "External id": 38571,"Sequence number": 480111, "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": 2338707, "tid": 2379456, "ts": 6197200096415.035, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200096416.322, "dur": 1.478, + "args": { + "External id": 38572,"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": 2338707, "tid": 2379456, + "ts": 6197200096416.922, "dur": 0.747, + "args": { + "External id": 38573,"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": 2338707, "tid": 2379456, + "ts": 6197200096423.025, "dur": 92.120, + "args": { + "External id": 38574,"Record function id": 0, "Sequence number": 480110, "Fwd thread id": 1, "Ev Idx": 6829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200096426.069, "dur": 81.514, + "args": { + "External id": 38575,"Sequence number": 480110, "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": 2338707, "tid": 2379456, "ts": 6197200096426.069, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197200096428.671, "dur": 2.829, + "args": { + "External id": 38576,"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": 2338707, "tid": 2379456, + "ts": 6197200096429.143, "dur": 1.908, + "args": { + "External id": 38577,"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": 2338707, "tid": 2379456, + "ts": 6197200096430.379, "dur": 0.570, + "args": { + "External id": 38578,"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": 2338707, "tid": 2379456, + "ts": 6197200096432.024, "dur": 32.240, + "args": { + "External id": 38579,"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": 2338707, "tid": 2379456, + "ts": 6197200096465.304, "dur": 5.528, + "args": { + "External id": 38580,"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": 2338707, "tid": 2379456, + "ts": 6197200096466.030, "dur": 4.267, + "args": { + "External id": 38581,"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": 2338707, "tid": 2379456, + "ts": 6197200096469.100, "dur": 1.066, + "args": { + "External id": 38582,"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": 2338707, "tid": 2379456, + "ts": 6197200096472.011, "dur": 3.944, + "args": { + "External id": 38583,"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": 2338707, "tid": 2379456, + "ts": 6197200096473.285, "dur": 1.857, + "args": { + "External id": 38584,"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": 2338707, "tid": 2379456, + "ts": 6197200096474.540, "dur": 0.500, + "args": { + "External id": 38585,"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": 2338707, "tid": 2379456, + "ts": 6197200096476.360, "dur": 30.602, + "args": { + "External id": 38586,"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": 2338707, "tid": 2379456, + "ts": 6197200096519.265, "dur": 30.073, + "args": { + "External id": 38587,"Record function id": 0, "Sequence number": 480109, "Fwd thread id": 1, "Ev Idx": 6842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200096520.251, "dur": 3.890, + "args": { + "External id": 38588,"Sequence number": 480109, "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": 2338707, "tid": 2379456, "ts": 6197200096520.251, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200096521.792, "dur": 2.139, + "args": { + "External id": 38589,"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": 2338707, "tid": 2379456, + "ts": 6197200096522.683, "dur": 1.128, + "args": { + "External id": 38590,"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": 2338707, "tid": 2379456, + "ts": 6197200096526.893, "dur": 19.804, + "args": { + "External id": 38591,"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": 2338707, "tid": 2379456, + "ts": 6197200096553.272, "dur": 10.016, + "args": { + "External id": 38592,"Record function id": 0, "Sequence number": 480108, "Fwd thread id": 1, "Ev Idx": 6847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200096556.413, "dur": 4.634, + "args": { + "External id": 38593,"Sequence number": 480108, "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": 2338707, "tid": 2379456, "ts": 6197200096556.413, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197200096557.265, "dur": 3.614, + "args": { + "External id": 38594,"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": 2338707, "tid": 2379456, + "ts": 6197200096558.059, "dur": 2.266, + "args": { + "External id": 38595,"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": 2338707, "tid": 2379456, + "ts": 6197200096559.462, "dur": 0.732, + "args": { + "External id": 38596,"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": 2338707, "tid": 2379456, + "ts": 6197200096567.127, "dur": 6.071, + "args": { + "External id": 38597,"Record function id": 0, "Ev Idx": 6852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200096568.863, "dur": 3.835, + "args": { + "External id": 38598,"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": 2338707, "tid": 2379456, + "ts": 6197200096569.880, "dur": 2.533, + "args": { + "External id": 38599,"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": 2338707, "tid": 2379456, + "ts": 6197200096570.557, "dur": 1.789, + "args": { + "External id": 38600,"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": 2338707, "tid": 2379456, + "ts": 6197200096577.512, "dur": 434.200, + "args": { + "External id": 38601,"Record function id": 0, "Sequence number": 480107, "Fwd thread id": 1, "Ev Idx": 6856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197200096578.913, "dur": 397.052, + "args": { + "External id": 38602,"Sequence number": 480107, "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": 2338707, "tid": 2379456, "ts": 6197200096578.913, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338707, "tid": 2379456, + "ts": 6197200096599.392, "dur": 38.094, + "args": { + "External id": 38603,"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": 2338707, "tid": 2379456, + "ts": 6197200096600.914, "dur": 36.365, + "args": { + "External id": 38604,"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": 2338707, "tid": 2379456, + "ts": 6197200096603.460, "dur": 10.174, + "args": { + "External id": 38605,"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": 2338707, "tid": 2379456, + "ts": 6197200096610.356, "dur": 2.797, + "args": { + "External id": 38606,"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": 2338707, "tid": 2379456, + "ts": 6197200096614.964, "dur": 21.715, + "args": { + "External id": 38607,"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": 2338707, "tid": 2379456, + "ts": 6197200096651.384, "dur": 2.267, + "args": { + "External id": 38608,"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": 2338707, "tid": 2379456, + "ts": 6197200096652.143, "dur": 1.376, + "args": { + "External id": 38609,"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": 2338707, "tid": 2379456, + "ts": 6197200096657.508, "dur": 1.622, + "args": { + "External id": 38610,"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": 2338707, "tid": 2379456, + "ts": 6197200096658.197, "dur": 0.776, + "args": { + "External id": 38611,"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": 2338707, "tid": 2379456, + "ts": 6197200096672.920, "dur": 2.334, + "args": { + "External id": 38612,"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": 2338707, "tid": 2379456, + "ts": 6197200096685.276, "dur": 2.816, + "args": { + "External id": 38613,"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": 2338707, "tid": 2379456, + "ts": 6197200096864.653, "dur": 4.254, + "args": { + "External id": 38614,"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": 2338707, "tid": 2379456, + "ts": 6197200096873.186, "dur": 34.159, + "args": { + "External id": 38615,"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": 2338707, "tid": 2379456, + "ts": 6197200096882.439, "dur": 1.328, + "args": { + "External id": 38616,"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": 2338707, "tid": 2379456, + "ts": 6197200096912.910, "dur": 30.906, + "args": { + "External id": 38617,"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": 2338707, "tid": 2379456, + "ts": 6197200096914.595, "dur": 29.024, + "args": { + "External id": 38618,"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": 2338707, "tid": 2379456, + "ts": 6197200096919.157, "dur": 4.537, + "args": { + "External id": 38619,"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": 2338707, "tid": 2379456, + "ts": 6197200096926.829, "dur": 16.271, + "args": { + "External id": 38620,"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": 2338707, "tid": 2379456, + "ts": 6197200096948.222, "dur": 3.466, + "args": { + "External id": 38621,"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": 2338707, "tid": 2379456, + "ts": 6197200096950.167, "dur": 1.423, + "args": { + "External id": 38622,"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": 2338707, "tid": 2379456, + "ts": 6197200096957.547, "dur": 2.610, + "args": { + "External id": 38623,"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": 2338707, "tid": 2379456, + "ts": 6197200096958.727, "dur": 1.285, + "args": { + "External id": 38624,"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": 2338707, "tid": 2379456, + "ts": 6197200096962.621, "dur": 1.790, + "args": { + "External id": 38625,"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": 2338707, "tid": 2379456, + "ts": 6197200096963.349, "dur": 0.965, + "args": { + "External id": 38626,"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": 2338707, "tid": 2379456, + "ts": 6197200096992.698, "dur": 17.193, + "args": { + "External id": 38627,"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": 2338707, "tid": 2379456, + "ts": 6197200097024.099, "dur": 8.730, + "args": { + "External id": 38628,"Record function id": 0, "Ev Idx": 6883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200097026.708, "dur": 5.519, + "args": { + "External id": 38629,"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": 2338707, "tid": 2379456, + "ts": 6197200097028.608, "dur": 2.790, + "args": { + "External id": 38630,"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": 2338707, "tid": 2379456, + "ts": 6197200097029.478, "dur": 1.805, + "args": { + "External id": 38631,"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": 2338707, "tid": 2379456, + "ts": 6197200097036.433, "dur": 7.317, + "args": { + "External id": 38632,"Record function id": 0, "Sequence number": 480106, "Fwd thread id": 1, "Ev Idx": 6887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200097037.673, "dur": 3.488, + "args": { + "External id": 38633,"Sequence number": 480106, "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": 2338707, "tid": 2379456, "ts": 6197200097037.673, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200097039.193, "dur": 1.741, + "args": { + "External id": 38634,"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": 2338707, "tid": 2379456, + "ts": 6197200097039.779, "dur": 1.035, + "args": { + "External id": 38635,"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": 2338707, "tid": 2379456, + "ts": 6197200097047.067, "dur": 205.029, + "args": { + "External id": 38636,"Record function id": 0, "Sequence number": 480105, "Fwd thread id": 1, "Ev Idx": 6891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200097047.843, "dur": 195.622, + "args": { + "External id": 38637,"Sequence number": 480105, "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": 2338707, "tid": 2379456, "ts": 6197200097047.843, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197200097053.534, "dur": 55.125, + "args": { + "External id": 38638,"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": 2338707, "tid": 2379456, + "ts": 6197200097054.876, "dur": 52.742, + "args": { + "External id": 38639,"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": 2338707, "tid": 2379456, + "ts": 6197200097105.873, "dur": 1.230, + "args": { + "External id": 38640,"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": 2338707, "tid": 2379456, + "ts": 6197200097110.202, "dur": 78.228, + "args": { + "External id": 38641,"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": 2338707, "tid": 2379456, + "ts": 6197200097189.662, "dur": 7.678, + "args": { + "External id": 38642,"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": 2338707, "tid": 2379456, + "ts": 6197200097190.668, "dur": 6.061, + "args": { + "External id": 38643,"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": 2338707, "tid": 2379456, + "ts": 6197200097194.392, "dur": 2.159, + "args": { + "External id": 38644,"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": 2338707, "tid": 2379456, + "ts": 6197200097199.562, "dur": 4.100, + "args": { + "External id": 38645,"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": 2338707, "tid": 2379456, + "ts": 6197200097200.975, "dur": 2.047, + "args": { + "External id": 38646,"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": 2338707, "tid": 2379456, + "ts": 6197200097202.213, "dur": 0.705, + "args": { + "External id": 38647,"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": 2338707, "tid": 2379456, + "ts": 6197200097204.300, "dur": 38.390, + "args": { + "External id": 38648,"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": 2338707, "tid": 2379456, + "ts": 6197200097259.072, "dur": 8.403, + "args": { + "External id": 38649,"Record function id": 0, "Sequence number": 480104, "Fwd thread id": 1, "Ev Idx": 6904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200097260.296, "dur": 4.551, + "args": { + "External id": 38650,"Sequence number": 480104, "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": 2338707, "tid": 2379456, "ts": 6197200097260.296, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200097262.214, "dur": 2.478, + "args": { + "External id": 38651,"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": 2338707, "tid": 2379456, + "ts": 6197200097263.231, "dur": 1.305, + "args": { + "External id": 38652,"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": 2338707, "tid": 2379456, + "ts": 6197200097270.996, "dur": 10.253, + "args": { + "External id": 38653,"Record function id": 0, "Sequence number": 480103, "Fwd thread id": 1, "Ev Idx": 6908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200097271.977, "dur": 7.529, + "args": { + "External id": 38654,"Sequence number": 480103, "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": 2338707, "tid": 2379456, "ts": 6197200097271.977, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197200097273.045, "dur": 6.272, + "args": { + "External id": 38655,"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": 2338707, "tid": 2379456, + "ts": 6197200097273.856, "dur": 4.963, + "args": { + "External id": 38656,"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": 2338707, "tid": 2379456, + "ts": 6197200097277.773, "dur": 0.958, + "args": { + "External id": 38657,"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": 2338707, "tid": 2379456, + "ts": 6197200097285.462, "dur": 7.430, + "args": { + "External id": 38658,"Record function id": 0, "Ev Idx": 6913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200097287.128, "dur": 5.216, + "args": { + "External id": 38659,"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": 2338707, "tid": 2379456, + "ts": 6197200097288.696, "dur": 3.300, + "args": { + "External id": 38660,"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": 2338707, "tid": 2379456, + "ts": 6197200097289.465, "dur": 2.401, + "args": { + "External id": 38661,"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": 2338707, "tid": 2379456, + "ts": 6197200097296.254, "dur": 7.037, + "args": { + "External id": 38662,"Record function id": 0, "Sequence number": 480102, "Fwd thread id": 1, "Ev Idx": 6917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200097297.200, "dur": 3.789, + "args": { + "External id": 38663,"Sequence number": 480102, "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": 2338707, "tid": 2379456, "ts": 6197200097297.200, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200097298.180, "dur": 2.635, + "args": { + "External id": 38664,"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": 2338707, "tid": 2379456, + "ts": 6197200097299.480, "dur": 1.202, + "args": { + "External id": 38665,"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": 2338707, "tid": 2379456, + "ts": 6197200097307.538, "dur": 347.150, + "args": { + "External id": 38666,"Record function id": 0, "Sequence number": 480101, "Fwd thread id": 1, "Ev Idx": 6921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFuncBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197200097309.127, "dur": 324.424, + "args": { + "External id": 38667,"Sequence number": 480101, "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": 2338707, "tid": 2379456, "ts": 6197200097309.127, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338707, "tid": 2379456, + "ts": 6197200097327.380, "dur": 7.967, + "args": { + "External id": 38668,"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": 2338707, "tid": 2379456, + "ts": 6197200097330.671, "dur": 4.258, + "args": { + "External id": 38669,"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": 2338707, "tid": 2379456, + "ts": 6197200097337.421, "dur": 4.442, + "args": { + "External id": 38670,"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": 2338707, "tid": 2379456, + "ts": 6197200097339.534, "dur": 2.102, + "args": { + "External id": 38671,"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": 2338707, "tid": 2379456, + "ts": 6197200097343.263, "dur": 4.979, + "args": { + "External id": 38672,"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": 2338707, "tid": 2379456, + "ts": 6197200097344.985, "dur": 2.964, + "args": { + "External id": 38673,"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": 2338707, "tid": 2379456, + "ts": 6197200097373.287, "dur": 236.447, + "args": { + "External id": 38674,"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": 2338707, "tid": 2379456, + "ts": 6197200097454.217, "dur": 3.440, + "args": { + "External id": 38675,"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": 2338707, "tid": 2379456, + "ts": 6197200097459.804, "dur": 2.724, + "args": { + "External id": 38676,"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": 2338707, "tid": 2379456, + "ts": 6197200097464.313, "dur": 2.613, + "args": { + "External id": 38677,"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": 2338707, "tid": 2379456, + "ts": 6197200097468.490, "dur": 2.084, + "args": { + "External id": 38678,"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": 2338707, "tid": 2379456, + "ts": 6197200097514.520, "dur": 2.964, + "args": { + "External id": 38679,"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": 2338707, "tid": 2379456, + "ts": 6197200097515.874, "dur": 1.483, + "args": { + "External id": 38680,"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": 2338707, "tid": 2379456, + "ts": 6197200097519.180, "dur": 26.281, + "args": { + "External id": 38681,"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": 2338707, "tid": 2379456, + "ts": 6197200097525.379, "dur": 0.765, + "args": { + "External id": 38682,"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": 2338707, "tid": 2379456, + "ts": 6197200097549.441, "dur": 1.997, + "args": { + "External id": 38683,"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": 2338707, "tid": 2379456, + "ts": 6197200097550.864, "dur": 0.492, + "args": { + "External id": 38684,"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": 2338707, "tid": 2379456, + "ts": 6197200097552.390, "dur": 14.066, + "args": { + "External id": 38685,"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": 2338707, "tid": 2379456, + "ts": 6197200097554.793, "dur": 0.716, + "args": { + "External id": 38686,"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": 2338707, "tid": 2379456, + "ts": 6197200097621.726, "dur": 3.232, + "args": { + "External id": 38687,"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": 2338707, "tid": 2379456, + "ts": 6197200097627.709, "dur": 0.565, + "args": { + "External id": 38688,"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": 2338707, "tid": 2379456, + "ts": 6197200097630.301, "dur": 0.443, + "args": { + "External id": 38689,"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": 2338707, "tid": 2379456, + "ts": 6197200097662.461, "dur": 253.901, + "args": { + "External id": 38690,"Record function id": 0, "Sequence number": 480100, "Fwd thread id": 1, "Ev Idx": 6945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197200097663.795, "dur": 244.666, + "args": { + "External id": 38691,"Sequence number": 480100, "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": 2338707, "tid": 2379456, "ts": 6197200097663.795, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338707, "tid": 2379456, + "ts": 6197200097683.914, "dur": 64.697, + "args": { + "External id": 38692,"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": 2338707, "tid": 2379456, + "ts": 6197200097687.067, "dur": 3.256, + "args": { + "External id": 38693,"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": 2338707, "tid": 2379456, + "ts": 6197200097691.868, "dur": 55.800, + "args": { + "External id": 38694,"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": 2338707, "tid": 2379456, + "ts": 6197200097760.645, "dur": 5.929, + "args": { + "External id": 38695,"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": 2338707, "tid": 2379456, + "ts": 6197200097762.871, "dur": 3.387, + "args": { + "External id": 38696,"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": 2338707, "tid": 2379456, + "ts": 6197200097925.086, "dur": 216.193, + "args": { + "External id": 38697,"Record function id": 0, "Sequence number": 480099, "Fwd thread id": 1, "Ev Idx": 6952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197200097926.833, "dur": 205.400, + "args": { + "External id": 38698,"Sequence number": 480099, "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": 2338707, "tid": 2379456, "ts": 6197200097926.833, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338707, "tid": 2379456, + "ts": 6197200097938.621, "dur": 49.964, + "args": { + "External id": 38699,"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": 2338707, "tid": 2379456, + "ts": 6197200097945.421, "dur": 3.330, + "args": { + "External id": 38700,"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": 2338707, "tid": 2379456, + "ts": 6197200097951.639, "dur": 36.399, + "args": { + "External id": 38701,"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": 2338707, "tid": 2379456, + "ts": 6197200097995.840, "dur": 4.860, + "args": { + "External id": 38702,"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": 2338707, "tid": 2379456, + "ts": 6197200097997.313, "dur": 3.127, + "args": { + "External id": 38703,"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": 2338707, "tid": 2379456, + "ts": 6197200098150.537, "dur": 14.997, + "args": { + "External id": 38704,"Record function id": 0, "Sequence number": 480098, "Fwd thread id": 1, "Ev Idx": 6959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200098152.172, "dur": 10.704, + "args": { + "External id": 38705,"Sequence number": 480098, "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": 2338707, "tid": 2379456, "ts": 6197200098152.172, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200098155.487, "dur": 7.096, + "args": { + "External id": 38706,"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": 2338707, "tid": 2379456, + "ts": 6197200098156.944, "dur": 5.398, + "args": { + "External id": 38707,"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": 2338707, "tid": 2379456, + "ts": 6197200098169.319, "dur": 6.838, + "args": { + "External id": 38708,"Record function id": 0, "Sequence number": 480097, "Fwd thread id": 1, "Ev Idx": 6963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200098170.283, "dur": 3.623, + "args": { + "External id": 38709,"Sequence number": 480097, "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": 2338707, "tid": 2379456, "ts": 6197200098170.283, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200098172.033, "dur": 1.700, + "args": { + "External id": 38710,"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": 2338707, "tid": 2379456, + "ts": 6197200098172.708, "dur": 0.891, + "args": { + "External id": 38711,"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": 2338707, "tid": 2379456, + "ts": 6197200098179.451, "dur": 9.425, + "args": { + "External id": 38712,"Record function id": 0, "Sequence number": 480096, "Fwd thread id": 1, "Ev Idx": 6967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200098180.534, "dur": 5.972, + "args": { + "External id": 38713,"Sequence number": 480096, "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": 2338707, "tid": 2379456, "ts": 6197200098180.534, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200098181.963, "dur": 4.367, + "args": { + "External id": 38714,"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": 2338707, "tid": 2379456, + "ts": 6197200098185.094, "dur": 1.100, + "args": { + "External id": 38715,"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": 2338707, "tid": 2379456, + "ts": 6197200098192.974, "dur": 6.412, + "args": { + "External id": 38716,"Record function id": 0, "Sequence number": 480095, "Fwd thread id": 1, "Ev Idx": 6971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200098194.062, "dur": 3.384, + "args": { + "External id": 38717,"Sequence number": 480095, "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": 2338707, "tid": 2379456, "ts": 6197200098194.062, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200098195.310, "dur": 1.983, + "args": { + "External id": 38718,"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": 2338707, "tid": 2379456, + "ts": 6197200098196.164, "dur": 0.991, + "args": { + "External id": 38719,"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": 2338707, "tid": 2379456, + "ts": 6197200098202.734, "dur": 155.108, + "args": { + "External id": 38720,"Record function id": 0, "Sequence number": 480094, "Fwd thread id": 1, "Ev Idx": 6975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200098203.711, "dur": 145.799, + "args": { + "External id": 38721,"Sequence number": 480094, "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": 2338707, "tid": 2379456, "ts": 6197200098203.711, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197200098208.034, "dur": 8.896, + "args": { + "External id": 38722,"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": 2338707, "tid": 2379456, + "ts": 6197200098211.921, "dur": 4.364, + "args": { + "External id": 38723,"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": 2338707, "tid": 2379456, + "ts": 6197200098214.530, "dur": 1.503, + "args": { + "External id": 38724,"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": 2338707, "tid": 2379456, + "ts": 6197200098218.520, "dur": 70.940, + "args": { + "External id": 38725,"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": 2338707, "tid": 2379456, + "ts": 6197200098290.608, "dur": 5.155, + "args": { + "External id": 38726,"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": 2338707, "tid": 2379456, + "ts": 6197200098291.328, "dur": 3.407, + "args": { + "External id": 38727,"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": 2338707, "tid": 2379456, + "ts": 6197200098293.355, "dur": 1.262, + "args": { + "External id": 38728,"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": 2338707, "tid": 2379456, + "ts": 6197200098297.558, "dur": 5.799, + "args": { + "External id": 38729,"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": 2338707, "tid": 2379456, + "ts": 6197200098300.922, "dur": 1.799, + "args": { + "External id": 38730,"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": 2338707, "tid": 2379456, + "ts": 6197200098302.067, "dur": 0.588, + "args": { + "External id": 38731,"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": 2338707, "tid": 2379456, + "ts": 6197200098304.044, "dur": 44.528, + "args": { + "External id": 38732,"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": 2338707, "tid": 2379456, + "ts": 6197200098363.616, "dur": 8.359, + "args": { + "External id": 38733,"Record function id": 0, "Sequence number": 480093, "Fwd thread id": 1, "Ev Idx": 6988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200098364.988, "dur": 4.552, + "args": { + "External id": 38734,"Sequence number": 480093, "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": 2338707, "tid": 2379456, "ts": 6197200098364.988, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200098366.795, "dur": 2.607, + "args": { + "External id": 38735,"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": 2338707, "tid": 2379456, + "ts": 6197200098367.740, "dur": 1.515, + "args": { + "External id": 38736,"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": 2338707, "tid": 2379456, + "ts": 6197200098375.616, "dur": 9.541, + "args": { + "External id": 38737,"Record function id": 0, "Sequence number": 480092, "Fwd thread id": 1, "Ev Idx": 6992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200098376.725, "dur": 6.291, + "args": { + "External id": 38738,"Sequence number": 480092, "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": 2338707, "tid": 2379456, "ts": 6197200098376.725, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197200098377.572, "dur": 5.246, + "args": { + "External id": 38739,"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": 2338707, "tid": 2379456, + "ts": 6197200098378.216, "dur": 4.114, + "args": { + "External id": 38740,"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": 2338707, "tid": 2379456, + "ts": 6197200098381.486, "dur": 0.762, + "args": { + "External id": 38741,"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": 2338707, "tid": 2379456, + "ts": 6197200098390.958, "dur": 9.394, + "args": { + "External id": 38742,"Record function id": 0, "Ev Idx": 6997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200098392.379, "dur": 7.200, + "args": { + "External id": 38743,"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": 2338707, "tid": 2379456, + "ts": 6197200098394.979, "dur": 4.127, + "args": { + "External id": 38744,"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": 2338707, "tid": 2379456, + "ts": 6197200098396.189, "dur": 2.790, + "args": { + "External id": 38745,"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": 2338707, "tid": 2379456, + "ts": 6197200098404.280, "dur": 6.677, + "args": { + "External id": 38746,"Record function id": 0, "Sequence number": 480091, "Fwd thread id": 1, "Ev Idx": 7001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200098405.465, "dur": 3.052, + "args": { + "External id": 38747,"Sequence number": 480091, "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": 2338707, "tid": 2379456, "ts": 6197200098405.465, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200098406.559, "dur": 1.807, + "args": { + "External id": 38748,"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": 2338707, "tid": 2379456, + "ts": 6197200098407.348, "dur": 0.892, + "args": { + "External id": 38749,"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": 2338707, "tid": 2379456, + "ts": 6197200098414.127, "dur": 89.627, + "args": { + "External id": 38750,"Record function id": 0, "Sequence number": 480090, "Fwd thread id": 1, "Ev Idx": 7005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200098417.176, "dur": 79.512, + "args": { + "External id": 38751,"Sequence number": 480090, "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": 2338707, "tid": 2379456, "ts": 6197200098417.176, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197200098419.893, "dur": 2.960, + "args": { + "External id": 38752,"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": 2338707, "tid": 2379456, + "ts": 6197200098420.435, "dur": 1.998, + "args": { + "External id": 38753,"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": 2338707, "tid": 2379456, + "ts": 6197200098421.570, "dur": 0.746, + "args": { + "External id": 38754,"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": 2338707, "tid": 2379456, + "ts": 6197200098423.553, "dur": 26.037, + "args": { + "External id": 38755,"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": 2338707, "tid": 2379456, + "ts": 6197200098450.611, "dur": 5.965, + "args": { + "External id": 38756,"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": 2338707, "tid": 2379456, + "ts": 6197200098451.311, "dur": 4.811, + "args": { + "External id": 38757,"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": 2338707, "tid": 2379456, + "ts": 6197200098455.142, "dur": 0.860, + "args": { + "External id": 38758,"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": 2338707, "tid": 2379456, + "ts": 6197200098457.775, "dur": 4.158, + "args": { + "External id": 38759,"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": 2338707, "tid": 2379456, + "ts": 6197200098459.120, "dur": 1.993, + "args": { + "External id": 38760,"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": 2338707, "tid": 2379456, + "ts": 6197200098460.170, "dur": 0.860, + "args": { + "External id": 38761,"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": 2338707, "tid": 2379456, + "ts": 6197200098462.636, "dur": 33.380, + "args": { + "External id": 38762,"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": 2338707, "tid": 2379456, + "ts": 6197200098508.787, "dur": 31.292, + "args": { + "External id": 38763,"Record function id": 0, "Sequence number": 480089, "Fwd thread id": 1, "Ev Idx": 7018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200098509.855, "dur": 4.282, + "args": { + "External id": 38764,"Sequence number": 480089, "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": 2338707, "tid": 2379456, "ts": 6197200098509.855, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200098511.281, "dur": 2.713, + "args": { + "External id": 38765,"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": 2338707, "tid": 2379456, + "ts": 6197200098512.726, "dur": 1.116, + "args": { + "External id": 38766,"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": 2338707, "tid": 2379456, + "ts": 6197200098517.084, "dur": 20.866, + "args": { + "External id": 38767,"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": 2338707, "tid": 2379456, + "ts": 6197200098546.208, "dur": 7.327, + "args": { + "External id": 38768,"Record function id": 0, "Sequence number": 480088, "Fwd thread id": 1, "Ev Idx": 7023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200098547.186, "dur": 4.290, + "args": { + "External id": 38769,"Sequence number": 480088, "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": 2338707, "tid": 2379456, "ts": 6197200098547.186, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197200098547.988, "dur": 3.293, + "args": { + "External id": 38770,"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": 2338707, "tid": 2379456, + "ts": 6197200098548.837, "dur": 1.962, + "args": { + "External id": 38771,"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": 2338707, "tid": 2379456, + "ts": 6197200098550.095, "dur": 0.619, + "args": { + "External id": 38772,"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": 2338707, "tid": 2379456, + "ts": 6197200098557.382, "dur": 5.521, + "args": { + "External id": 38773,"Record function id": 0, "Ev Idx": 7028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200098558.846, "dur": 3.567, + "args": { + "External id": 38774,"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": 2338707, "tid": 2379456, + "ts": 6197200098559.915, "dur": 1.960, + "args": { + "External id": 38775,"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": 2338707, "tid": 2379456, + "ts": 6197200098560.335, "dur": 1.468, + "args": { + "External id": 38776,"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": 2338707, "tid": 2379456, + "ts": 6197200098566.199, "dur": 7.795, + "args": { + "External id": 38777,"Record function id": 0, "Sequence number": 480087, "Fwd thread id": 1, "Ev Idx": 7032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200098567.203, "dur": 4.676, + "args": { + "External id": 38778,"Sequence number": 480087, "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": 2338707, "tid": 2379456, "ts": 6197200098567.203, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200098568.308, "dur": 3.411, + "args": { + "External id": 38779,"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": 2338707, "tid": 2379456, + "ts": 6197200098570.956, "dur": 0.666, + "args": { + "External id": 38780,"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": 2338707, "tid": 2379456, + "ts": 6197200098577.137, "dur": 97.147, + "args": { + "External id": 38781,"Record function id": 0, "Sequence number": 480086, "Fwd thread id": 1, "Ev Idx": 7036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200098577.819, "dur": 87.910, + "args": { + "External id": 38782,"Sequence number": 480086, "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": 2338707, "tid": 2379456, "ts": 6197200098577.819, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197200098580.248, "dur": 2.991, + "args": { + "External id": 38783,"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": 2338707, "tid": 2379456, + "ts": 6197200098580.782, "dur": 2.024, + "args": { + "External id": 38784,"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": 2338707, "tid": 2379456, + "ts": 6197200098582.029, "dur": 0.680, + "args": { + "External id": 38785,"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": 2338707, "tid": 2379456, + "ts": 6197200098583.768, "dur": 33.523, + "args": { + "External id": 38786,"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": 2338707, "tid": 2379456, + "ts": 6197200098620.743, "dur": 4.245, + "args": { + "External id": 38787,"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": 2338707, "tid": 2379456, + "ts": 6197200098621.356, "dur": 3.114, + "args": { + "External id": 38788,"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": 2338707, "tid": 2379456, + "ts": 6197200098622.899, "dur": 1.432, + "args": { + "External id": 38789,"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": 2338707, "tid": 2379456, + "ts": 6197200098626.193, "dur": 3.806, + "args": { + "External id": 38790,"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": 2338707, "tid": 2379456, + "ts": 6197200098627.408, "dur": 2.143, + "args": { + "External id": 38791,"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": 2338707, "tid": 2379456, + "ts": 6197200098628.800, "dur": 0.663, + "args": { + "External id": 38792,"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": 2338707, "tid": 2379456, + "ts": 6197200098632.819, "dur": 32.224, + "args": { + "External id": 38793,"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": 2338707, "tid": 2379456, + "ts": 6197200098678.930, "dur": 40.715, + "args": { + "External id": 38794,"Record function id": 0, "Sequence number": 480085, "Fwd thread id": 1, "Ev Idx": 7049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200098679.857, "dur": 3.482, + "args": { + "External id": 38795,"Sequence number": 480085, "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": 2338707, "tid": 2379456, "ts": 6197200098679.857, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200098681.270, "dur": 1.909, + "args": { + "External id": 38796,"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": 2338707, "tid": 2379456, + "ts": 6197200098682.179, "dur": 0.906, + "args": { + "External id": 38797,"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": 2338707, "tid": 2379456, + "ts": 6197200098685.525, "dur": 14.337, + "args": { + "External id": 38798,"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": 2338707, "tid": 2379456, + "ts": 6197200098725.487, "dur": 9.005, + "args": { + "External id": 38799,"Record function id": 0, "Sequence number": 480084, "Fwd thread id": 1, "Ev Idx": 7054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200098726.770, "dur": 5.931, + "args": { + "External id": 38800,"Sequence number": 480084, "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": 2338707, "tid": 2379456, "ts": 6197200098726.770, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197200098727.737, "dur": 4.778, + "args": { + "External id": 38801,"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": 2338707, "tid": 2379456, + "ts": 6197200098728.596, "dur": 3.156, + "args": { + "External id": 38802,"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": 2338707, "tid": 2379456, + "ts": 6197200098730.702, "dur": 0.929, + "args": { + "External id": 38803,"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": 2338707, "tid": 2379456, + "ts": 6197200098738.551, "dur": 6.422, + "args": { + "External id": 38804,"Record function id": 0, "Ev Idx": 7059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200098740.020, "dur": 4.379, + "args": { + "External id": 38805,"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": 2338707, "tid": 2379456, + "ts": 6197200098741.230, "dur": 2.772, + "args": { + "External id": 38806,"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": 2338707, "tid": 2379456, + "ts": 6197200098741.822, "dur": 2.062, + "args": { + "External id": 38807,"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": 2338707, "tid": 2379456, + "ts": 6197200098749.628, "dur": 400.093, + "args": { + "External id": 38808,"Record function id": 0, "Sequence number": 480083, "Fwd thread id": 1, "Ev Idx": 7063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197200098750.914, "dur": 363.048, + "args": { + "External id": 38809,"Sequence number": 480083, "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": 2338707, "tid": 2379456, "ts": 6197200098750.914, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200098787.957, "dur": 2.119, + "args": { + "External id": 38810,"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": 2338707, "tid": 2379456, + "ts": 6197200098788.724, "dur": 1.219, + "args": { + "External id": 38811,"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": 2338707, "tid": 2379456, + "ts": 6197200098804.727, "dur": 4.804, + "args": { + "External id": 38812,"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": 2338707, "tid": 2379456, + "ts": 6197200098818.505, "dur": 2.201, + "args": { + "External id": 38813,"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": 2338707, "tid": 2379456, + "ts": 6197200098968.330, "dur": 1.795, + "args": { + "External id": 38814,"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": 2338707, "tid": 2379456, + "ts": 6197200098974.639, "dur": 33.533, + "args": { + "External id": 38815,"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": 2338707, "tid": 2379456, + "ts": 6197200098985.362, "dur": 0.637, + "args": { + "External id": 38816,"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": 2338707, "tid": 2379456, + "ts": 6197200099013.508, "dur": 30.157, + "args": { + "External id": 38817,"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": 2338707, "tid": 2379456, + "ts": 6197200099017.525, "dur": 25.897, + "args": { + "External id": 38818,"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": 2338707, "tid": 2379456, + "ts": 6197200099021.587, "dur": 4.341, + "args": { + "External id": 38819,"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": 2338707, "tid": 2379456, + "ts": 6197200099027.450, "dur": 15.481, + "args": { + "External id": 38820,"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": 2338707, "tid": 2379456, + "ts": 6197200099047.751, "dur": 2.558, + "args": { + "External id": 38821,"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": 2338707, "tid": 2379456, + "ts": 6197200099048.806, "dur": 1.359, + "args": { + "External id": 38822,"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": 2338707, "tid": 2379456, + "ts": 6197200099096.448, "dur": 5.118, + "args": { + "External id": 38823,"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": 2338707, "tid": 2379456, + "ts": 6197200099099.549, "dur": 1.744, + "args": { + "External id": 38824,"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": 2338707, "tid": 2379456, + "ts": 6197200099126.021, "dur": 19.368, + "args": { + "External id": 38825,"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": 2338707, "tid": 2379456, + "ts": 6197200099161.784, "dur": 9.156, + "args": { + "External id": 38826,"Record function id": 0, "Ev Idx": 7081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200099163.913, "dur": 6.424, + "args": { + "External id": 38827,"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": 2338707, "tid": 2379456, + "ts": 6197200099165.835, "dur": 2.964, + "args": { + "External id": 38828,"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": 2338707, "tid": 2379456, + "ts": 6197200099166.779, "dur": 1.932, + "args": { + "External id": 38829,"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": 2338707, "tid": 2379456, + "ts": 6197200099175.171, "dur": 6.464, + "args": { + "External id": 38830,"Record function id": 0, "Sequence number": 480082, "Fwd thread id": 1, "Ev Idx": 7085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200099176.717, "dur": 1.563, + "args": { + "External id": 38831,"Sequence number": 480082, "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": 2338707, "tid": 2379456, "ts": 6197200099176.717, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SwiGLULinearFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197200099185.720, "dur": 426.809, + "args": { + "External id": 38832,"Record function id": 0, "Sequence number": 480081, "Fwd thread id": 1, "Ev Idx": 7087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197200099186.996, "dur": 413.724, + "args": { + "External id": 38833,"Sequence number": 480081, "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": 2338707, "tid": 2379456, "ts": 6197200099186.996, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200099221.117, "dur": 8.188, + "args": { + "External id": 38834,"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": 2338707, "tid": 2379456, + "ts": 6197200099225.852, "dur": 3.196, + "args": { + "External id": 38835,"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": 2338707, "tid": 2379456, + "ts": 6197200099233.048, "dur": 5.031, + "args": { + "External id": 38836,"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": 2338707, "tid": 2379456, + "ts": 6197200099234.431, "dur": 3.076, + "args": { + "External id": 38837,"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": 2338707, "tid": 2379456, + "ts": 6197200099236.338, "dur": 0.964, + "args": { + "External id": 38838,"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": 2338707, "tid": 2379456, + "ts": 6197200099244.047, "dur": 102.032, + "args": { + "External id": 38839,"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": 2338707, "tid": 2379456, + "ts": 6197200099244.874, "dur": 3.080, + "args": { + "External id": 38840,"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": 2338707, "tid": 2379456, + "ts": 6197200099245.356, "dur": 2.099, + "args": { + "External id": 38841,"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": 2338707, "tid": 2379456, + "ts": 6197200099246.589, "dur": 0.784, + "args": { + "External id": 38842,"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": 2338707, "tid": 2379456, + "ts": 6197200099249.181, "dur": 96.464, + "args": { + "External id": 38843,"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": 2338707, "tid": 2379456, + "ts": 6197200099250.820, "dur": 94.052, + "args": { + "External id": 38844,"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": 2338707, "tid": 2379456, + "ts": 6197200099350.027, "dur": 4.975, + "args": { + "External id": 38845,"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": 2338707, "tid": 2379456, + "ts": 6197200099353.564, "dur": 1.287, + "args": { + "External id": 38846,"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": 2338707, "tid": 2379456, + "ts": 6197200099384.561, "dur": 4.490, + "args": { + "External id": 38847,"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": 2338707, "tid": 2379456, + "ts": 6197200099390.219, "dur": 3.061, + "args": { + "External id": 38848,"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": 2338707, "tid": 2379456, + "ts": 6197200099394.534, "dur": 2.499, + "args": { + "External id": 38849,"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": 2338707, "tid": 2379456, + "ts": 6197200099425.493, "dur": 2.142, + "args": { + "External id": 38850,"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": 2338707, "tid": 2379456, + "ts": 6197200099426.284, "dur": 1.203, + "args": { + "External id": 38851,"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": 2338707, "tid": 2379456, + "ts": 6197200099450.982, "dur": 131.276, + "args": { + "External id": 38852,"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": 2338707, "tid": 2379456, + "ts": 6197200099456.773, "dur": 5.460, + "args": { + "External id": 38853,"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": 2338707, "tid": 2379456, + "ts": 6197200099460.246, "dur": 1.127, + "args": { + "External id": 38854,"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": 2338707, "tid": 2379456, + "ts": 6197200099463.735, "dur": 5.552, + "args": { + "External id": 38855,"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": 2338707, "tid": 2379456, + "ts": 6197200099467.652, "dur": 0.876, + "args": { + "External id": 38856,"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": 2338707, "tid": 2379456, + "ts": 6197200099470.415, "dur": 2.382, + "args": { + "External id": 38857,"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": 2338707, "tid": 2379456, + "ts": 6197200099471.792, "dur": 0.703, + "args": { + "External id": 38858,"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": 2338707, "tid": 2379456, + "ts": 6197200099473.585, "dur": 3.186, + "args": { + "External id": 38859,"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": 2338707, "tid": 2379456, + "ts": 6197200099475.556, "dur": 0.779, + "args": { + "External id": 38860,"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": 2338707, "tid": 2379456, + "ts": 6197200099480.178, "dur": 4.316, + "args": { + "External id": 38861,"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": 2338707, "tid": 2379456, + "ts": 6197200099483.377, "dur": 0.801, + "args": { + "External id": 38862,"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": 2338707, "tid": 2379456, + "ts": 6197200099485.962, "dur": 5.740, + "args": { + "External id": 38863,"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": 2338707, "tid": 2379456, + "ts": 6197200099489.546, "dur": 1.972, + "args": { + "External id": 38864,"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": 2338707, "tid": 2379456, + "ts": 6197200099495.007, "dur": 3.514, + "args": { + "External id": 38865,"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": 2338707, "tid": 2379456, + "ts": 6197200099497.424, "dur": 0.770, + "args": { + "External id": 38866,"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": 2338707, "tid": 2379456, + "ts": 6197200099499.121, "dur": 3.334, + "args": { + "External id": 38867,"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": 2338707, "tid": 2379456, + "ts": 6197200099499.994, "dur": 2.372, + "args": { + "External id": 38868,"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": 2338707, "tid": 2379456, + "ts": 6197200099503.592, "dur": 68.077, + "args": { + "External id": 38869,"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": 2338707, "tid": 2379456, + "ts": 6197200099573.364, "dur": 1.282, + "args": { + "External id": 38870,"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": 2338707, "tid": 2379456, + "ts": 6197200099575.470, "dur": 2.598, + "args": { + "External id": 38871,"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": 2338707, "tid": 2379456, + "ts": 6197200099577.044, "dur": 0.682, + "args": { + "External id": 38872,"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": 2338707, "tid": 2379456, + "ts": 6197200099580.374, "dur": 0.868, + "args": { + "External id": 38873,"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": 2338707, "tid": 2379456, + "ts": 6197200099621.703, "dur": 7.697, + "args": { + "External id": 38874,"Record function id": 0, "Ev Idx": 7129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200099623.550, "dur": 5.169, + "args": { + "External id": 38875,"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": 2338707, "tid": 2379456, + "ts": 6197200099625.032, "dur": 2.903, + "args": { + "External id": 38876,"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": 2338707, "tid": 2379456, + "ts": 6197200099625.769, "dur": 2.027, + "args": { + "External id": 38877,"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": 2338707, "tid": 2379456, + "ts": 6197200099633.271, "dur": 6.889, + "args": { + "External id": 38878,"Record function id": 0, "Sequence number": 480080, "Fwd thread id": 1, "Ev Idx": 7133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200099634.404, "dur": 3.659, + "args": { + "External id": 38879,"Sequence number": 480080, "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": 2338707, "tid": 2379456, "ts": 6197200099634.404, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200099636.242, "dur": 1.614, + "args": { + "External id": 38880,"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": 2338707, "tid": 2379456, + "ts": 6197200099636.903, "dur": 0.827, + "args": { + "External id": 38881,"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": 2338707, "tid": 2379456, + "ts": 6197200099643.975, "dur": 156.232, + "args": { + "External id": 38882,"Record function id": 0, "Sequence number": 480079, "Fwd thread id": 1, "Ev Idx": 7137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200099644.957, "dur": 147.766, + "args": { + "External id": 38883,"Sequence number": 480079, "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": 2338707, "tid": 2379456, "ts": 6197200099644.957, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197200099648.156, "dur": 5.753, + "args": { + "External id": 38884,"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": 2338707, "tid": 2379456, + "ts": 6197200099649.062, "dur": 4.270, + "args": { + "External id": 38885,"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": 2338707, "tid": 2379456, + "ts": 6197200099652.622, "dur": 0.582, + "args": { + "External id": 38886,"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": 2338707, "tid": 2379456, + "ts": 6197200099655.104, "dur": 65.650, + "args": { + "External id": 38887,"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": 2338707, "tid": 2379456, + "ts": 6197200099722.888, "dur": 4.676, + "args": { + "External id": 38888,"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": 2338707, "tid": 2379456, + "ts": 6197200099723.768, "dur": 3.047, + "args": { + "External id": 38889,"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": 2338707, "tid": 2379456, + "ts": 6197200099725.505, "dur": 1.135, + "args": { + "External id": 38890,"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": 2338707, "tid": 2379456, + "ts": 6197200099729.500, "dur": 5.962, + "args": { + "External id": 38891,"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": 2338707, "tid": 2379456, + "ts": 6197200099732.860, "dur": 2.142, + "args": { + "External id": 38892,"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": 2338707, "tid": 2379456, + "ts": 6197200099734.140, "dur": 0.775, + "args": { + "External id": 38893,"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": 2338707, "tid": 2379456, + "ts": 6197200099735.985, "dur": 55.988, + "args": { + "External id": 38894,"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": 2338707, "tid": 2379456, + "ts": 6197200099806.910, "dur": 7.322, + "args": { + "External id": 38895,"Record function id": 0, "Sequence number": 480078, "Fwd thread id": 1, "Ev Idx": 7150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200099808.113, "dur": 4.352, + "args": { + "External id": 38896,"Sequence number": 480078, "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": 2338707, "tid": 2379456, "ts": 6197200099808.113, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200099809.540, "dur": 2.754, + "args": { + "External id": 38897,"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": 2338707, "tid": 2379456, + "ts": 6197200099810.667, "dur": 1.517, + "args": { + "External id": 38898,"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": 2338707, "tid": 2379456, + "ts": 6197200099817.834, "dur": 9.779, + "args": { + "External id": 38899,"Record function id": 0, "Sequence number": 480077, "Fwd thread id": 1, "Ev Idx": 7154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200099818.778, "dur": 6.714, + "args": { + "External id": 38900,"Sequence number": 480077, "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": 2338707, "tid": 2379456, "ts": 6197200099818.778, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197200099819.630, "dur": 5.660, + "args": { + "External id": 38901,"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": 2338707, "tid": 2379456, + "ts": 6197200099822.419, "dur": 2.447, + "args": { + "External id": 38902,"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": 2338707, "tid": 2379456, + "ts": 6197200099823.896, "dur": 0.864, + "args": { + "External id": 38903,"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": 2338707, "tid": 2379456, + "ts": 6197200099831.720, "dur": 6.113, + "args": { + "External id": 38904,"Record function id": 0, "Ev Idx": 7159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200099833.077, "dur": 4.156, + "args": { + "External id": 38905,"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": 2338707, "tid": 2379456, + "ts": 6197200099834.194, "dur": 2.693, + "args": { + "External id": 38906,"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": 2338707, "tid": 2379456, + "ts": 6197200099834.980, "dur": 1.784, + "args": { + "External id": 38907,"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": 2338707, "tid": 2379456, + "ts": 6197200099841.098, "dur": 5.232, + "args": { + "External id": 38908,"Record function id": 0, "Sequence number": 480076, "Fwd thread id": 1, "Ev Idx": 7163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200099842.278, "dur": 2.345, + "args": { + "External id": 38909,"Sequence number": 480076, "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": 2338707, "tid": 2379456, "ts": 6197200099842.278, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200099843.310, "dur": 1.152, + "args": { + "External id": 38910,"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": 2338707, "tid": 2379456, + "ts": 6197200099843.710, "dur": 0.628, + "args": { + "External id": 38911,"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": 2338707, "tid": 2379456, + "ts": 6197200099849.429, "dur": 187.381, + "args": { + "External id": 38912,"Record function id": 0, "Sequence number": 480075, "Fwd thread id": 1, "Ev Idx": 7167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200099903.637, "dur": 126.147, + "args": { + "External id": 38913,"Sequence number": 480075, "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": 2338707, "tid": 2379456, "ts": 6197200099903.637, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197200099906.400, "dur": 2.990, + "args": { + "External id": 38914,"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": 2338707, "tid": 2379456, + "ts": 6197200099906.825, "dur": 2.070, + "args": { + "External id": 38915,"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": 2338707, "tid": 2379456, + "ts": 6197200099908.060, "dur": 0.683, + "args": { + "External id": 38916,"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": 2338707, "tid": 2379456, + "ts": 6197200099909.974, "dur": 55.406, + "args": { + "External id": 38917,"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": 2338707, "tid": 2379456, + "ts": 6197200099966.354, "dur": 6.136, + "args": { + "External id": 38918,"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": 2338707, "tid": 2379456, + "ts": 6197200099966.811, "dur": 5.202, + "args": { + "External id": 38919,"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": 2338707, "tid": 2379456, + "ts": 6197200099970.580, "dur": 1.263, + "args": { + "External id": 38920,"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": 2338707, "tid": 2379456, + "ts": 6197200099973.797, "dur": 3.590, + "args": { + "External id": 38921,"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": 2338707, "tid": 2379456, + "ts": 6197200099974.831, "dur": 1.860, + "args": { + "External id": 38922,"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": 2338707, "tid": 2379456, + "ts": 6197200099976.018, "dur": 0.546, + "args": { + "External id": 38923,"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": 2338707, "tid": 2379456, + "ts": 6197200099977.811, "dur": 51.283, + "args": { + "External id": 38924,"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": 2338707, "tid": 2379456, + "ts": 6197200100041.375, "dur": 68.819, + "args": { + "External id": 38925,"Record function id": 0, "Sequence number": 480074, "Fwd thread id": 1, "Ev Idx": 7180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200100042.361, "dur": 3.733, + "args": { + "External id": 38926,"Sequence number": 480074, "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": 2338707, "tid": 2379456, "ts": 6197200100042.361, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200100043.868, "dur": 2.069, + "args": { + "External id": 38927,"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": 2338707, "tid": 2379456, + "ts": 6197200100044.595, "dur": 1.234, + "args": { + "External id": 38928,"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": 2338707, "tid": 2379456, + "ts": 6197200100048.860, "dur": 57.044, + "args": { + "External id": 38929,"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": 2338707, "tid": 2379456, + "ts": 6197200100116.552, "dur": 10.172, + "args": { + "External id": 38930,"Record function id": 0, "Sequence number": 480073, "Fwd thread id": 1, "Ev Idx": 7185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200100119.918, "dur": 5.248, + "args": { + "External id": 38931,"Sequence number": 480073, "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": 2338707, "tid": 2379456, "ts": 6197200100119.918, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197200100120.863, "dur": 4.107, + "args": { + "External id": 38932,"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": 2338707, "tid": 2379456, + "ts": 6197200100121.708, "dur": 2.590, + "args": { + "External id": 38933,"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": 2338707, "tid": 2379456, + "ts": 6197200100123.245, "dur": 0.936, + "args": { + "External id": 38934,"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": 2338707, "tid": 2379456, + "ts": 6197200100131.127, "dur": 6.606, + "args": { + "External id": 38935,"Record function id": 0, "Ev Idx": 7190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200100132.803, "dur": 4.375, + "args": { + "External id": 38936,"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": 2338707, "tid": 2379456, + "ts": 6197200100134.083, "dur": 2.540, + "args": { + "External id": 38937,"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": 2338707, "tid": 2379456, + "ts": 6197200100134.878, "dur": 1.664, + "args": { + "External id": 38938,"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": 2338707, "tid": 2379456, + "ts": 6197200100142.292, "dur": 431.466, + "args": { + "External id": 38939,"Record function id": 0, "Sequence number": 480072, "Fwd thread id": 1, "Ev Idx": 7194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197200100146.284, "dur": 391.467, + "args": { + "External id": 38940,"Sequence number": 480072, "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": 2338707, "tid": 2379456, "ts": 6197200100146.284, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338707, "tid": 2379456, + "ts": 6197200100169.930, "dur": 39.204, + "args": { + "External id": 38941,"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": 2338707, "tid": 2379456, + "ts": 6197200100171.547, "dur": 37.367, + "args": { + "External id": 38942,"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": 2338707, "tid": 2379456, + "ts": 6197200100174.486, "dur": 6.491, + "args": { + "External id": 38943,"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": 2338707, "tid": 2379456, + "ts": 6197200100177.014, "dur": 3.435, + "args": { + "External id": 38944,"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": 2338707, "tid": 2379456, + "ts": 6197200100182.318, "dur": 26.174, + "args": { + "External id": 38945,"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": 2338707, "tid": 2379456, + "ts": 6197200100224.219, "dur": 2.277, + "args": { + "External id": 38946,"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": 2338707, "tid": 2379456, + "ts": 6197200100224.677, "dur": 1.659, + "args": { + "External id": 38947,"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": 2338707, "tid": 2379456, + "ts": 6197200100230.294, "dur": 1.522, + "args": { + "External id": 38948,"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": 2338707, "tid": 2379456, + "ts": 6197200100230.868, "dur": 0.828, + "args": { + "External id": 38949,"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": 2338707, "tid": 2379456, + "ts": 6197200100246.827, "dur": 2.600, + "args": { + "External id": 38950,"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": 2338707, "tid": 2379456, + "ts": 6197200100260.071, "dur": 2.797, + "args": { + "External id": 38951,"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": 2338707, "tid": 2379456, + "ts": 6197200100424.644, "dur": 2.817, + "args": { + "External id": 38952,"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": 2338707, "tid": 2379456, + "ts": 6197200100432.087, "dur": 36.329, + "args": { + "External id": 38953,"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": 2338707, "tid": 2379456, + "ts": 6197200100441.569, "dur": 0.965, + "args": { + "External id": 38954,"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": 2338707, "tid": 2379456, + "ts": 6197200100473.967, "dur": 30.819, + "args": { + "External id": 38955,"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": 2338707, "tid": 2379456, + "ts": 6197200100475.650, "dur": 28.927, + "args": { + "External id": 38956,"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": 2338707, "tid": 2379456, + "ts": 6197200100479.772, "dur": 4.496, + "args": { + "External id": 38957,"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": 2338707, "tid": 2379456, + "ts": 6197200100487.712, "dur": 16.385, + "args": { + "External id": 38958,"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": 2338707, "tid": 2379456, + "ts": 6197200100509.158, "dur": 2.669, + "args": { + "External id": 38959,"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": 2338707, "tid": 2379456, + "ts": 6197200100510.523, "dur": 1.166, + "args": { + "External id": 38960,"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": 2338707, "tid": 2379456, + "ts": 6197200100518.693, "dur": 2.908, + "args": { + "External id": 38961,"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": 2338707, "tid": 2379456, + "ts": 6197200100519.948, "dur": 1.524, + "args": { + "External id": 38962,"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": 2338707, "tid": 2379456, + "ts": 6197200100523.514, "dur": 2.590, + "args": { + "External id": 38963,"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": 2338707, "tid": 2379456, + "ts": 6197200100524.781, "dur": 1.206, + "args": { + "External id": 38964,"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": 2338707, "tid": 2379456, + "ts": 6197200100554.625, "dur": 17.557, + "args": { + "External id": 38965,"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": 2338707, "tid": 2379456, + "ts": 6197200100584.248, "dur": 8.133, + "args": { + "External id": 38966,"Record function id": 0, "Ev Idx": 7221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200100586.294, "dur": 5.418, + "args": { + "External id": 38967,"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": 2338707, "tid": 2379456, + "ts": 6197200100588.036, "dur": 2.742, + "args": { + "External id": 38968,"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": 2338707, "tid": 2379456, + "ts": 6197200100589.178, "dur": 1.457, + "args": { + "External id": 38969,"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": 2338707, "tid": 2379456, + "ts": 6197200100596.418, "dur": 8.336, + "args": { + "External id": 38970,"Record function id": 0, "Sequence number": 480071, "Fwd thread id": 1, "Ev Idx": 7225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200100597.723, "dur": 4.382, + "args": { + "External id": 38971,"Sequence number": 480071, "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": 2338707, "tid": 2379456, "ts": 6197200100597.723, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200100599.404, "dur": 2.501, + "args": { + "External id": 38972,"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": 2338707, "tid": 2379456, + "ts": 6197200100600.662, "dur": 1.096, + "args": { + "External id": 38973,"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": 2338707, "tid": 2379456, + "ts": 6197200100608.222, "dur": 174.975, + "args": { + "External id": 38974,"Record function id": 0, "Sequence number": 480070, "Fwd thread id": 1, "Ev Idx": 7229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200100609.034, "dur": 165.275, + "args": { + "External id": 38975,"Sequence number": 480070, "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": 2338707, "tid": 2379456, "ts": 6197200100609.034, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197200100612.428, "dur": 6.836, + "args": { + "External id": 38976,"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": 2338707, "tid": 2379456, + "ts": 6197200100615.705, "dur": 2.962, + "args": { + "External id": 38977,"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": 2338707, "tid": 2379456, + "ts": 6197200100617.428, "dur": 1.017, + "args": { + "External id": 38978,"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": 2338707, "tid": 2379456, + "ts": 6197200100620.649, "dur": 73.426, + "args": { + "External id": 38979,"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": 2338707, "tid": 2379456, + "ts": 6197200100695.235, "dur": 23.372, + "args": { + "External id": 38980,"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": 2338707, "tid": 2379456, + "ts": 6197200100696.004, "dur": 3.639, + "args": { + "External id": 38981,"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": 2338707, "tid": 2379456, + "ts": 6197200100697.734, "dur": 1.738, + "args": { + "External id": 38982,"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": 2338707, "tid": 2379456, + "ts": 6197200100721.643, "dur": 6.512, + "args": { + "External id": 38983,"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": 2338707, "tid": 2379456, + "ts": 6197200100725.163, "dur": 2.373, + "args": { + "External id": 38984,"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": 2338707, "tid": 2379456, + "ts": 6197200100726.715, "dur": 0.697, + "args": { + "External id": 38985,"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": 2338707, "tid": 2379456, + "ts": 6197200100728.773, "dur": 44.935, + "args": { + "External id": 38986,"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": 2338707, "tid": 2379456, + "ts": 6197200100790.435, "dur": 8.366, + "args": { + "External id": 38987,"Record function id": 0, "Sequence number": 480069, "Fwd thread id": 1, "Ev Idx": 7242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200100791.716, "dur": 5.026, + "args": { + "External id": 38988,"Sequence number": 480069, "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": 2338707, "tid": 2379456, "ts": 6197200100791.716, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200100794.216, "dur": 2.358, + "args": { + "External id": 38989,"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": 2338707, "tid": 2379456, + "ts": 6197200100794.979, "dur": 1.451, + "args": { + "External id": 38990,"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": 2338707, "tid": 2379456, + "ts": 6197200100802.234, "dur": 13.768, + "args": { + "External id": 38991,"Record function id": 0, "Sequence number": 480068, "Fwd thread id": 1, "Ev Idx": 7246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200100803.372, "dur": 10.451, + "args": { + "External id": 38992,"Sequence number": 480068, "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": 2338707, "tid": 2379456, "ts": 6197200100803.372, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197200100804.156, "dur": 9.473, + "args": { + "External id": 38993,"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": 2338707, "tid": 2379456, + "ts": 6197200100804.923, "dur": 8.200, + "args": { + "External id": 38994,"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": 2338707, "tid": 2379456, + "ts": 6197200100812.371, "dur": 0.657, + "args": { + "External id": 38995,"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": 2338707, "tid": 2379456, + "ts": 6197200100820.468, "dur": 6.788, + "args": { + "External id": 38996,"Record function id": 0, "Ev Idx": 7251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200100821.771, "dur": 4.900, + "args": { + "External id": 38997,"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": 2338707, "tid": 2379456, + "ts": 6197200100823.452, "dur": 2.767, + "args": { + "External id": 38998,"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": 2338707, "tid": 2379456, + "ts": 6197200100824.218, "dur": 1.853, + "args": { + "External id": 38999,"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": 2338707, "tid": 2379456, + "ts": 6197200100830.811, "dur": 6.647, + "args": { + "External id": 39000,"Record function id": 0, "Sequence number": 480067, "Fwd thread id": 1, "Ev Idx": 7255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200100831.881, "dur": 3.289, + "args": { + "External id": 39001,"Sequence number": 480067, "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": 2338707, "tid": 2379456, "ts": 6197200100831.881, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200100833.018, "dur": 1.993, + "args": { + "External id": 39002,"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": 2338707, "tid": 2379456, + "ts": 6197200100833.729, "dur": 1.135, + "args": { + "External id": 39003,"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": 2338707, "tid": 2379456, + "ts": 6197200100841.889, "dur": 399.981, + "args": { + "External id": 39004,"Record function id": 0, "Sequence number": 480066, "Fwd thread id": 1, "Ev Idx": 7259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFuncBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197200100843.077, "dur": 374.961, + "args": { + "External id": 39005,"Sequence number": 480066, "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": 2338707, "tid": 2379456, "ts": 6197200100843.077, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338707, "tid": 2379456, + "ts": 6197200100861.081, "dur": 7.010, + "args": { + "External id": 39006,"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": 2338707, "tid": 2379456, + "ts": 6197200100863.748, "dur": 3.917, + "args": { + "External id": 39007,"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": 2338707, "tid": 2379456, + "ts": 6197200100870.362, "dur": 4.013, + "args": { + "External id": 39008,"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": 2338707, "tid": 2379456, + "ts": 6197200100871.902, "dur": 2.264, + "args": { + "External id": 39009,"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": 2338707, "tid": 2379456, + "ts": 6197200100875.728, "dur": 3.815, + "args": { + "External id": 39010,"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": 2338707, "tid": 2379456, + "ts": 6197200100877.154, "dur": 2.225, + "args": { + "External id": 39011,"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": 2338707, "tid": 2379456, + "ts": 6197200100904.424, "dur": 287.087, + "args": { + "External id": 39012,"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": 2338707, "tid": 2379456, + "ts": 6197200100983.610, "dur": 3.860, + "args": { + "External id": 39013,"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": 2338707, "tid": 2379456, + "ts": 6197200100989.545, "dur": 2.873, + "args": { + "External id": 39014,"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": 2338707, "tid": 2379456, + "ts": 6197200100993.390, "dur": 1.906, + "args": { + "External id": 39015,"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": 2338707, "tid": 2379456, + "ts": 6197200100996.517, "dur": 2.217, + "args": { + "External id": 39016,"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": 2338707, "tid": 2379456, + "ts": 6197200101046.200, "dur": 3.754, + "args": { + "External id": 39017,"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": 2338707, "tid": 2379456, + "ts": 6197200101048.316, "dur": 1.494, + "args": { + "External id": 39018,"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": 2338707, "tid": 2379456, + "ts": 6197200101051.885, "dur": 68.024, + "args": { + "External id": 39019,"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": 2338707, "tid": 2379456, + "ts": 6197200101093.318, "dur": 1.535, + "args": { + "External id": 39020,"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": 2338707, "tid": 2379456, + "ts": 6197200101123.676, "dur": 2.334, + "args": { + "External id": 39021,"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": 2338707, "tid": 2379456, + "ts": 6197200101125.299, "dur": 0.629, + "args": { + "External id": 39022,"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": 2338707, "tid": 2379456, + "ts": 6197200101127.575, "dur": 18.210, + "args": { + "External id": 39023,"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": 2338707, "tid": 2379456, + "ts": 6197200101130.865, "dur": 0.924, + "args": { + "External id": 39024,"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": 2338707, "tid": 2379456, + "ts": 6197200101204.924, "dur": 3.828, + "args": { + "External id": 39025,"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": 2338707, "tid": 2379456, + "ts": 6197200101211.884, "dur": 0.701, + "args": { + "External id": 39026,"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": 2338707, "tid": 2379456, + "ts": 6197200101214.629, "dur": 0.562, + "args": { + "External id": 39027,"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": 2338707, "tid": 2379456, + "ts": 6197200101252.072, "dur": 225.527, + "args": { + "External id": 39028,"Record function id": 0, "Sequence number": 480065, "Fwd thread id": 1, "Ev Idx": 7283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197200101253.964, "dur": 216.852, + "args": { + "External id": 39029,"Sequence number": 480065, "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": 2338707, "tid": 2379456, "ts": 6197200101253.964, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338707, "tid": 2379456, + "ts": 6197200101274.949, "dur": 44.323, + "args": { + "External id": 39030,"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": 2338707, "tid": 2379456, + "ts": 6197200101277.891, "dur": 4.026, + "args": { + "External id": 39031,"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": 2338707, "tid": 2379456, + "ts": 6197200101283.472, "dur": 35.037, + "args": { + "External id": 39032,"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": 2338707, "tid": 2379456, + "ts": 6197200101329.495, "dur": 5.489, + "args": { + "External id": 39033,"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": 2338707, "tid": 2379456, + "ts": 6197200101331.965, "dur": 2.649, + "args": { + "External id": 39034,"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": 2338707, "tid": 2379456, + "ts": 6197200101484.419, "dur": 156.412, + "args": { + "External id": 39035,"Record function id": 0, "Sequence number": 480064, "Fwd thread id": 1, "Ev Idx": 7290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197200101486.336, "dur": 148.430, + "args": { + "External id": 39036,"Sequence number": 480064, "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": 2338707, "tid": 2379456, "ts": 6197200101486.336, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338707, "tid": 2379456, + "ts": 6197200101497.499, "dur": 41.643, + "args": { + "External id": 39037,"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": 2338707, "tid": 2379456, + "ts": 6197200101499.995, "dur": 2.372, + "args": { + "External id": 39038,"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": 2338707, "tid": 2379456, + "ts": 6197200101503.588, "dur": 34.971, + "args": { + "External id": 39039,"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": 2338707, "tid": 2379456, + "ts": 6197200101546.284, "dur": 4.689, + "args": { + "External id": 39040,"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": 2338707, "tid": 2379456, + "ts": 6197200101548.151, "dur": 2.553, + "args": { + "External id": 39041,"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": 2338707, "tid": 2379456, + "ts": 6197200101647.017, "dur": 11.337, + "args": { + "External id": 39042,"Record function id": 0, "Sequence number": 480063, "Fwd thread id": 1, "Ev Idx": 7297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200101648.426, "dur": 7.540, + "args": { + "External id": 39043,"Sequence number": 480063, "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": 2338707, "tid": 2379456, "ts": 6197200101648.426, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200101650.714, "dur": 4.973, + "args": { + "External id": 39044,"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": 2338707, "tid": 2379456, + "ts": 6197200101651.953, "dur": 3.523, + "args": { + "External id": 39045,"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": 2338707, "tid": 2379456, + "ts": 6197200101661.975, "dur": 7.382, + "args": { + "External id": 39046,"Record function id": 0, "Sequence number": 480062, "Fwd thread id": 1, "Ev Idx": 7301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200101663.257, "dur": 4.000, + "args": { + "External id": 39047,"Sequence number": 480062, "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": 2338707, "tid": 2379456, "ts": 6197200101663.257, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200101664.892, "dur": 2.215, + "args": { + "External id": 39048,"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": 2338707, "tid": 2379456, + "ts": 6197200101665.994, "dur": 0.977, + "args": { + "External id": 39049,"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": 2338707, "tid": 2379456, + "ts": 6197200101672.857, "dur": 6.956, + "args": { + "External id": 39050,"Record function id": 0, "Sequence number": 480061, "Fwd thread id": 1, "Ev Idx": 7305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200101673.860, "dur": 4.060, + "args": { + "External id": 39051,"Sequence number": 480061, "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": 2338707, "tid": 2379456, "ts": 6197200101673.860, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200101675.522, "dur": 2.258, + "args": { + "External id": 39052,"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": 2338707, "tid": 2379456, + "ts": 6197200101676.560, "dur": 1.128, + "args": { + "External id": 39053,"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": 2338707, "tid": 2379456, + "ts": 6197200101683.266, "dur": 9.735, + "args": { + "External id": 39054,"Record function id": 0, "Sequence number": 480060, "Fwd thread id": 1, "Ev Idx": 7309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200101684.764, "dur": 5.708, + "args": { + "External id": 39055,"Sequence number": 480060, "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": 2338707, "tid": 2379456, "ts": 6197200101684.764, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200101686.233, "dur": 4.101, + "args": { + "External id": 39056,"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": 2338707, "tid": 2379456, + "ts": 6197200101689.342, "dur": 0.899, + "args": { + "External id": 39057,"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": 2338707, "tid": 2379456, + "ts": 6197200101696.444, "dur": 180.518, + "args": { + "External id": 39058,"Record function id": 0, "Sequence number": 480059, "Fwd thread id": 1, "Ev Idx": 7313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200101697.424, "dur": 170.438, + "args": { + "External id": 39059,"Sequence number": 480059, "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": 2338707, "tid": 2379456, "ts": 6197200101697.424, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197200101719.026, "dur": 8.415, + "args": { + "External id": 39060,"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": 2338707, "tid": 2379456, + "ts": 6197200101721.044, "dur": 5.469, + "args": { + "External id": 39061,"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": 2338707, "tid": 2379456, + "ts": 6197200101724.437, "dur": 1.592, + "args": { + "External id": 39062,"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": 2338707, "tid": 2379456, + "ts": 6197200101731.733, "dur": 73.389, + "args": { + "External id": 39063,"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": 2338707, "tid": 2379456, + "ts": 6197200101806.390, "dur": 5.524, + "args": { + "External id": 39064,"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": 2338707, "tid": 2379456, + "ts": 6197200101807.614, "dur": 3.563, + "args": { + "External id": 39065,"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": 2338707, "tid": 2379456, + "ts": 6197200101809.479, "dur": 1.525, + "args": { + "External id": 39066,"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": 2338707, "tid": 2379456, + "ts": 6197200101814.193, "dur": 5.315, + "args": { + "External id": 39067,"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": 2338707, "tid": 2379456, + "ts": 6197200101815.557, "dur": 3.550, + "args": { + "External id": 39068,"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": 2338707, "tid": 2379456, + "ts": 6197200101818.510, "dur": 0.488, + "args": { + "External id": 39069,"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": 2338707, "tid": 2379456, + "ts": 6197200101820.196, "dur": 46.737, + "args": { + "External id": 39070,"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": 2338707, "tid": 2379456, + "ts": 6197200101884.526, "dur": 7.215, + "args": { + "External id": 39071,"Record function id": 0, "Sequence number": 480058, "Fwd thread id": 1, "Ev Idx": 7326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200101885.552, "dur": 4.529, + "args": { + "External id": 39072,"Sequence number": 480058, "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": 2338707, "tid": 2379456, "ts": 6197200101885.552, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200101887.154, "dur": 2.790, + "args": { + "External id": 39073,"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": 2338707, "tid": 2379456, + "ts": 6197200101888.323, "dur": 1.487, + "args": { + "External id": 39074,"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": 2338707, "tid": 2379456, + "ts": 6197200101895.146, "dur": 10.762, + "args": { + "External id": 39075,"Record function id": 0, "Sequence number": 480057, "Fwd thread id": 1, "Ev Idx": 7330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200101896.345, "dur": 7.490, + "args": { + "External id": 39076,"Sequence number": 480057, "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": 2338707, "tid": 2379456, "ts": 6197200101896.345, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197200101897.333, "dur": 6.289, + "args": { + "External id": 39077,"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": 2338707, "tid": 2379456, + "ts": 6197200101900.708, "dur": 2.380, + "args": { + "External id": 39078,"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": 2338707, "tid": 2379456, + "ts": 6197200101902.046, "dur": 0.925, + "args": { + "External id": 39079,"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": 2338707, "tid": 2379456, + "ts": 6197200101912.254, "dur": 10.641, + "args": { + "External id": 39080,"Record function id": 0, "Ev Idx": 7335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200101914.206, "dur": 8.042, + "args": { + "External id": 39081,"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": 2338707, "tid": 2379456, + "ts": 6197200101917.252, "dur": 4.454, + "args": { + "External id": 39082,"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": 2338707, "tid": 2379456, + "ts": 6197200101918.683, "dur": 2.921, + "args": { + "External id": 39083,"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": 2338707, "tid": 2379456, + "ts": 6197200101926.362, "dur": 6.604, + "args": { + "External id": 39084,"Record function id": 0, "Sequence number": 480056, "Fwd thread id": 1, "Ev Idx": 7339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200101927.680, "dur": 3.130, + "args": { + "External id": 39085,"Sequence number": 480056, "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": 2338707, "tid": 2379456, "ts": 6197200101927.680, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200101929.028, "dur": 1.642, + "args": { + "External id": 39086,"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": 2338707, "tid": 2379456, + "ts": 6197200101929.638, "dur": 0.896, + "args": { + "External id": 39087,"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": 2338707, "tid": 2379456, + "ts": 6197200101936.375, "dur": 91.055, + "args": { + "External id": 39088,"Record function id": 0, "Sequence number": 480055, "Fwd thread id": 1, "Ev Idx": 7343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200101939.282, "dur": 81.267, + "args": { + "External id": 39089,"Sequence number": 480055, "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": 2338707, "tid": 2379456, "ts": 6197200101939.282, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197200101942.021, "dur": 2.648, + "args": { + "External id": 39090,"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": 2338707, "tid": 2379456, + "ts": 6197200101942.560, "dur": 1.672, + "args": { + "External id": 39091,"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": 2338707, "tid": 2379456, + "ts": 6197200101943.453, "dur": 0.656, + "args": { + "External id": 39092,"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": 2338707, "tid": 2379456, + "ts": 6197200101945.583, "dur": 27.112, + "args": { + "External id": 39093,"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": 2338707, "tid": 2379456, + "ts": 6197200101973.560, "dur": 6.324, + "args": { + "External id": 39094,"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": 2338707, "tid": 2379456, + "ts": 6197200101974.189, "dur": 5.180, + "args": { + "External id": 39095,"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": 2338707, "tid": 2379456, + "ts": 6197200101977.722, "dur": 1.515, + "args": { + "External id": 39096,"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": 2338707, "tid": 2379456, + "ts": 6197200101981.261, "dur": 3.642, + "args": { + "External id": 39097,"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": 2338707, "tid": 2379456, + "ts": 6197200101982.006, "dur": 2.362, + "args": { + "External id": 39098,"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": 2338707, "tid": 2379456, + "ts": 6197200101983.553, "dur": 0.708, + "args": { + "External id": 39099,"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": 2338707, "tid": 2379456, + "ts": 6197200101985.542, "dur": 34.142, + "args": { + "External id": 39100,"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": 2338707, "tid": 2379456, + "ts": 6197200102032.090, "dur": 84.772, + "args": { + "External id": 39101,"Record function id": 0, "Sequence number": 480054, "Fwd thread id": 1, "Ev Idx": 7356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200102040.789, "dur": 8.161, + "args": { + "External id": 39102,"Sequence number": 480054, "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": 2338707, "tid": 2379456, "ts": 6197200102040.789, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200102046.660, "dur": 2.147, + "args": { + "External id": 39103,"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": 2338707, "tid": 2379456, + "ts": 6197200102047.693, "dur": 1.003, + "args": { + "External id": 39104,"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": 2338707, "tid": 2379456, + "ts": 6197200102052.276, "dur": 61.173, + "args": { + "External id": 39105,"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": 2338707, "tid": 2379456, + "ts": 6197200102123.138, "dur": 12.710, + "args": { + "External id": 39106,"Record function id": 0, "Sequence number": 480053, "Fwd thread id": 1, "Ev Idx": 7361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200102124.479, "dur": 8.957, + "args": { + "External id": 39107,"Sequence number": 480053, "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": 2338707, "tid": 2379456, "ts": 6197200102124.479, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197200102128.307, "dur": 4.890, + "args": { + "External id": 39108,"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": 2338707, "tid": 2379456, + "ts": 6197200102129.427, "dur": 3.078, + "args": { + "External id": 39109,"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": 2338707, "tid": 2379456, + "ts": 6197200102131.340, "dur": 1.010, + "args": { + "External id": 39110,"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": 2338707, "tid": 2379456, + "ts": 6197200102140.643, "dur": 7.154, + "args": { + "External id": 39111,"Record function id": 0, "Ev Idx": 7366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200102142.217, "dur": 4.979, + "args": { + "External id": 39112,"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": 2338707, "tid": 2379456, + "ts": 6197200102143.849, "dur": 2.838, + "args": { + "External id": 39113,"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": 2338707, "tid": 2379456, + "ts": 6197200102144.685, "dur": 1.875, + "args": { + "External id": 39114,"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": 2338707, "tid": 2379456, + "ts": 6197200102151.082, "dur": 6.442, + "args": { + "External id": 39115,"Record function id": 0, "Sequence number": 480052, "Fwd thread id": 1, "Ev Idx": 7370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200102152.151, "dur": 3.514, + "args": { + "External id": 39116,"Sequence number": 480052, "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": 2338707, "tid": 2379456, "ts": 6197200102152.151, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200102153.558, "dur": 1.956, + "args": { + "External id": 39117,"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": 2338707, "tid": 2379456, + "ts": 6197200102154.217, "dur": 1.211, + "args": { + "External id": 39118,"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": 2338707, "tid": 2379456, + "ts": 6197200102160.924, "dur": 104.547, + "args": { + "External id": 39119,"Record function id": 0, "Sequence number": 480051, "Fwd thread id": 1, "Ev Idx": 7374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200102164.036, "dur": 93.085, + "args": { + "External id": 39120,"Sequence number": 480051, "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": 2338707, "tid": 2379456, "ts": 6197200102164.036, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197200102166.794, "dur": 2.822, + "args": { + "External id": 39121,"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": 2338707, "tid": 2379456, + "ts": 6197200102167.367, "dur": 1.803, + "args": { + "External id": 39122,"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": 2338707, "tid": 2379456, + "ts": 6197200102168.164, "dur": 0.894, + "args": { + "External id": 39123,"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": 2338707, "tid": 2379456, + "ts": 6197200102170.617, "dur": 40.076, + "args": { + "External id": 39124,"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": 2338707, "tid": 2379456, + "ts": 6197200102211.838, "dur": 5.479, + "args": { + "External id": 39125,"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": 2338707, "tid": 2379456, + "ts": 6197200102212.421, "dur": 4.332, + "args": { + "External id": 39126,"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": 2338707, "tid": 2379456, + "ts": 6197200102215.987, "dur": 0.636, + "args": { + "External id": 39127,"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": 2338707, "tid": 2379456, + "ts": 6197200102219.050, "dur": 4.088, + "args": { + "External id": 39128,"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": 2338707, "tid": 2379456, + "ts": 6197200102219.948, "dur": 2.525, + "args": { + "External id": 39129,"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": 2338707, "tid": 2379456, + "ts": 6197200102221.536, "dur": 0.847, + "args": { + "External id": 39130,"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": 2338707, "tid": 2379456, + "ts": 6197200102223.707, "dur": 32.623, + "args": { + "External id": 39131,"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": 2338707, "tid": 2379456, + "ts": 6197200102270.726, "dur": 37.770, + "args": { + "External id": 39132,"Record function id": 0, "Sequence number": 480050, "Fwd thread id": 1, "Ev Idx": 7387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200102272.250, "dur": 9.376, + "args": { + "External id": 39133,"Sequence number": 480050, "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": 2338707, "tid": 2379456, "ts": 6197200102272.250, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200102276.576, "dur": 4.830, + "args": { + "External id": 39134,"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": 2338707, "tid": 2379456, + "ts": 6197200102277.803, "dur": 3.371, + "args": { + "External id": 39135,"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": 2338707, "tid": 2379456, + "ts": 6197200102285.151, "dur": 19.730, + "args": { + "External id": 39136,"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": 2338707, "tid": 2379456, + "ts": 6197200102314.033, "dur": 10.627, + "args": { + "External id": 39137,"Record function id": 0, "Sequence number": 480049, "Fwd thread id": 1, "Ev Idx": 7392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6197200102315.547, "dur": 6.822, + "args": { + "External id": 39138,"Sequence number": 480049, "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": 2338707, "tid": 2379456, "ts": 6197200102315.547, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6197200102316.712, "dur": 5.372, + "args": { + "External id": 39139,"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": 2338707, "tid": 2379456, + "ts": 6197200102317.863, "dur": 3.419, + "args": { + "External id": 39140,"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": 2338707, "tid": 2379456, + "ts": 6197200102320.012, "dur": 1.077, + "args": { + "External id": 39141,"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": 2338707, "tid": 2379456, + "ts": 6197200102330.286, "dur": 8.703, + "args": { + "External id": 39142,"Record function id": 0, "Ev Idx": 7397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200102332.408, "dur": 5.745, + "args": { + "External id": 39143,"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": 2338707, "tid": 2379456, + "ts": 6197200102334.056, "dur": 3.475, + "args": { + "External id": 39144,"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": 2338707, "tid": 2379456, + "ts": 6197200102335.117, "dur": 2.283, + "args": { + "External id": 39145,"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": 2338707, "tid": 2379456, + "ts": 6197200102344.910, "dur": 418.729, + "args": { + "External id": 39146,"Record function id": 0, "Sequence number": 480048, "Fwd thread id": 1, "Ev Idx": 7401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197200102347.028, "dur": 374.353, + "args": { + "External id": 39147,"Sequence number": 480048, "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": 2338707, "tid": 2379456, "ts": 6197200102347.028, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6197200102394.976, "dur": 3.121, + "args": { + "External id": 39148,"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": 2338707, "tid": 2379456, + "ts": 6197200102396.144, "dur": 1.692, + "args": { + "External id": 39149,"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": 2338707, "tid": 2379456, + "ts": 6197200102416.415, "dur": 5.591, + "args": { + "External id": 39150,"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": 2338707, "tid": 2379456, + "ts": 6197200102431.778, "dur": 2.827, + "args": { + "External id": 39151,"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": 2338707, "tid": 2379456, + "ts": 6197200102596.385, "dur": 2.185, + "args": { + "External id": 39152,"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": 2338707, "tid": 2379456, + "ts": 6197200102606.251, "dur": 35.666, + "args": { + "External id": 39153,"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": 2338707, "tid": 2379456, + "ts": 6197200102617.271, "dur": 1.181, + "args": { + "External id": 39154,"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": 2338707, "tid": 2379456, + "ts": 6197200102647.736, "dur": 31.662, + "args": { + "External id": 39155,"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": 2338707, "tid": 2379456, + "ts": 6197200102651.824, "dur": 27.363, + "args": { + "External id": 39156,"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": 2338707, "tid": 2379456, + "ts": 6197200102656.184, "dur": 4.545, + "args": { + "External id": 39157,"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": 2338707, "tid": 2379456, + "ts": 6197200102662.441, "dur": 16.179, + "args": { + "External id": 39158,"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": 2338707, "tid": 2379456, + "ts": 6197200102684.261, "dur": 2.819, + "args": { + "External id": 39159,"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": 2338707, "tid": 2379456, + "ts": 6197200102685.612, "dur": 1.321, + "args": { + "External id": 39160,"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": 2338707, "tid": 2379456, + "ts": 6197200102693.917, "dur": 4.811, + "args": { + "External id": 39161,"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": 2338707, "tid": 2379456, + "ts": 6197200102697.423, "dur": 1.195, + "args": { + "External id": 39162,"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": 2338707, "tid": 2379456, + "ts": 6197200102739.429, "dur": 19.051, + "args": { + "External id": 39163,"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": 2338707, "tid": 2379456, + "ts": 6197200102777.493, "dur": 9.729, + "args": { + "External id": 39164,"Record function id": 0, "Ev Idx": 7419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200102779.438, "dur": 7.000, + "args": { + "External id": 39165,"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": 2338707, "tid": 2379456, + "ts": 6197200102781.490, "dur": 3.566, + "args": { + "External id": 39166,"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": 2338707, "tid": 2379456, + "ts": 6197200102782.804, "dur": 2.114, + "args": { + "External id": 39167,"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": 2338707, "tid": 2379456, + "ts": 6197200102791.587, "dur": 2737.313, + "args": { + "External id": 39168,"Record function id": 0, "Ev Idx": 7423 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.25)", "pid": 2338707, "tid": 2379456, + "ts": 6197200102823.687, "dur": 928.138, + "args": { + "External id": 39169,"Record function id": 0, "Ev Idx": 7424 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.24", "pid": 2338707, "tid": 2379456, + "ts": 6197200102847.902, "dur": 894.858, + "args": { + "External id": 39170,"Record function id": 0, "Ev Idx": 7425 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.24)", "pid": 2338707, "tid": 2379456, + "ts": 6197200102867.439, "dur": 858.292, + "args": { + "External id": 39171,"Record function id": 0, "Ev Idx": 7426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197200102958.238, "dur": 5.766, + "args": { + "External id": 39172,"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": 2338707, "tid": 2379456, + "ts": 6197200102979.365, "dur": 29.724, + "args": { + "External id": 39173,"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": 2338707, "tid": 2379456, + "ts": 6197200102985.384, "dur": 1.149, + "args": { + "External id": 39174,"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": 2338707, "tid": 2379456, + "ts": 6197200102987.986, "dur": 0.247, + "args": { + "External id": 39175,"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": 2338707, "tid": 2379456, + "ts": 6197200102989.584, "dur": 0.754, + "args": { + "External id": 39176,"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": 2338707, "tid": 2379456, + "ts": 6197200102992.985, "dur": 0.977, + "args": { + "External id": 39177,"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": 2338707, "tid": 2379456, + "ts": 6197200102995.061, "dur": 0.692, + "args": { + "External id": 39178,"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": 2338707, "tid": 2379456, + "ts": 6197200102996.942, "dur": 1.615, + "args": { + "External id": 39179,"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": 2338707, "tid": 2379456, + "ts": 6197200102999.695, "dur": 0.587, + "args": { + "External id": 39180,"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": 2338707, "tid": 2379456, + "ts": 6197200103001.188, "dur": 0.440, + "args": { + "External id": 39181,"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": 2338707, "tid": 2379456, + "ts": 6197200103004.042, "dur": 0.590, + "args": { + "External id": 39182,"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": 2338707, "tid": 2379456, + "ts": 6197200103021.087, "dur": 83.611, + "args": { + "External id": 39183,"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": 2338707, "tid": 2379456, + "ts": 6197200103146.476, "dur": 120.987, + "args": { + "External id": 39184,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2379456, + "ts": 6197200103157.734, "dur": 5.348, + "args": { + "External id": 39185,"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": 2338707, "tid": 2379456, + "ts": 6197200103168.769, "dur": 12.325, + "args": { + "External id": 39186,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2379456, + "ts": 6197200103174.687, "dur": 6.005, + "args": { + "External id": 39187,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2379456, + "ts": 6197200103178.256, "dur": 0.998, + "args": { + "External id": 39188,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197200103188.284, "dur": 25.759, + "args": { + "External id": 39189,"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": 2338707, "tid": 2379456, + "ts": 6197200103191.118, "dur": 0.620, + "args": { + "External id": 39190,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197200103193.169, "dur": 1.086, + "args": { + "External id": 39191,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2379456, + "ts": 6197200103196.901, "dur": 0.690, + "args": { + "External id": 39192,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2379456, + "ts": 6197200103198.591, "dur": 0.718, + "args": { + "External id": 39193,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2379456, + "ts": 6197200103200.731, "dur": 0.645, + "args": { + "External id": 39194,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2379456, + "ts": 6197200103203.549, "dur": 0.605, + "args": { + "External id": 39195,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2379456, + "ts": 6197200103205.549, "dur": 0.736, + "args": { + "External id": 39196,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2379456, + "ts": 6197200103207.311, "dur": 1.785, + "args": { + "External id": 39197,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2379456, + "ts": 6197200103209.953, "dur": 0.636, + "args": { + "External id": 39198,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2379456, + "ts": 6197200103225.968, "dur": 33.170, + "args": { + "External id": 39199,"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": 2338707, "tid": 2379456, + "ts": 6197200103326.864, "dur": 287.456, + "args": { + "External id": 39200,"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": 2338707, "tid": 2379456, + "ts": 6197200103357.303, "dur": 252.320, + "args": { + "External id": 39201,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197200103367.404, "dur": 236.379, + "args": { + "External id": 39202,"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": 2338707, "tid": 2379456, + "ts": 6197200103635.582, "dur": 2.178, + "args": { + "External id": 39203,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197200103759.763, "dur": 1748.148, + "args": { + "External id": 39204,"Sequence number": 480047, "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": 2338707, "tid": 2379456, "ts": 6197200103759.763, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6197200103885.092, "dur": 110.980, + "args": { + "External id": 39205,"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": 2338707, "tid": 2379456, + "ts": 6197200104039.916, "dur": 79.574, + "args": { + "External id": 39206,"kernel_hash": "cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/u7/cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs.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": 2338707, "tid": 2379456, + "ts": 6197200104142.349, "dur": 56.330, + "args": { + "External id": 39207,"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": 2338707, "tid": 2379456, + "ts": 6197200104208.810, "dur": 32.505, + "args": { + "External id": 39208,"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": 2338707, "tid": 2379456, + "ts": 6197200104247.476, "dur": 37.687, + "args": { + "External id": 39209,"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": 2338707, "tid": 2379456, + "ts": 6197200104292.551, "dur": 27.991, + "args": { + "External id": 39210,"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": 2338707, "tid": 2379456, + "ts": 6197200104328.422, "dur": 29.180, + "args": { + "External id": 39211,"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": 2338707, "tid": 2379456, + "ts": 6197200104385.965, "dur": 24.697, + "args": { + "External id": 39212,"kernel_hash": "cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/wm/cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s.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": 2338707, "tid": 2379456, + "ts": 6197200104427.525, "dur": 30.767, + "args": { + "External id": 39213,"kernel_hash": "cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql", "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/qt/cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql.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": 2338707, "tid": 2379456, + "ts": 6197200104481.739, "dur": 22.651, + "args": { + "External id": 39214,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197200104517.454, "dur": 15.595, + "args": { + "External id": 39215,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197200104542.241, "dur": 37.978, + "args": { + "External id": 39216,"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": 2338707, "tid": 2379456, + "ts": 6197200104583.935, "dur": 32.600, + "args": { + "External id": 39217,"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": 2338707, "tid": 2379456, + "ts": 6197200104646.080, "dur": 264.526, + "args": { + "External id": 39218,"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": 2338707, "tid": 2379456, + "ts": 6197200104741.617, "dur": 7.371, + "args": { + "External id": 39219,"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": 2338707, "tid": 2379456, + "ts": 6197200104751.197, "dur": 3.195, + "args": { + "External id": 39220,"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": 2338707, "tid": 2379456, + "ts": 6197200104755.257, "dur": 3.729, + "args": { + "External id": 39221,"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": 2338707, "tid": 2379456, + "ts": 6197200104759.997, "dur": 3.182, + "args": { + "External id": 39222,"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": 2338707, "tid": 2379456, + "ts": 6197200104808.245, "dur": 7.026, + "args": { + "External id": 39223,"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": 2338707, "tid": 2379456, + "ts": 6197200104812.331, "dur": 2.729, + "args": { + "External id": 39224,"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": 2338707, "tid": 2379456, + "ts": 6197200104817.355, "dur": 31.710, + "args": { + "External id": 39225,"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": 2338707, "tid": 2379456, + "ts": 6197200104822.878, "dur": 2.773, + "args": { + "External id": 39226,"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": 2338707, "tid": 2379456, + "ts": 6197200104850.189, "dur": 1.910, + "args": { + "External id": 39227,"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": 2338707, "tid": 2379456, + "ts": 6197200104851.320, "dur": 0.701, + "args": { + "External id": 39228,"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": 2338707, "tid": 2379456, + "ts": 6197200104852.868, "dur": 14.166, + "args": { + "External id": 39229,"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": 2338707, "tid": 2379456, + "ts": 6197200104855.076, "dur": 1.041, + "args": { + "External id": 39230,"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": 2338707, "tid": 2379456, + "ts": 6197200104949.130, "dur": 26.274, + "args": { + "External id": 39231,"kernel_hash": "cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4", "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/yk/cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4.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": 2338707, "tid": 2379456, + "ts": 6197200104994.199, "dur": 14.556, + "args": { + "External id": 39232,"kernel_hash": "ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg", "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/eu/ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg.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": 2338707, "tid": 2379456, + "ts": 6197200105015.628, "dur": 81.927, + "args": { + "External id": 39233,"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": 2338707, "tid": 2379456, + "ts": 6197200105107.413, "dur": 44.271, + "args": { + "External id": 39234,"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": 2338707, "tid": 2379456, + "ts": 6197200105161.687, "dur": 23.460, + "args": { + "External id": 39235,"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": 2338707, "tid": 2379456, + "ts": 6197200105191.238, "dur": 30.329, + "args": { + "External id": 39236,"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": 2338707, "tid": 2379456, + "ts": 6197200105228.735, "dur": 27.204, + "args": { + "External id": 39237,"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": 2338707, "tid": 2379456, + "ts": 6197200105263.680, "dur": 30.233, + "args": { + "External id": 39238,"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": 2338707, "tid": 2379456, + "ts": 6197200105316.174, "dur": 24.484, + "args": { + "External id": 39239,"kernel_hash": "c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/6w/c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7.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": 2338707, "tid": 2379456, + "ts": 6197200105359.863, "dur": 24.506, + "args": { + "External id": 39240,"kernel_hash": "ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx", "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/kj/ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx.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": 2338707, "tid": 2379456, + "ts": 6197200105401.034, "dur": 15.929, + "args": { + "External id": 39241,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197200105433.282, "dur": 13.850, + "args": { + "External id": 39242,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197200105461.413, "dur": 15.515, + "args": { + "External id": 39243,"kernel_hash": "cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/eb/cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b.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": 2338707, "tid": 2379456, + "ts": 6197200105550.427, "dur": 15.193, + "args": { + "External id": 39244,"Record function id": 0, "Ev Idx": 7499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200105553.525, "dur": 11.206, + "args": { + "External id": 39245,"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": 2338707, "tid": 2379456, + "ts": 6197200105557.741, "dur": 5.948, + "args": { + "External id": 39246,"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": 2338707, "tid": 2379456, + "ts": 6197200105559.397, "dur": 4.179, + "args": { + "External id": 39247,"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": 2338707, "tid": 2379456, + "ts": 6197200105569.509, "dur": 5.709, + "args": { + "External id": 39248,"Record function id": 0, "Ev Idx": 7503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200105571.229, "dur": 3.579, + "args": { + "External id": 39249,"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": 2338707, "tid": 2379456, + "ts": 6197200105572.231, "dur": 2.066, + "args": { + "External id": 39250,"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": 2338707, "tid": 2379456, + "ts": 6197200105572.983, "dur": 1.233, + "args": { + "External id": 39251,"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": 2338707, "tid": 2379456, + "ts": 6197200105578.639, "dur": 4.576, + "args": { + "External id": 39252,"Record function id": 0, "Ev Idx": 7507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200105579.922, "dur": 2.851, + "args": { + "External id": 39253,"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": 2338707, "tid": 2379456, + "ts": 6197200105580.765, "dur": 1.564, + "args": { + "External id": 39254,"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": 2338707, "tid": 2379456, + "ts": 6197200105581.352, "dur": 0.877, + "args": { + "External id": 39255,"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": 2338707, "tid": 2379456, + "ts": 6197200105586.503, "dur": 4.246, + "args": { + "External id": 39256,"Record function id": 0, "Ev Idx": 7511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200105587.859, "dur": 2.494, + "args": { + "External id": 39257,"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": 2338707, "tid": 2379456, + "ts": 6197200105588.567, "dur": 1.120, + "args": { + "External id": 39258,"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": 2338707, "tid": 2379456, + "ts": 6197200105588.856, "dur": 0.748, + "args": { + "External id": 39259,"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": 2338707, "tid": 2379456, + "ts": 6197200105593.875, "dur": 4.055, + "args": { + "External id": 39260,"Record function id": 0, "Ev Idx": 7515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200105594.976, "dur": 2.566, + "args": { + "External id": 39261,"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": 2338707, "tid": 2379456, + "ts": 6197200105595.440, "dur": 1.458, + "args": { + "External id": 39262,"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": 2338707, "tid": 2379456, + "ts": 6197200105595.922, "dur": 0.910, + "args": { + "External id": 39263,"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": 2338707, "tid": 2379456, + "ts": 6197200105601.040, "dur": 4.202, + "args": { + "External id": 39264,"Record function id": 0, "Ev Idx": 7519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200105602.281, "dur": 2.586, + "args": { + "External id": 39265,"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": 2338707, "tid": 2379456, + "ts": 6197200105602.740, "dur": 1.342, + "args": { + "External id": 39266,"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": 2338707, "tid": 2379456, + "ts": 6197200105603.194, "dur": 0.820, + "args": { + "External id": 39267,"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": 2338707, "tid": 2379456, + "ts": 6197200105608.577, "dur": 3.679, + "args": { + "External id": 39268,"Record function id": 0, "Ev Idx": 7523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200105609.549, "dur": 2.306, + "args": { + "External id": 39269,"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": 2338707, "tid": 2379456, + "ts": 6197200105610.036, "dur": 1.126, + "args": { + "External id": 39270,"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": 2338707, "tid": 2379456, + "ts": 6197200105610.291, "dur": 0.805, + "args": { + "External id": 39271,"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": 2338707, "tid": 2379456, + "ts": 6197200105615.424, "dur": 6.045, + "args": { + "External id": 39272,"Record function id": 0, "Ev Idx": 7527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200105616.544, "dur": 4.540, + "args": { + "External id": 39273,"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": 2338707, "tid": 2379456, + "ts": 6197200105617.011, "dur": 3.372, + "args": { + "External id": 39274,"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": 2338707, "tid": 2379456, + "ts": 6197200105619.407, "dur": 0.876, + "args": { + "External id": 39275,"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": 2338707, "tid": 2379456, + "ts": 6197200105624.614, "dur": 4.065, + "args": { + "External id": 39276,"Record function id": 0, "Ev Idx": 7531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200105625.918, "dur": 2.351, + "args": { + "External id": 39277,"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": 2338707, "tid": 2379456, + "ts": 6197200105626.334, "dur": 1.254, + "args": { + "External id": 39278,"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": 2338707, "tid": 2379456, + "ts": 6197200105626.623, "dur": 0.898, + "args": { + "External id": 39279,"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": 2338707, "tid": 2379456, + "ts": 6197200105632.460, "dur": 291936.354, + "args": { + "External id": 39280,"Record function id": 0, "Sequence number": 480046, "Fwd thread id": 1, "Ev Idx": 7535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197200105633.729, "dur": 291925.963, + "args": { + "External id": 39281,"Sequence number": 480046, "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": 2338707, "tid": 2379456, "ts": 6197200105633.729, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.25)", "pid": 2338707, "tid": 2379456, + "ts": 6197200105664.724, "dur": 60.512, + "args": { + "External id": 39282,"Record function id": 0, "Ev Idx": 7537 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.25)", "pid": 2338707, "tid": 2379456, + "ts": 6197200105735.426, "dur": 84.144, + "args": { + "External id": 39283,"Record function id": 0, "Ev Idx": 7538 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.25)", "pid": 2338707, "tid": 2379456, + "ts": 6197200105825.550, "dur": 291725.962, + "args": { + "External id": 39284,"Record function id": 0, "Ev Idx": 7539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197200105883.232, "dur": 8.297, + "args": { + "External id": 39285,"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": 2338707, "tid": 2379456, + "ts": 6197200105903.831, "dur": 5.069, + "args": { + "External id": 39286,"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": 2338707, "tid": 2379456, + "ts": 6197200105922.869, "dur": 290654.876, + "args": { + "External id": 39287,"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": 2338707, "tid": 2379456, + "ts": 6197200105936.723, "dur": 290627.979, + "args": { + "External id": 39288,"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": 2338707, "tid": 2379456, + "ts": 6197200106040.524, "dur": 4.560, + "args": { + "External id": 39289,"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": 2338707, "tid": 2379456, + "ts": 6197200106109.597, "dur": 290403.591, + "args": { + "External id": 39290,"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": 2338707, "tid": 2379456, + "ts": 6197200106112.656, "dur": 290399.225, + "args": { + "External id": 39291,"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": 2338707, "tid": 2379456, + "ts": 6197200106117.267, "dur": 12.502, + "args": { + "External id": 39292,"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": 2338707, "tid": 2379456, + "ts": 6197200106132.176, "dur": 290373.108, + "args": { + "External id": 39293,"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": 2338707, "tid": 2379456, + "ts": 6197200396693.761, "dur": 28.407, + "args": { + "External id": 39294,"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": 2338707, "tid": 2379456, + "ts": 6197200396697.844, "dur": 23.476, + "args": { + "External id": 39295,"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": 2338707, "tid": 2379456, + "ts": 6197200396758.453, "dur": 398.944, + "args": { + "External id": 39296,"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": 2338707, "tid": 2379456, + "ts": 6197200396790.611, "dur": 361.180, + "args": { + "External id": 39297,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197200396804.384, "dur": 341.803, + "args": { + "External id": 39298,"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": 2338707, "tid": 2379456, + "ts": 6197200397182.126, "dur": 2.400, + "args": { + "External id": 39299,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2379456, + "ts": 6197200397249.193, "dur": 6.854, + "args": { + "External id": 39300,"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": 2338707, "tid": 2379456, + "ts": 6197200397268.560, "dur": 36.858, + "args": { + "External id": 39301,"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": 2338707, "tid": 2379456, + "ts": 6197200397316.792, "dur": 1.963, + "args": { + "External id": 39302,"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": 2338707, "tid": 2379456, + "ts": 6197200397324.585, "dur": 11.960, + "args": { + "External id": 39303,"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": 2338707, "tid": 2379456, + "ts": 6197200397341.264, "dur": 0.997, + "args": { + "External id": 39304,"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": 2338707, "tid": 2379456, + "ts": 6197200397347.030, "dur": 10.836, + "args": { + "External id": 39305,"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": 2338707, "tid": 2379456, + "ts": 6197200397362.647, "dur": 0.817, + "args": { + "External id": 39306,"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": 2338707, "tid": 2379456, + "ts": 6197200397370.125, "dur": 10.893, + "args": { + "External id": 39307,"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": 2338707, "tid": 2379456, + "ts": 6197200397385.937, "dur": 1.205, + "args": { + "External id": 39308,"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": 2338707, "tid": 2379456, + "ts": 6197200397391.600, "dur": 10.560, + "args": { + "External id": 39309,"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": 2338707, "tid": 2379456, + "ts": 6197200397406.873, "dur": 1.554, + "args": { + "External id": 39310,"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": 2338707, "tid": 2379456, + "ts": 6197200397413.079, "dur": 10.592, + "args": { + "External id": 39311,"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": 2338707, "tid": 2379456, + "ts": 6197200397428.335, "dur": 1.104, + "args": { + "External id": 39312,"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": 2338707, "tid": 2379456, + "ts": 6197200397434.428, "dur": 12.895, + "args": { + "External id": 39313,"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": 2338707, "tid": 2379456, + "ts": 6197200397453.695, "dur": 0.752, + "args": { + "External id": 39314,"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": 2338707, "tid": 2379456, + "ts": 6197200397459.068, "dur": 11.148, + "args": { + "External id": 39315,"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": 2338707, "tid": 2379456, + "ts": 6197200397473.862, "dur": 0.974, + "args": { + "External id": 39316,"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": 2338707, "tid": 2379456, + "ts": 6197200397478.985, "dur": 12.850, + "args": { + "External id": 39317,"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": 2338707, "tid": 2379456, + "ts": 6197200397583.026, "dur": 2976.692, + "args": { + "External id": 39318,"Record function id": 0, "Ev Idx": 7573 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.24)", "pid": 2338707, "tid": 2379456, + "ts": 6197200397603.622, "dur": 1086.397, + "args": { + "External id": 39319,"Record function id": 0, "Ev Idx": 7574 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.24)", "pid": 2338707, "tid": 2379456, + "ts": 6197200397620.587, "dur": 356.629, + "args": { + "External id": 39320,"Record function id": 0, "Ev Idx": 7575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6197200397728.143, "dur": 5.010, + "args": { + "External id": 39321,"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": 2338707, "tid": 2379456, + "ts": 6197200397736.782, "dur": 1.073, + "args": { + "External id": 39322,"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": 2338707, "tid": 2379456, + "ts": 6197200397739.540, "dur": 0.990, + "args": { + "External id": 39323,"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": 2338707, "tid": 2379456, + "ts": 6197200397742.200, "dur": 1.065, + "args": { + "External id": 39324,"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": 2338707, "tid": 2379456, + "ts": 6197200397746.711, "dur": 0.946, + "args": { + "External id": 39325,"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": 2338707, "tid": 2379456, + "ts": 6197200397749.111, "dur": 0.954, + "args": { + "External id": 39326,"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": 2338707, "tid": 2379456, + "ts": 6197200397751.412, "dur": 0.968, + "args": { + "External id": 39327,"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": 2338707, "tid": 2379456, + "ts": 6197200397758.667, "dur": 1.588, + "args": { + "External id": 39328,"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": 2338707, "tid": 2379456, + "ts": 6197200397763.606, "dur": 1.310, + "args": { + "External id": 39329,"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": 2338707, "tid": 2379456, + "ts": 6197200397766.421, "dur": 0.848, + "args": { + "External id": 39330,"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": 2338707, "tid": 2379456, + "ts": 6197200397785.410, "dur": 160.195, + "args": { + "External id": 39331,"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": 2338707, "tid": 2379456, + "ts": 6197200397800.730, "dur": 140.208, + "args": { + "External id": 39332,"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": 2338707, "tid": 2379456, + "ts": 6197200397825.799, "dur": 13.572, + "args": { + "External id": 39333,"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": 2338707, "tid": 2379456, + "ts": 6197200397844.922, "dur": 67.734, + "args": { + "External id": 39334,"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": 2338707, "tid": 2379456, + "ts": 6197200397849.660, "dur": 62.631, + "args": { + "External id": 39335,"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": 2338707, "tid": 2379456, + "ts": 6197200397853.638, "dur": 6.545, + "args": { + "External id": 39336,"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": 2338707, "tid": 2379456, + "ts": 6197200397861.716, "dur": 49.912, + "args": { + "External id": 39337,"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": 2338707, "tid": 2379456, + "ts": 6197200398104.977, "dur": 577.412, + "args": { + "External id": 39338,"Record function id": 0, "Ev Idx": 7593 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.23)", "pid": 2338707, "tid": 2379456, + "ts": 6197200398122.805, "dur": 546.659, + "args": { + "External id": 39339,"Record function id": 0, "Ev Idx": 7594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197200398188.728, "dur": 7.474, + "args": { + "External id": 39340,"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": 2338707, "tid": 2379456, + "ts": 6197200398211.686, "dur": 30.212, + "args": { + "External id": 39341,"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": 2338707, "tid": 2379456, + "ts": 6197200398216.997, "dur": 2.002, + "args": { + "External id": 39342,"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": 2338707, "tid": 2379456, + "ts": 6197200398220.798, "dur": 0.635, + "args": { + "External id": 39343,"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": 2338707, "tid": 2379456, + "ts": 6197200398222.845, "dur": 1.191, + "args": { + "External id": 39344,"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": 2338707, "tid": 2379456, + "ts": 6197200398225.462, "dur": 0.870, + "args": { + "External id": 39345,"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": 2338707, "tid": 2379456, + "ts": 6197200398227.795, "dur": 0.617, + "args": { + "External id": 39346,"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": 2338707, "tid": 2379456, + "ts": 6197200398229.649, "dur": 0.617, + "args": { + "External id": 39347,"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": 2338707, "tid": 2379456, + "ts": 6197200398231.660, "dur": 0.686, + "args": { + "External id": 39348,"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": 2338707, "tid": 2379456, + "ts": 6197200398234.060, "dur": 0.765, + "args": { + "External id": 39349,"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": 2338707, "tid": 2379456, + "ts": 6197200398236.018, "dur": 0.750, + "args": { + "External id": 39350,"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": 2338707, "tid": 2379456, + "ts": 6197200398252.760, "dur": 45.247, + "args": { + "External id": 39351,"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": 2338707, "tid": 2379456, + "ts": 6197200398327.798, "dur": 109.596, + "args": { + "External id": 39352,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2379456, + "ts": 6197200398338.592, "dur": 3.513, + "args": { + "External id": 39353,"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": 2338707, "tid": 2379456, + "ts": 6197200398347.052, "dur": 10.669, + "args": { + "External id": 39354,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2379456, + "ts": 6197200398351.545, "dur": 5.755, + "args": { + "External id": 39355,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2379456, + "ts": 6197200398355.097, "dur": 1.070, + "args": { + "External id": 39356,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197200398364.335, "dur": 24.327, + "args": { + "External id": 39357,"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": 2338707, "tid": 2379456, + "ts": 6197200398366.294, "dur": 0.826, + "args": { + "External id": 39358,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197200398368.337, "dur": 0.748, + "args": { + "External id": 39359,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2379456, + "ts": 6197200398370.184, "dur": 0.941, + "args": { + "External id": 39360,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2379456, + "ts": 6197200398372.640, "dur": 1.061, + "args": { + "External id": 39361,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2379456, + "ts": 6197200398375.173, "dur": 1.216, + "args": { + "External id": 39362,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2379456, + "ts": 6197200398377.607, "dur": 0.769, + "args": { + "External id": 39363,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2379456, + "ts": 6197200398379.782, "dur": 0.699, + "args": { + "External id": 39364,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2379456, + "ts": 6197200398381.823, "dur": 0.725, + "args": { + "External id": 39365,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2379456, + "ts": 6197200398383.854, "dur": 0.600, + "args": { + "External id": 39366,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2379456, + "ts": 6197200398399.723, "dur": 30.304, + "args": { + "External id": 39367,"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": 2338707, "tid": 2379456, + "ts": 6197200398484.804, "dur": 116.046, + "args": { + "External id": 39368,"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": 2338707, "tid": 2379456, + "ts": 6197200398508.883, "dur": 88.482, + "args": { + "External id": 39369,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197200398519.093, "dur": 74.150, + "args": { + "External id": 39370,"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": 2338707, "tid": 2379456, + "ts": 6197200398615.983, "dur": 2.003, + "args": { + "External id": 39371,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197200398697.283, "dur": 1841.644, + "args": { + "External id": 39372,"Sequence number": 480045, "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": 2338707, "tid": 2379456, "ts": 6197200398697.283, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6197200398834.211, "dur": 110.353, + "args": { + "External id": 39373,"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": 2338707, "tid": 2379456, + "ts": 6197200398988.717, "dur": 44.533, + "args": { + "External id": 39374,"kernel_hash": "cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/u7/cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs.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": 2338707, "tid": 2379456, + "ts": 6197200399051.737, "dur": 97.326, + "args": { + "External id": 39375,"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": 2338707, "tid": 2379456, + "ts": 6197200399164.341, "dur": 34.109, + "args": { + "External id": 39376,"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": 2338707, "tid": 2379456, + "ts": 6197200399204.997, "dur": 33.116, + "args": { + "External id": 39377,"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": 2338707, "tid": 2379456, + "ts": 6197200399245.019, "dur": 28.719, + "args": { + "External id": 39378,"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": 2338707, "tid": 2379456, + "ts": 6197200399280.953, "dur": 29.270, + "args": { + "External id": 39379,"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": 2338707, "tid": 2379456, + "ts": 6197200399337.168, "dur": 24.735, + "args": { + "External id": 39380,"kernel_hash": "cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/wm/cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s.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": 2338707, "tid": 2379456, + "ts": 6197200399379.937, "dur": 30.115, + "args": { + "External id": 39381,"kernel_hash": "cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql", "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/qt/cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql.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": 2338707, "tid": 2379456, + "ts": 6197200399432.940, "dur": 21.840, + "args": { + "External id": 39382,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197200399466.594, "dur": 17.024, + "args": { + "External id": 39383,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197200399493.035, "dur": 39.760, + "args": { + "External id": 39384,"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": 2338707, "tid": 2379456, + "ts": 6197200399537.083, "dur": 34.772, + "args": { + "External id": 39385,"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": 2338707, "tid": 2379456, + "ts": 6197200399599.660, "dur": 265.817, + "args": { + "External id": 39386,"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": 2338707, "tid": 2379456, + "ts": 6197200399679.889, "dur": 6.189, + "args": { + "External id": 39387,"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": 2338707, "tid": 2379456, + "ts": 6197200399688.383, "dur": 2.132, + "args": { + "External id": 39388,"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": 2338707, "tid": 2379456, + "ts": 6197200399691.870, "dur": 2.284, + "args": { + "External id": 39389,"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": 2338707, "tid": 2379456, + "ts": 6197200399695.204, "dur": 1.475, + "args": { + "External id": 39390,"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": 2338707, "tid": 2379456, + "ts": 6197200399760.744, "dur": 5.461, + "args": { + "External id": 39391,"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": 2338707, "tid": 2379456, + "ts": 6197200399762.859, "dur": 3.018, + "args": { + "External id": 39392,"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": 2338707, "tid": 2379456, + "ts": 6197200399768.278, "dur": 33.328, + "args": { + "External id": 39393,"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": 2338707, "tid": 2379456, + "ts": 6197200399773.488, "dur": 1.671, + "args": { + "External id": 39394,"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": 2338707, "tid": 2379456, + "ts": 6197200399802.950, "dur": 1.769, + "args": { + "External id": 39395,"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": 2338707, "tid": 2379456, + "ts": 6197200399803.887, "dur": 0.763, + "args": { + "External id": 39396,"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": 2338707, "tid": 2379456, + "ts": 6197200399805.702, "dur": 16.031, + "args": { + "External id": 39397,"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": 2338707, "tid": 2379456, + "ts": 6197200399807.497, "dur": 0.482, + "args": { + "External id": 39398,"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": 2338707, "tid": 2379456, + "ts": 6197200399901.266, "dur": 31.111, + "args": { + "External id": 39399,"kernel_hash": "cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4", "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/yk/cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4.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": 2338707, "tid": 2379456, + "ts": 6197200399949.723, "dur": 17.053, + "args": { + "External id": 39400,"kernel_hash": "ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg", "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/eu/ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg.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": 2338707, "tid": 2379456, + "ts": 6197200399976.309, "dur": 48.889, + "args": { + "External id": 39401,"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": 2338707, "tid": 2379456, + "ts": 6197200400032.360, "dur": 76.653, + "args": { + "External id": 39402,"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": 2338707, "tid": 2379456, + "ts": 6197200400123.846, "dur": 28.444, + "args": { + "External id": 39403,"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": 2338707, "tid": 2379456, + "ts": 6197200400159.038, "dur": 33.906, + "args": { + "External id": 39404,"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": 2338707, "tid": 2379456, + "ts": 6197200400200.631, "dur": 44.240, + "args": { + "External id": 39405,"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": 2338707, "tid": 2379456, + "ts": 6197200400260.151, "dur": 40.279, + "args": { + "External id": 39406,"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": 2338707, "tid": 2379456, + "ts": 6197200400321.811, "dur": 32.234, + "args": { + "External id": 39407,"kernel_hash": "c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/6w/c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7.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": 2338707, "tid": 2379456, + "ts": 6197200400370.531, "dur": 32.211, + "args": { + "External id": 39408,"kernel_hash": "ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx", "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/kj/ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx.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": 2338707, "tid": 2379456, + "ts": 6197200400417.558, "dur": 18.794, + "args": { + "External id": 39409,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197200400449.542, "dur": 17.217, + "args": { + "External id": 39410,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197200400490.659, "dur": 17.202, + "args": { + "External id": 39411,"kernel_hash": "cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/eb/cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b.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": 2338707, "tid": 2379456, + "ts": 6197200400580.601, "dur": 14.643, + "args": { + "External id": 39412,"Record function id": 0, "Ev Idx": 7667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200400583.613, "dur": 10.607, + "args": { + "External id": 39413,"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": 2338707, "tid": 2379456, + "ts": 6197200400587.539, "dur": 5.598, + "args": { + "External id": 39414,"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": 2338707, "tid": 2379456, + "ts": 6197200400589.059, "dur": 3.968, + "args": { + "External id": 39415,"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": 2338707, "tid": 2379456, + "ts": 6197200400599.338, "dur": 4.854, + "args": { + "External id": 39416,"Record function id": 0, "Ev Idx": 7671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200400600.604, "dur": 3.151, + "args": { + "External id": 39417,"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": 2338707, "tid": 2379456, + "ts": 6197200400601.475, "dur": 1.702, + "args": { + "External id": 39418,"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": 2338707, "tid": 2379456, + "ts": 6197200400602.023, "dur": 1.085, + "args": { + "External id": 39419,"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": 2338707, "tid": 2379456, + "ts": 6197200400607.504, "dur": 3.996, + "args": { + "External id": 39420,"Record function id": 0, "Ev Idx": 7675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200400608.555, "dur": 2.545, + "args": { + "External id": 39421,"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": 2338707, "tid": 2379456, + "ts": 6197200400609.234, "dur": 1.168, + "args": { + "External id": 39422,"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": 2338707, "tid": 2379456, + "ts": 6197200400609.719, "dur": 0.621, + "args": { + "External id": 39423,"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": 2338707, "tid": 2379456, + "ts": 6197200400614.685, "dur": 43.199, + "args": { + "External id": 39424,"Record function id": 0, "Ev Idx": 7679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200400654.766, "dur": 2.698, + "args": { + "External id": 39425,"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": 2338707, "tid": 2379456, + "ts": 6197200400655.448, "dur": 1.430, + "args": { + "External id": 39426,"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": 2338707, "tid": 2379456, + "ts": 6197200400655.997, "dur": 0.800, + "args": { + "External id": 39427,"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": 2338707, "tid": 2379456, + "ts": 6197200400661.234, "dur": 5.817, + "args": { + "External id": 39428,"Record function id": 0, "Ev Idx": 7683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200400662.443, "dur": 4.172, + "args": { + "External id": 39429,"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": 2338707, "tid": 2379456, + "ts": 6197200400662.913, "dur": 3.174, + "args": { + "External id": 39430,"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": 2338707, "tid": 2379456, + "ts": 6197200400665.402, "dur": 0.606, + "args": { + "External id": 39431,"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": 2338707, "tid": 2379456, + "ts": 6197200400670.246, "dur": 4.322, + "args": { + "External id": 39432,"Record function id": 0, "Ev Idx": 7687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200400671.409, "dur": 2.746, + "args": { + "External id": 39433,"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": 2338707, "tid": 2379456, + "ts": 6197200400671.896, "dur": 1.391, + "args": { + "External id": 39434,"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": 2338707, "tid": 2379456, + "ts": 6197200400672.384, "dur": 0.826, + "args": { + "External id": 39435,"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": 2338707, "tid": 2379456, + "ts": 6197200400677.993, "dur": 3.848, + "args": { + "External id": 39436,"Record function id": 0, "Ev Idx": 7691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200400679.278, "dur": 2.151, + "args": { + "External id": 39437,"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": 2338707, "tid": 2379456, + "ts": 6197200400679.897, "dur": 1.076, + "args": { + "External id": 39438,"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": 2338707, "tid": 2379456, + "ts": 6197200400680.187, "dur": 0.721, + "args": { + "External id": 39439,"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": 2338707, "tid": 2379456, + "ts": 6197200400685.028, "dur": 3.783, + "args": { + "External id": 39440,"Record function id": 0, "Ev Idx": 7695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200400686.005, "dur": 2.398, + "args": { + "External id": 39441,"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": 2338707, "tid": 2379456, + "ts": 6197200400686.693, "dur": 1.150, + "args": { + "External id": 39442,"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": 2338707, "tid": 2379456, + "ts": 6197200400687.046, "dur": 0.735, + "args": { + "External id": 39443,"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": 2338707, "tid": 2379456, + "ts": 6197200400691.875, "dur": 5.993, + "args": { + "External id": 39444,"Record function id": 0, "Ev Idx": 7699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200400692.981, "dur": 4.487, + "args": { + "External id": 39445,"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": 2338707, "tid": 2379456, + "ts": 6197200400693.608, "dur": 3.410, + "args": { + "External id": 39446,"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": 2338707, "tid": 2379456, + "ts": 6197200400696.336, "dur": 0.619, + "args": { + "External id": 39447,"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": 2338707, "tid": 2379456, + "ts": 6197200400717.614, "dur": 79413.019, + "args": { + "External id": 39448,"Record function id": 0, "Sequence number": 480044, "Fwd thread id": 1, "Ev Idx": 7703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197200400719.888, "dur": 79400.986, + "args": { + "External id": 39449,"Sequence number": 480044, "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": 2338707, "tid": 2379456, "ts": 6197200400719.888, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.24)", "pid": 2338707, "tid": 2379456, + "ts": 6197200400752.307, "dur": 38.713, + "args": { + "External id": 39450,"Record function id": 0, "Ev Idx": 7705 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.24)", "pid": 2338707, "tid": 2379456, + "ts": 6197200400798.701, "dur": 68.549, + "args": { + "External id": 39451,"Record function id": 0, "Ev Idx": 7706 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.24)", "pid": 2338707, "tid": 2379456, + "ts": 6197200400873.271, "dur": 79238.695, + "args": { + "External id": 39452,"Record function id": 0, "Ev Idx": 7707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197200400963.929, "dur": 7.775, + "args": { + "External id": 39453,"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": 2338707, "tid": 2379456, + "ts": 6197200400981.485, "dur": 4.637, + "args": { + "External id": 39454,"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": 2338707, "tid": 2379456, + "ts": 6197200401002.994, "dur": 78182.317, + "args": { + "External id": 39455,"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": 2338707, "tid": 2379456, + "ts": 6197200401016.353, "dur": 78155.819, + "args": { + "External id": 39456,"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": 2338707, "tid": 2379456, + "ts": 6197200401158.429, "dur": 19.736, + "args": { + "External id": 39457,"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": 2338707, "tid": 2379456, + "ts": 6197200401199.429, "dur": 77924.196, + "args": { + "External id": 39458,"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": 2338707, "tid": 2379456, + "ts": 6197200401202.605, "dur": 77920.266, + "args": { + "External id": 39459,"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": 2338707, "tid": 2379456, + "ts": 6197200401207.329, "dur": 10.380, + "args": { + "External id": 39460,"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": 2338707, "tid": 2379456, + "ts": 6197200401219.796, "dur": 77898.305, + "args": { + "External id": 39461,"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": 2338707, "tid": 2379456, + "ts": 6197200479290.334, "dur": 11.834, + "args": { + "External id": 39462,"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": 2338707, "tid": 2379456, + "ts": 6197200479293.799, "dur": 7.832, + "args": { + "External id": 39463,"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": 2338707, "tid": 2379456, + "ts": 6197200479330.691, "dur": 349.704, + "args": { + "External id": 39464,"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": 2338707, "tid": 2379456, + "ts": 6197200479362.713, "dur": 312.985, + "args": { + "External id": 39465,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197200479373.252, "dur": 296.740, + "args": { + "External id": 39466,"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": 2338707, "tid": 2379456, + "ts": 6197200479716.760, "dur": 3.256, + "args": { + "External id": 39467,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2379456, + "ts": 6197200479778.978, "dur": 6.893, + "args": { + "External id": 39468,"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": 2338707, "tid": 2379456, + "ts": 6197200479797.974, "dur": 34.992, + "args": { + "External id": 39469,"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": 2338707, "tid": 2379456, + "ts": 6197200479843.140, "dur": 1.681, + "args": { + "External id": 39470,"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": 2338707, "tid": 2379456, + "ts": 6197200479849.750, "dur": 13.054, + "args": { + "External id": 39471,"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": 2338707, "tid": 2379456, + "ts": 6197200479868.076, "dur": 1.164, + "args": { + "External id": 39472,"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": 2338707, "tid": 2379456, + "ts": 6197200479873.344, "dur": 13.957, + "args": { + "External id": 39473,"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": 2338707, "tid": 2379456, + "ts": 6197200479892.491, "dur": 0.905, + "args": { + "External id": 39474,"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": 2338707, "tid": 2379456, + "ts": 6197200479897.705, "dur": 10.901, + "args": { + "External id": 39475,"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": 2338707, "tid": 2379456, + "ts": 6197200479912.882, "dur": 0.771, + "args": { + "External id": 39476,"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": 2338707, "tid": 2379456, + "ts": 6197200479918.115, "dur": 11.793, + "args": { + "External id": 39477,"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": 2338707, "tid": 2379456, + "ts": 6197200479933.792, "dur": 1.130, + "args": { + "External id": 39478,"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": 2338707, "tid": 2379456, + "ts": 6197200479940.017, "dur": 9.983, + "args": { + "External id": 39479,"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": 2338707, "tid": 2379456, + "ts": 6197200479954.317, "dur": 0.826, + "args": { + "External id": 39480,"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": 2338707, "tid": 2379456, + "ts": 6197200479963.721, "dur": 10.622, + "args": { + "External id": 39481,"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": 2338707, "tid": 2379456, + "ts": 6197200479980.493, "dur": 0.974, + "args": { + "External id": 39482,"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": 2338707, "tid": 2379456, + "ts": 6197200479985.944, "dur": 9.643, + "args": { + "External id": 39483,"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": 2338707, "tid": 2379456, + "ts": 6197200480001.679, "dur": 0.848, + "args": { + "External id": 39484,"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": 2338707, "tid": 2379456, + "ts": 6197200480006.351, "dur": 10.386, + "args": { + "External id": 39485,"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": 2338707, "tid": 2379456, + "ts": 6197200480147.025, "dur": 2856.369, + "args": { + "External id": 39486,"Record function id": 0, "Ev Idx": 7741 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.23)", "pid": 2338707, "tid": 2379456, + "ts": 6197200480167.933, "dur": 1058.473, + "args": { + "External id": 39487,"Record function id": 0, "Ev Idx": 7742 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.23)", "pid": 2338707, "tid": 2379456, + "ts": 6197200480182.945, "dur": 328.956, + "args": { + "External id": 39488,"Record function id": 0, "Ev Idx": 7743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6197200480276.952, "dur": 4.733, + "args": { + "External id": 39489,"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": 2338707, "tid": 2379456, + "ts": 6197200480285.786, "dur": 0.757, + "args": { + "External id": 39490,"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": 2338707, "tid": 2379456, + "ts": 6197200480288.645, "dur": 0.862, + "args": { + "External id": 39491,"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": 2338707, "tid": 2379456, + "ts": 6197200480291.185, "dur": 1.486, + "args": { + "External id": 39492,"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": 2338707, "tid": 2379456, + "ts": 6197200480294.440, "dur": 0.992, + "args": { + "External id": 39493,"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": 2338707, "tid": 2379456, + "ts": 6197200480296.913, "dur": 0.946, + "args": { + "External id": 39494,"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": 2338707, "tid": 2379456, + "ts": 6197200480301.067, "dur": 1.023, + "args": { + "External id": 39495,"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": 2338707, "tid": 2379456, + "ts": 6197200480303.513, "dur": 1.106, + "args": { + "External id": 39496,"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": 2338707, "tid": 2379456, + "ts": 6197200480306.048, "dur": 1.621, + "args": { + "External id": 39497,"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": 2338707, "tid": 2379456, + "ts": 6197200480309.087, "dur": 1.405, + "args": { + "External id": 39498,"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": 2338707, "tid": 2379456, + "ts": 6197200480328.915, "dur": 154.264, + "args": { + "External id": 39499,"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": 2338707, "tid": 2379456, + "ts": 6197200480343.880, "dur": 134.343, + "args": { + "External id": 39500,"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": 2338707, "tid": 2379456, + "ts": 6197200480358.409, "dur": 24.433, + "args": { + "External id": 39501,"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": 2338707, "tid": 2379456, + "ts": 6197200480388.077, "dur": 62.817, + "args": { + "External id": 39502,"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": 2338707, "tid": 2379456, + "ts": 6197200480390.981, "dur": 59.531, + "args": { + "External id": 39503,"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": 2338707, "tid": 2379456, + "ts": 6197200480395.489, "dur": 5.701, + "args": { + "External id": 39504,"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": 2338707, "tid": 2379456, + "ts": 6197200480402.942, "dur": 46.715, + "args": { + "External id": 39505,"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": 2338707, "tid": 2379456, + "ts": 6197200480595.260, "dur": 623.018, + "args": { + "External id": 39506,"Record function id": 0, "Ev Idx": 7761 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.22)", "pid": 2338707, "tid": 2379456, + "ts": 6197200480611.669, "dur": 593.697, + "args": { + "External id": 39507,"Record function id": 0, "Ev Idx": 7762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197200480670.227, "dur": 5.176, + "args": { + "External id": 39508,"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": 2338707, "tid": 2379456, + "ts": 6197200480690.859, "dur": 41.441, + "args": { + "External id": 39509,"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": 2338707, "tid": 2379456, + "ts": 6197200480696.044, "dur": 1.831, + "args": { + "External id": 39510,"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": 2338707, "tid": 2379456, + "ts": 6197200480715.844, "dur": 0.851, + "args": { + "External id": 39511,"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": 2338707, "tid": 2379456, + "ts": 6197200480719.128, "dur": 0.290, + "args": { + "External id": 39512,"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": 2338707, "tid": 2379456, + "ts": 6197200480720.325, "dur": 0.385, + "args": { + "External id": 39513,"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": 2338707, "tid": 2379456, + "ts": 6197200480722.204, "dur": 0.577, + "args": { + "External id": 39514,"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": 2338707, "tid": 2379456, + "ts": 6197200480723.954, "dur": 0.227, + "args": { + "External id": 39515,"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": 2338707, "tid": 2379456, + "ts": 6197200480725.070, "dur": 0.209, + "args": { + "External id": 39516,"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": 2338707, "tid": 2379456, + "ts": 6197200480725.985, "dur": 0.331, + "args": { + "External id": 39517,"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": 2338707, "tid": 2379456, + "ts": 6197200480727.493, "dur": 0.488, + "args": { + "External id": 39518,"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": 2338707, "tid": 2379456, + "ts": 6197200480745.076, "dur": 42.547, + "args": { + "External id": 39519,"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": 2338707, "tid": 2379456, + "ts": 6197200480820.496, "dur": 110.265, + "args": { + "External id": 39520,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2379456, + "ts": 6197200480830.710, "dur": 4.743, + "args": { + "External id": 39521,"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": 2338707, "tid": 2379456, + "ts": 6197200480840.805, "dur": 10.666, + "args": { + "External id": 39522,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2379456, + "ts": 6197200480845.647, "dur": 5.402, + "args": { + "External id": 39523,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2379456, + "ts": 6197200480848.882, "dur": 0.654, + "args": { + "External id": 39524,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197200480858.100, "dur": 26.060, + "args": { + "External id": 39525,"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": 2338707, "tid": 2379456, + "ts": 6197200480860.049, "dur": 1.035, + "args": { + "External id": 39526,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197200480863.052, "dur": 0.719, + "args": { + "External id": 39527,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2379456, + "ts": 6197200480865.168, "dur": 0.517, + "args": { + "External id": 39528,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2379456, + "ts": 6197200480867.006, "dur": 0.506, + "args": { + "External id": 39529,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2379456, + "ts": 6197200480869.214, "dur": 0.571, + "args": { + "External id": 39530,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2379456, + "ts": 6197200480870.646, "dur": 0.666, + "args": { + "External id": 39531,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2379456, + "ts": 6197200480873.025, "dur": 0.392, + "args": { + "External id": 39532,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2379456, + "ts": 6197200480874.485, "dur": 0.579, + "args": { + "External id": 39533,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2379456, + "ts": 6197200480876.581, "dur": 0.981, + "args": { + "External id": 39534,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2379456, + "ts": 6197200480894.521, "dur": 28.813, + "args": { + "External id": 39535,"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": 2338707, "tid": 2379456, + "ts": 6197200480975.296, "dur": 154.417, + "args": { + "External id": 39536,"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": 2338707, "tid": 2379456, + "ts": 6197200481000.932, "dur": 124.791, + "args": { + "External id": 39537,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197200481012.499, "dur": 108.820, + "args": { + "External id": 39538,"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": 2338707, "tid": 2379456, + "ts": 6197200481149.520, "dur": 1.928, + "args": { + "External id": 39539,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197200481232.694, "dur": 1748.288, + "args": { + "External id": 39540,"Sequence number": 480043, "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": 2338707, "tid": 2379456, "ts": 6197200481232.694, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6197200481344.134, "dur": 109.189, + "args": { + "External id": 39541,"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": 2338707, "tid": 2379456, + "ts": 6197200481493.205, "dur": 40.178, + "args": { + "External id": 39542,"kernel_hash": "cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/u7/cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs.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": 2338707, "tid": 2379456, + "ts": 6197200481550.752, "dur": 52.101, + "args": { + "External id": 39543,"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": 2338707, "tid": 2379456, + "ts": 6197200481613.003, "dur": 32.784, + "args": { + "External id": 39544,"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": 2338707, "tid": 2379456, + "ts": 6197200481652.299, "dur": 33.270, + "args": { + "External id": 39545,"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": 2338707, "tid": 2379456, + "ts": 6197200481692.261, "dur": 48.400, + "args": { + "External id": 39546,"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": 2338707, "tid": 2379456, + "ts": 6197200481751.213, "dur": 31.786, + "args": { + "External id": 39547,"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": 2338707, "tid": 2379456, + "ts": 6197200481810.827, "dur": 24.499, + "args": { + "External id": 39548,"kernel_hash": "cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/wm/cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s.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": 2338707, "tid": 2379456, + "ts": 6197200481855.239, "dur": 28.903, + "args": { + "External id": 39549,"kernel_hash": "cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql", "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/qt/cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql.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": 2338707, "tid": 2379456, + "ts": 6197200481906.458, "dur": 21.095, + "args": { + "External id": 39550,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197200481940.154, "dur": 16.720, + "args": { + "External id": 39551,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197200481965.896, "dur": 42.261, + "args": { + "External id": 39552,"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": 2338707, "tid": 2379456, + "ts": 6197200482012.051, "dur": 34.454, + "args": { + "External id": 39553,"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": 2338707, "tid": 2379456, + "ts": 6197200482128.902, "dur": 250.359, + "args": { + "External id": 39554,"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": 2338707, "tid": 2379456, + "ts": 6197200482208.558, "dur": 6.483, + "args": { + "External id": 39555,"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": 2338707, "tid": 2379456, + "ts": 6197200482217.290, "dur": 3.554, + "args": { + "External id": 39556,"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": 2338707, "tid": 2379456, + "ts": 6197200482222.446, "dur": 2.697, + "args": { + "External id": 39557,"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": 2338707, "tid": 2379456, + "ts": 6197200482226.050, "dur": 3.158, + "args": { + "External id": 39558,"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": 2338707, "tid": 2379456, + "ts": 6197200482276.222, "dur": 6.064, + "args": { + "External id": 39559,"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": 2338707, "tid": 2379456, + "ts": 6197200482278.680, "dur": 3.418, + "args": { + "External id": 39560,"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": 2338707, "tid": 2379456, + "ts": 6197200482284.323, "dur": 33.172, + "args": { + "External id": 39561,"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": 2338707, "tid": 2379456, + "ts": 6197200482289.902, "dur": 1.748, + "args": { + "External id": 39562,"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": 2338707, "tid": 2379456, + "ts": 6197200482319.175, "dur": 1.697, + "args": { + "External id": 39563,"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": 2338707, "tid": 2379456, + "ts": 6197200482320.148, "dur": 0.643, + "args": { + "External id": 39564,"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": 2338707, "tid": 2379456, + "ts": 6197200482322.415, "dur": 15.288, + "args": { + "External id": 39565,"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": 2338707, "tid": 2379456, + "ts": 6197200482324.683, "dur": 0.413, + "args": { + "External id": 39566,"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": 2338707, "tid": 2379456, + "ts": 6197200482412.785, "dur": 26.330, + "args": { + "External id": 39567,"kernel_hash": "cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4", "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/yk/cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4.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": 2338707, "tid": 2379456, + "ts": 6197200482456.585, "dur": 16.466, + "args": { + "External id": 39568,"kernel_hash": "ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg", "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/eu/ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg.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": 2338707, "tid": 2379456, + "ts": 6197200482482.195, "dur": 48.211, + "args": { + "External id": 39569,"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": 2338707, "tid": 2379456, + "ts": 6197200482538.375, "dur": 41.469, + "args": { + "External id": 39570,"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": 2338707, "tid": 2379456, + "ts": 6197200482589.120, "dur": 20.856, + "args": { + "External id": 39571,"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": 2338707, "tid": 2379456, + "ts": 6197200482616.148, "dur": 31.196, + "args": { + "External id": 39572,"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": 2338707, "tid": 2379456, + "ts": 6197200482654.984, "dur": 28.732, + "args": { + "External id": 39573,"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": 2338707, "tid": 2379456, + "ts": 6197200482690.395, "dur": 48.668, + "args": { + "External id": 39574,"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": 2338707, "tid": 2379456, + "ts": 6197200482760.900, "dur": 22.919, + "args": { + "External id": 39575,"kernel_hash": "c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/6w/c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7.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": 2338707, "tid": 2379456, + "ts": 6197200482798.854, "dur": 38.406, + "args": { + "External id": 39576,"kernel_hash": "ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx", "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/kj/ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx.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": 2338707, "tid": 2379456, + "ts": 6197200482863.053, "dur": 20.271, + "args": { + "External id": 39577,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197200482902.220, "dur": 14.553, + "args": { + "External id": 39578,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197200482930.281, "dur": 16.359, + "args": { + "External id": 39579,"kernel_hash": "cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/eb/cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b.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": 2338707, "tid": 2379456, + "ts": 6197200483028.687, "dur": 15.567, + "args": { + "External id": 39580,"Record function id": 0, "Ev Idx": 7835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200483031.874, "dur": 11.333, + "args": { + "External id": 39581,"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": 2338707, "tid": 2379456, + "ts": 6197200483036.034, "dur": 6.110, + "args": { + "External id": 39582,"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": 2338707, "tid": 2379456, + "ts": 6197200483037.541, "dur": 4.515, + "args": { + "External id": 39583,"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": 2338707, "tid": 2379456, + "ts": 6197200483047.905, "dur": 42.646, + "args": { + "External id": 39584,"Record function id": 0, "Ev Idx": 7839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200483049.542, "dur": 39.730, + "args": { + "External id": 39585,"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": 2338707, "tid": 2379456, + "ts": 6197200483050.349, "dur": 37.698, + "args": { + "External id": 39586,"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": 2338707, "tid": 2379456, + "ts": 6197200483050.932, "dur": 36.248, + "args": { + "External id": 39587,"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": 2338707, "tid": 2379456, + "ts": 6197200483096.768, "dur": 6.049, + "args": { + "External id": 39588,"Record function id": 0, "Ev Idx": 7843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200483098.311, "dur": 4.070, + "args": { + "External id": 39589,"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": 2338707, "tid": 2379456, + "ts": 6197200483099.671, "dur": 2.047, + "args": { + "External id": 39590,"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": 2338707, "tid": 2379456, + "ts": 6197200483100.308, "dur": 1.296, + "args": { + "External id": 39591,"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": 2338707, "tid": 2379456, + "ts": 6197200483106.020, "dur": 4.373, + "args": { + "External id": 39592,"Record function id": 0, "Ev Idx": 7847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200483107.264, "dur": 2.727, + "args": { + "External id": 39593,"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": 2338707, "tid": 2379456, + "ts": 6197200483107.988, "dur": 1.400, + "args": { + "External id": 39594,"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": 2338707, "tid": 2379456, + "ts": 6197200483108.527, "dur": 0.796, + "args": { + "External id": 39595,"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": 2338707, "tid": 2379456, + "ts": 6197200483113.472, "dur": 4.272, + "args": { + "External id": 39596,"Record function id": 0, "Ev Idx": 7851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200483114.643, "dur": 2.681, + "args": { + "External id": 39597,"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": 2338707, "tid": 2379456, + "ts": 6197200483115.464, "dur": 1.345, + "args": { + "External id": 39598,"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": 2338707, "tid": 2379456, + "ts": 6197200483115.779, "dur": 0.962, + "args": { + "External id": 39599,"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": 2338707, "tid": 2379456, + "ts": 6197200483120.926, "dur": 4.284, + "args": { + "External id": 39600,"Record function id": 0, "Ev Idx": 7855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200483122.197, "dur": 2.607, + "args": { + "External id": 39601,"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": 2338707, "tid": 2379456, + "ts": 6197200483122.929, "dur": 1.173, + "args": { + "External id": 39602,"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": 2338707, "tid": 2379456, + "ts": 6197200483123.454, "dur": 0.584, + "args": { + "External id": 39603,"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": 2338707, "tid": 2379456, + "ts": 6197200483128.503, "dur": 4.526, + "args": { + "External id": 39604,"Record function id": 0, "Ev Idx": 7859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200483130.185, "dur": 2.403, + "args": { + "External id": 39605,"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": 2338707, "tid": 2379456, + "ts": 6197200483130.621, "dur": 1.527, + "args": { + "External id": 39606,"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": 2338707, "tid": 2379456, + "ts": 6197200483131.447, "dur": 0.635, + "args": { + "External id": 39607,"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": 2338707, "tid": 2379456, + "ts": 6197200483136.403, "dur": 3.999, + "args": { + "External id": 39608,"Record function id": 0, "Ev Idx": 7863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200483137.587, "dur": 2.387, + "args": { + "External id": 39609,"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": 2338707, "tid": 2379456, + "ts": 6197200483138.038, "dur": 1.483, + "args": { + "External id": 39610,"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": 2338707, "tid": 2379456, + "ts": 6197200483138.651, "dur": 0.770, + "args": { + "External id": 39611,"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": 2338707, "tid": 2379456, + "ts": 6197200483143.561, "dur": 4.138, + "args": { + "External id": 39612,"Record function id": 0, "Ev Idx": 7867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200483144.682, "dur": 2.596, + "args": { + "External id": 39613,"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": 2338707, "tid": 2379456, + "ts": 6197200483145.131, "dur": 1.531, + "args": { + "External id": 39614,"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": 2338707, "tid": 2379456, + "ts": 6197200483145.418, "dur": 1.148, + "args": { + "External id": 39615,"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": 2338707, "tid": 2379456, + "ts": 6197200483151.724, "dur": 72743.518, + "args": { + "External id": 39616,"Record function id": 0, "Sequence number": 480042, "Fwd thread id": 1, "Ev Idx": 7871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197200483152.871, "dur": 72732.657, + "args": { + "External id": 39617,"Sequence number": 480042, "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": 2338707, "tid": 2379456, "ts": 6197200483152.871, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.23)", "pid": 2338707, "tid": 2379456, + "ts": 6197200483183.348, "dur": 38.999, + "args": { + "External id": 39618,"Record function id": 0, "Ev Idx": 7873 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.23)", "pid": 2338707, "tid": 2379456, + "ts": 6197200483230.300, "dur": 67.229, + "args": { + "External id": 39619,"Record function id": 0, "Ev Idx": 7874 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.23)", "pid": 2338707, "tid": 2379456, + "ts": 6197200483303.109, "dur": 72575.006, + "args": { + "External id": 39620,"Record function id": 0, "Ev Idx": 7875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197200483393.550, "dur": 7.070, + "args": { + "External id": 39621,"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": 2338707, "tid": 2379456, + "ts": 6197200483409.920, "dur": 5.102, + "args": { + "External id": 39622,"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": 2338707, "tid": 2379456, + "ts": 6197200483431.362, "dur": 71467.008, + "args": { + "External id": 39623,"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": 2338707, "tid": 2379456, + "ts": 6197200483444.429, "dur": 71441.087, + "args": { + "External id": 39624,"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": 2338707, "tid": 2379456, + "ts": 6197200483541.872, "dur": 17.078, + "args": { + "External id": 39625,"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": 2338707, "tid": 2379456, + "ts": 6197200483579.177, "dur": 71259.254, + "args": { + "External id": 39626,"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": 2338707, "tid": 2379456, + "ts": 6197200483582.104, "dur": 71255.286, + "args": { + "External id": 39627,"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": 2338707, "tid": 2379456, + "ts": 6197200483586.966, "dur": 8.667, + "args": { + "External id": 39628,"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": 2338707, "tid": 2379456, + "ts": 6197200483598.076, "dur": 71233.027, + "args": { + "External id": 39629,"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": 2338707, "tid": 2379456, + "ts": 6197200555011.154, "dur": 12.877, + "args": { + "External id": 39630,"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": 2338707, "tid": 2379456, + "ts": 6197200555014.749, "dur": 8.899, + "args": { + "External id": 39631,"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": 2338707, "tid": 2379456, + "ts": 6197200555084.922, "dur": 391.388, + "args": { + "External id": 39632,"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": 2338707, "tid": 2379456, + "ts": 6197200555116.117, "dur": 355.155, + "args": { + "External id": 39633,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197200555130.499, "dur": 335.209, + "args": { + "External id": 39634,"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": 2338707, "tid": 2379456, + "ts": 6197200555496.092, "dur": 2.154, + "args": { + "External id": 39635,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2379456, + "ts": 6197200555558.994, "dur": 6.594, + "args": { + "External id": 39636,"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": 2338707, "tid": 2379456, + "ts": 6197200555577.018, "dur": 35.032, + "args": { + "External id": 39637,"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": 2338707, "tid": 2379456, + "ts": 6197200555622.438, "dur": 2.073, + "args": { + "External id": 39638,"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": 2338707, "tid": 2379456, + "ts": 6197200555629.680, "dur": 12.384, + "args": { + "External id": 39639,"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": 2338707, "tid": 2379456, + "ts": 6197200555647.267, "dur": 0.904, + "args": { + "External id": 39640,"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": 2338707, "tid": 2379456, + "ts": 6197200555658.023, "dur": 11.385, + "args": { + "External id": 39641,"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": 2338707, "tid": 2379456, + "ts": 6197200555676.387, "dur": 1.184, + "args": { + "External id": 39642,"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": 2338707, "tid": 2379456, + "ts": 6197200555681.241, "dur": 10.114, + "args": { + "External id": 39643,"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": 2338707, "tid": 2379456, + "ts": 6197200555695.188, "dur": 0.987, + "args": { + "External id": 39644,"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": 2338707, "tid": 2379456, + "ts": 6197200555699.890, "dur": 30.096, + "args": { + "External id": 39645,"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": 2338707, "tid": 2379456, + "ts": 6197200555737.945, "dur": 1.545, + "args": { + "External id": 39646,"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": 2338707, "tid": 2379456, + "ts": 6197200555743.886, "dur": 11.256, + "args": { + "External id": 39647,"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": 2338707, "tid": 2379456, + "ts": 6197200555761.324, "dur": 1.097, + "args": { + "External id": 39648,"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": 2338707, "tid": 2379456, + "ts": 6197200555766.441, "dur": 11.090, + "args": { + "External id": 39649,"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": 2338707, "tid": 2379456, + "ts": 6197200555781.854, "dur": 0.814, + "args": { + "External id": 39650,"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": 2338707, "tid": 2379456, + "ts": 6197200555786.587, "dur": 9.590, + "args": { + "External id": 39651,"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": 2338707, "tid": 2379456, + "ts": 6197200555799.975, "dur": 1.512, + "args": { + "External id": 39652,"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": 2338707, "tid": 2379456, + "ts": 6197200555805.793, "dur": 11.880, + "args": { + "External id": 39653,"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": 2338707, "tid": 2379456, + "ts": 6197200555911.748, "dur": 2859.132, + "args": { + "External id": 39654,"Record function id": 0, "Ev Idx": 7909 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.22)", "pid": 2338707, "tid": 2379456, + "ts": 6197200555935.823, "dur": 1047.235, + "args": { + "External id": 39655,"Record function id": 0, "Ev Idx": 7910 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.22)", "pid": 2338707, "tid": 2379456, + "ts": 6197200555952.555, "dur": 361.381, + "args": { + "External id": 39656,"Record function id": 0, "Ev Idx": 7911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6197200556037.877, "dur": 4.402, + "args": { + "External id": 39657,"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": 2338707, "tid": 2379456, + "ts": 6197200556045.936, "dur": 0.821, + "args": { + "External id": 39658,"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": 2338707, "tid": 2379456, + "ts": 6197200556048.788, "dur": 0.888, + "args": { + "External id": 39659,"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": 2338707, "tid": 2379456, + "ts": 6197200556051.559, "dur": 33.794, + "args": { + "External id": 39660,"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": 2338707, "tid": 2379456, + "ts": 6197200556089.815, "dur": 1.608, + "args": { + "External id": 39661,"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": 2338707, "tid": 2379456, + "ts": 6197200556092.916, "dur": 0.857, + "args": { + "External id": 39662,"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": 2338707, "tid": 2379456, + "ts": 6197200556095.135, "dur": 1.114, + "args": { + "External id": 39663,"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": 2338707, "tid": 2379456, + "ts": 6197200556099.837, "dur": 0.825, + "args": { + "External id": 39664,"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": 2338707, "tid": 2379456, + "ts": 6197200556102.116, "dur": 0.965, + "args": { + "External id": 39665,"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": 2338707, "tid": 2379456, + "ts": 6197200556104.304, "dur": 1.191, + "args": { + "External id": 39666,"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": 2338707, "tid": 2379456, + "ts": 6197200556124.242, "dur": 157.545, + "args": { + "External id": 39667,"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": 2338707, "tid": 2379456, + "ts": 6197200556139.652, "dur": 137.539, + "args": { + "External id": 39668,"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": 2338707, "tid": 2379456, + "ts": 6197200556164.437, "dur": 14.723, + "args": { + "External id": 39669,"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": 2338707, "tid": 2379456, + "ts": 6197200556185.199, "dur": 66.327, + "args": { + "External id": 39670,"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": 2338707, "tid": 2379456, + "ts": 6197200556188.240, "dur": 62.883, + "args": { + "External id": 39671,"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": 2338707, "tid": 2379456, + "ts": 6197200556192.480, "dur": 6.663, + "args": { + "External id": 39672,"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": 2338707, "tid": 2379456, + "ts": 6197200556200.772, "dur": 49.752, + "args": { + "External id": 39673,"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": 2338707, "tid": 2379456, + "ts": 6197200556403.671, "dur": 571.770, + "args": { + "External id": 39674,"Record function id": 0, "Ev Idx": 7929 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.21)", "pid": 2338707, "tid": 2379456, + "ts": 6197200556420.185, "dur": 542.832, + "args": { + "External id": 39675,"Record function id": 0, "Ev Idx": 7930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197200556483.800, "dur": 5.281, + "args": { + "External id": 39676,"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": 2338707, "tid": 2379456, + "ts": 6197200556503.621, "dur": 26.403, + "args": { + "External id": 39677,"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": 2338707, "tid": 2379456, + "ts": 6197200556508.592, "dur": 1.796, + "args": { + "External id": 39678,"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": 2338707, "tid": 2379456, + "ts": 6197200556512.389, "dur": 0.309, + "args": { + "External id": 39679,"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": 2338707, "tid": 2379456, + "ts": 6197200556513.696, "dur": 0.251, + "args": { + "External id": 39680,"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": 2338707, "tid": 2379456, + "ts": 6197200556515.914, "dur": 0.411, + "args": { + "External id": 39681,"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": 2338707, "tid": 2379456, + "ts": 6197200556517.692, "dur": 0.776, + "args": { + "External id": 39682,"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": 2338707, "tid": 2379456, + "ts": 6197200556520.047, "dur": 0.385, + "args": { + "External id": 39683,"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": 2338707, "tid": 2379456, + "ts": 6197200556521.896, "dur": 0.427, + "args": { + "External id": 39684,"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": 2338707, "tid": 2379456, + "ts": 6197200556523.783, "dur": 0.531, + "args": { + "External id": 39685,"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": 2338707, "tid": 2379456, + "ts": 6197200556525.426, "dur": 0.639, + "args": { + "External id": 39686,"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": 2338707, "tid": 2379456, + "ts": 6197200556543.155, "dur": 41.583, + "args": { + "External id": 39687,"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": 2338707, "tid": 2379456, + "ts": 6197200556612.277, "dur": 123.636, + "args": { + "External id": 39688,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2379456, + "ts": 6197200556622.165, "dur": 2.770, + "args": { + "External id": 39689,"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": 2338707, "tid": 2379456, + "ts": 6197200556629.965, "dur": 10.154, + "args": { + "External id": 39690,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2379456, + "ts": 6197200556634.165, "dur": 5.561, + "args": { + "External id": 39691,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2379456, + "ts": 6197200556637.197, "dur": 0.827, + "args": { + "External id": 39692,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197200556646.195, "dur": 25.438, + "args": { + "External id": 39693,"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": 2338707, "tid": 2379456, + "ts": 6197200556647.858, "dur": 0.767, + "args": { + "External id": 39694,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197200556649.993, "dur": 0.753, + "args": { + "External id": 39695,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2379456, + "ts": 6197200556651.686, "dur": 0.673, + "args": { + "External id": 39696,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2379456, + "ts": 6197200556653.324, "dur": 0.836, + "args": { + "External id": 39697,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2379456, + "ts": 6197200556655.240, "dur": 0.846, + "args": { + "External id": 39698,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2379456, + "ts": 6197200556657.284, "dur": 0.927, + "args": { + "External id": 39699,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2379456, + "ts": 6197200556659.118, "dur": 0.485, + "args": { + "External id": 39700,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2379456, + "ts": 6197200556660.545, "dur": 0.640, + "args": { + "External id": 39701,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2379456, + "ts": 6197200556662.249, "dur": 0.696, + "args": { + "External id": 39702,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2379456, + "ts": 6197200556681.367, "dur": 45.754, + "args": { + "External id": 39703,"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": 2338707, "tid": 2379456, + "ts": 6197200556780.451, "dur": 114.816, + "args": { + "External id": 39704,"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": 2338707, "tid": 2379456, + "ts": 6197200556808.027, "dur": 83.583, + "args": { + "External id": 39705,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197200556818.494, "dur": 69.113, + "args": { + "External id": 39706,"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": 2338707, "tid": 2379456, + "ts": 6197200556912.222, "dur": 1.869, + "args": { + "External id": 39707,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197200556999.652, "dur": 1746.107, + "args": { + "External id": 39708,"Sequence number": 480041, "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": 2338707, "tid": 2379456, "ts": 6197200556999.652, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6197200557151.388, "dur": 108.122, + "args": { + "External id": 39709,"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": 2338707, "tid": 2379456, + "ts": 6197200557301.527, "dur": 40.941, + "args": { + "External id": 39710,"kernel_hash": "cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/u7/cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs.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": 2338707, "tid": 2379456, + "ts": 6197200557359.454, "dur": 49.626, + "args": { + "External id": 39711,"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": 2338707, "tid": 2379456, + "ts": 6197200557418.898, "dur": 30.878, + "args": { + "External id": 39712,"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": 2338707, "tid": 2379456, + "ts": 6197200557456.198, "dur": 31.430, + "args": { + "External id": 39713,"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": 2338707, "tid": 2379456, + "ts": 6197200557495.484, "dur": 28.430, + "args": { + "External id": 39714,"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": 2338707, "tid": 2379456, + "ts": 6197200557530.530, "dur": 29.067, + "args": { + "External id": 39715,"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": 2338707, "tid": 2379456, + "ts": 6197200557585.452, "dur": 22.247, + "args": { + "External id": 39716,"kernel_hash": "cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/wm/cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s.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": 2338707, "tid": 2379456, + "ts": 6197200557628.101, "dur": 28.277, + "args": { + "External id": 39717,"kernel_hash": "cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql", "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/qt/cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql.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": 2338707, "tid": 2379456, + "ts": 6197200557676.882, "dur": 18.292, + "args": { + "External id": 39718,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197200557726.325, "dur": 17.569, + "args": { + "External id": 39719,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197200557754.332, "dur": 41.196, + "args": { + "External id": 39720,"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": 2338707, "tid": 2379456, + "ts": 6197200557799.303, "dur": 32.922, + "args": { + "External id": 39721,"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": 2338707, "tid": 2379456, + "ts": 6197200557860.627, "dur": 283.066, + "args": { + "External id": 39722,"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": 2338707, "tid": 2379456, + "ts": 6197200557939.834, "dur": 6.813, + "args": { + "External id": 39723,"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": 2338707, "tid": 2379456, + "ts": 6197200557948.792, "dur": 3.455, + "args": { + "External id": 39724,"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": 2338707, "tid": 2379456, + "ts": 6197200557953.333, "dur": 1.894, + "args": { + "External id": 39725,"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": 2338707, "tid": 2379456, + "ts": 6197200557955.982, "dur": 2.638, + "args": { + "External id": 39726,"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": 2338707, "tid": 2379456, + "ts": 6197200558002.957, "dur": 5.247, + "args": { + "External id": 39727,"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": 2338707, "tid": 2379456, + "ts": 6197200558005.022, "dur": 2.993, + "args": { + "External id": 39728,"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": 2338707, "tid": 2379456, + "ts": 6197200558010.355, "dur": 30.782, + "args": { + "External id": 39729,"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": 2338707, "tid": 2379456, + "ts": 6197200558016.687, "dur": 1.826, + "args": { + "External id": 39730,"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": 2338707, "tid": 2379456, + "ts": 6197200558043.074, "dur": 2.281, + "args": { + "External id": 39731,"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": 2338707, "tid": 2379456, + "ts": 6197200558044.808, "dur": 0.474, + "args": { + "External id": 39732,"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": 2338707, "tid": 2379456, + "ts": 6197200558046.569, "dur": 51.785, + "args": { + "External id": 39733,"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": 2338707, "tid": 2379456, + "ts": 6197200558048.595, "dur": 0.944, + "args": { + "External id": 39734,"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": 2338707, "tid": 2379456, + "ts": 6197200558180.833, "dur": 29.712, + "args": { + "External id": 39735,"kernel_hash": "cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4", "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/yk/cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4.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": 2338707, "tid": 2379456, + "ts": 6197200558229.250, "dur": 17.108, + "args": { + "External id": 39736,"kernel_hash": "ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg", "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/eu/ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg.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": 2338707, "tid": 2379456, + "ts": 6197200558254.514, "dur": 50.816, + "args": { + "External id": 39737,"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": 2338707, "tid": 2379456, + "ts": 6197200558311.149, "dur": 39.108, + "args": { + "External id": 39738,"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": 2338707, "tid": 2379456, + "ts": 6197200558359.450, "dur": 20.599, + "args": { + "External id": 39739,"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": 2338707, "tid": 2379456, + "ts": 6197200558386.623, "dur": 32.790, + "args": { + "External id": 39740,"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": 2338707, "tid": 2379456, + "ts": 6197200558427.566, "dur": 28.434, + "args": { + "External id": 39741,"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": 2338707, "tid": 2379456, + "ts": 6197200558462.563, "dur": 30.666, + "args": { + "External id": 39742,"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": 2338707, "tid": 2379456, + "ts": 6197200558527.836, "dur": 29.660, + "args": { + "External id": 39743,"kernel_hash": "c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/6w/c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7.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": 2338707, "tid": 2379456, + "ts": 6197200558577.291, "dur": 22.566, + "args": { + "External id": 39744,"kernel_hash": "ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx", "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/kj/ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx.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": 2338707, "tid": 2379456, + "ts": 6197200558617.344, "dur": 15.978, + "args": { + "External id": 39745,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197200558649.324, "dur": 13.414, + "args": { + "External id": 39746,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197200558682.156, "dur": 15.161, + "args": { + "External id": 39747,"kernel_hash": "cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/eb/cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b.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": 2338707, "tid": 2379456, + "ts": 6197200558793.082, "dur": 14.917, + "args": { + "External id": 39748,"Record function id": 0, "Ev Idx": 8003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200558796.237, "dur": 10.780, + "args": { + "External id": 39749,"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": 2338707, "tid": 2379456, + "ts": 6197200558800.635, "dur": 5.287, + "args": { + "External id": 39750,"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": 2338707, "tid": 2379456, + "ts": 6197200558802.250, "dur": 3.562, + "args": { + "External id": 39751,"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": 2338707, "tid": 2379456, + "ts": 6197200558812.046, "dur": 5.013, + "args": { + "External id": 39752,"Record function id": 0, "Ev Idx": 8007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200558813.556, "dur": 3.001, + "args": { + "External id": 39753,"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": 2338707, "tid": 2379456, + "ts": 6197200558814.378, "dur": 1.691, + "args": { + "External id": 39754,"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": 2338707, "tid": 2379456, + "ts": 6197200558815.160, "dur": 0.831, + "args": { + "External id": 39755,"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": 2338707, "tid": 2379456, + "ts": 6197200558820.448, "dur": 6.087, + "args": { + "External id": 39756,"Record function id": 0, "Ev Idx": 8011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200558822.001, "dur": 4.084, + "args": { + "External id": 39757,"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": 2338707, "tid": 2379456, + "ts": 6197200558823.093, "dur": 2.551, + "args": { + "External id": 39758,"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": 2338707, "tid": 2379456, + "ts": 6197200558823.778, "dur": 1.761, + "args": { + "External id": 39759,"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": 2338707, "tid": 2379456, + "ts": 6197200558829.938, "dur": 4.193, + "args": { + "External id": 39760,"Record function id": 0, "Ev Idx": 8015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200558831.109, "dur": 2.588, + "args": { + "External id": 39761,"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": 2338707, "tid": 2379456, + "ts": 6197200558831.916, "dur": 1.388, + "args": { + "External id": 39762,"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": 2338707, "tid": 2379456, + "ts": 6197200558832.566, "dur": 0.656, + "args": { + "External id": 39763,"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": 2338707, "tid": 2379456, + "ts": 6197200558837.358, "dur": 4.221, + "args": { + "External id": 39764,"Record function id": 0, "Ev Idx": 8019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200558838.578, "dur": 2.550, + "args": { + "External id": 39765,"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": 2338707, "tid": 2379456, + "ts": 6197200558839.209, "dur": 1.469, + "args": { + "External id": 39766,"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": 2338707, "tid": 2379456, + "ts": 6197200558839.522, "dur": 1.091, + "args": { + "External id": 39767,"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": 2338707, "tid": 2379456, + "ts": 6197200558844.743, "dur": 3.695, + "args": { + "External id": 39768,"Record function id": 0, "Ev Idx": 8023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200558845.673, "dur": 2.332, + "args": { + "External id": 39769,"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": 2338707, "tid": 2379456, + "ts": 6197200558846.133, "dur": 1.480, + "args": { + "External id": 39770,"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": 2338707, "tid": 2379456, + "ts": 6197200558846.663, "dur": 0.862, + "args": { + "External id": 39771,"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": 2338707, "tid": 2379456, + "ts": 6197200558851.712, "dur": 4.611, + "args": { + "External id": 39772,"Record function id": 0, "Ev Idx": 8027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200558852.796, "dur": 3.075, + "args": { + "External id": 39773,"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": 2338707, "tid": 2379456, + "ts": 6197200558853.446, "dur": 1.787, + "args": { + "External id": 39774,"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": 2338707, "tid": 2379456, + "ts": 6197200558853.937, "dur": 1.205, + "args": { + "External id": 39775,"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": 2338707, "tid": 2379456, + "ts": 6197200558859.604, "dur": 3.735, + "args": { + "External id": 39776,"Record function id": 0, "Ev Idx": 8031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200558860.695, "dur": 2.214, + "args": { + "External id": 39777,"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": 2338707, "tid": 2379456, + "ts": 6197200558861.225, "dur": 1.260, + "args": { + "External id": 39778,"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": 2338707, "tid": 2379456, + "ts": 6197200558861.758, "dur": 0.662, + "args": { + "External id": 39779,"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": 2338707, "tid": 2379456, + "ts": 6197200558866.418, "dur": 4.079, + "args": { + "External id": 39780,"Record function id": 0, "Ev Idx": 8035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200558867.406, "dur": 2.664, + "args": { + "External id": 39781,"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": 2338707, "tid": 2379456, + "ts": 6197200558867.933, "dur": 1.476, + "args": { + "External id": 39782,"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": 2338707, "tid": 2379456, + "ts": 6197200558868.491, "dur": 0.854, + "args": { + "External id": 39783,"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": 2338707, "tid": 2379456, + "ts": 6197200558874.321, "dur": 64989.248, + "args": { + "External id": 39784,"Record function id": 0, "Sequence number": 480040, "Fwd thread id": 1, "Ev Idx": 8039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197200558875.475, "dur": 64979.309, + "args": { + "External id": 39785,"Sequence number": 480040, "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": 2338707, "tid": 2379456, "ts": 6197200558875.475, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.22)", "pid": 2338707, "tid": 2379456, + "ts": 6197200558906.558, "dur": 39.087, + "args": { + "External id": 39786,"Record function id": 0, "Ev Idx": 8041 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.22)", "pid": 2338707, "tid": 2379456, + "ts": 6197200558954.519, "dur": 64.292, + "args": { + "External id": 39787,"Record function id": 0, "Ev Idx": 8042 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.22)", "pid": 2338707, "tid": 2379456, + "ts": 6197200559025.021, "dur": 64822.396, + "args": { + "External id": 39788,"Record function id": 0, "Ev Idx": 8043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197200559151.476, "dur": 7.689, + "args": { + "External id": 39789,"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": 2338707, "tid": 2379456, + "ts": 6197200559170.152, "dur": 5.141, + "args": { + "External id": 39790,"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": 2338707, "tid": 2379456, + "ts": 6197200559190.850, "dur": 63702.931, + "args": { + "External id": 39791,"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": 2338707, "tid": 2379456, + "ts": 6197200559204.203, "dur": 63677.134, + "args": { + "External id": 39792,"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": 2338707, "tid": 2379456, + "ts": 6197200559300.887, "dur": 17.947, + "args": { + "External id": 39793,"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": 2338707, "tid": 2379456, + "ts": 6197200559339.584, "dur": 63498.913, + "args": { + "External id": 39794,"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": 2338707, "tid": 2379456, + "ts": 6197200559342.765, "dur": 63494.488, + "args": { + "External id": 39795,"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": 2338707, "tid": 2379456, + "ts": 6197200559347.271, "dur": 7.883, + "args": { + "External id": 39796,"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": 2338707, "tid": 2379456, + "ts": 6197200559359.966, "dur": 63472.275, + "args": { + "External id": 39797,"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": 2338707, "tid": 2379456, + "ts": 6197200623001.626, "dur": 12.531, + "args": { + "External id": 39798,"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": 2338707, "tid": 2379456, + "ts": 6197200623005.111, "dur": 8.619, + "args": { + "External id": 39799,"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": 2338707, "tid": 2379456, + "ts": 6197200623042.268, "dur": 397.913, + "args": { + "External id": 39800,"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": 2338707, "tid": 2379456, + "ts": 6197200623114.957, "dur": 319.657, + "args": { + "External id": 39801,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197200623127.373, "dur": 301.324, + "args": { + "External id": 39802,"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": 2338707, "tid": 2379456, + "ts": 6197200623460.344, "dur": 2.074, + "args": { + "External id": 39803,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2379456, + "ts": 6197200623522.316, "dur": 6.369, + "args": { + "External id": 39804,"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": 2338707, "tid": 2379456, + "ts": 6197200623540.253, "dur": 32.758, + "args": { + "External id": 39805,"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": 2338707, "tid": 2379456, + "ts": 6197200623583.218, "dur": 1.833, + "args": { + "External id": 39806,"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": 2338707, "tid": 2379456, + "ts": 6197200623590.978, "dur": 13.761, + "args": { + "External id": 39807,"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": 2338707, "tid": 2379456, + "ts": 6197200623609.691, "dur": 1.446, + "args": { + "External id": 39808,"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": 2338707, "tid": 2379456, + "ts": 6197200623615.144, "dur": 12.521, + "args": { + "External id": 39809,"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": 2338707, "tid": 2379456, + "ts": 6197200623634.142, "dur": 0.796, + "args": { + "External id": 39810,"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": 2338707, "tid": 2379456, + "ts": 6197200623639.741, "dur": 11.319, + "args": { + "External id": 39811,"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": 2338707, "tid": 2379456, + "ts": 6197200623655.568, "dur": 1.186, + "args": { + "External id": 39812,"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": 2338707, "tid": 2379456, + "ts": 6197200623661.026, "dur": 12.872, + "args": { + "External id": 39813,"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": 2338707, "tid": 2379456, + "ts": 6197200623678.807, "dur": 1.109, + "args": { + "External id": 39814,"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": 2338707, "tid": 2379456, + "ts": 6197200623684.628, "dur": 11.893, + "args": { + "External id": 39815,"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": 2338707, "tid": 2379456, + "ts": 6197200623719.488, "dur": 1.577, + "args": { + "External id": 39816,"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": 2338707, "tid": 2379456, + "ts": 6197200623726.547, "dur": 15.662, + "args": { + "External id": 39817,"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": 2338707, "tid": 2379456, + "ts": 6197200623748.283, "dur": 1.048, + "args": { + "External id": 39818,"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": 2338707, "tid": 2379456, + "ts": 6197200623752.937, "dur": 12.125, + "args": { + "External id": 39819,"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": 2338707, "tid": 2379456, + "ts": 6197200623769.103, "dur": 0.933, + "args": { + "External id": 39820,"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": 2338707, "tid": 2379456, + "ts": 6197200623774.666, "dur": 12.812, + "args": { + "External id": 39821,"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": 2338707, "tid": 2379456, + "ts": 6197200623879.468, "dur": 2900.918, + "args": { + "External id": 39822,"Record function id": 0, "Ev Idx": 8077 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.21)", "pid": 2338707, "tid": 2379456, + "ts": 6197200623902.157, "dur": 1062.466, + "args": { + "External id": 39823,"Record function id": 0, "Ev Idx": 8078 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.21)", "pid": 2338707, "tid": 2379456, + "ts": 6197200623917.506, "dur": 374.995, + "args": { + "External id": 39824,"Record function id": 0, "Ev Idx": 8079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6197200624014.339, "dur": 4.569, + "args": { + "External id": 39825,"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": 2338707, "tid": 2379456, + "ts": 6197200624022.396, "dur": 1.607, + "args": { + "External id": 39826,"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": 2338707, "tid": 2379456, + "ts": 6197200624026.158, "dur": 0.889, + "args": { + "External id": 39827,"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": 2338707, "tid": 2379456, + "ts": 6197200624028.630, "dur": 1.293, + "args": { + "External id": 39828,"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": 2338707, "tid": 2379456, + "ts": 6197200624031.317, "dur": 1.098, + "args": { + "External id": 39829,"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": 2338707, "tid": 2379456, + "ts": 6197200624033.603, "dur": 1.262, + "args": { + "External id": 39830,"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": 2338707, "tid": 2379456, + "ts": 6197200624036.502, "dur": 1.001, + "args": { + "External id": 39831,"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": 2338707, "tid": 2379456, + "ts": 6197200624040.844, "dur": 1.459, + "args": { + "External id": 39832,"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": 2338707, "tid": 2379456, + "ts": 6197200624043.876, "dur": 1.254, + "args": { + "External id": 39833,"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": 2338707, "tid": 2379456, + "ts": 6197200624046.735, "dur": 1.359, + "args": { + "External id": 39834,"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": 2338707, "tid": 2379456, + "ts": 6197200624100.798, "dur": 158.010, + "args": { + "External id": 39835,"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": 2338707, "tid": 2379456, + "ts": 6197200624118.597, "dur": 135.548, + "args": { + "External id": 39836,"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": 2338707, "tid": 2379456, + "ts": 6197200624134.318, "dur": 25.060, + "args": { + "External id": 39837,"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": 2338707, "tid": 2379456, + "ts": 6197200624165.234, "dur": 62.224, + "args": { + "External id": 39838,"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": 2338707, "tid": 2379456, + "ts": 6197200624167.958, "dur": 59.179, + "args": { + "External id": 39839,"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": 2338707, "tid": 2379456, + "ts": 6197200624171.980, "dur": 5.881, + "args": { + "External id": 39840,"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": 2338707, "tid": 2379456, + "ts": 6197200624179.677, "dur": 46.748, + "args": { + "External id": 39841,"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": 2338707, "tid": 2379456, + "ts": 6197200624382.146, "dur": 574.642, + "args": { + "External id": 39842,"Record function id": 0, "Ev Idx": 8097 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.20)", "pid": 2338707, "tid": 2379456, + "ts": 6197200624398.985, "dur": 544.462, + "args": { + "External id": 39843,"Record function id": 0, "Ev Idx": 8098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197200624460.869, "dur": 5.403, + "args": { + "External id": 39844,"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": 2338707, "tid": 2379456, + "ts": 6197200624480.308, "dur": 27.092, + "args": { + "External id": 39845,"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": 2338707, "tid": 2379456, + "ts": 6197200624485.441, "dur": 2.008, + "args": { + "External id": 39846,"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": 2338707, "tid": 2379456, + "ts": 6197200624489.221, "dur": 0.323, + "args": { + "External id": 39847,"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": 2338707, "tid": 2379456, + "ts": 6197200624490.799, "dur": 0.481, + "args": { + "External id": 39848,"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": 2338707, "tid": 2379456, + "ts": 6197200624493.141, "dur": 0.432, + "args": { + "External id": 39849,"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": 2338707, "tid": 2379456, + "ts": 6197200624495.392, "dur": 0.734, + "args": { + "External id": 39850,"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": 2338707, "tid": 2379456, + "ts": 6197200624497.699, "dur": 0.688, + "args": { + "External id": 39851,"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": 2338707, "tid": 2379456, + "ts": 6197200624499.602, "dur": 0.635, + "args": { + "External id": 39852,"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": 2338707, "tid": 2379456, + "ts": 6197200624501.252, "dur": 0.338, + "args": { + "External id": 39853,"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": 2338707, "tid": 2379456, + "ts": 6197200624502.786, "dur": 0.632, + "args": { + "External id": 39854,"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": 2338707, "tid": 2379456, + "ts": 6197200624517.317, "dur": 40.295, + "args": { + "External id": 39855,"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": 2338707, "tid": 2379456, + "ts": 6197200624586.492, "dur": 104.955, + "args": { + "External id": 39856,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2379456, + "ts": 6197200624595.599, "dur": 3.271, + "args": { + "External id": 39857,"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": 2338707, "tid": 2379456, + "ts": 6197200624604.121, "dur": 10.409, + "args": { + "External id": 39858,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2379456, + "ts": 6197200624608.508, "dur": 5.612, + "args": { + "External id": 39859,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2379456, + "ts": 6197200624611.509, "dur": 1.302, + "args": { + "External id": 39860,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197200624620.783, "dur": 22.583, + "args": { + "External id": 39861,"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": 2338707, "tid": 2379456, + "ts": 6197200624622.601, "dur": 0.853, + "args": { + "External id": 39862,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197200624624.923, "dur": 0.716, + "args": { + "External id": 39863,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2379456, + "ts": 6197200624626.732, "dur": 0.785, + "args": { + "External id": 39864,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2379456, + "ts": 6197200624629.026, "dur": 0.391, + "args": { + "External id": 39865,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2379456, + "ts": 6197200624630.742, "dur": 0.454, + "args": { + "External id": 39866,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2379456, + "ts": 6197200624632.043, "dur": 0.611, + "args": { + "External id": 39867,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2379456, + "ts": 6197200624633.694, "dur": 0.439, + "args": { + "External id": 39868,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2379456, + "ts": 6197200624635.361, "dur": 0.885, + "args": { + "External id": 39869,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2379456, + "ts": 6197200624637.227, "dur": 0.610, + "args": { + "External id": 39870,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2379456, + "ts": 6197200624653.523, "dur": 30.606, + "args": { + "External id": 39871,"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": 2338707, "tid": 2379456, + "ts": 6197200624754.080, "dur": 120.199, + "args": { + "External id": 39872,"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": 2338707, "tid": 2379456, + "ts": 6197200624783.086, "dur": 87.481, + "args": { + "External id": 39873,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197200624792.480, "dur": 73.794, + "args": { + "External id": 39874,"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": 2338707, "tid": 2379456, + "ts": 6197200624890.701, "dur": 1.820, + "args": { + "External id": 39875,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197200624971.939, "dur": 1781.770, + "args": { + "External id": 39876,"Sequence number": 480039, "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": 2338707, "tid": 2379456, "ts": 6197200624971.939, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6197200625123.635, "dur": 108.702, + "args": { + "External id": 39877,"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": 2338707, "tid": 2379456, + "ts": 6197200625278.013, "dur": 39.937, + "args": { + "External id": 39878,"kernel_hash": "cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/u7/cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs.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": 2338707, "tid": 2379456, + "ts": 6197200625335.757, "dur": 50.975, + "args": { + "External id": 39879,"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": 2338707, "tid": 2379456, + "ts": 6197200625396.724, "dur": 33.355, + "args": { + "External id": 39880,"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": 2338707, "tid": 2379456, + "ts": 6197200625437.133, "dur": 32.971, + "args": { + "External id": 39881,"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": 2338707, "tid": 2379456, + "ts": 6197200625476.973, "dur": 28.146, + "args": { + "External id": 39882,"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": 2338707, "tid": 2379456, + "ts": 6197200625511.760, "dur": 28.971, + "args": { + "External id": 39883,"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": 2338707, "tid": 2379456, + "ts": 6197200625566.188, "dur": 25.710, + "args": { + "External id": 39884,"kernel_hash": "cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/wm/cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s.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": 2338707, "tid": 2379456, + "ts": 6197200625610.906, "dur": 29.352, + "args": { + "External id": 39885,"kernel_hash": "cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql", "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/qt/cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql.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": 2338707, "tid": 2379456, + "ts": 6197200625666.203, "dur": 20.820, + "args": { + "External id": 39886,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197200625716.226, "dur": 25.093, + "args": { + "External id": 39887,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197200625751.522, "dur": 43.315, + "args": { + "External id": 39888,"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": 2338707, "tid": 2379456, + "ts": 6197200625798.709, "dur": 33.823, + "args": { + "External id": 39889,"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": 2338707, "tid": 2379456, + "ts": 6197200625860.199, "dur": 295.348, + "args": { + "External id": 39890,"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": 2338707, "tid": 2379456, + "ts": 6197200625940.416, "dur": 6.572, + "args": { + "External id": 39891,"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": 2338707, "tid": 2379456, + "ts": 6197200625949.204, "dur": 2.387, + "args": { + "External id": 39892,"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": 2338707, "tid": 2379456, + "ts": 6197200625953.080, "dur": 2.644, + "args": { + "External id": 39893,"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": 2338707, "tid": 2379456, + "ts": 6197200625956.899, "dur": 2.349, + "args": { + "External id": 39894,"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": 2338707, "tid": 2379456, + "ts": 6197200626007.949, "dur": 5.306, + "args": { + "External id": 39895,"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": 2338707, "tid": 2379456, + "ts": 6197200626010.240, "dur": 2.835, + "args": { + "External id": 39896,"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": 2338707, "tid": 2379456, + "ts": 6197200626014.995, "dur": 32.203, + "args": { + "External id": 39897,"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": 2338707, "tid": 2379456, + "ts": 6197200626020.229, "dur": 1.630, + "args": { + "External id": 39898,"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": 2338707, "tid": 2379456, + "ts": 6197200626048.528, "dur": 2.016, + "args": { + "External id": 39899,"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": 2338707, "tid": 2379456, + "ts": 6197200626049.971, "dur": 0.504, + "args": { + "External id": 39900,"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": 2338707, "tid": 2379456, + "ts": 6197200626087.252, "dur": 22.224, + "args": { + "External id": 39901,"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": 2338707, "tid": 2379456, + "ts": 6197200626091.023, "dur": 1.619, + "args": { + "External id": 39902,"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": 2338707, "tid": 2379456, + "ts": 6197200626190.933, "dur": 31.106, + "args": { + "External id": 39903,"kernel_hash": "cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4", "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/yk/cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4.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": 2338707, "tid": 2379456, + "ts": 6197200626238.532, "dur": 17.505, + "args": { + "External id": 39904,"kernel_hash": "ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg", "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/eu/ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg.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": 2338707, "tid": 2379456, + "ts": 6197200626263.942, "dur": 50.335, + "args": { + "External id": 39905,"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": 2338707, "tid": 2379456, + "ts": 6197200626321.269, "dur": 40.936, + "args": { + "External id": 39906,"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": 2338707, "tid": 2379456, + "ts": 6197200626370.703, "dur": 23.731, + "args": { + "External id": 39907,"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": 2338707, "tid": 2379456, + "ts": 6197200626400.878, "dur": 32.160, + "args": { + "External id": 39908,"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": 2338707, "tid": 2379456, + "ts": 6197200626441.073, "dur": 28.732, + "args": { + "External id": 39909,"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": 2338707, "tid": 2379456, + "ts": 6197200626476.952, "dur": 31.485, + "args": { + "External id": 39910,"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": 2338707, "tid": 2379456, + "ts": 6197200626529.177, "dur": 26.879, + "args": { + "External id": 39911,"kernel_hash": "c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/6w/c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7.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": 2338707, "tid": 2379456, + "ts": 6197200626571.744, "dur": 25.810, + "args": { + "External id": 39912,"kernel_hash": "ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx", "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/kj/ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx.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": 2338707, "tid": 2379456, + "ts": 6197200626612.124, "dur": 18.982, + "args": { + "External id": 39913,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197200626648.133, "dur": 14.676, + "args": { + "External id": 39914,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197200626676.942, "dur": 16.598, + "args": { + "External id": 39915,"kernel_hash": "cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/eb/cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b.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": 2338707, "tid": 2379456, + "ts": 6197200626804.118, "dur": 14.698, + "args": { + "External id": 39916,"Record function id": 0, "Ev Idx": 8171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200626807.398, "dur": 10.487, + "args": { + "External id": 39917,"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": 2338707, "tid": 2379456, + "ts": 6197200626811.414, "dur": 5.588, + "args": { + "External id": 39918,"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": 2338707, "tid": 2379456, + "ts": 6197200626813.133, "dur": 3.756, + "args": { + "External id": 39919,"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": 2338707, "tid": 2379456, + "ts": 6197200626822.580, "dur": 7.979, + "args": { + "External id": 39920,"Record function id": 0, "Ev Idx": 8175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200626824.172, "dur": 5.921, + "args": { + "External id": 39921,"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": 2338707, "tid": 2379456, + "ts": 6197200626825.047, "dur": 1.422, + "args": { + "External id": 39922,"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": 2338707, "tid": 2379456, + "ts": 6197200626825.376, "dur": 1.010, + "args": { + "External id": 39923,"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": 2338707, "tid": 2379456, + "ts": 6197200626833.935, "dur": 4.928, + "args": { + "External id": 39924,"Record function id": 0, "Ev Idx": 8179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200626835.249, "dur": 3.189, + "args": { + "External id": 39925,"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": 2338707, "tid": 2379456, + "ts": 6197200626835.811, "dur": 2.192, + "args": { + "External id": 39926,"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": 2338707, "tid": 2379456, + "ts": 6197200626836.719, "dur": 1.197, + "args": { + "External id": 39927,"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": 2338707, "tid": 2379456, + "ts": 6197200626842.017, "dur": 4.331, + "args": { + "External id": 39928,"Record function id": 0, "Ev Idx": 8183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200626843.505, "dur": 2.433, + "args": { + "External id": 39929,"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": 2338707, "tid": 2379456, + "ts": 6197200626844.106, "dur": 1.179, + "args": { + "External id": 39930,"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": 2338707, "tid": 2379456, + "ts": 6197200626844.549, "dur": 0.638, + "args": { + "External id": 39931,"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": 2338707, "tid": 2379456, + "ts": 6197200626849.473, "dur": 3.716, + "args": { + "External id": 39932,"Record function id": 0, "Ev Idx": 8187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200626850.584, "dur": 2.209, + "args": { + "External id": 39933,"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": 2338707, "tid": 2379456, + "ts": 6197200626851.054, "dur": 1.253, + "args": { + "External id": 39934,"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": 2338707, "tid": 2379456, + "ts": 6197200626851.332, "dur": 0.908, + "args": { + "External id": 39935,"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": 2338707, "tid": 2379456, + "ts": 6197200626856.205, "dur": 50.462, + "args": { + "External id": 39936,"Record function id": 0, "Ev Idx": 8191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200626901.200, "dur": 4.939, + "args": { + "External id": 39937,"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": 2338707, "tid": 2379456, + "ts": 6197200626901.994, "dur": 3.495, + "args": { + "External id": 39938,"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": 2338707, "tid": 2379456, + "ts": 6197200626904.373, "dur": 1.003, + "args": { + "External id": 39939,"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": 2338707, "tid": 2379456, + "ts": 6197200626909.900, "dur": 3.507, + "args": { + "External id": 39940,"Record function id": 0, "Ev Idx": 8195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200626910.892, "dur": 2.125, + "args": { + "External id": 39941,"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": 2338707, "tid": 2379456, + "ts": 6197200626911.511, "dur": 1.096, + "args": { + "External id": 39942,"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": 2338707, "tid": 2379456, + "ts": 6197200626911.773, "dur": 0.770, + "args": { + "External id": 39943,"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": 2338707, "tid": 2379456, + "ts": 6197200626916.426, "dur": 3.883, + "args": { + "External id": 39944,"Record function id": 0, "Ev Idx": 8199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200626917.679, "dur": 2.220, + "args": { + "External id": 39945,"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": 2338707, "tid": 2379456, + "ts": 6197200626918.273, "dur": 1.227, + "args": { + "External id": 39946,"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": 2338707, "tid": 2379456, + "ts": 6197200626918.713, "dur": 0.723, + "args": { + "External id": 39947,"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": 2338707, "tid": 2379456, + "ts": 6197200626923.334, "dur": 3.987, + "args": { + "External id": 39948,"Record function id": 0, "Ev Idx": 8203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200626924.200, "dur": 2.679, + "args": { + "External id": 39949,"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": 2338707, "tid": 2379456, + "ts": 6197200626924.636, "dur": 1.731, + "args": { + "External id": 39950,"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": 2338707, "tid": 2379456, + "ts": 6197200626924.999, "dur": 1.305, + "args": { + "External id": 39951,"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": 2338707, "tid": 2379456, + "ts": 6197200626931.213, "dur": 66710.719, + "args": { + "External id": 39952,"Record function id": 0, "Sequence number": 480038, "Fwd thread id": 1, "Ev Idx": 8207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197200626932.472, "dur": 66699.330, + "args": { + "External id": 39953,"Sequence number": 480038, "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": 2338707, "tid": 2379456, "ts": 6197200626932.472, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.21)", "pid": 2338707, "tid": 2379456, + "ts": 6197200626964.207, "dur": 39.432, + "args": { + "External id": 39954,"Record function id": 0, "Ev Idx": 8209 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.21)", "pid": 2338707, "tid": 2379456, + "ts": 6197200627011.373, "dur": 108.569, + "args": { + "External id": 39955,"Record function id": 0, "Ev Idx": 8210 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.21)", "pid": 2338707, "tid": 2379456, + "ts": 6197200627128.012, "dur": 66496.240, + "args": { + "External id": 39956,"Record function id": 0, "Ev Idx": 8211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197200627223.641, "dur": 7.892, + "args": { + "External id": 39957,"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": 2338707, "tid": 2379456, + "ts": 6197200627242.229, "dur": 4.626, + "args": { + "External id": 39958,"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": 2338707, "tid": 2379456, + "ts": 6197200627263.814, "dur": 65416.519, + "args": { + "External id": 39959,"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": 2338707, "tid": 2379456, + "ts": 6197200627280.288, "dur": 65387.379, + "args": { + "External id": 39960,"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": 2338707, "tid": 2379456, + "ts": 6197200627370.314, "dur": 17.480, + "args": { + "External id": 39961,"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": 2338707, "tid": 2379456, + "ts": 6197200627408.377, "dur": 65216.533, + "args": { + "External id": 39962,"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": 2338707, "tid": 2379456, + "ts": 6197200627411.276, "dur": 65212.691, + "args": { + "External id": 39963,"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": 2338707, "tid": 2379456, + "ts": 6197200627416.008, "dur": 7.713, + "args": { + "External id": 39964,"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": 2338707, "tid": 2379456, + "ts": 6197200627425.631, "dur": 65193.576, + "args": { + "External id": 39965,"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": 2338707, "tid": 2379456, + "ts": 6197200692799.331, "dur": 12.800, + "args": { + "External id": 39966,"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": 2338707, "tid": 2379456, + "ts": 6197200692802.815, "dur": 8.713, + "args": { + "External id": 39967,"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": 2338707, "tid": 2379456, + "ts": 6197200692841.777, "dur": 395.836, + "args": { + "External id": 39968,"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": 2338707, "tid": 2379456, + "ts": 6197200692872.891, "dur": 359.296, + "args": { + "External id": 39969,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197200692884.529, "dur": 342.049, + "args": { + "External id": 39970,"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": 2338707, "tid": 2379456, + "ts": 6197200693262.031, "dur": 2.442, + "args": { + "External id": 39971,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2379456, + "ts": 6197200693327.944, "dur": 6.485, + "args": { + "External id": 39972,"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": 2338707, "tid": 2379456, + "ts": 6197200693350.211, "dur": 36.484, + "args": { + "External id": 39973,"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": 2338707, "tid": 2379456, + "ts": 6197200693397.635, "dur": 1.758, + "args": { + "External id": 39974,"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": 2338707, "tid": 2379456, + "ts": 6197200693405.131, "dur": 13.089, + "args": { + "External id": 39975,"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": 2338707, "tid": 2379456, + "ts": 6197200693423.672, "dur": 0.970, + "args": { + "External id": 39976,"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": 2338707, "tid": 2379456, + "ts": 6197200693428.553, "dur": 12.976, + "args": { + "External id": 39977,"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": 2338707, "tid": 2379456, + "ts": 6197200693447.018, "dur": 0.931, + "args": { + "External id": 39978,"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": 2338707, "tid": 2379456, + "ts": 6197200693451.830, "dur": 11.485, + "args": { + "External id": 39979,"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": 2338707, "tid": 2379456, + "ts": 6197200693467.498, "dur": 0.911, + "args": { + "External id": 39980,"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": 2338707, "tid": 2379456, + "ts": 6197200693474.048, "dur": 12.335, + "args": { + "External id": 39981,"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": 2338707, "tid": 2379456, + "ts": 6197200693490.689, "dur": 1.143, + "args": { + "External id": 39982,"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": 2338707, "tid": 2379456, + "ts": 6197200693495.809, "dur": 10.061, + "args": { + "External id": 39983,"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": 2338707, "tid": 2379456, + "ts": 6197200693512.394, "dur": 1.001, + "args": { + "External id": 39984,"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": 2338707, "tid": 2379456, + "ts": 6197200693517.338, "dur": 9.592, + "args": { + "External id": 39985,"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": 2338707, "tid": 2379456, + "ts": 6197200693530.802, "dur": 0.970, + "args": { + "External id": 39986,"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": 2338707, "tid": 2379456, + "ts": 6197200693536.115, "dur": 10.156, + "args": { + "External id": 39987,"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": 2338707, "tid": 2379456, + "ts": 6197200693550.307, "dur": 0.813, + "args": { + "External id": 39988,"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": 2338707, "tid": 2379456, + "ts": 6197200693554.699, "dur": 12.474, + "args": { + "External id": 39989,"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": 2338707, "tid": 2379456, + "ts": 6197200693656.081, "dur": 2917.356, + "args": { + "External id": 39990,"Record function id": 0, "Ev Idx": 8245 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.20)", "pid": 2338707, "tid": 2379456, + "ts": 6197200693678.181, "dur": 1097.995, + "args": { + "External id": 39991,"Record function id": 0, "Ev Idx": 8246 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.20)", "pid": 2338707, "tid": 2379456, + "ts": 6197200693695.269, "dur": 341.967, + "args": { + "External id": 39992,"Record function id": 0, "Ev Idx": 8247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6197200693799.381, "dur": 4.857, + "args": { + "External id": 39993,"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": 2338707, "tid": 2379456, + "ts": 6197200693807.628, "dur": 0.764, + "args": { + "External id": 39994,"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": 2338707, "tid": 2379456, + "ts": 6197200693810.355, "dur": 1.105, + "args": { + "External id": 39995,"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": 2338707, "tid": 2379456, + "ts": 6197200693813.374, "dur": 0.801, + "args": { + "External id": 39996,"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": 2338707, "tid": 2379456, + "ts": 6197200693815.502, "dur": 0.986, + "args": { + "External id": 39997,"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": 2338707, "tid": 2379456, + "ts": 6197200693817.968, "dur": 0.864, + "args": { + "External id": 39998,"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": 2338707, "tid": 2379456, + "ts": 6197200693820.392, "dur": 1.517, + "args": { + "External id": 39999,"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": 2338707, "tid": 2379456, + "ts": 6197200693825.892, "dur": 1.217, + "args": { + "External id": 40000,"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": 2338707, "tid": 2379456, + "ts": 6197200693828.428, "dur": 1.485, + "args": { + "External id": 40001,"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": 2338707, "tid": 2379456, + "ts": 6197200693831.313, "dur": 1.016, + "args": { + "External id": 40002,"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": 2338707, "tid": 2379456, + "ts": 6197200693849.980, "dur": 155.758, + "args": { + "External id": 40003,"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": 2338707, "tid": 2379456, + "ts": 6197200693865.436, "dur": 135.858, + "args": { + "External id": 40004,"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": 2338707, "tid": 2379456, + "ts": 6197200693880.982, "dur": 24.110, + "args": { + "External id": 40005,"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": 2338707, "tid": 2379456, + "ts": 6197200693910.856, "dur": 63.435, + "args": { + "External id": 40006,"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": 2338707, "tid": 2379456, + "ts": 6197200693913.589, "dur": 60.370, + "args": { + "External id": 40007,"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": 2338707, "tid": 2379456, + "ts": 6197200693917.402, "dur": 5.245, + "args": { + "External id": 40008,"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": 2338707, "tid": 2379456, + "ts": 6197200693924.577, "dur": 48.843, + "args": { + "External id": 40009,"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": 2338707, "tid": 2379456, + "ts": 6197200694176.529, "dur": 591.990, + "args": { + "External id": 40010,"Record function id": 0, "Ev Idx": 8265 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.19)", "pid": 2338707, "tid": 2379456, + "ts": 6197200694194.568, "dur": 561.177, + "args": { + "External id": 40011,"Record function id": 0, "Ev Idx": 8266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197200694257.688, "dur": 6.399, + "args": { + "External id": 40012,"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": 2338707, "tid": 2379456, + "ts": 6197200694278.996, "dur": 26.558, + "args": { + "External id": 40013,"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": 2338707, "tid": 2379456, + "ts": 6197200694284.145, "dur": 1.875, + "args": { + "External id": 40014,"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": 2338707, "tid": 2379456, + "ts": 6197200694287.757, "dur": 0.303, + "args": { + "External id": 40015,"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": 2338707, "tid": 2379456, + "ts": 6197200694289.842, "dur": 0.467, + "args": { + "External id": 40016,"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": 2338707, "tid": 2379456, + "ts": 6197200694291.069, "dur": 0.924, + "args": { + "External id": 40017,"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": 2338707, "tid": 2379456, + "ts": 6197200694293.352, "dur": 0.462, + "args": { + "External id": 40018,"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": 2338707, "tid": 2379456, + "ts": 6197200694295.063, "dur": 0.665, + "args": { + "External id": 40019,"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": 2338707, "tid": 2379456, + "ts": 6197200694297.110, "dur": 0.573, + "args": { + "External id": 40020,"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": 2338707, "tid": 2379456, + "ts": 6197200694298.923, "dur": 0.740, + "args": { + "External id": 40021,"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": 2338707, "tid": 2379456, + "ts": 6197200694300.897, "dur": 0.546, + "args": { + "External id": 40022,"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": 2338707, "tid": 2379456, + "ts": 6197200694316.981, "dur": 46.628, + "args": { + "External id": 40023,"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": 2338707, "tid": 2379456, + "ts": 6197200694393.188, "dur": 111.523, + "args": { + "External id": 40024,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2379456, + "ts": 6197200694402.903, "dur": 3.265, + "args": { + "External id": 40025,"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": 2338707, "tid": 2379456, + "ts": 6197200694411.293, "dur": 10.381, + "args": { + "External id": 40026,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2379456, + "ts": 6197200694415.508, "dur": 5.749, + "args": { + "External id": 40027,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2379456, + "ts": 6197200694418.837, "dur": 1.184, + "args": { + "External id": 40028,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197200694432.645, "dur": 23.063, + "args": { + "External id": 40029,"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": 2338707, "tid": 2379456, + "ts": 6197200694434.438, "dur": 0.619, + "args": { + "External id": 40030,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197200694436.214, "dur": 0.491, + "args": { + "External id": 40031,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2379456, + "ts": 6197200694437.799, "dur": 0.674, + "args": { + "External id": 40032,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2379456, + "ts": 6197200694439.728, "dur": 0.683, + "args": { + "External id": 40033,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2379456, + "ts": 6197200694441.748, "dur": 0.464, + "args": { + "External id": 40034,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2379456, + "ts": 6197200694443.724, "dur": 0.750, + "args": { + "External id": 40035,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2379456, + "ts": 6197200694445.689, "dur": 0.508, + "args": { + "External id": 40036,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2379456, + "ts": 6197200694447.552, "dur": 0.385, + "args": { + "External id": 40037,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2379456, + "ts": 6197200694448.826, "dur": 0.793, + "args": { + "External id": 40038,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2379456, + "ts": 6197200694467.974, "dur": 29.442, + "args": { + "External id": 40039,"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": 2338707, "tid": 2379456, + "ts": 6197200694549.384, "dur": 117.359, + "args": { + "External id": 40040,"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": 2338707, "tid": 2379456, + "ts": 6197200694577.001, "dur": 86.193, + "args": { + "External id": 40041,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197200694586.269, "dur": 73.023, + "args": { + "External id": 40042,"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": 2338707, "tid": 2379456, + "ts": 6197200694684.076, "dur": 1.869, + "args": { + "External id": 40043,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197200694783.891, "dur": 1762.319, + "args": { + "External id": 40044,"Sequence number": 480037, "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": 2338707, "tid": 2379456, "ts": 6197200694783.891, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6197200694897.210, "dur": 116.618, + "args": { + "External id": 40045,"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": 2338707, "tid": 2379456, + "ts": 6197200695089.987, "dur": 42.967, + "args": { + "External id": 40046,"kernel_hash": "cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/u7/cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs.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": 2338707, "tid": 2379456, + "ts": 6197200695154.777, "dur": 56.840, + "args": { + "External id": 40047,"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": 2338707, "tid": 2379456, + "ts": 6197200695221.820, "dur": 32.584, + "args": { + "External id": 40048,"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": 2338707, "tid": 2379456, + "ts": 6197200695260.781, "dur": 33.451, + "args": { + "External id": 40049,"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": 2338707, "tid": 2379456, + "ts": 6197200695301.387, "dur": 28.688, + "args": { + "External id": 40050,"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": 2338707, "tid": 2379456, + "ts": 6197200695337.874, "dur": 30.079, + "args": { + "External id": 40051,"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": 2338707, "tid": 2379456, + "ts": 6197200695394.511, "dur": 22.912, + "args": { + "External id": 40052,"kernel_hash": "cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/wm/cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s.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": 2338707, "tid": 2379456, + "ts": 6197200695435.586, "dur": 27.921, + "args": { + "External id": 40053,"kernel_hash": "cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql", "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/qt/cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql.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": 2338707, "tid": 2379456, + "ts": 6197200695483.149, "dur": 19.495, + "args": { + "External id": 40054,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197200695518.336, "dur": 14.572, + "args": { + "External id": 40055,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197200695540.938, "dur": 44.061, + "args": { + "External id": 40056,"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": 2338707, "tid": 2379456, + "ts": 6197200695588.899, "dur": 32.843, + "args": { + "External id": 40057,"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": 2338707, "tid": 2379456, + "ts": 6197200695648.914, "dur": 265.065, + "args": { + "External id": 40058,"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": 2338707, "tid": 2379456, + "ts": 6197200695747.153, "dur": 6.369, + "args": { + "External id": 40059,"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": 2338707, "tid": 2379456, + "ts": 6197200695755.655, "dur": 2.643, + "args": { + "External id": 40060,"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": 2338707, "tid": 2379456, + "ts": 6197200695759.886, "dur": 2.164, + "args": { + "External id": 40061,"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": 2338707, "tid": 2379456, + "ts": 6197200695763.175, "dur": 3.006, + "args": { + "External id": 40062,"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": 2338707, "tid": 2379456, + "ts": 6197200695812.897, "dur": 5.361, + "args": { + "External id": 40063,"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": 2338707, "tid": 2379456, + "ts": 6197200695815.354, "dur": 2.712, + "args": { + "External id": 40064,"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": 2338707, "tid": 2379456, + "ts": 6197200695820.627, "dur": 30.892, + "args": { + "External id": 40065,"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": 2338707, "tid": 2379456, + "ts": 6197200695826.055, "dur": 2.135, + "args": { + "External id": 40066,"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": 2338707, "tid": 2379456, + "ts": 6197200695853.028, "dur": 2.126, + "args": { + "External id": 40067,"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": 2338707, "tid": 2379456, + "ts": 6197200695854.360, "dur": 0.715, + "args": { + "External id": 40068,"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": 2338707, "tid": 2379456, + "ts": 6197200695856.458, "dur": 14.522, + "args": { + "External id": 40069,"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": 2338707, "tid": 2379456, + "ts": 6197200695859.111, "dur": 0.609, + "args": { + "External id": 40070,"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": 2338707, "tid": 2379456, + "ts": 6197200695947.773, "dur": 26.021, + "args": { + "External id": 40071,"kernel_hash": "cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4", "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/yk/cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4.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": 2338707, "tid": 2379456, + "ts": 6197200695994.400, "dur": 17.741, + "args": { + "External id": 40072,"kernel_hash": "ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg", "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/eu/ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg.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": 2338707, "tid": 2379456, + "ts": 6197200696021.119, "dur": 86.153, + "args": { + "External id": 40073,"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": 2338707, "tid": 2379456, + "ts": 6197200696118.549, "dur": 44.364, + "args": { + "External id": 40074,"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": 2338707, "tid": 2379456, + "ts": 6197200696173.793, "dur": 23.529, + "args": { + "External id": 40075,"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": 2338707, "tid": 2379456, + "ts": 6197200696204.264, "dur": 32.811, + "args": { + "External id": 40076,"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": 2338707, "tid": 2379456, + "ts": 6197200696244.494, "dur": 27.597, + "args": { + "External id": 40077,"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": 2338707, "tid": 2379456, + "ts": 6197200696279.827, "dur": 29.620, + "args": { + "External id": 40078,"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": 2338707, "tid": 2379456, + "ts": 6197200696330.371, "dur": 41.007, + "args": { + "External id": 40079,"kernel_hash": "c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/6w/c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7.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": 2338707, "tid": 2379456, + "ts": 6197200696395.962, "dur": 25.293, + "args": { + "External id": 40080,"kernel_hash": "ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx", "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/kj/ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx.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": 2338707, "tid": 2379456, + "ts": 6197200696436.596, "dur": 17.259, + "args": { + "External id": 40081,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197200696468.853, "dur": 14.029, + "args": { + "External id": 40082,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197200696496.715, "dur": 18.674, + "args": { + "External id": 40083,"kernel_hash": "cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/eb/cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b.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": 2338707, "tid": 2379456, + "ts": 6197200696595.171, "dur": 14.776, + "args": { + "External id": 40084,"Record function id": 0, "Ev Idx": 8339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200696598.507, "dur": 10.558, + "args": { + "External id": 40085,"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": 2338707, "tid": 2379456, + "ts": 6197200696602.377, "dur": 5.937, + "args": { + "External id": 40086,"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": 2338707, "tid": 2379456, + "ts": 6197200696603.906, "dur": 4.327, + "args": { + "External id": 40087,"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": 2338707, "tid": 2379456, + "ts": 6197200696614.009, "dur": 4.655, + "args": { + "External id": 40088,"Record function id": 0, "Ev Idx": 8343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200696615.433, "dur": 2.800, + "args": { + "External id": 40089,"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": 2338707, "tid": 2379456, + "ts": 6197200696616.122, "dur": 1.609, + "args": { + "External id": 40090,"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": 2338707, "tid": 2379456, + "ts": 6197200696616.739, "dur": 0.917, + "args": { + "External id": 40091,"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": 2338707, "tid": 2379456, + "ts": 6197200696621.942, "dur": 4.446, + "args": { + "External id": 40092,"Record function id": 0, "Ev Idx": 8347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200696623.453, "dur": 2.498, + "args": { + "External id": 40093,"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": 2338707, "tid": 2379456, + "ts": 6197200696624.096, "dur": 1.442, + "args": { + "External id": 40094,"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": 2338707, "tid": 2379456, + "ts": 6197200696624.840, "dur": 0.634, + "args": { + "External id": 40095,"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": 2338707, "tid": 2379456, + "ts": 6197200696629.691, "dur": 4.358, + "args": { + "External id": 40096,"Record function id": 0, "Ev Idx": 8351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200696630.889, "dur": 2.714, + "args": { + "External id": 40097,"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": 2338707, "tid": 2379456, + "ts": 6197200696631.636, "dur": 1.419, + "args": { + "External id": 40098,"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": 2338707, "tid": 2379456, + "ts": 6197200696632.165, "dur": 0.813, + "args": { + "External id": 40099,"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": 2338707, "tid": 2379456, + "ts": 6197200696637.218, "dur": 4.059, + "args": { + "External id": 40100,"Record function id": 0, "Ev Idx": 8355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200696638.378, "dur": 2.486, + "args": { + "External id": 40101,"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": 2338707, "tid": 2379456, + "ts": 6197200696639.052, "dur": 1.326, + "args": { + "External id": 40102,"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": 2338707, "tid": 2379456, + "ts": 6197200696639.611, "dur": 0.701, + "args": { + "External id": 40103,"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": 2338707, "tid": 2379456, + "ts": 6197200696644.409, "dur": 3.705, + "args": { + "External id": 40104,"Record function id": 0, "Ev Idx": 8359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200696645.557, "dur": 2.123, + "args": { + "External id": 40105,"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": 2338707, "tid": 2379456, + "ts": 6197200696646.056, "dur": 1.031, + "args": { + "External id": 40106,"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": 2338707, "tid": 2379456, + "ts": 6197200696646.316, "dur": 0.707, + "args": { + "External id": 40107,"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": 2338707, "tid": 2379456, + "ts": 6197200696651.324, "dur": 4.423, + "args": { + "External id": 40108,"Record function id": 0, "Ev Idx": 8363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200696652.643, "dur": 2.680, + "args": { + "External id": 40109,"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": 2338707, "tid": 2379456, + "ts": 6197200696653.123, "dur": 1.440, + "args": { + "External id": 40110,"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": 2338707, "tid": 2379456, + "ts": 6197200696653.670, "dur": 0.828, + "args": { + "External id": 40111,"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": 2338707, "tid": 2379456, + "ts": 6197200696658.947, "dur": 3.957, + "args": { + "External id": 40112,"Record function id": 0, "Ev Idx": 8367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200696660.242, "dur": 2.254, + "args": { + "External id": 40113,"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": 2338707, "tid": 2379456, + "ts": 6197200696660.702, "dur": 1.069, + "args": { + "External id": 40114,"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": 2338707, "tid": 2379456, + "ts": 6197200696661.000, "dur": 0.707, + "args": { + "External id": 40115,"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": 2338707, "tid": 2379456, + "ts": 6197200696665.946, "dur": 3.630, + "args": { + "External id": 40116,"Record function id": 0, "Ev Idx": 8371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200696666.996, "dur": 2.150, + "args": { + "External id": 40117,"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": 2338707, "tid": 2379456, + "ts": 6197200696667.504, "dur": 1.040, + "args": { + "External id": 40118,"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": 2338707, "tid": 2379456, + "ts": 6197200696667.844, "dur": 0.633, + "args": { + "External id": 40119,"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": 2338707, "tid": 2379456, + "ts": 6197200696674.043, "dur": 64425.378, + "args": { + "External id": 40120,"Record function id": 0, "Sequence number": 480036, "Fwd thread id": 1, "Ev Idx": 8375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197200696675.466, "dur": 64412.085, + "args": { + "External id": 40121,"Sequence number": 480036, "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": 2338707, "tid": 2379456, "ts": 6197200696675.466, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.20)", "pid": 2338707, "tid": 2379456, + "ts": 6197200696724.047, "dur": 41.461, + "args": { + "External id": 40122,"Record function id": 0, "Ev Idx": 8377 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.20)", "pid": 2338707, "tid": 2379456, + "ts": 6197200696773.612, "dur": 67.188, + "args": { + "External id": 40123,"Record function id": 0, "Ev Idx": 8378 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.20)", "pid": 2338707, "tid": 2379456, + "ts": 6197200696846.346, "dur": 64198.637, + "args": { + "External id": 40124,"Record function id": 0, "Ev Idx": 8379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197200696935.059, "dur": 6.918, + "args": { + "External id": 40125,"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": 2338707, "tid": 2379456, + "ts": 6197200696952.552, "dur": 4.759, + "args": { + "External id": 40126,"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": 2338707, "tid": 2379456, + "ts": 6197200696975.431, "dur": 63135.850, + "args": { + "External id": 40127,"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": 2338707, "tid": 2379456, + "ts": 6197200696988.824, "dur": 63109.598, + "args": { + "External id": 40128,"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": 2338707, "tid": 2379456, + "ts": 6197200697120.436, "dur": 19.244, + "args": { + "External id": 40129,"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": 2338707, "tid": 2379456, + "ts": 6197200697160.496, "dur": 62869.988, + "args": { + "External id": 40130,"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": 2338707, "tid": 2379456, + "ts": 6197200697163.445, "dur": 62866.177, + "args": { + "External id": 40131,"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": 2338707, "tid": 2379456, + "ts": 6197200697172.520, "dur": 9.824, + "args": { + "External id": 40132,"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": 2338707, "tid": 2379456, + "ts": 6197200697184.374, "dur": 62840.164, + "args": { + "External id": 40133,"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": 2338707, "tid": 2379456, + "ts": 6197200760217.351, "dur": 12.223, + "args": { + "External id": 40134,"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": 2338707, "tid": 2379456, + "ts": 6197200760220.858, "dur": 8.285, + "args": { + "External id": 40135,"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": 2338707, "tid": 2379456, + "ts": 6197200760257.745, "dur": 395.426, + "args": { + "External id": 40136,"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": 2338707, "tid": 2379456, + "ts": 6197200760289.585, "dur": 358.566, + "args": { + "External id": 40137,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197200760301.573, "dur": 341.358, + "args": { + "External id": 40138,"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": 2338707, "tid": 2379456, + "ts": 6197200760673.814, "dur": 2.024, + "args": { + "External id": 40139,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2379456, + "ts": 6197200760753.020, "dur": 6.978, + "args": { + "External id": 40140,"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": 2338707, "tid": 2379456, + "ts": 6197200760772.821, "dur": 35.473, + "args": { + "External id": 40141,"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": 2338707, "tid": 2379456, + "ts": 6197200760818.322, "dur": 2.149, + "args": { + "External id": 40142,"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": 2338707, "tid": 2379456, + "ts": 6197200760825.622, "dur": 13.107, + "args": { + "External id": 40143,"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": 2338707, "tid": 2379456, + "ts": 6197200760844.202, "dur": 0.996, + "args": { + "External id": 40144,"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": 2338707, "tid": 2379456, + "ts": 6197200760849.878, "dur": 13.293, + "args": { + "External id": 40145,"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": 2338707, "tid": 2379456, + "ts": 6197200760868.398, "dur": 1.096, + "args": { + "External id": 40146,"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": 2338707, "tid": 2379456, + "ts": 6197200760873.333, "dur": 11.133, + "args": { + "External id": 40147,"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": 2338707, "tid": 2379456, + "ts": 6197200760888.809, "dur": 0.984, + "args": { + "External id": 40148,"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": 2338707, "tid": 2379456, + "ts": 6197200760895.894, "dur": 11.154, + "args": { + "External id": 40149,"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": 2338707, "tid": 2379456, + "ts": 6197200760911.584, "dur": 1.345, + "args": { + "External id": 40150,"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": 2338707, "tid": 2379456, + "ts": 6197200760916.684, "dur": 9.979, + "args": { + "External id": 40151,"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": 2338707, "tid": 2379456, + "ts": 6197200760931.168, "dur": 0.977, + "args": { + "External id": 40152,"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": 2338707, "tid": 2379456, + "ts": 6197200760935.704, "dur": 10.747, + "args": { + "External id": 40153,"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": 2338707, "tid": 2379456, + "ts": 6197200760950.727, "dur": 1.124, + "args": { + "External id": 40154,"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": 2338707, "tid": 2379456, + "ts": 6197200760955.244, "dur": 9.833, + "args": { + "External id": 40155,"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": 2338707, "tid": 2379456, + "ts": 6197200760971.069, "dur": 0.805, + "args": { + "External id": 40156,"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": 2338707, "tid": 2379456, + "ts": 6197200760975.502, "dur": 10.394, + "args": { + "External id": 40157,"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": 2338707, "tid": 2379456, + "ts": 6197200761115.750, "dur": 2796.022, + "args": { + "External id": 40158,"Record function id": 0, "Ev Idx": 8413 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.19)", "pid": 2338707, "tid": 2379456, + "ts": 6197200761139.305, "dur": 1069.493, + "args": { + "External id": 40159,"Record function id": 0, "Ev Idx": 8414 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.19)", "pid": 2338707, "tid": 2379456, + "ts": 6197200761157.331, "dur": 338.688, + "args": { + "External id": 40160,"Record function id": 0, "Ev Idx": 8415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6197200761255.774, "dur": 4.830, + "args": { + "External id": 40161,"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": 2338707, "tid": 2379456, + "ts": 6197200761263.980, "dur": 1.137, + "args": { + "External id": 40162,"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": 2338707, "tid": 2379456, + "ts": 6197200761266.885, "dur": 1.189, + "args": { + "External id": 40163,"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": 2338707, "tid": 2379456, + "ts": 6197200761269.631, "dur": 0.994, + "args": { + "External id": 40164,"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": 2338707, "tid": 2379456, + "ts": 6197200761272.185, "dur": 0.795, + "args": { + "External id": 40165,"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": 2338707, "tid": 2379456, + "ts": 6197200761274.503, "dur": 1.259, + "args": { + "External id": 40166,"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": 2338707, "tid": 2379456, + "ts": 6197200761279.394, "dur": 0.536, + "args": { + "External id": 40167,"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": 2338707, "tid": 2379456, + "ts": 6197200761281.304, "dur": 1.085, + "args": { + "External id": 40168,"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": 2338707, "tid": 2379456, + "ts": 6197200761283.902, "dur": 1.278, + "args": { + "External id": 40169,"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": 2338707, "tid": 2379456, + "ts": 6197200761287.051, "dur": 1.810, + "args": { + "External id": 40170,"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": 2338707, "tid": 2379456, + "ts": 6197200761308.331, "dur": 158.133, + "args": { + "External id": 40171,"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": 2338707, "tid": 2379456, + "ts": 6197200761324.593, "dur": 137.377, + "args": { + "External id": 40172,"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": 2338707, "tid": 2379456, + "ts": 6197200761340.127, "dur": 28.796, + "args": { + "External id": 40173,"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": 2338707, "tid": 2379456, + "ts": 6197200761372.728, "dur": 62.790, + "args": { + "External id": 40174,"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": 2338707, "tid": 2379456, + "ts": 6197200761375.312, "dur": 59.789, + "args": { + "External id": 40175,"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": 2338707, "tid": 2379456, + "ts": 6197200761379.226, "dur": 5.461, + "args": { + "External id": 40176,"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": 2338707, "tid": 2379456, + "ts": 6197200761386.213, "dur": 48.305, + "args": { + "External id": 40177,"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": 2338707, "tid": 2379456, + "ts": 6197200761578.931, "dur": 621.945, + "args": { + "External id": 40178,"Record function id": 0, "Ev Idx": 8433 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.18)", "pid": 2338707, "tid": 2379456, + "ts": 6197200761594.353, "dur": 593.395, + "args": { + "External id": 40179,"Record function id": 0, "Ev Idx": 8434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197200761651.907, "dur": 5.326, + "args": { + "External id": 40180,"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": 2338707, "tid": 2379456, + "ts": 6197200761671.683, "dur": 25.352, + "args": { + "External id": 40181,"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": 2338707, "tid": 2379456, + "ts": 6197200761676.154, "dur": 1.689, + "args": { + "External id": 40182,"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": 2338707, "tid": 2379456, + "ts": 6197200761679.584, "dur": 0.326, + "args": { + "External id": 40183,"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": 2338707, "tid": 2379456, + "ts": 6197200761681.248, "dur": 0.774, + "args": { + "External id": 40184,"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": 2338707, "tid": 2379456, + "ts": 6197200761683.303, "dur": 0.449, + "args": { + "External id": 40185,"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": 2338707, "tid": 2379456, + "ts": 6197200761684.496, "dur": 1.170, + "args": { + "External id": 40186,"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": 2338707, "tid": 2379456, + "ts": 6197200761686.410, "dur": 0.645, + "args": { + "External id": 40187,"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": 2338707, "tid": 2379456, + "ts": 6197200761688.318, "dur": 0.832, + "args": { + "External id": 40188,"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": 2338707, "tid": 2379456, + "ts": 6197200761690.534, "dur": 1.153, + "args": { + "External id": 40189,"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": 2338707, "tid": 2379456, + "ts": 6197200761692.874, "dur": 0.583, + "args": { + "External id": 40190,"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": 2338707, "tid": 2379456, + "ts": 6197200761725.231, "dur": 43.723, + "args": { + "External id": 40191,"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": 2338707, "tid": 2379456, + "ts": 6197200761799.952, "dur": 106.337, + "args": { + "External id": 40192,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2379456, + "ts": 6197200761810.125, "dur": 4.376, + "args": { + "External id": 40193,"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": 2338707, "tid": 2379456, + "ts": 6197200761819.947, "dur": 10.200, + "args": { + "External id": 40194,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2379456, + "ts": 6197200761824.054, "dur": 5.670, + "args": { + "External id": 40195,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2379456, + "ts": 6197200761827.521, "dur": 0.640, + "args": { + "External id": 40196,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197200761837.035, "dur": 22.373, + "args": { + "External id": 40197,"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": 2338707, "tid": 2379456, + "ts": 6197200761838.858, "dur": 0.747, + "args": { + "External id": 40198,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197200761840.812, "dur": 0.235, + "args": { + "External id": 40199,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2379456, + "ts": 6197200761842.541, "dur": 0.471, + "args": { + "External id": 40200,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2379456, + "ts": 6197200761844.253, "dur": 0.803, + "args": { + "External id": 40201,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2379456, + "ts": 6197200761846.273, "dur": 0.513, + "args": { + "External id": 40202,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2379456, + "ts": 6197200761848.002, "dur": 0.509, + "args": { + "External id": 40203,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2379456, + "ts": 6197200761849.501, "dur": 0.729, + "args": { + "External id": 40204,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2379456, + "ts": 6197200761851.426, "dur": 0.429, + "args": { + "External id": 40205,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2379456, + "ts": 6197200761853.294, "dur": 0.456, + "args": { + "External id": 40206,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2379456, + "ts": 6197200761869.061, "dur": 30.023, + "args": { + "External id": 40207,"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": 2338707, "tid": 2379456, + "ts": 6197200761949.642, "dur": 157.564, + "args": { + "External id": 40208,"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": 2338707, "tid": 2379456, + "ts": 6197200761975.655, "dur": 127.482, + "args": { + "External id": 40209,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197200761986.819, "dur": 110.809, + "args": { + "External id": 40210,"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": 2338707, "tid": 2379456, + "ts": 6197200762126.707, "dur": 2.406, + "args": { + "External id": 40211,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197200762215.805, "dur": 1674.995, + "args": { + "External id": 40212,"Sequence number": 480035, "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": 2338707, "tid": 2379456, "ts": 6197200762215.805, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6197200762326.230, "dur": 108.614, + "args": { + "External id": 40213,"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": 2338707, "tid": 2379456, + "ts": 6197200762472.838, "dur": 41.202, + "args": { + "External id": 40214,"kernel_hash": "cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/u7/cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs.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": 2338707, "tid": 2379456, + "ts": 6197200762531.391, "dur": 49.757, + "args": { + "External id": 40215,"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": 2338707, "tid": 2379456, + "ts": 6197200762590.681, "dur": 32.811, + "args": { + "External id": 40216,"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": 2338707, "tid": 2379456, + "ts": 6197200762629.967, "dur": 32.815, + "args": { + "External id": 40217,"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": 2338707, "tid": 2379456, + "ts": 6197200762669.715, "dur": 29.654, + "args": { + "External id": 40218,"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": 2338707, "tid": 2379456, + "ts": 6197200762727.067, "dur": 34.982, + "args": { + "External id": 40219,"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": 2338707, "tid": 2379456, + "ts": 6197200762787.871, "dur": 24.217, + "args": { + "External id": 40220,"kernel_hash": "cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/wm/cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s.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": 2338707, "tid": 2379456, + "ts": 6197200762831.580, "dur": 30.677, + "args": { + "External id": 40221,"kernel_hash": "cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql", "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/qt/cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql.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": 2338707, "tid": 2379456, + "ts": 6197200762881.527, "dur": 19.115, + "args": { + "External id": 40222,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197200762919.620, "dur": 15.537, + "args": { + "External id": 40223,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197200762942.798, "dur": 37.580, + "args": { + "External id": 40224,"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": 2338707, "tid": 2379456, + "ts": 6197200762983.778, "dur": 34.109, + "args": { + "External id": 40225,"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": 2338707, "tid": 2379456, + "ts": 6197200763044.745, "dur": 285.310, + "args": { + "External id": 40226,"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": 2338707, "tid": 2379456, + "ts": 6197200763162.501, "dur": 7.950, + "args": { + "External id": 40227,"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": 2338707, "tid": 2379456, + "ts": 6197200763172.551, "dur": 3.044, + "args": { + "External id": 40228,"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": 2338707, "tid": 2379456, + "ts": 6197200763176.661, "dur": 2.380, + "args": { + "External id": 40229,"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": 2338707, "tid": 2379456, + "ts": 6197200763179.835, "dur": 2.929, + "args": { + "External id": 40230,"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": 2338707, "tid": 2379456, + "ts": 6197200763229.187, "dur": 5.471, + "args": { + "External id": 40231,"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": 2338707, "tid": 2379456, + "ts": 6197200763231.577, "dur": 2.903, + "args": { + "External id": 40232,"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": 2338707, "tid": 2379456, + "ts": 6197200763236.802, "dur": 31.434, + "args": { + "External id": 40233,"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": 2338707, "tid": 2379456, + "ts": 6197200763242.947, "dur": 2.353, + "args": { + "External id": 40234,"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": 2338707, "tid": 2379456, + "ts": 6197200763269.664, "dur": 1.812, + "args": { + "External id": 40235,"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": 2338707, "tid": 2379456, + "ts": 6197200763270.715, "dur": 0.694, + "args": { + "External id": 40236,"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": 2338707, "tid": 2379456, + "ts": 6197200763273.097, "dur": 14.703, + "args": { + "External id": 40237,"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": 2338707, "tid": 2379456, + "ts": 6197200763275.477, "dur": 0.592, + "args": { + "External id": 40238,"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": 2338707, "tid": 2379456, + "ts": 6197200763364.219, "dur": 26.587, + "args": { + "External id": 40239,"kernel_hash": "cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4", "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/yk/cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4.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": 2338707, "tid": 2379456, + "ts": 6197200763407.987, "dur": 14.779, + "args": { + "External id": 40240,"kernel_hash": "ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg", "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/eu/ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg.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": 2338707, "tid": 2379456, + "ts": 6197200763431.527, "dur": 46.151, + "args": { + "External id": 40241,"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": 2338707, "tid": 2379456, + "ts": 6197200763483.574, "dur": 38.461, + "args": { + "External id": 40242,"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": 2338707, "tid": 2379456, + "ts": 6197200763530.355, "dur": 20.553, + "args": { + "External id": 40243,"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": 2338707, "tid": 2379456, + "ts": 6197200763556.623, "dur": 32.609, + "args": { + "External id": 40244,"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": 2338707, "tid": 2379456, + "ts": 6197200763596.644, "dur": 28.527, + "args": { + "External id": 40245,"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": 2338707, "tid": 2379456, + "ts": 6197200763631.991, "dur": 30.267, + "args": { + "External id": 40246,"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": 2338707, "tid": 2379456, + "ts": 6197200763681.776, "dur": 38.014, + "args": { + "External id": 40247,"kernel_hash": "c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/6w/c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7.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": 2338707, "tid": 2379456, + "ts": 6197200763741.327, "dur": 26.547, + "args": { + "External id": 40248,"kernel_hash": "ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx", "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/kj/ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx.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": 2338707, "tid": 2379456, + "ts": 6197200763783.152, "dur": 19.204, + "args": { + "External id": 40249,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197200763819.344, "dur": 13.271, + "args": { + "External id": 40250,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197200763845.980, "dur": 15.200, + "args": { + "External id": 40251,"kernel_hash": "cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/eb/cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b.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": 2338707, "tid": 2379456, + "ts": 6197200763945.231, "dur": 18.272, + "args": { + "External id": 40252,"Record function id": 0, "Ev Idx": 8507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200763949.539, "dur": 12.546, + "args": { + "External id": 40253,"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": 2338707, "tid": 2379456, + "ts": 6197200763954.162, "dur": 6.005, + "args": { + "External id": 40254,"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": 2338707, "tid": 2379456, + "ts": 6197200763955.712, "dur": 4.203, + "args": { + "External id": 40255,"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": 2338707, "tid": 2379456, + "ts": 6197200763967.808, "dur": 5.325, + "args": { + "External id": 40256,"Record function id": 0, "Ev Idx": 8511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200763969.272, "dur": 3.321, + "args": { + "External id": 40257,"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": 2338707, "tid": 2379456, + "ts": 6197200763970.559, "dur": 1.444, + "args": { + "External id": 40258,"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": 2338707, "tid": 2379456, + "ts": 6197200763971.093, "dur": 0.840, + "args": { + "External id": 40259,"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": 2338707, "tid": 2379456, + "ts": 6197200763976.360, "dur": 5.460, + "args": { + "External id": 40260,"Record function id": 0, "Ev Idx": 8515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200763977.818, "dur": 3.527, + "args": { + "External id": 40261,"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": 2338707, "tid": 2379456, + "ts": 6197200763978.461, "dur": 2.451, + "args": { + "External id": 40262,"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": 2338707, "tid": 2379456, + "ts": 6197200763979.459, "dur": 1.354, + "args": { + "External id": 40263,"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": 2338707, "tid": 2379456, + "ts": 6197200763985.110, "dur": 4.021, + "args": { + "External id": 40264,"Record function id": 0, "Ev Idx": 8519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200763986.500, "dur": 2.225, + "args": { + "External id": 40265,"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": 2338707, "tid": 2379456, + "ts": 6197200763987.196, "dur": 1.147, + "args": { + "External id": 40266,"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": 2338707, "tid": 2379456, + "ts": 6197200763987.515, "dur": 0.764, + "args": { + "External id": 40267,"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": 2338707, "tid": 2379456, + "ts": 6197200763992.219, "dur": 3.612, + "args": { + "External id": 40268,"Record function id": 0, "Ev Idx": 8523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200763993.240, "dur": 2.184, + "args": { + "External id": 40269,"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": 2338707, "tid": 2379456, + "ts": 6197200763993.783, "dur": 1.222, + "args": { + "External id": 40270,"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": 2338707, "tid": 2379456, + "ts": 6197200763994.404, "dur": 0.536, + "args": { + "External id": 40271,"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": 2338707, "tid": 2379456, + "ts": 6197200763998.774, "dur": 5.811, + "args": { + "External id": 40272,"Record function id": 0, "Ev Idx": 8527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200763999.846, "dur": 4.353, + "args": { + "External id": 40273,"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": 2338707, "tid": 2379456, + "ts": 6197200764000.359, "dur": 3.370, + "args": { + "External id": 40274,"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": 2338707, "tid": 2379456, + "ts": 6197200764002.828, "dur": 0.838, + "args": { + "External id": 40275,"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": 2338707, "tid": 2379456, + "ts": 6197200764007.841, "dur": 3.821, + "args": { + "External id": 40276,"Record function id": 0, "Ev Idx": 8531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200764008.908, "dur": 2.341, + "args": { + "External id": 40277,"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": 2338707, "tid": 2379456, + "ts": 6197200764009.336, "dur": 1.324, + "args": { + "External id": 40278,"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": 2338707, "tid": 2379456, + "ts": 6197200764009.604, "dur": 0.923, + "args": { + "External id": 40279,"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": 2338707, "tid": 2379456, + "ts": 6197200764014.656, "dur": 7.097, + "args": { + "External id": 40280,"Record function id": 0, "Ev Idx": 8535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200764018.909, "dur": 2.400, + "args": { + "External id": 40281,"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": 2338707, "tid": 2379456, + "ts": 6197200764019.597, "dur": 1.330, + "args": { + "External id": 40282,"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": 2338707, "tid": 2379456, + "ts": 6197200764019.863, "dur": 0.990, + "args": { + "External id": 40283,"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": 2338707, "tid": 2379456, + "ts": 6197200764024.859, "dur": 5.911, + "args": { + "External id": 40284,"Record function id": 0, "Ev Idx": 8539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200764025.935, "dur": 4.418, + "args": { + "External id": 40285,"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": 2338707, "tid": 2379456, + "ts": 6197200764026.599, "dur": 3.179, + "args": { + "External id": 40286,"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": 2338707, "tid": 2379456, + "ts": 6197200764028.870, "dur": 0.817, + "args": { + "External id": 40287,"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": 2338707, "tid": 2379456, + "ts": 6197200764037.863, "dur": 65645.131, + "args": { + "External id": 40288,"Record function id": 0, "Sequence number": 480034, "Fwd thread id": 1, "Ev Idx": 8543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197200764045.695, "dur": 65628.638, + "args": { + "External id": 40289,"Sequence number": 480034, "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": 2338707, "tid": 2379456, "ts": 6197200764045.695, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.19)", "pid": 2338707, "tid": 2379456, + "ts": 6197200764116.907, "dur": 40.452, + "args": { + "External id": 40290,"Record function id": 0, "Ev Idx": 8545 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.19)", "pid": 2338707, "tid": 2379456, + "ts": 6197200764165.476, "dur": 69.019, + "args": { + "External id": 40291,"Record function id": 0, "Ev Idx": 8546 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.19)", "pid": 2338707, "tid": 2379456, + "ts": 6197200764240.402, "dur": 65426.411, + "args": { + "External id": 40292,"Record function id": 0, "Ev Idx": 8547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197200764330.455, "dur": 7.414, + "args": { + "External id": 40293,"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": 2338707, "tid": 2379456, + "ts": 6197200764348.304, "dur": 5.252, + "args": { + "External id": 40294,"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": 2338707, "tid": 2379456, + "ts": 6197200764367.495, "dur": 64387.842, + "args": { + "External id": 40295,"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": 2338707, "tid": 2379456, + "ts": 6197200764382.152, "dur": 64356.136, + "args": { + "External id": 40296,"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": 2338707, "tid": 2379456, + "ts": 6197200764471.210, "dur": 17.822, + "args": { + "External id": 40297,"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": 2338707, "tid": 2379456, + "ts": 6197200764511.522, "dur": 64167.974, + "args": { + "External id": 40298,"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": 2338707, "tid": 2379456, + "ts": 6197200764514.351, "dur": 64164.254, + "args": { + "External id": 40299,"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": 2338707, "tid": 2379456, + "ts": 6197200764518.719, "dur": 8.130, + "args": { + "External id": 40300,"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": 2338707, "tid": 2379456, + "ts": 6197200764528.966, "dur": 64144.434, + "args": { + "External id": 40301,"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": 2338707, "tid": 2379456, + "ts": 6197200828867.819, "dur": 13.209, + "args": { + "External id": 40302,"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": 2338707, "tid": 2379456, + "ts": 6197200828871.589, "dur": 9.014, + "args": { + "External id": 40303,"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": 2338707, "tid": 2379456, + "ts": 6197200828908.969, "dur": 381.557, + "args": { + "External id": 40304,"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": 2338707, "tid": 2379456, + "ts": 6197200828941.436, "dur": 343.779, + "args": { + "External id": 40305,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197200828952.710, "dur": 325.960, + "args": { + "External id": 40306,"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": 2338707, "tid": 2379456, + "ts": 6197200829312.339, "dur": 2.355, + "args": { + "External id": 40307,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2379456, + "ts": 6197200829375.845, "dur": 6.585, + "args": { + "External id": 40308,"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": 2338707, "tid": 2379456, + "ts": 6197200829394.665, "dur": 31.663, + "args": { + "External id": 40309,"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": 2338707, "tid": 2379456, + "ts": 6197200829437.132, "dur": 1.496, + "args": { + "External id": 40310,"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": 2338707, "tid": 2379456, + "ts": 6197200829444.381, "dur": 11.427, + "args": { + "External id": 40311,"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": 2338707, "tid": 2379456, + "ts": 6197200829461.159, "dur": 0.903, + "args": { + "External id": 40312,"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": 2338707, "tid": 2379456, + "ts": 6197200829465.802, "dur": 14.065, + "args": { + "External id": 40313,"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": 2338707, "tid": 2379456, + "ts": 6197200829485.032, "dur": 0.974, + "args": { + "External id": 40314,"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": 2338707, "tid": 2379456, + "ts": 6197200829489.910, "dur": 11.262, + "args": { + "External id": 40315,"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": 2338707, "tid": 2379456, + "ts": 6197200829505.539, "dur": 1.027, + "args": { + "External id": 40316,"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": 2338707, "tid": 2379456, + "ts": 6197200829512.247, "dur": 12.721, + "args": { + "External id": 40317,"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": 2338707, "tid": 2379456, + "ts": 6197200829529.756, "dur": 1.094, + "args": { + "External id": 40318,"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": 2338707, "tid": 2379456, + "ts": 6197200829534.983, "dur": 11.092, + "args": { + "External id": 40319,"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": 2338707, "tid": 2379456, + "ts": 6197200829550.165, "dur": 0.810, + "args": { + "External id": 40320,"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": 2338707, "tid": 2379456, + "ts": 6197200829555.073, "dur": 12.408, + "args": { + "External id": 40321,"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": 2338707, "tid": 2379456, + "ts": 6197200829571.630, "dur": 1.063, + "args": { + "External id": 40322,"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": 2338707, "tid": 2379456, + "ts": 6197200829576.264, "dur": 10.592, + "args": { + "External id": 40323,"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": 2338707, "tid": 2379456, + "ts": 6197200829593.621, "dur": 0.844, + "args": { + "External id": 40324,"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": 2338707, "tid": 2379456, + "ts": 6197200829598.540, "dur": 10.396, + "args": { + "External id": 40325,"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": 2338707, "tid": 2379456, + "ts": 6197200829697.187, "dur": 2892.908, + "args": { + "External id": 40326,"Record function id": 0, "Ev Idx": 8581 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.18)", "pid": 2338707, "tid": 2379456, + "ts": 6197200829736.994, "dur": 1071.092, + "args": { + "External id": 40327,"Record function id": 0, "Ev Idx": 8582 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.18)", "pid": 2338707, "tid": 2379456, + "ts": 6197200829752.634, "dur": 371.584, + "args": { + "External id": 40328,"Record function id": 0, "Ev Idx": 8583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6197200829846.480, "dur": 4.560, + "args": { + "External id": 40329,"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": 2338707, "tid": 2379456, + "ts": 6197200829854.678, "dur": 0.680, + "args": { + "External id": 40330,"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": 2338707, "tid": 2379456, + "ts": 6197200829857.424, "dur": 0.886, + "args": { + "External id": 40331,"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": 2338707, "tid": 2379456, + "ts": 6197200829860.381, "dur": 0.792, + "args": { + "External id": 40332,"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": 2338707, "tid": 2379456, + "ts": 6197200829862.599, "dur": 1.103, + "args": { + "External id": 40333,"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": 2338707, "tid": 2379456, + "ts": 6197200829865.055, "dur": 0.809, + "args": { + "External id": 40334,"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": 2338707, "tid": 2379456, + "ts": 6197200829870.231, "dur": 1.110, + "args": { + "External id": 40335,"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": 2338707, "tid": 2379456, + "ts": 6197200829872.860, "dur": 1.161, + "args": { + "External id": 40336,"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": 2338707, "tid": 2379456, + "ts": 6197200829875.527, "dur": 1.225, + "args": { + "External id": 40337,"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": 2338707, "tid": 2379456, + "ts": 6197200829878.088, "dur": 1.646, + "args": { + "External id": 40338,"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": 2338707, "tid": 2379456, + "ts": 6197200829899.320, "dur": 188.664, + "args": { + "External id": 40339,"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": 2338707, "tid": 2379456, + "ts": 6197200829914.759, "dur": 134.613, + "args": { + "External id": 40340,"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": 2338707, "tid": 2379456, + "ts": 6197200829940.751, "dur": 14.066, + "args": { + "External id": 40341,"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": 2338707, "tid": 2379456, + "ts": 6197200829958.892, "dur": 62.328, + "args": { + "External id": 40342,"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": 2338707, "tid": 2379456, + "ts": 6197200829961.790, "dur": 59.091, + "args": { + "External id": 40343,"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": 2338707, "tid": 2379456, + "ts": 6197200829965.782, "dur": 5.705, + "args": { + "External id": 40344,"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": 2338707, "tid": 2379456, + "ts": 6197200829973.449, "dur": 46.791, + "args": { + "External id": 40345,"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": 2338707, "tid": 2379456, + "ts": 6197200830221.754, "dur": 578.154, + "args": { + "External id": 40346,"Record function id": 0, "Ev Idx": 8601 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.17)", "pid": 2338707, "tid": 2379456, + "ts": 6197200830238.497, "dur": 548.783, + "args": { + "External id": 40347,"Record function id": 0, "Ev Idx": 8602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197200830304.041, "dur": 5.596, + "args": { + "External id": 40348,"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": 2338707, "tid": 2379456, + "ts": 6197200830328.064, "dur": 25.893, + "args": { + "External id": 40349,"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": 2338707, "tid": 2379456, + "ts": 6197200830333.471, "dur": 1.699, + "args": { + "External id": 40350,"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": 2338707, "tid": 2379456, + "ts": 6197200830337.185, "dur": 0.299, + "args": { + "External id": 40351,"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": 2338707, "tid": 2379456, + "ts": 6197200830339.227, "dur": 0.600, + "args": { + "External id": 40352,"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": 2338707, "tid": 2379456, + "ts": 6197200830341.246, "dur": 0.736, + "args": { + "External id": 40353,"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": 2338707, "tid": 2379456, + "ts": 6197200830343.331, "dur": 0.481, + "args": { + "External id": 40354,"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": 2338707, "tid": 2379456, + "ts": 6197200830344.854, "dur": 0.627, + "args": { + "External id": 40355,"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": 2338707, "tid": 2379456, + "ts": 6197200830346.632, "dur": 0.314, + "args": { + "External id": 40356,"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": 2338707, "tid": 2379456, + "ts": 6197200830348.125, "dur": 0.472, + "args": { + "External id": 40357,"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": 2338707, "tid": 2379456, + "ts": 6197200830349.577, "dur": 0.479, + "args": { + "External id": 40358,"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": 2338707, "tid": 2379456, + "ts": 6197200830364.437, "dur": 40.906, + "args": { + "External id": 40359,"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": 2338707, "tid": 2379456, + "ts": 6197200830434.270, "dur": 105.133, + "args": { + "External id": 40360,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2379456, + "ts": 6197200830444.498, "dur": 3.332, + "args": { + "External id": 40361,"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": 2338707, "tid": 2379456, + "ts": 6197200830452.920, "dur": 10.042, + "args": { + "External id": 40362,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2379456, + "ts": 6197200830457.320, "dur": 5.227, + "args": { + "External id": 40363,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2379456, + "ts": 6197200830460.512, "dur": 0.927, + "args": { + "External id": 40364,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197200830469.354, "dur": 24.207, + "args": { + "External id": 40365,"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": 2338707, "tid": 2379456, + "ts": 6197200830470.992, "dur": 0.644, + "args": { + "External id": 40366,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197200830472.761, "dur": 0.250, + "args": { + "External id": 40367,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2379456, + "ts": 6197200830474.407, "dur": 0.762, + "args": { + "External id": 40368,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2379456, + "ts": 6197200830476.368, "dur": 0.621, + "args": { + "External id": 40369,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2379456, + "ts": 6197200830478.424, "dur": 0.799, + "args": { + "External id": 40370,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2379456, + "ts": 6197200830480.651, "dur": 0.799, + "args": { + "External id": 40371,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2379456, + "ts": 6197200830482.749, "dur": 0.322, + "args": { + "External id": 40372,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2379456, + "ts": 6197200830484.284, "dur": 0.831, + "args": { + "External id": 40373,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2379456, + "ts": 6197200830486.195, "dur": 0.196, + "args": { + "External id": 40374,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2379456, + "ts": 6197200830503.652, "dur": 28.853, + "args": { + "External id": 40375,"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": 2338707, "tid": 2379456, + "ts": 6197200830582.909, "dur": 112.123, + "args": { + "External id": 40376,"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": 2338707, "tid": 2379456, + "ts": 6197200830608.032, "dur": 83.426, + "args": { + "External id": 40377,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197200830619.533, "dur": 68.116, + "args": { + "External id": 40378,"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": 2338707, "tid": 2379456, + "ts": 6197200830730.649, "dur": 2.616, + "args": { + "External id": 40379,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197200830815.309, "dur": 1753.500, + "args": { + "External id": 40380,"Sequence number": 480033, "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": 2338707, "tid": 2379456, "ts": 6197200830815.309, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6197200830924.887, "dur": 107.817, + "args": { + "External id": 40381,"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": 2338707, "tid": 2379456, + "ts": 6197200831107.714, "dur": 43.003, + "args": { + "External id": 40382,"kernel_hash": "cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/u7/cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs.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": 2338707, "tid": 2379456, + "ts": 6197200831171.125, "dur": 57.049, + "args": { + "External id": 40383,"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": 2338707, "tid": 2379456, + "ts": 6197200831238.465, "dur": 32.741, + "args": { + "External id": 40384,"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": 2338707, "tid": 2379456, + "ts": 6197200831277.617, "dur": 34.388, + "args": { + "External id": 40385,"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": 2338707, "tid": 2379456, + "ts": 6197200831318.696, "dur": 28.949, + "args": { + "External id": 40386,"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": 2338707, "tid": 2379456, + "ts": 6197200831355.295, "dur": 30.195, + "args": { + "External id": 40387,"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": 2338707, "tid": 2379456, + "ts": 6197200831410.563, "dur": 22.856, + "args": { + "External id": 40388,"kernel_hash": "cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/wm/cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s.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": 2338707, "tid": 2379456, + "ts": 6197200831453.170, "dur": 29.115, + "args": { + "External id": 40389,"kernel_hash": "cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql", "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/qt/cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql.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": 2338707, "tid": 2379456, + "ts": 6197200831503.362, "dur": 17.927, + "args": { + "External id": 40390,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197200831537.451, "dur": 13.531, + "args": { + "External id": 40391,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197200831559.071, "dur": 37.279, + "args": { + "External id": 40392,"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": 2338707, "tid": 2379456, + "ts": 6197200831599.605, "dur": 33.549, + "args": { + "External id": 40393,"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": 2338707, "tid": 2379456, + "ts": 6197200831661.774, "dur": 267.263, + "args": { + "External id": 40394,"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": 2338707, "tid": 2379456, + "ts": 6197200831756.999, "dur": 6.638, + "args": { + "External id": 40395,"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": 2338707, "tid": 2379456, + "ts": 6197200831765.852, "dur": 2.836, + "args": { + "External id": 40396,"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": 2338707, "tid": 2379456, + "ts": 6197200831769.834, "dur": 2.256, + "args": { + "External id": 40397,"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": 2338707, "tid": 2379456, + "ts": 6197200831773.019, "dur": 2.313, + "args": { + "External id": 40398,"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": 2338707, "tid": 2379456, + "ts": 6197200831823.295, "dur": 4.964, + "args": { + "External id": 40399,"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": 2338707, "tid": 2379456, + "ts": 6197200831825.337, "dur": 2.727, + "args": { + "External id": 40400,"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": 2338707, "tid": 2379456, + "ts": 6197200831830.068, "dur": 33.699, + "args": { + "External id": 40401,"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": 2338707, "tid": 2379456, + "ts": 6197200831836.002, "dur": 2.295, + "args": { + "External id": 40402,"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": 2338707, "tid": 2379456, + "ts": 6197200831865.163, "dur": 1.965, + "args": { + "External id": 40403,"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": 2338707, "tid": 2379456, + "ts": 6197200831866.280, "dur": 0.726, + "args": { + "External id": 40404,"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": 2338707, "tid": 2379456, + "ts": 6197200831868.248, "dur": 16.900, + "args": { + "External id": 40405,"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": 2338707, "tid": 2379456, + "ts": 6197200831870.963, "dur": 0.951, + "args": { + "External id": 40406,"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": 2338707, "tid": 2379456, + "ts": 6197200831971.483, "dur": 31.959, + "args": { + "External id": 40407,"kernel_hash": "cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4", "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/yk/cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4.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": 2338707, "tid": 2379456, + "ts": 6197200832022.928, "dur": 16.640, + "args": { + "External id": 40408,"kernel_hash": "ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg", "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/eu/ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg.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": 2338707, "tid": 2379456, + "ts": 6197200832048.213, "dur": 86.009, + "args": { + "External id": 40409,"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": 2338707, "tid": 2379456, + "ts": 6197200832143.630, "dur": 41.103, + "args": { + "External id": 40410,"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": 2338707, "tid": 2379456, + "ts": 6197200832193.877, "dur": 22.197, + "args": { + "External id": 40411,"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": 2338707, "tid": 2379456, + "ts": 6197200832222.067, "dur": 31.683, + "args": { + "External id": 40412,"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": 2338707, "tid": 2379456, + "ts": 6197200832261.429, "dur": 27.364, + "args": { + "External id": 40413,"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": 2338707, "tid": 2379456, + "ts": 6197200832295.617, "dur": 29.571, + "args": { + "External id": 40414,"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": 2338707, "tid": 2379456, + "ts": 6197200832348.426, "dur": 37.631, + "args": { + "External id": 40415,"kernel_hash": "c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/6w/c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7.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": 2338707, "tid": 2379456, + "ts": 6197200832411.721, "dur": 28.688, + "args": { + "External id": 40416,"kernel_hash": "ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx", "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/kj/ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx.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": 2338707, "tid": 2379456, + "ts": 6197200832458.676, "dur": 16.178, + "args": { + "External id": 40417,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197200832493.853, "dur": 13.667, + "args": { + "External id": 40418,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197200832521.141, "dur": 14.312, + "args": { + "External id": 40419,"kernel_hash": "cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/eb/cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b.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": 2338707, "tid": 2379456, + "ts": 6197200832611.608, "dur": 18.101, + "args": { + "External id": 40420,"Record function id": 0, "Ev Idx": 8675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200832618.283, "dur": 10.466, + "args": { + "External id": 40421,"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": 2338707, "tid": 2379456, + "ts": 6197200832622.308, "dur": 5.571, + "args": { + "External id": 40422,"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": 2338707, "tid": 2379456, + "ts": 6197200832623.626, "dur": 4.164, + "args": { + "External id": 40423,"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": 2338707, "tid": 2379456, + "ts": 6197200832633.754, "dur": 5.345, + "args": { + "External id": 40424,"Record function id": 0, "Ev Idx": 8679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200832635.169, "dur": 3.488, + "args": { + "External id": 40425,"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": 2338707, "tid": 2379456, + "ts": 6197200832636.052, "dur": 1.951, + "args": { + "External id": 40426,"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": 2338707, "tid": 2379456, + "ts": 6197200832637.029, "dur": 0.897, + "args": { + "External id": 40427,"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": 2338707, "tid": 2379456, + "ts": 6197200832642.373, "dur": 4.751, + "args": { + "External id": 40428,"Record function id": 0, "Ev Idx": 8683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200832643.394, "dur": 3.289, + "args": { + "External id": 40429,"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": 2338707, "tid": 2379456, + "ts": 6197200832643.915, "dur": 1.890, + "args": { + "External id": 40430,"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": 2338707, "tid": 2379456, + "ts": 6197200832644.721, "dur": 0.996, + "args": { + "External id": 40431,"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": 2338707, "tid": 2379456, + "ts": 6197200832650.304, "dur": 3.958, + "args": { + "External id": 40432,"Record function id": 0, "Ev Idx": 8687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200832651.375, "dur": 2.459, + "args": { + "External id": 40433,"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": 2338707, "tid": 2379456, + "ts": 6197200832651.969, "dur": 1.310, + "args": { + "External id": 40434,"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": 2338707, "tid": 2379456, + "ts": 6197200832652.513, "dur": 0.669, + "args": { + "External id": 40435,"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": 2338707, "tid": 2379456, + "ts": 6197200832657.430, "dur": 7.676, + "args": { + "External id": 40436,"Record function id": 0, "Ev Idx": 8691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200832662.039, "dur": 2.609, + "args": { + "External id": 40437,"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": 2338707, "tid": 2379456, + "ts": 6197200832662.830, "dur": 1.399, + "args": { + "External id": 40438,"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": 2338707, "tid": 2379456, + "ts": 6197200832663.282, "dur": 0.882, + "args": { + "External id": 40439,"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": 2338707, "tid": 2379456, + "ts": 6197200832668.170, "dur": 9.556, + "args": { + "External id": 40440,"Record function id": 0, "Ev Idx": 8695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200832669.421, "dur": 7.903, + "args": { + "External id": 40441,"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": 2338707, "tid": 2379456, + "ts": 6197200832670.179, "dur": 6.550, + "args": { + "External id": 40442,"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": 2338707, "tid": 2379456, + "ts": 6197200832675.801, "dur": 0.823, + "args": { + "External id": 40443,"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": 2338707, "tid": 2379456, + "ts": 6197200832680.873, "dur": 4.093, + "args": { + "External id": 40444,"Record function id": 0, "Ev Idx": 8699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200832682.240, "dur": 2.297, + "args": { + "External id": 40445,"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": 2338707, "tid": 2379456, + "ts": 6197200832682.764, "dur": 1.357, + "args": { + "External id": 40446,"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": 2338707, "tid": 2379456, + "ts": 6197200832683.368, "dur": 0.690, + "args": { + "External id": 40447,"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": 2338707, "tid": 2379456, + "ts": 6197200832687.965, "dur": 62.950, + "args": { + "External id": 40448,"Record function id": 0, "Ev Idx": 8703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200832744.358, "dur": 5.426, + "args": { + "External id": 40449,"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": 2338707, "tid": 2379456, + "ts": 6197200832746.107, "dur": 2.736, + "args": { + "External id": 40450,"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": 2338707, "tid": 2379456, + "ts": 6197200832746.659, "dur": 1.872, + "args": { + "External id": 40451,"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": 2338707, "tid": 2379456, + "ts": 6197200832755.957, "dur": 6.020, + "args": { + "External id": 40452,"Record function id": 0, "Ev Idx": 8707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200832757.324, "dur": 4.227, + "args": { + "External id": 40453,"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": 2338707, "tid": 2379456, + "ts": 6197200832757.822, "dur": 3.102, + "args": { + "External id": 40454,"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": 2338707, "tid": 2379456, + "ts": 6197200832759.973, "dur": 0.864, + "args": { + "External id": 40455,"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": 2338707, "tid": 2379456, + "ts": 6197200832766.254, "dur": 62772.825, + "args": { + "External id": 40456,"Record function id": 0, "Sequence number": 480032, "Fwd thread id": 1, "Ev Idx": 8711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197200832767.496, "dur": 62762.306, + "args": { + "External id": 40457,"Sequence number": 480032, "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": 2338707, "tid": 2379456, "ts": 6197200832767.496, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.18)", "pid": 2338707, "tid": 2379456, + "ts": 6197200832797.815, "dur": 39.740, + "args": { + "External id": 40458,"Record function id": 0, "Ev Idx": 8713 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.18)", "pid": 2338707, "tid": 2379456, + "ts": 6197200832845.633, "dur": 64.906, + "args": { + "External id": 40459,"Record function id": 0, "Ev Idx": 8714 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.18)", "pid": 2338707, "tid": 2379456, + "ts": 6197200832916.408, "dur": 62605.967, + "args": { + "External id": 40460,"Record function id": 0, "Ev Idx": 8715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197200833007.699, "dur": 7.080, + "args": { + "External id": 40461,"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": 2338707, "tid": 2379456, + "ts": 6197200833026.275, "dur": 4.581, + "args": { + "External id": 40462,"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": 2338707, "tid": 2379456, + "ts": 6197200833045.008, "dur": 61479.670, + "args": { + "External id": 40463,"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": 2338707, "tid": 2379456, + "ts": 6197200833094.584, "dur": 61417.394, + "args": { + "External id": 40464,"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": 2338707, "tid": 2379456, + "ts": 6197200833184.420, "dur": 18.734, + "args": { + "External id": 40465,"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": 2338707, "tid": 2379456, + "ts": 6197200833223.898, "dur": 61243.413, + "args": { + "External id": 40466,"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": 2338707, "tid": 2379456, + "ts": 6197200833226.989, "dur": 61239.492, + "args": { + "External id": 40467,"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": 2338707, "tid": 2379456, + "ts": 6197200833231.658, "dur": 10.364, + "args": { + "External id": 40468,"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": 2338707, "tid": 2379456, + "ts": 6197200833244.235, "dur": 61217.024, + "args": { + "External id": 40469,"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": 2338707, "tid": 2379456, + "ts": 6197200894632.760, "dur": 12.126, + "args": { + "External id": 40470,"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": 2338707, "tid": 2379456, + "ts": 6197200894636.278, "dur": 8.222, + "args": { + "External id": 40471,"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": 2338707, "tid": 2379456, + "ts": 6197200894674.187, "dur": 455.173, + "args": { + "External id": 40472,"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": 2338707, "tid": 2379456, + "ts": 6197200894718.391, "dur": 404.821, + "args": { + "External id": 40473,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197200894731.747, "dur": 381.706, + "args": { + "External id": 40474,"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": 2338707, "tid": 2379456, + "ts": 6197200895154.909, "dur": 2.414, + "args": { + "External id": 40475,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2379456, + "ts": 6197200895225.827, "dur": 6.887, + "args": { + "External id": 40476,"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": 2338707, "tid": 2379456, + "ts": 6197200895243.972, "dur": 36.989, + "args": { + "External id": 40477,"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": 2338707, "tid": 2379456, + "ts": 6197200895291.701, "dur": 1.856, + "args": { + "External id": 40478,"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": 2338707, "tid": 2379456, + "ts": 6197200895298.810, "dur": 11.804, + "args": { + "External id": 40479,"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": 2338707, "tid": 2379456, + "ts": 6197200895315.987, "dur": 0.972, + "args": { + "External id": 40480,"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": 2338707, "tid": 2379456, + "ts": 6197200895320.866, "dur": 11.045, + "args": { + "External id": 40481,"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": 2338707, "tid": 2379456, + "ts": 6197200895336.865, "dur": 0.843, + "args": { + "External id": 40482,"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": 2338707, "tid": 2379456, + "ts": 6197200895342.124, "dur": 11.821, + "args": { + "External id": 40483,"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": 2338707, "tid": 2379456, + "ts": 6197200895360.213, "dur": 1.054, + "args": { + "External id": 40484,"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": 2338707, "tid": 2379456, + "ts": 6197200895365.490, "dur": 12.226, + "args": { + "External id": 40485,"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": 2338707, "tid": 2379456, + "ts": 6197200895382.333, "dur": 1.270, + "args": { + "External id": 40486,"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": 2338707, "tid": 2379456, + "ts": 6197200895387.066, "dur": 11.713, + "args": { + "External id": 40487,"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": 2338707, "tid": 2379456, + "ts": 6197200895403.787, "dur": 1.003, + "args": { + "External id": 40488,"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": 2338707, "tid": 2379456, + "ts": 6197200895408.555, "dur": 12.694, + "args": { + "External id": 40489,"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": 2338707, "tid": 2379456, + "ts": 6197200895425.679, "dur": 0.786, + "args": { + "External id": 40490,"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": 2338707, "tid": 2379456, + "ts": 6197200895431.881, "dur": 10.655, + "args": { + "External id": 40491,"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": 2338707, "tid": 2379456, + "ts": 6197200895446.815, "dur": 0.961, + "args": { + "External id": 40492,"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": 2338707, "tid": 2379456, + "ts": 6197200895452.044, "dur": 11.938, + "args": { + "External id": 40493,"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": 2338707, "tid": 2379456, + "ts": 6197200895553.011, "dur": 2870.477, + "args": { + "External id": 40494,"Record function id": 0, "Ev Idx": 8749 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.17)", "pid": 2338707, "tid": 2379456, + "ts": 6197200895574.530, "dur": 1052.856, + "args": { + "External id": 40495,"Record function id": 0, "Ev Idx": 8750 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.17)", "pid": 2338707, "tid": 2379456, + "ts": 6197200895589.131, "dur": 348.708, + "args": { + "External id": 40496,"Record function id": 0, "Ev Idx": 8751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6197200895674.149, "dur": 4.123, + "args": { + "External id": 40497,"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": 2338707, "tid": 2379456, + "ts": 6197200895682.112, "dur": 0.858, + "args": { + "External id": 40498,"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": 2338707, "tid": 2379456, + "ts": 6197200895684.889, "dur": 1.016, + "args": { + "External id": 40499,"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": 2338707, "tid": 2379456, + "ts": 6197200895687.586, "dur": 0.726, + "args": { + "External id": 40500,"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": 2338707, "tid": 2379456, + "ts": 6197200895694.162, "dur": 1.283, + "args": { + "External id": 40501,"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": 2338707, "tid": 2379456, + "ts": 6197200895699.483, "dur": 17.145, + "args": { + "External id": 40502,"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": 2338707, "tid": 2379456, + "ts": 6197200895720.601, "dur": 1.812, + "args": { + "External id": 40503,"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": 2338707, "tid": 2379456, + "ts": 6197200895724.142, "dur": 1.331, + "args": { + "External id": 40504,"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": 2338707, "tid": 2379456, + "ts": 6197200895726.966, "dur": 1.131, + "args": { + "External id": 40505,"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": 2338707, "tid": 2379456, + "ts": 6197200895731.958, "dur": 1.515, + "args": { + "External id": 40506,"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": 2338707, "tid": 2379456, + "ts": 6197200895751.590, "dur": 153.198, + "args": { + "External id": 40507,"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": 2338707, "tid": 2379456, + "ts": 6197200895766.819, "dur": 133.316, + "args": { + "External id": 40508,"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": 2338707, "tid": 2379456, + "ts": 6197200895780.737, "dur": 23.516, + "args": { + "External id": 40509,"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": 2338707, "tid": 2379456, + "ts": 6197200895808.048, "dur": 64.956, + "args": { + "External id": 40510,"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": 2338707, "tid": 2379456, + "ts": 6197200895810.570, "dur": 62.028, + "args": { + "External id": 40511,"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": 2338707, "tid": 2379456, + "ts": 6197200895814.643, "dur": 6.299, + "args": { + "External id": 40512,"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": 2338707, "tid": 2379456, + "ts": 6197200895822.637, "dur": 49.309, + "args": { + "External id": 40513,"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": 2338707, "tid": 2379456, + "ts": 6197200896025.448, "dur": 595.062, + "args": { + "External id": 40514,"Record function id": 0, "Ev Idx": 8769 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.16)", "pid": 2338707, "tid": 2379456, + "ts": 6197200896040.971, "dur": 567.475, + "args": { + "External id": 40515,"Record function id": 0, "Ev Idx": 8770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197200896146.155, "dur": 6.907, + "args": { + "External id": 40516,"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": 2338707, "tid": 2379456, + "ts": 6197200896169.227, "dur": 24.888, + "args": { + "External id": 40517,"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": 2338707, "tid": 2379456, + "ts": 6197200896174.315, "dur": 1.829, + "args": { + "External id": 40518,"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": 2338707, "tid": 2379456, + "ts": 6197200896178.212, "dur": 0.712, + "args": { + "External id": 40519,"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": 2338707, "tid": 2379456, + "ts": 6197200896180.265, "dur": 0.345, + "args": { + "External id": 40520,"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": 2338707, "tid": 2379456, + "ts": 6197200896181.486, "dur": 0.591, + "args": { + "External id": 40521,"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": 2338707, "tid": 2379456, + "ts": 6197200896183.480, "dur": 0.330, + "args": { + "External id": 40522,"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": 2338707, "tid": 2379456, + "ts": 6197200896184.506, "dur": 0.944, + "args": { + "External id": 40523,"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": 2338707, "tid": 2379456, + "ts": 6197200896186.785, "dur": 0.285, + "args": { + "External id": 40524,"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": 2338707, "tid": 2379456, + "ts": 6197200896188.326, "dur": 0.767, + "args": { + "External id": 40525,"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": 2338707, "tid": 2379456, + "ts": 6197200896189.739, "dur": 0.265, + "args": { + "External id": 40526,"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": 2338707, "tid": 2379456, + "ts": 6197200896205.892, "dur": 41.989, + "args": { + "External id": 40527,"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": 2338707, "tid": 2379456, + "ts": 6197200896278.015, "dur": 102.553, + "args": { + "External id": 40528,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2379456, + "ts": 6197200896288.008, "dur": 3.037, + "args": { + "External id": 40529,"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": 2338707, "tid": 2379456, + "ts": 6197200896296.386, "dur": 10.137, + "args": { + "External id": 40530,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2379456, + "ts": 6197200896300.553, "dur": 5.589, + "args": { + "External id": 40531,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2379456, + "ts": 6197200896303.902, "dur": 0.535, + "args": { + "External id": 40532,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197200896313.249, "dur": 21.822, + "args": { + "External id": 40533,"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": 2338707, "tid": 2379456, + "ts": 6197200896315.261, "dur": 0.371, + "args": { + "External id": 40534,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197200896317.215, "dur": 0.298, + "args": { + "External id": 40535,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2379456, + "ts": 6197200896318.620, "dur": 0.473, + "args": { + "External id": 40536,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2379456, + "ts": 6197200896320.377, "dur": 0.409, + "args": { + "External id": 40537,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2379456, + "ts": 6197200896321.444, "dur": 0.528, + "args": { + "External id": 40538,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2379456, + "ts": 6197200896322.871, "dur": 0.299, + "args": { + "External id": 40539,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2379456, + "ts": 6197200896324.650, "dur": 0.623, + "args": { + "External id": 40540,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2379456, + "ts": 6197200896326.673, "dur": 0.491, + "args": { + "External id": 40541,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2379456, + "ts": 6197200896328.510, "dur": 0.656, + "args": { + "External id": 40542,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2379456, + "ts": 6197200896344.908, "dur": 28.259, + "args": { + "External id": 40543,"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": 2338707, "tid": 2379456, + "ts": 6197200896425.807, "dur": 114.308, + "args": { + "External id": 40544,"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": 2338707, "tid": 2379456, + "ts": 6197200896453.233, "dur": 83.407, + "args": { + "External id": 40545,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197200896464.117, "dur": 68.836, + "args": { + "External id": 40546,"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": 2338707, "tid": 2379456, + "ts": 6197200896559.161, "dur": 1.786, + "args": { + "External id": 40547,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197200896634.096, "dur": 1765.511, + "args": { + "External id": 40548,"Sequence number": 480031, "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": 2338707, "tid": 2379456, "ts": 6197200896634.096, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6197200896762.556, "dur": 107.249, + "args": { + "External id": 40549,"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": 2338707, "tid": 2379456, + "ts": 6197200896910.317, "dur": 39.626, + "args": { + "External id": 40550,"kernel_hash": "cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/u7/cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs.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": 2338707, "tid": 2379456, + "ts": 6197200896967.822, "dur": 49.318, + "args": { + "External id": 40551,"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": 2338707, "tid": 2379456, + "ts": 6197200897027.183, "dur": 68.579, + "args": { + "External id": 40552,"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": 2338707, "tid": 2379456, + "ts": 6197200897106.444, "dur": 38.089, + "args": { + "External id": 40553,"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": 2338707, "tid": 2379456, + "ts": 6197200897151.646, "dur": 29.246, + "args": { + "External id": 40554,"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": 2338707, "tid": 2379456, + "ts": 6197200897188.993, "dur": 30.865, + "args": { + "External id": 40555,"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": 2338707, "tid": 2379456, + "ts": 6197200897247.067, "dur": 24.582, + "args": { + "External id": 40556,"kernel_hash": "cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/wm/cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s.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": 2338707, "tid": 2379456, + "ts": 6197200897289.618, "dur": 27.015, + "args": { + "External id": 40557,"kernel_hash": "cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql", "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/qt/cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql.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": 2338707, "tid": 2379456, + "ts": 6197200897338.673, "dur": 19.153, + "args": { + "External id": 40558,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197200897370.522, "dur": 14.403, + "args": { + "External id": 40559,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197200897392.713, "dur": 37.521, + "args": { + "External id": 40560,"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": 2338707, "tid": 2379456, + "ts": 6197200897433.909, "dur": 33.812, + "args": { + "External id": 40561,"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": 2338707, "tid": 2379456, + "ts": 6197200897497.064, "dur": 260.476, + "args": { + "External id": 40562,"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": 2338707, "tid": 2379456, + "ts": 6197200897577.136, "dur": 6.432, + "args": { + "External id": 40563,"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": 2338707, "tid": 2379456, + "ts": 6197200897585.357, "dur": 2.863, + "args": { + "External id": 40564,"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": 2338707, "tid": 2379456, + "ts": 6197200897589.147, "dur": 2.503, + "args": { + "External id": 40565,"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": 2338707, "tid": 2379456, + "ts": 6197200897592.438, "dur": 2.256, + "args": { + "External id": 40566,"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": 2338707, "tid": 2379456, + "ts": 6197200897637.754, "dur": 5.140, + "args": { + "External id": 40567,"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": 2338707, "tid": 2379456, + "ts": 6197200897639.862, "dur": 2.831, + "args": { + "External id": 40568,"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": 2338707, "tid": 2379456, + "ts": 6197200897645.174, "dur": 30.963, + "args": { + "External id": 40569,"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": 2338707, "tid": 2379456, + "ts": 6197200897650.645, "dur": 1.697, + "args": { + "External id": 40570,"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": 2338707, "tid": 2379456, + "ts": 6197200897677.244, "dur": 1.675, + "args": { + "External id": 40571,"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": 2338707, "tid": 2379456, + "ts": 6197200897678.296, "dur": 0.544, + "args": { + "External id": 40572,"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": 2338707, "tid": 2379456, + "ts": 6197200897679.786, "dur": 17.142, + "args": { + "External id": 40573,"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": 2338707, "tid": 2379456, + "ts": 6197200897682.003, "dur": 0.591, + "args": { + "External id": 40574,"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": 2338707, "tid": 2379456, + "ts": 6197200897794.649, "dur": 29.742, + "args": { + "External id": 40575,"kernel_hash": "cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4", "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/yk/cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4.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": 2338707, "tid": 2379456, + "ts": 6197200897842.620, "dur": 16.606, + "args": { + "External id": 40576,"kernel_hash": "ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg", "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/eu/ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg.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": 2338707, "tid": 2379456, + "ts": 6197200897868.488, "dur": 46.945, + "args": { + "External id": 40577,"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": 2338707, "tid": 2379456, + "ts": 6197200897921.985, "dur": 40.411, + "args": { + "External id": 40578,"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": 2338707, "tid": 2379456, + "ts": 6197200897971.154, "dur": 24.368, + "args": { + "External id": 40579,"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": 2338707, "tid": 2379456, + "ts": 6197200898001.715, "dur": 31.831, + "args": { + "External id": 40580,"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": 2338707, "tid": 2379456, + "ts": 6197200898044.738, "dur": 67.279, + "args": { + "External id": 40581,"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": 2338707, "tid": 2379456, + "ts": 6197200898123.770, "dur": 33.024, + "args": { + "External id": 40582,"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": 2338707, "tid": 2379456, + "ts": 6197200898178.370, "dur": 37.374, + "args": { + "External id": 40583,"kernel_hash": "c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/6w/c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7.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": 2338707, "tid": 2379456, + "ts": 6197200898242.843, "dur": 28.666, + "args": { + "External id": 40584,"kernel_hash": "ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx", "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/kj/ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx.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": 2338707, "tid": 2379456, + "ts": 6197200898286.500, "dur": 16.774, + "args": { + "External id": 40585,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197200898324.291, "dur": 14.972, + "args": { + "External id": 40586,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197200898350.530, "dur": 14.735, + "args": { + "External id": 40587,"kernel_hash": "cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/eb/cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b.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": 2338707, "tid": 2379456, + "ts": 6197200898444.805, "dur": 19.992, + "args": { + "External id": 40588,"Record function id": 0, "Ev Idx": 8843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200898448.065, "dur": 15.815, + "args": { + "External id": 40589,"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": 2338707, "tid": 2379456, + "ts": 6197200898456.554, "dur": 6.259, + "args": { + "External id": 40590,"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": 2338707, "tid": 2379456, + "ts": 6197200898458.350, "dur": 4.367, + "args": { + "External id": 40591,"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": 2338707, "tid": 2379456, + "ts": 6197200898468.990, "dur": 4.333, + "args": { + "External id": 40592,"Record function id": 0, "Ev Idx": 8847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200898470.297, "dur": 2.598, + "args": { + "External id": 40593,"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": 2338707, "tid": 2379456, + "ts": 6197200898471.087, "dur": 1.307, + "args": { + "External id": 40594,"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": 2338707, "tid": 2379456, + "ts": 6197200898471.657, "dur": 0.653, + "args": { + "External id": 40595,"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": 2338707, "tid": 2379456, + "ts": 6197200898476.580, "dur": 6.625, + "args": { + "External id": 40596,"Record function id": 0, "Ev Idx": 8851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200898478.114, "dur": 4.651, + "args": { + "External id": 40597,"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": 2338707, "tid": 2379456, + "ts": 6197200898478.627, "dur": 3.685, + "args": { + "External id": 40598,"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": 2338707, "tid": 2379456, + "ts": 6197200898481.488, "dur": 0.724, + "args": { + "External id": 40599,"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": 2338707, "tid": 2379456, + "ts": 6197200898486.471, "dur": 3.994, + "args": { + "External id": 40600,"Record function id": 0, "Ev Idx": 8855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200898487.688, "dur": 2.364, + "args": { + "External id": 40601,"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": 2338707, "tid": 2379456, + "ts": 6197200898488.221, "dur": 1.427, + "args": { + "External id": 40602,"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": 2338707, "tid": 2379456, + "ts": 6197200898488.775, "dur": 0.790, + "args": { + "External id": 40603,"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": 2338707, "tid": 2379456, + "ts": 6197200898493.565, "dur": 3.580, + "args": { + "External id": 40604,"Record function id": 0, "Ev Idx": 8859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200898494.705, "dur": 2.027, + "args": { + "External id": 40605,"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": 2338707, "tid": 2379456, + "ts": 6197200898495.182, "dur": 1.082, + "args": { + "External id": 40606,"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": 2338707, "tid": 2379456, + "ts": 6197200898495.449, "dur": 0.750, + "args": { + "External id": 40607,"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": 2338707, "tid": 2379456, + "ts": 6197200898500.239, "dur": 3.402, + "args": { + "External id": 40608,"Record function id": 0, "Ev Idx": 8863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200898501.290, "dur": 1.953, + "args": { + "External id": 40609,"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": 2338707, "tid": 2379456, + "ts": 6197200898501.783, "dur": 1.049, + "args": { + "External id": 40610,"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": 2338707, "tid": 2379456, + "ts": 6197200898502.143, "dur": 0.624, + "args": { + "External id": 40611,"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": 2338707, "tid": 2379456, + "ts": 6197200898506.837, "dur": 5.648, + "args": { + "External id": 40612,"Record function id": 0, "Ev Idx": 8867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200898508.062, "dur": 4.022, + "args": { + "External id": 40613,"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": 2338707, "tid": 2379456, + "ts": 6197200898508.517, "dur": 3.055, + "args": { + "External id": 40614,"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": 2338707, "tid": 2379456, + "ts": 6197200898510.642, "dur": 0.843, + "args": { + "External id": 40615,"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": 2338707, "tid": 2379456, + "ts": 6197200898515.569, "dur": 3.748, + "args": { + "External id": 40616,"Record function id": 0, "Ev Idx": 8871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200898516.761, "dur": 2.149, + "args": { + "External id": 40617,"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": 2338707, "tid": 2379456, + "ts": 6197200898517.241, "dur": 1.134, + "args": { + "External id": 40618,"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": 2338707, "tid": 2379456, + "ts": 6197200898517.630, "dur": 0.678, + "args": { + "External id": 40619,"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": 2338707, "tid": 2379456, + "ts": 6197200898522.372, "dur": 3.878, + "args": { + "External id": 40620,"Record function id": 0, "Ev Idx": 8875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200898523.366, "dur": 2.462, + "args": { + "External id": 40621,"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": 2338707, "tid": 2379456, + "ts": 6197200898524.061, "dur": 1.178, + "args": { + "External id": 40622,"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": 2338707, "tid": 2379456, + "ts": 6197200898524.590, "dur": 0.582, + "args": { + "External id": 40623,"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": 2338707, "tid": 2379456, + "ts": 6197200898530.173, "dur": 61582.588, + "args": { + "External id": 40624,"Record function id": 0, "Sequence number": 480030, "Fwd thread id": 1, "Ev Idx": 8879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197200898531.622, "dur": 61570.526, + "args": { + "External id": 40625,"Sequence number": 480030, "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": 2338707, "tid": 2379456, "ts": 6197200898531.622, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.17)", "pid": 2338707, "tid": 2379456, + "ts": 6197200898560.757, "dur": 42.760, + "args": { + "External id": 40626,"Record function id": 0, "Ev Idx": 8881 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.17)", "pid": 2338707, "tid": 2379456, + "ts": 6197200898611.620, "dur": 66.687, + "args": { + "External id": 40627,"Record function id": 0, "Ev Idx": 8882 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.17)", "pid": 2338707, "tid": 2379456, + "ts": 6197200898683.910, "dur": 61409.972, + "args": { + "External id": 40628,"Record function id": 0, "Ev Idx": 8883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197200898792.180, "dur": 6.951, + "args": { + "External id": 40629,"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": 2338707, "tid": 2379456, + "ts": 6197200898810.299, "dur": 4.890, + "args": { + "External id": 40630,"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": 2338707, "tid": 2379456, + "ts": 6197200898829.525, "dur": 60405.260, + "args": { + "External id": 40631,"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": 2338707, "tid": 2379456, + "ts": 6197200898842.807, "dur": 60379.038, + "args": { + "External id": 40632,"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": 2338707, "tid": 2379456, + "ts": 6197200898930.032, "dur": 17.096, + "args": { + "External id": 40633,"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": 2338707, "tid": 2379456, + "ts": 6197200898967.525, "dur": 60207.209, + "args": { + "External id": 40634,"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": 2338707, "tid": 2379456, + "ts": 6197200898970.303, "dur": 60203.367, + "args": { + "External id": 40635,"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": 2338707, "tid": 2379456, + "ts": 6197200898979.460, "dur": 8.204, + "args": { + "External id": 40636,"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": 2338707, "tid": 2379456, + "ts": 6197200898989.552, "dur": 60179.198, + "args": { + "External id": 40637,"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": 2338707, "tid": 2379456, + "ts": 6197200959343.010, "dur": 12.369, + "args": { + "External id": 40638,"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": 2338707, "tid": 2379456, + "ts": 6197200959346.688, "dur": 8.248, + "args": { + "External id": 40639,"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": 2338707, "tid": 2379456, + "ts": 6197200959382.756, "dur": 286.986, + "args": { + "External id": 40640,"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": 2338707, "tid": 2379456, + "ts": 6197200959414.184, "dur": 250.970, + "args": { + "External id": 40641,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197200959425.055, "dur": 234.918, + "args": { + "External id": 40642,"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": 2338707, "tid": 2379456, + "ts": 6197200959689.681, "dur": 2.180, + "args": { + "External id": 40643,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2379456, + "ts": 6197200959766.765, "dur": 7.243, + "args": { + "External id": 40644,"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": 2338707, "tid": 2379456, + "ts": 6197200959785.802, "dur": 32.845, + "args": { + "External id": 40645,"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": 2338707, "tid": 2379456, + "ts": 6197200959828.890, "dur": 1.493, + "args": { + "External id": 40646,"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": 2338707, "tid": 2379456, + "ts": 6197200959835.715, "dur": 16.865, + "args": { + "External id": 40647,"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": 2338707, "tid": 2379456, + "ts": 6197200959857.934, "dur": 0.995, + "args": { + "External id": 40648,"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": 2338707, "tid": 2379456, + "ts": 6197200959863.359, "dur": 11.590, + "args": { + "External id": 40649,"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": 2338707, "tid": 2379456, + "ts": 6197200959879.890, "dur": 1.136, + "args": { + "External id": 40650,"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": 2338707, "tid": 2379456, + "ts": 6197200959884.444, "dur": 10.152, + "args": { + "External id": 40651,"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": 2338707, "tid": 2379456, + "ts": 6197200959898.940, "dur": 1.083, + "args": { + "External id": 40652,"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": 2338707, "tid": 2379456, + "ts": 6197200959906.396, "dur": 11.000, + "args": { + "External id": 40653,"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": 2338707, "tid": 2379456, + "ts": 6197200959921.992, "dur": 1.207, + "args": { + "External id": 40654,"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": 2338707, "tid": 2379456, + "ts": 6197200959927.551, "dur": 10.299, + "args": { + "External id": 40655,"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": 2338707, "tid": 2379456, + "ts": 6197200959941.873, "dur": 0.758, + "args": { + "External id": 40656,"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": 2338707, "tid": 2379456, + "ts": 6197200959946.750, "dur": 15.173, + "args": { + "External id": 40657,"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": 2338707, "tid": 2379456, + "ts": 6197200959966.008, "dur": 1.128, + "args": { + "External id": 40658,"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": 2338707, "tid": 2379456, + "ts": 6197200959970.812, "dur": 11.028, + "args": { + "External id": 40659,"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": 2338707, "tid": 2379456, + "ts": 6197200959988.001, "dur": 0.852, + "args": { + "External id": 40660,"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": 2338707, "tid": 2379456, + "ts": 6197200959992.722, "dur": 11.749, + "args": { + "External id": 40661,"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": 2338707, "tid": 2379456, + "ts": 6197200960129.072, "dur": 2846.621, + "args": { + "External id": 40662,"Record function id": 0, "Ev Idx": 8917 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.16)", "pid": 2338707, "tid": 2379456, + "ts": 6197200960150.627, "dur": 1082.029, + "args": { + "External id": 40663,"Record function id": 0, "Ev Idx": 8918 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.16)", "pid": 2338707, "tid": 2379456, + "ts": 6197200960165.428, "dur": 326.671, + "args": { + "External id": 40664,"Record function id": 0, "Ev Idx": 8919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6197200960258.854, "dur": 5.181, + "args": { + "External id": 40665,"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": 2338707, "tid": 2379456, + "ts": 6197200960268.052, "dur": 0.800, + "args": { + "External id": 40666,"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": 2338707, "tid": 2379456, + "ts": 6197200960270.551, "dur": 1.050, + "args": { + "External id": 40667,"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": 2338707, "tid": 2379456, + "ts": 6197200960273.918, "dur": 1.259, + "args": { + "External id": 40668,"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": 2338707, "tid": 2379456, + "ts": 6197200960276.644, "dur": 0.711, + "args": { + "External id": 40669,"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": 2338707, "tid": 2379456, + "ts": 6197200960278.656, "dur": 0.856, + "args": { + "External id": 40670,"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": 2338707, "tid": 2379456, + "ts": 6197200960283.111, "dur": 0.909, + "args": { + "External id": 40671,"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": 2338707, "tid": 2379456, + "ts": 6197200960285.331, "dur": 0.831, + "args": { + "External id": 40672,"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": 2338707, "tid": 2379456, + "ts": 6197200960287.410, "dur": 1.355, + "args": { + "External id": 40673,"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": 2338707, "tid": 2379456, + "ts": 6197200960290.134, "dur": 0.991, + "args": { + "External id": 40674,"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": 2338707, "tid": 2379456, + "ts": 6197200960310.470, "dur": 151.721, + "args": { + "External id": 40675,"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": 2338707, "tid": 2379456, + "ts": 6197200960326.362, "dur": 131.344, + "args": { + "External id": 40676,"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": 2338707, "tid": 2379456, + "ts": 6197200960341.652, "dur": 24.773, + "args": { + "External id": 40677,"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": 2338707, "tid": 2379456, + "ts": 6197200960370.257, "dur": 60.685, + "args": { + "External id": 40678,"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": 2338707, "tid": 2379456, + "ts": 6197200960373.039, "dur": 57.459, + "args": { + "External id": 40679,"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": 2338707, "tid": 2379456, + "ts": 6197200960376.919, "dur": 5.451, + "args": { + "External id": 40680,"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": 2338707, "tid": 2379456, + "ts": 6197200960384.091, "dur": 45.937, + "args": { + "External id": 40681,"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": 2338707, "tid": 2379456, + "ts": 6197200960578.617, "dur": 646.434, + "args": { + "External id": 40682,"Record function id": 0, "Ev Idx": 8937 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.15)", "pid": 2338707, "tid": 2379456, + "ts": 6197200960593.719, "dur": 617.598, + "args": { + "External id": 40683,"Record function id": 0, "Ev Idx": 8938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197200960655.652, "dur": 5.076, + "args": { + "External id": 40684,"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": 2338707, "tid": 2379456, + "ts": 6197200960675.451, "dur": 23.655, + "args": { + "External id": 40685,"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": 2338707, "tid": 2379456, + "ts": 6197200960680.233, "dur": 1.834, + "args": { + "External id": 40686,"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": 2338707, "tid": 2379456, + "ts": 6197200960683.955, "dur": 0.361, + "args": { + "External id": 40687,"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": 2338707, "tid": 2379456, + "ts": 6197200960685.424, "dur": 0.798, + "args": { + "External id": 40688,"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": 2338707, "tid": 2379456, + "ts": 6197200960687.244, "dur": 0.316, + "args": { + "External id": 40689,"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": 2338707, "tid": 2379456, + "ts": 6197200960688.871, "dur": 0.671, + "args": { + "External id": 40690,"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": 2338707, "tid": 2379456, + "ts": 6197200960690.584, "dur": 0.186, + "args": { + "External id": 40691,"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": 2338707, "tid": 2379456, + "ts": 6197200960691.682, "dur": 0.845, + "args": { + "External id": 40692,"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": 2338707, "tid": 2379456, + "ts": 6197200960693.908, "dur": 0.372, + "args": { + "External id": 40693,"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": 2338707, "tid": 2379456, + "ts": 6197200960695.502, "dur": 0.592, + "args": { + "External id": 40694,"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": 2338707, "tid": 2379456, + "ts": 6197200960732.093, "dur": 43.644, + "args": { + "External id": 40695,"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": 2338707, "tid": 2379456, + "ts": 6197200960813.572, "dur": 112.293, + "args": { + "External id": 40696,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2379456, + "ts": 6197200960824.060, "dur": 3.868, + "args": { + "External id": 40697,"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": 2338707, "tid": 2379456, + "ts": 6197200960833.504, "dur": 14.267, + "args": { + "External id": 40698,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2379456, + "ts": 6197200960837.537, "dur": 6.091, + "args": { + "External id": 40699,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2379456, + "ts": 6197200960841.187, "dur": 1.010, + "args": { + "External id": 40700,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197200960854.423, "dur": 24.925, + "args": { + "External id": 40701,"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": 2338707, "tid": 2379456, + "ts": 6197200960856.361, "dur": 0.633, + "args": { + "External id": 40702,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197200960858.412, "dur": 0.654, + "args": { + "External id": 40703,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2379456, + "ts": 6197200960860.291, "dur": 0.810, + "args": { + "External id": 40704,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2379456, + "ts": 6197200960862.337, "dur": 0.298, + "args": { + "External id": 40705,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2379456, + "ts": 6197200960864.177, "dur": 0.783, + "args": { + "External id": 40706,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2379456, + "ts": 6197200960866.267, "dur": 0.427, + "args": { + "External id": 40707,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2379456, + "ts": 6197200960868.397, "dur": 0.903, + "args": { + "External id": 40708,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2379456, + "ts": 6197200960870.517, "dur": 0.627, + "args": { + "External id": 40709,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2379456, + "ts": 6197200960873.017, "dur": 0.798, + "args": { + "External id": 40710,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2379456, + "ts": 6197200960888.771, "dur": 29.997, + "args": { + "External id": 40711,"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": 2338707, "tid": 2379456, + "ts": 6197200960971.333, "dur": 161.829, + "args": { + "External id": 40712,"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": 2338707, "tid": 2379456, + "ts": 6197200960999.413, "dur": 129.559, + "args": { + "External id": 40713,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197200961008.986, "dur": 115.214, + "args": { + "External id": 40714,"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": 2338707, "tid": 2379456, + "ts": 6197200961152.643, "dur": 2.136, + "args": { + "External id": 40715,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197200961240.765, "dur": 1713.239, + "args": { + "External id": 40716,"Sequence number": 480029, "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": 2338707, "tid": 2379456, "ts": 6197200961240.765, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6197200961353.250, "dur": 108.175, + "args": { + "External id": 40717,"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": 2338707, "tid": 2379456, + "ts": 6197200961500.464, "dur": 39.259, + "args": { + "External id": 40718,"kernel_hash": "cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/u7/cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs.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": 2338707, "tid": 2379456, + "ts": 6197200961558.186, "dur": 50.713, + "args": { + "External id": 40719,"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": 2338707, "tid": 2379456, + "ts": 6197200961618.825, "dur": 32.398, + "args": { + "External id": 40720,"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": 2338707, "tid": 2379456, + "ts": 6197200961657.761, "dur": 33.655, + "args": { + "External id": 40721,"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": 2338707, "tid": 2379456, + "ts": 6197200961697.421, "dur": 48.679, + "args": { + "External id": 40722,"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": 2338707, "tid": 2379456, + "ts": 6197200961757.040, "dur": 31.555, + "args": { + "External id": 40723,"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": 2338707, "tid": 2379456, + "ts": 6197200961815.138, "dur": 24.406, + "args": { + "External id": 40724,"kernel_hash": "cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/wm/cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s.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": 2338707, "tid": 2379456, + "ts": 6197200961857.840, "dur": 28.562, + "args": { + "External id": 40725,"kernel_hash": "cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql", "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/qt/cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql.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": 2338707, "tid": 2379456, + "ts": 6197200961906.461, "dur": 19.833, + "args": { + "External id": 40726,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197200961941.594, "dur": 20.198, + "args": { + "External id": 40727,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197200961970.507, "dur": 40.795, + "args": { + "External id": 40728,"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": 2338707, "tid": 2379456, + "ts": 6197200962015.079, "dur": 33.878, + "args": { + "External id": 40729,"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": 2338707, "tid": 2379456, + "ts": 6197200962115.723, "dur": 245.064, + "args": { + "External id": 40730,"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": 2338707, "tid": 2379456, + "ts": 6197200962192.434, "dur": 6.607, + "args": { + "External id": 40731,"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": 2338707, "tid": 2379456, + "ts": 6197200962201.196, "dur": 2.824, + "args": { + "External id": 40732,"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": 2338707, "tid": 2379456, + "ts": 6197200962205.129, "dur": 2.531, + "args": { + "External id": 40733,"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": 2338707, "tid": 2379456, + "ts": 6197200962208.676, "dur": 2.060, + "args": { + "External id": 40734,"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": 2338707, "tid": 2379456, + "ts": 6197200962257.656, "dur": 5.039, + "args": { + "External id": 40735,"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": 2338707, "tid": 2379456, + "ts": 6197200962259.621, "dur": 2.890, + "args": { + "External id": 40736,"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": 2338707, "tid": 2379456, + "ts": 6197200962264.551, "dur": 32.355, + "args": { + "External id": 40737,"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": 2338707, "tid": 2379456, + "ts": 6197200962270.115, "dur": 1.934, + "args": { + "External id": 40738,"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": 2338707, "tid": 2379456, + "ts": 6197200962298.172, "dur": 1.833, + "args": { + "External id": 40739,"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": 2338707, "tid": 2379456, + "ts": 6197200962299.314, "dur": 0.602, + "args": { + "External id": 40740,"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": 2338707, "tid": 2379456, + "ts": 6197200962301.114, "dur": 15.767, + "args": { + "External id": 40741,"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": 2338707, "tid": 2379456, + "ts": 6197200962303.176, "dur": 0.722, + "args": { + "External id": 40742,"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": 2338707, "tid": 2379456, + "ts": 6197200962400.068, "dur": 27.317, + "args": { + "External id": 40743,"kernel_hash": "cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4", "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/yk/cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4.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": 2338707, "tid": 2379456, + "ts": 6197200962449.541, "dur": 17.809, + "args": { + "External id": 40744,"kernel_hash": "ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg", "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/eu/ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg.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": 2338707, "tid": 2379456, + "ts": 6197200962475.693, "dur": 48.709, + "args": { + "External id": 40745,"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": 2338707, "tid": 2379456, + "ts": 6197200962530.114, "dur": 38.432, + "args": { + "External id": 40746,"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": 2338707, "tid": 2379456, + "ts": 6197200962576.096, "dur": 22.836, + "args": { + "External id": 40747,"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": 2338707, "tid": 2379456, + "ts": 6197200962604.334, "dur": 33.873, + "args": { + "External id": 40748,"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": 2338707, "tid": 2379456, + "ts": 6197200962645.390, "dur": 32.162, + "args": { + "External id": 40749,"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": 2338707, "tid": 2379456, + "ts": 6197200962684.664, "dur": 52.101, + "args": { + "External id": 40750,"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": 2338707, "tid": 2379456, + "ts": 6197200962759.448, "dur": 25.658, + "args": { + "External id": 40751,"kernel_hash": "c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/6w/c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7.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": 2338707, "tid": 2379456, + "ts": 6197200962801.853, "dur": 26.450, + "args": { + "External id": 40752,"kernel_hash": "ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx", "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/kj/ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx.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": 2338707, "tid": 2379456, + "ts": 6197200962847.410, "dur": 18.817, + "args": { + "External id": 40753,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197200962881.142, "dur": 16.255, + "args": { + "External id": 40754,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197200962908.822, "dur": 16.438, + "args": { + "External id": 40755,"kernel_hash": "cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/eb/cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b.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": 2338707, "tid": 2379456, + "ts": 6197200962997.364, "dur": 15.025, + "args": { + "External id": 40756,"Record function id": 0, "Ev Idx": 9011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200963000.532, "dur": 10.938, + "args": { + "External id": 40757,"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": 2338707, "tid": 2379456, + "ts": 6197200963004.497, "dur": 5.750, + "args": { + "External id": 40758,"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": 2338707, "tid": 2379456, + "ts": 6197200963006.111, "dur": 4.047, + "args": { + "External id": 40759,"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": 2338707, "tid": 2379456, + "ts": 6197200963016.666, "dur": 5.092, + "args": { + "External id": 40760,"Record function id": 0, "Ev Idx": 9015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200963018.122, "dur": 3.139, + "args": { + "External id": 40761,"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": 2338707, "tid": 2379456, + "ts": 6197200963019.051, "dur": 1.765, + "args": { + "External id": 40762,"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": 2338707, "tid": 2379456, + "ts": 6197200963019.678, "dur": 1.057, + "args": { + "External id": 40763,"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": 2338707, "tid": 2379456, + "ts": 6197200963025.583, "dur": 4.479, + "args": { + "External id": 40764,"Record function id": 0, "Ev Idx": 9019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200963026.783, "dur": 2.845, + "args": { + "External id": 40765,"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": 2338707, "tid": 2379456, + "ts": 6197200963027.541, "dur": 1.610, + "args": { + "External id": 40766,"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": 2338707, "tid": 2379456, + "ts": 6197200963028.237, "dur": 0.848, + "args": { + "External id": 40767,"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": 2338707, "tid": 2379456, + "ts": 6197200963033.264, "dur": 4.008, + "args": { + "External id": 40768,"Record function id": 0, "Ev Idx": 9023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200963034.326, "dur": 2.540, + "args": { + "External id": 40769,"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": 2338707, "tid": 2379456, + "ts": 6197200963035.234, "dur": 1.212, + "args": { + "External id": 40770,"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": 2338707, "tid": 2379456, + "ts": 6197200963035.657, "dur": 0.713, + "args": { + "External id": 40771,"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": 2338707, "tid": 2379456, + "ts": 6197200963089.414, "dur": 13.652, + "args": { + "External id": 40772,"Record function id": 0, "Ev Idx": 9027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200963093.719, "dur": 7.985, + "args": { + "External id": 40773,"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": 2338707, "tid": 2379456, + "ts": 6197200963095.622, "dur": 3.340, + "args": { + "External id": 40774,"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": 2338707, "tid": 2379456, + "ts": 6197200963096.564, "dur": 2.116, + "args": { + "External id": 40775,"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": 2338707, "tid": 2379456, + "ts": 6197200963107.650, "dur": 7.203, + "args": { + "External id": 40776,"Record function id": 0, "Ev Idx": 9031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200963109.152, "dur": 5.245, + "args": { + "External id": 40777,"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": 2338707, "tid": 2379456, + "ts": 6197200963109.884, "dur": 3.786, + "args": { + "External id": 40778,"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": 2338707, "tid": 2379456, + "ts": 6197200963112.753, "dur": 0.851, + "args": { + "External id": 40779,"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": 2338707, "tid": 2379456, + "ts": 6197200963118.134, "dur": 4.271, + "args": { + "External id": 40780,"Record function id": 0, "Ev Idx": 9035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200963119.435, "dur": 2.533, + "args": { + "External id": 40781,"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": 2338707, "tid": 2379456, + "ts": 6197200963120.164, "dur": 1.350, + "args": { + "External id": 40782,"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": 2338707, "tid": 2379456, + "ts": 6197200963120.683, "dur": 0.765, + "args": { + "External id": 40783,"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": 2338707, "tid": 2379456, + "ts": 6197200963125.801, "dur": 4.816, + "args": { + "External id": 40784,"Record function id": 0, "Ev Idx": 9039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200963127.020, "dur": 3.153, + "args": { + "External id": 40785,"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": 2338707, "tid": 2379456, + "ts": 6197200963127.996, "dur": 1.611, + "args": { + "External id": 40786,"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": 2338707, "tid": 2379456, + "ts": 6197200963128.543, "dur": 0.999, + "args": { + "External id": 40787,"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": 2338707, "tid": 2379456, + "ts": 6197200963133.926, "dur": 4.159, + "args": { + "External id": 40788,"Record function id": 0, "Ev Idx": 9043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197200963135.060, "dur": 2.573, + "args": { + "External id": 40789,"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": 2338707, "tid": 2379456, + "ts": 6197200963135.620, "dur": 1.535, + "args": { + "External id": 40790,"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": 2338707, "tid": 2379456, + "ts": 6197200963136.118, "dur": 0.966, + "args": { + "External id": 40791,"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": 2338707, "tid": 2379456, + "ts": 6197200963142.581, "dur": 64515.110, + "args": { + "External id": 40792,"Record function id": 0, "Sequence number": 480028, "Fwd thread id": 1, "Ev Idx": 9047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197200963144.104, "dur": 64504.573, + "args": { + "External id": 40793,"Sequence number": 480028, "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": 2338707, "tid": 2379456, "ts": 6197200963144.104, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.16)", "pid": 2338707, "tid": 2379456, + "ts": 6197200963183.754, "dur": 38.422, + "args": { + "External id": 40794,"Record function id": 0, "Ev Idx": 9049 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.16)", "pid": 2338707, "tid": 2379456, + "ts": 6197200963233.775, "dur": 65.289, + "args": { + "External id": 40795,"Record function id": 0, "Ev Idx": 9050 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.16)", "pid": 2338707, "tid": 2379456, + "ts": 6197200963304.902, "dur": 64337.349, + "args": { + "External id": 40796,"Record function id": 0, "Ev Idx": 9051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197200963392.334, "dur": 7.740, + "args": { + "External id": 40797,"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": 2338707, "tid": 2379456, + "ts": 6197200963410.201, "dur": 4.623, + "args": { + "External id": 40798,"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": 2338707, "tid": 2379456, + "ts": 6197200963431.235, "dur": 63304.568, + "args": { + "External id": 40799,"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": 2338707, "tid": 2379456, + "ts": 6197200963444.404, "dur": 63278.893, + "args": { + "External id": 40800,"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": 2338707, "tid": 2379456, + "ts": 6197200963530.705, "dur": 17.559, + "args": { + "External id": 40801,"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": 2338707, "tid": 2379456, + "ts": 6197200963568.884, "dur": 63101.812, + "args": { + "External id": 40802,"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": 2338707, "tid": 2379456, + "ts": 6197200963572.233, "dur": 63097.521, + "args": { + "External id": 40803,"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": 2338707, "tid": 2379456, + "ts": 6197200963576.891, "dur": 8.233, + "args": { + "External id": 40804,"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": 2338707, "tid": 2379456, + "ts": 6197200963587.314, "dur": 63077.808, + "args": { + "External id": 40805,"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": 2338707, "tid": 2379456, + "ts": 6197201026843.627, "dur": 11.732, + "args": { + "External id": 40806,"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": 2338707, "tid": 2379456, + "ts": 6197201026847.117, "dur": 7.795, + "args": { + "External id": 40807,"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": 2338707, "tid": 2379456, + "ts": 6197201026885.652, "dur": 392.834, + "args": { + "External id": 40808,"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": 2338707, "tid": 2379456, + "ts": 6197201026916.299, "dur": 356.472, + "args": { + "External id": 40809,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197201026927.704, "dur": 338.979, + "args": { + "External id": 40810,"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": 2338707, "tid": 2379456, + "ts": 6197201027300.573, "dur": 2.266, + "args": { + "External id": 40811,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2379456, + "ts": 6197201027362.000, "dur": 6.519, + "args": { + "External id": 40812,"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": 2338707, "tid": 2379456, + "ts": 6197201027380.188, "dur": 32.375, + "args": { + "External id": 40813,"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": 2338707, "tid": 2379456, + "ts": 6197201027422.404, "dur": 1.862, + "args": { + "External id": 40814,"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": 2338707, "tid": 2379456, + "ts": 6197201027429.497, "dur": 11.754, + "args": { + "External id": 40815,"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": 2338707, "tid": 2379456, + "ts": 6197201027446.741, "dur": 1.518, + "args": { + "External id": 40816,"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": 2338707, "tid": 2379456, + "ts": 6197201027452.590, "dur": 11.581, + "args": { + "External id": 40817,"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": 2338707, "tid": 2379456, + "ts": 6197201027468.943, "dur": 1.075, + "args": { + "External id": 40818,"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": 2338707, "tid": 2379456, + "ts": 6197201027474.587, "dur": 10.048, + "args": { + "External id": 40819,"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": 2338707, "tid": 2379456, + "ts": 6197201027489.362, "dur": 1.002, + "args": { + "External id": 40820,"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": 2338707, "tid": 2379456, + "ts": 6197201027496.628, "dur": 10.465, + "args": { + "External id": 40821,"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": 2338707, "tid": 2379456, + "ts": 6197201027511.371, "dur": 1.156, + "args": { + "External id": 40822,"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": 2338707, "tid": 2379456, + "ts": 6197201027516.815, "dur": 9.331, + "args": { + "External id": 40823,"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": 2338707, "tid": 2379456, + "ts": 6197201027530.593, "dur": 1.055, + "args": { + "External id": 40824,"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": 2338707, "tid": 2379456, + "ts": 6197201027536.176, "dur": 9.880, + "args": { + "External id": 40825,"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": 2338707, "tid": 2379456, + "ts": 6197201027550.742, "dur": 0.845, + "args": { + "External id": 40826,"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": 2338707, "tid": 2379456, + "ts": 6197201027556.086, "dur": 10.329, + "args": { + "External id": 40827,"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": 2338707, "tid": 2379456, + "ts": 6197201027572.587, "dur": 0.981, + "args": { + "External id": 40828,"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": 2338707, "tid": 2379456, + "ts": 6197201027576.920, "dur": 10.480, + "args": { + "External id": 40829,"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": 2338707, "tid": 2379456, + "ts": 6197201027671.204, "dur": 2899.269, + "args": { + "External id": 40830,"Record function id": 0, "Ev Idx": 9085 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.15)", "pid": 2338707, "tid": 2379456, + "ts": 6197201027690.687, "dur": 1082.011, + "args": { + "External id": 40831,"Record function id": 0, "Ev Idx": 9086 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.15)", "pid": 2338707, "tid": 2379456, + "ts": 6197201027723.922, "dur": 370.108, + "args": { + "External id": 40832,"Record function id": 0, "Ev Idx": 9087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6197201027816.302, "dur": 4.705, + "args": { + "External id": 40833,"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": 2338707, "tid": 2379456, + "ts": 6197201027824.938, "dur": 0.733, + "args": { + "External id": 40834,"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": 2338707, "tid": 2379456, + "ts": 6197201027827.719, "dur": 1.107, + "args": { + "External id": 40835,"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": 2338707, "tid": 2379456, + "ts": 6197201027830.498, "dur": 0.671, + "args": { + "External id": 40836,"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": 2338707, "tid": 2379456, + "ts": 6197201027832.582, "dur": 1.011, + "args": { + "External id": 40837,"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": 2338707, "tid": 2379456, + "ts": 6197201027835.123, "dur": 0.695, + "args": { + "External id": 40838,"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": 2338707, "tid": 2379456, + "ts": 6197201027839.724, "dur": 0.876, + "args": { + "External id": 40839,"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": 2338707, "tid": 2379456, + "ts": 6197201027842.056, "dur": 1.600, + "args": { + "External id": 40840,"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": 2338707, "tid": 2379456, + "ts": 6197201027845.303, "dur": 0.914, + "args": { + "External id": 40841,"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": 2338707, "tid": 2379456, + "ts": 6197201027847.656, "dur": 1.020, + "args": { + "External id": 40842,"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": 2338707, "tid": 2379456, + "ts": 6197201027870.813, "dur": 152.324, + "args": { + "External id": 40843,"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": 2338707, "tid": 2379456, + "ts": 6197201027886.266, "dur": 132.471, + "args": { + "External id": 40844,"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": 2338707, "tid": 2379456, + "ts": 6197201027911.957, "dur": 18.441, + "args": { + "External id": 40845,"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": 2338707, "tid": 2379456, + "ts": 6197201027934.426, "dur": 57.883, + "args": { + "External id": 40846,"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": 2338707, "tid": 2379456, + "ts": 6197201027937.437, "dur": 54.559, + "args": { + "External id": 40847,"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": 2338707, "tid": 2379456, + "ts": 6197201027940.918, "dur": 5.145, + "args": { + "External id": 40848,"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": 2338707, "tid": 2379456, + "ts": 6197201027947.756, "dur": 43.582, + "args": { + "External id": 40849,"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": 2338707, "tid": 2379456, + "ts": 6197201028187.515, "dur": 578.178, + "args": { + "External id": 40850,"Record function id": 0, "Ev Idx": 9105 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.14)", "pid": 2338707, "tid": 2379456, + "ts": 6197201028204.246, "dur": 549.291, + "args": { + "External id": 40851,"Record function id": 0, "Ev Idx": 9106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197201028267.739, "dur": 5.742, + "args": { + "External id": 40852,"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": 2338707, "tid": 2379456, + "ts": 6197201028288.226, "dur": 24.447, + "args": { + "External id": 40853,"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": 2338707, "tid": 2379456, + "ts": 6197201028293.405, "dur": 1.940, + "args": { + "External id": 40854,"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": 2338707, "tid": 2379456, + "ts": 6197201028297.678, "dur": 0.356, + "args": { + "External id": 40855,"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": 2338707, "tid": 2379456, + "ts": 6197201028299.435, "dur": 0.770, + "args": { + "External id": 40856,"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": 2338707, "tid": 2379456, + "ts": 6197201028301.548, "dur": 0.418, + "args": { + "External id": 40857,"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": 2338707, "tid": 2379456, + "ts": 6197201028303.124, "dur": 0.765, + "args": { + "External id": 40858,"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": 2338707, "tid": 2379456, + "ts": 6197201028304.828, "dur": 0.185, + "args": { + "External id": 40859,"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": 2338707, "tid": 2379456, + "ts": 6197201028306.085, "dur": 0.603, + "args": { + "External id": 40860,"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": 2338707, "tid": 2379456, + "ts": 6197201028307.697, "dur": 0.305, + "args": { + "External id": 40861,"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": 2338707, "tid": 2379456, + "ts": 6197201028308.645, "dur": 0.642, + "args": { + "External id": 40862,"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": 2338707, "tid": 2379456, + "ts": 6197201028323.556, "dur": 42.856, + "args": { + "External id": 40863,"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": 2338707, "tid": 2379456, + "ts": 6197201028396.099, "dur": 115.782, + "args": { + "External id": 40864,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2379456, + "ts": 6197201028406.505, "dur": 3.366, + "args": { + "External id": 40865,"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": 2338707, "tid": 2379456, + "ts": 6197201028414.724, "dur": 9.602, + "args": { + "External id": 40866,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2379456, + "ts": 6197201028419.089, "dur": 4.840, + "args": { + "External id": 40867,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2379456, + "ts": 6197201028422.218, "dur": 0.552, + "args": { + "External id": 40868,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197201028430.613, "dur": 35.044, + "args": { + "External id": 40869,"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": 2338707, "tid": 2379456, + "ts": 6197201028439.112, "dur": 0.350, + "args": { + "External id": 40870,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197201028448.966, "dur": 0.486, + "args": { + "External id": 40871,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2379456, + "ts": 6197201028450.685, "dur": 0.445, + "args": { + "External id": 40872,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2379456, + "ts": 6197201028452.006, "dur": 0.430, + "args": { + "External id": 40873,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2379456, + "ts": 6197201028453.861, "dur": 0.303, + "args": { + "External id": 40874,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2379456, + "ts": 6197201028455.374, "dur": 1.122, + "args": { + "External id": 40875,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2379456, + "ts": 6197201028457.500, "dur": 0.192, + "args": { + "External id": 40876,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2379456, + "ts": 6197201028458.595, "dur": 0.582, + "args": { + "External id": 40877,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2379456, + "ts": 6197201028460.165, "dur": 0.270, + "args": { + "External id": 40878,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2379456, + "ts": 6197201028475.533, "dur": 29.226, + "args": { + "External id": 40879,"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": 2338707, "tid": 2379456, + "ts": 6197201028555.796, "dur": 113.298, + "args": { + "External id": 40880,"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": 2338707, "tid": 2379456, + "ts": 6197201028581.747, "dur": 84.062, + "args": { + "External id": 40881,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197201028590.912, "dur": 70.867, + "args": { + "External id": 40882,"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": 2338707, "tid": 2379456, + "ts": 6197201028685.177, "dur": 1.899, + "args": { + "External id": 40883,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197201028779.628, "dur": 1764.098, + "args": { + "External id": 40884,"Sequence number": 480027, "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": 2338707, "tid": 2379456, "ts": 6197201028779.628, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6197201028891.941, "dur": 108.910, + "args": { + "External id": 40885,"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": 2338707, "tid": 2379456, + "ts": 6197201029044.394, "dur": 83.751, + "args": { + "External id": 40886,"kernel_hash": "cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/u7/cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs.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": 2338707, "tid": 2379456, + "ts": 6197201029150.005, "dur": 58.185, + "args": { + "External id": 40887,"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": 2338707, "tid": 2379456, + "ts": 6197201029218.605, "dur": 33.296, + "args": { + "External id": 40888,"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": 2338707, "tid": 2379456, + "ts": 6197201029258.321, "dur": 34.670, + "args": { + "External id": 40889,"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": 2338707, "tid": 2379456, + "ts": 6197201029299.563, "dur": 27.978, + "args": { + "External id": 40890,"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": 2338707, "tid": 2379456, + "ts": 6197201029334.610, "dur": 29.674, + "args": { + "External id": 40891,"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": 2338707, "tid": 2379456, + "ts": 6197201029391.627, "dur": 23.412, + "args": { + "External id": 40892,"kernel_hash": "cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/wm/cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s.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": 2338707, "tid": 2379456, + "ts": 6197201029438.492, "dur": 26.171, + "args": { + "External id": 40893,"kernel_hash": "cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql", "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/qt/cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql.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": 2338707, "tid": 2379456, + "ts": 6197201029484.306, "dur": 20.401, + "args": { + "External id": 40894,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197201029518.451, "dur": 16.336, + "args": { + "External id": 40895,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197201029542.504, "dur": 38.156, + "args": { + "External id": 40896,"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": 2338707, "tid": 2379456, + "ts": 6197201029584.106, "dur": 33.405, + "args": { + "External id": 40897,"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": 2338707, "tid": 2379456, + "ts": 6197201029645.648, "dur": 260.312, + "args": { + "External id": 40898,"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": 2338707, "tid": 2379456, + "ts": 6197201029737.473, "dur": 7.351, + "args": { + "External id": 40899,"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": 2338707, "tid": 2379456, + "ts": 6197201029747.257, "dur": 2.941, + "args": { + "External id": 40900,"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": 2338707, "tid": 2379456, + "ts": 6197201029751.251, "dur": 1.663, + "args": { + "External id": 40901,"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": 2338707, "tid": 2379456, + "ts": 6197201029753.801, "dur": 2.556, + "args": { + "External id": 40902,"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": 2338707, "tid": 2379456, + "ts": 6197201029802.837, "dur": 5.483, + "args": { + "External id": 40903,"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": 2338707, "tid": 2379456, + "ts": 6197201029804.822, "dur": 3.291, + "args": { + "External id": 40904,"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": 2338707, "tid": 2379456, + "ts": 6197201029810.643, "dur": 33.113, + "args": { + "External id": 40905,"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": 2338707, "tid": 2379456, + "ts": 6197201029816.435, "dur": 2.111, + "args": { + "External id": 40906,"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": 2338707, "tid": 2379456, + "ts": 6197201029845.962, "dur": 1.872, + "args": { + "External id": 40907,"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": 2338707, "tid": 2379456, + "ts": 6197201029847.243, "dur": 0.511, + "args": { + "External id": 40908,"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": 2338707, "tid": 2379456, + "ts": 6197201029848.674, "dur": 16.075, + "args": { + "External id": 40909,"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": 2338707, "tid": 2379456, + "ts": 6197201029850.707, "dur": 0.629, + "args": { + "External id": 40910,"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": 2338707, "tid": 2379456, + "ts": 6197201029945.470, "dur": 28.278, + "args": { + "External id": 40911,"kernel_hash": "cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4", "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/yk/cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4.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": 2338707, "tid": 2379456, + "ts": 6197201029990.275, "dur": 16.762, + "args": { + "External id": 40912,"kernel_hash": "ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg", "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/eu/ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg.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": 2338707, "tid": 2379456, + "ts": 6197201030014.947, "dur": 82.560, + "args": { + "External id": 40913,"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": 2338707, "tid": 2379456, + "ts": 6197201030107.038, "dur": 44.570, + "args": { + "External id": 40914,"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": 2338707, "tid": 2379456, + "ts": 6197201030161.670, "dur": 23.461, + "args": { + "External id": 40915,"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": 2338707, "tid": 2379456, + "ts": 6197201030190.539, "dur": 31.264, + "args": { + "External id": 40916,"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": 2338707, "tid": 2379456, + "ts": 6197201030228.379, "dur": 28.001, + "args": { + "External id": 40917,"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": 2338707, "tid": 2379456, + "ts": 6197201030266.206, "dur": 30.878, + "args": { + "External id": 40918,"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": 2338707, "tid": 2379456, + "ts": 6197201030320.582, "dur": 26.364, + "args": { + "External id": 40919,"kernel_hash": "c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/6w/c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7.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": 2338707, "tid": 2379456, + "ts": 6197201030363.203, "dur": 31.191, + "args": { + "External id": 40920,"kernel_hash": "ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx", "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/kj/ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx.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": 2338707, "tid": 2379456, + "ts": 6197201030419.771, "dur": 25.146, + "args": { + "External id": 40921,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197201030462.048, "dur": 15.015, + "args": { + "External id": 40922,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197201030490.347, "dur": 22.201, + "args": { + "External id": 40923,"kernel_hash": "cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/eb/cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b.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": 2338707, "tid": 2379456, + "ts": 6197201030592.502, "dur": 15.212, + "args": { + "External id": 40924,"Record function id": 0, "Ev Idx": 9179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201030595.597, "dur": 11.094, + "args": { + "External id": 40925,"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": 2338707, "tid": 2379456, + "ts": 6197201030599.815, "dur": 5.949, + "args": { + "External id": 40926,"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": 2338707, "tid": 2379456, + "ts": 6197201030601.322, "dur": 4.359, + "args": { + "External id": 40927,"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": 2338707, "tid": 2379456, + "ts": 6197201030611.867, "dur": 7.879, + "args": { + "External id": 40928,"Record function id": 0, "Ev Idx": 9183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201030613.344, "dur": 5.960, + "args": { + "External id": 40929,"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": 2338707, "tid": 2379456, + "ts": 6197201030614.480, "dur": 4.411, + "args": { + "External id": 40930,"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": 2338707, "tid": 2379456, + "ts": 6197201030615.119, "dur": 3.694, + "args": { + "External id": 40931,"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": 2338707, "tid": 2379456, + "ts": 6197201030623.045, "dur": 4.030, + "args": { + "External id": 40932,"Record function id": 0, "Ev Idx": 9187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201030624.140, "dur": 2.508, + "args": { + "External id": 40933,"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": 2338707, "tid": 2379456, + "ts": 6197201030624.838, "dur": 1.191, + "args": { + "External id": 40934,"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": 2338707, "tid": 2379456, + "ts": 6197201030625.295, "dur": 0.669, + "args": { + "External id": 40935,"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": 2338707, "tid": 2379456, + "ts": 6197201030630.285, "dur": 4.034, + "args": { + "External id": 40936,"Record function id": 0, "Ev Idx": 9191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201030631.415, "dur": 2.476, + "args": { + "External id": 40937,"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": 2338707, "tid": 2379456, + "ts": 6197201030632.224, "dur": 1.281, + "args": { + "External id": 40938,"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": 2338707, "tid": 2379456, + "ts": 6197201030632.789, "dur": 0.651, + "args": { + "External id": 40939,"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": 2338707, "tid": 2379456, + "ts": 6197201030637.417, "dur": 4.315, + "args": { + "External id": 40940,"Record function id": 0, "Ev Idx": 9195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201030638.418, "dur": 2.900, + "args": { + "External id": 40941,"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": 2338707, "tid": 2379456, + "ts": 6197201030639.364, "dur": 1.367, + "args": { + "External id": 40942,"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": 2338707, "tid": 2379456, + "ts": 6197201030639.733, "dur": 0.938, + "args": { + "External id": 40943,"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": 2338707, "tid": 2379456, + "ts": 6197201030644.762, "dur": 4.320, + "args": { + "External id": 40944,"Record function id": 0, "Ev Idx": 9199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201030646.110, "dur": 2.530, + "args": { + "External id": 40945,"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": 2338707, "tid": 2379456, + "ts": 6197201030646.606, "dur": 1.249, + "args": { + "External id": 40946,"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": 2338707, "tid": 2379456, + "ts": 6197201030646.882, "dur": 0.906, + "args": { + "External id": 40947,"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": 2338707, "tid": 2379456, + "ts": 6197201030652.230, "dur": 3.299, + "args": { + "External id": 40948,"Record function id": 0, "Ev Idx": 9203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201030653.221, "dur": 1.890, + "args": { + "External id": 40949,"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": 2338707, "tid": 2379456, + "ts": 6197201030653.693, "dur": 0.993, + "args": { + "External id": 40950,"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": 2338707, "tid": 2379456, + "ts": 6197201030654.192, "dur": 0.428, + "args": { + "External id": 40951,"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": 2338707, "tid": 2379456, + "ts": 6197201030658.594, "dur": 3.657, + "args": { + "External id": 40952,"Record function id": 0, "Ev Idx": 9207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201030659.688, "dur": 2.146, + "args": { + "External id": 40953,"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": 2338707, "tid": 2379456, + "ts": 6197201030660.249, "dur": 1.156, + "args": { + "External id": 40954,"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": 2338707, "tid": 2379456, + "ts": 6197201030660.523, "dur": 0.815, + "args": { + "External id": 40955,"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": 2338707, "tid": 2379456, + "ts": 6197201030665.397, "dur": 3.618, + "args": { + "External id": 40956,"Record function id": 0, "Ev Idx": 9211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201030666.493, "dur": 2.080, + "args": { + "External id": 40957,"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": 2338707, "tid": 2379456, + "ts": 6197201030666.968, "dur": 1.070, + "args": { + "External id": 40958,"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": 2338707, "tid": 2379456, + "ts": 6197201030667.248, "dur": 0.727, + "args": { + "External id": 40959,"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": 2338707, "tid": 2379456, + "ts": 6197201030673.152, "dur": 62828.256, + "args": { + "External id": 40960,"Record function id": 0, "Sequence number": 480026, "Fwd thread id": 1, "Ev Idx": 9215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197201030728.498, "dur": 62763.772, + "args": { + "External id": 40961,"Sequence number": 480026, "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": 2338707, "tid": 2379456, "ts": 6197201030728.498, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.15)", "pid": 2338707, "tid": 2379456, + "ts": 6197201030768.697, "dur": 39.904, + "args": { + "External id": 40962,"Record function id": 0, "Ev Idx": 9217 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.15)", "pid": 2338707, "tid": 2379456, + "ts": 6197201030816.539, "dur": 67.301, + "args": { + "External id": 40963,"Record function id": 0, "Ev Idx": 9218 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.15)", "pid": 2338707, "tid": 2379456, + "ts": 6197201030889.358, "dur": 62595.285, + "args": { + "External id": 40964,"Record function id": 0, "Ev Idx": 9219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197201030980.216, "dur": 7.204, + "args": { + "External id": 40965,"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": 2338707, "tid": 2379456, + "ts": 6197201030998.124, "dur": 5.051, + "args": { + "External id": 40966,"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": 2338707, "tid": 2379456, + "ts": 6197201031019.542, "dur": 61469.796, + "args": { + "External id": 40967,"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": 2338707, "tid": 2379456, + "ts": 6197201031033.509, "dur": 61443.360, + "args": { + "External id": 40968,"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": 2338707, "tid": 2379456, + "ts": 6197201031166.406, "dur": 19.031, + "args": { + "External id": 40969,"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": 2338707, "tid": 2379456, + "ts": 6197201031209.411, "dur": 61216.626, + "args": { + "External id": 40970,"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": 2338707, "tid": 2379456, + "ts": 6197201031212.647, "dur": 61212.091, + "args": { + "External id": 40971,"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": 2338707, "tid": 2379456, + "ts": 6197201031217.753, "dur": 9.873, + "args": { + "External id": 40972,"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": 2338707, "tid": 2379456, + "ts": 6197201031229.788, "dur": 61188.932, + "args": { + "External id": 40973,"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": 2338707, "tid": 2379456, + "ts": 6197201092603.385, "dur": 12.675, + "args": { + "External id": 40974,"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": 2338707, "tid": 2379456, + "ts": 6197201092606.948, "dur": 8.752, + "args": { + "External id": 40975,"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": 2338707, "tid": 2379456, + "ts": 6197201092646.448, "dur": 449.603, + "args": { + "External id": 40976,"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": 2338707, "tid": 2379456, + "ts": 6197201092677.632, "dur": 412.412, + "args": { + "External id": 40977,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197201092688.512, "dur": 393.562, + "args": { + "External id": 40978,"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": 2338707, "tid": 2379456, + "ts": 6197201093122.634, "dur": 2.689, + "args": { + "External id": 40979,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2379456, + "ts": 6197201093189.861, "dur": 6.887, + "args": { + "External id": 40980,"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": 2338707, "tid": 2379456, + "ts": 6197201093208.821, "dur": 36.629, + "args": { + "External id": 40981,"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": 2338707, "tid": 2379456, + "ts": 6197201093256.289, "dur": 1.433, + "args": { + "External id": 40982,"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": 2338707, "tid": 2379456, + "ts": 6197201093263.548, "dur": 13.743, + "args": { + "External id": 40983,"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": 2338707, "tid": 2379456, + "ts": 6197201093282.552, "dur": 0.935, + "args": { + "External id": 40984,"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": 2338707, "tid": 2379456, + "ts": 6197201093287.882, "dur": 12.754, + "args": { + "External id": 40985,"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": 2338707, "tid": 2379456, + "ts": 6197201093305.539, "dur": 1.137, + "args": { + "External id": 40986,"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": 2338707, "tid": 2379456, + "ts": 6197201093310.722, "dur": 11.557, + "args": { + "External id": 40987,"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": 2338707, "tid": 2379456, + "ts": 6197201093326.469, "dur": 0.783, + "args": { + "External id": 40988,"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": 2338707, "tid": 2379456, + "ts": 6197201093331.359, "dur": 12.312, + "args": { + "External id": 40989,"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": 2338707, "tid": 2379456, + "ts": 6197201093348.131, "dur": 1.078, + "args": { + "External id": 40990,"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": 2338707, "tid": 2379456, + "ts": 6197201093353.909, "dur": 10.636, + "args": { + "External id": 40991,"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": 2338707, "tid": 2379456, + "ts": 6197201093371.658, "dur": 0.898, + "args": { + "External id": 40992,"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": 2338707, "tid": 2379456, + "ts": 6197201093376.323, "dur": 10.840, + "args": { + "External id": 40993,"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": 2338707, "tid": 2379456, + "ts": 6197201093391.498, "dur": 0.744, + "args": { + "External id": 40994,"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": 2338707, "tid": 2379456, + "ts": 6197201093395.566, "dur": 9.482, + "args": { + "External id": 40995,"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": 2338707, "tid": 2379456, + "ts": 6197201093409.116, "dur": 0.922, + "args": { + "External id": 40996,"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": 2338707, "tid": 2379456, + "ts": 6197201093415.779, "dur": 10.604, + "args": { + "External id": 40997,"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": 2338707, "tid": 2379456, + "ts": 6197201093516.094, "dur": 2909.516, + "args": { + "External id": 40998,"Record function id": 0, "Ev Idx": 9253 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.14)", "pid": 2338707, "tid": 2379456, + "ts": 6197201093536.550, "dur": 1071.147, + "args": { + "External id": 40999,"Record function id": 0, "Ev Idx": 9254 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.14)", "pid": 2338707, "tid": 2379456, + "ts": 6197201093551.223, "dur": 353.208, + "args": { + "External id": 41000,"Record function id": 0, "Ev Idx": 9255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6197201093637.678, "dur": 4.222, + "args": { + "External id": 41001,"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": 2338707, "tid": 2379456, + "ts": 6197201093645.483, "dur": 0.814, + "args": { + "External id": 41002,"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": 2338707, "tid": 2379456, + "ts": 6197201093648.181, "dur": 1.360, + "args": { + "External id": 41003,"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": 2338707, "tid": 2379456, + "ts": 6197201093651.403, "dur": 1.151, + "args": { + "External id": 41004,"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": 2338707, "tid": 2379456, + "ts": 6197201093653.917, "dur": 0.772, + "args": { + "External id": 41005,"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": 2338707, "tid": 2379456, + "ts": 6197201093656.175, "dur": 1.076, + "args": { + "External id": 41006,"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": 2338707, "tid": 2379456, + "ts": 6197201093658.959, "dur": 0.958, + "args": { + "External id": 41007,"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": 2338707, "tid": 2379456, + "ts": 6197201093663.443, "dur": 0.917, + "args": { + "External id": 41008,"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": 2338707, "tid": 2379456, + "ts": 6197201093665.970, "dur": 1.197, + "args": { + "External id": 41009,"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": 2338707, "tid": 2379456, + "ts": 6197201093668.639, "dur": 1.136, + "args": { + "External id": 41010,"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": 2338707, "tid": 2379456, + "ts": 6197201093687.527, "dur": 183.664, + "args": { + "External id": 41011,"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": 2338707, "tid": 2379456, + "ts": 6197201093720.001, "dur": 146.084, + "args": { + "External id": 41012,"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": 2338707, "tid": 2379456, + "ts": 6197201093738.040, "dur": 24.113, + "args": { + "External id": 41013,"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": 2338707, "tid": 2379456, + "ts": 6197201093765.778, "dur": 72.226, + "args": { + "External id": 41014,"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": 2338707, "tid": 2379456, + "ts": 6197201093772.179, "dur": 65.503, + "args": { + "External id": 41015,"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": 2338707, "tid": 2379456, + "ts": 6197201093775.785, "dur": 6.295, + "args": { + "External id": 41016,"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": 2338707, "tid": 2379456, + "ts": 6197201093783.732, "dur": 53.135, + "args": { + "External id": 41017,"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": 2338707, "tid": 2379456, + "ts": 6197201093995.233, "dur": 605.376, + "args": { + "External id": 41018,"Record function id": 0, "Ev Idx": 9273 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.13)", "pid": 2338707, "tid": 2379456, + "ts": 6197201094012.823, "dur": 575.716, + "args": { + "External id": 41019,"Record function id": 0, "Ev Idx": 9274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197201094113.833, "dur": 7.713, + "args": { + "External id": 41020,"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": 2338707, "tid": 2379456, + "ts": 6197201094137.514, "dur": 25.608, + "args": { + "External id": 41021,"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": 2338707, "tid": 2379456, + "ts": 6197201094142.191, "dur": 1.917, + "args": { + "External id": 41022,"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": 2338707, "tid": 2379456, + "ts": 6197201094146.206, "dur": 0.524, + "args": { + "External id": 41023,"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": 2338707, "tid": 2379456, + "ts": 6197201094147.968, "dur": 0.410, + "args": { + "External id": 41024,"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": 2338707, "tid": 2379456, + "ts": 6197201094149.721, "dur": 0.579, + "args": { + "External id": 41025,"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": 2338707, "tid": 2379456, + "ts": 6197201094151.203, "dur": 1.024, + "args": { + "External id": 41026,"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": 2338707, "tid": 2379456, + "ts": 6197201094153.580, "dur": 0.472, + "args": { + "External id": 41027,"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": 2338707, "tid": 2379456, + "ts": 6197201094154.844, "dur": 0.806, + "args": { + "External id": 41028,"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": 2338707, "tid": 2379456, + "ts": 6197201094157.110, "dur": 0.389, + "args": { + "External id": 41029,"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": 2338707, "tid": 2379456, + "ts": 6197201094158.013, "dur": 0.951, + "args": { + "External id": 41030,"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": 2338707, "tid": 2379456, + "ts": 6197201094174.978, "dur": 46.389, + "args": { + "External id": 41031,"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": 2338707, "tid": 2379456, + "ts": 6197201094251.640, "dur": 101.295, + "args": { + "External id": 41032,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2379456, + "ts": 6197201094261.860, "dur": 3.803, + "args": { + "External id": 41033,"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": 2338707, "tid": 2379456, + "ts": 6197201094270.626, "dur": 10.144, + "args": { + "External id": 41034,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2379456, + "ts": 6197201094275.097, "dur": 5.249, + "args": { + "External id": 41035,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2379456, + "ts": 6197201094278.073, "dur": 0.835, + "args": { + "External id": 41036,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197201094286.947, "dur": 21.533, + "args": { + "External id": 41037,"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": 2338707, "tid": 2379456, + "ts": 6197201094288.641, "dur": 0.703, + "args": { + "External id": 41038,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197201094291.178, "dur": 0.441, + "args": { + "External id": 41039,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2379456, + "ts": 6197201094292.982, "dur": 0.498, + "args": { + "External id": 41040,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2379456, + "ts": 6197201094294.711, "dur": 0.383, + "args": { + "External id": 41041,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2379456, + "ts": 6197201094295.934, "dur": 0.587, + "args": { + "External id": 41042,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2379456, + "ts": 6197201094298.134, "dur": 0.312, + "args": { + "External id": 41043,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2379456, + "ts": 6197201094299.392, "dur": 0.626, + "args": { + "External id": 41044,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2379456, + "ts": 6197201094301.097, "dur": 0.283, + "args": { + "External id": 41045,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2379456, + "ts": 6197201094302.129, "dur": 0.824, + "args": { + "External id": 41046,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2379456, + "ts": 6197201094317.960, "dur": 27.805, + "args": { + "External id": 41047,"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": 2338707, "tid": 2379456, + "ts": 6197201094397.397, "dur": 117.130, + "args": { + "External id": 41048,"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": 2338707, "tid": 2379456, + "ts": 6197201094425.770, "dur": 85.108, + "args": { + "External id": 41049,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197201094435.123, "dur": 71.827, + "args": { + "External id": 41050,"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": 2338707, "tid": 2379456, + "ts": 6197201094535.286, "dur": 1.822, + "args": { + "External id": 41051,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197201094614.843, "dur": 1788.401, + "args": { + "External id": 41052,"Sequence number": 480025, "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": 2338707, "tid": 2379456, "ts": 6197201094614.843, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6197201094744.900, "dur": 110.363, + "args": { + "External id": 41053,"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": 2338707, "tid": 2379456, + "ts": 6197201094896.878, "dur": 41.482, + "args": { + "External id": 41054,"kernel_hash": "cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/u7/cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs.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": 2338707, "tid": 2379456, + "ts": 6197201094956.934, "dur": 53.718, + "args": { + "External id": 41055,"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": 2338707, "tid": 2379456, + "ts": 6197201095021.275, "dur": 74.598, + "args": { + "External id": 41056,"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": 2338707, "tid": 2379456, + "ts": 6197201095107.633, "dur": 37.621, + "args": { + "External id": 41057,"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": 2338707, "tid": 2379456, + "ts": 6197201095152.761, "dur": 28.934, + "args": { + "External id": 41058,"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": 2338707, "tid": 2379456, + "ts": 6197201095189.383, "dur": 30.174, + "args": { + "External id": 41059,"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": 2338707, "tid": 2379456, + "ts": 6197201095247.231, "dur": 23.760, + "args": { + "External id": 41060,"kernel_hash": "cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/wm/cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s.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": 2338707, "tid": 2379456, + "ts": 6197201095289.225, "dur": 30.125, + "args": { + "External id": 41061,"kernel_hash": "cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql", "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/qt/cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql.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": 2338707, "tid": 2379456, + "ts": 6197201095341.222, "dur": 19.125, + "args": { + "External id": 41062,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197201095379.280, "dur": 13.888, + "args": { + "External id": 41063,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197201095402.001, "dur": 37.472, + "args": { + "External id": 41064,"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": 2338707, "tid": 2379456, + "ts": 6197201095442.951, "dur": 33.074, + "args": { + "External id": 41065,"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": 2338707, "tid": 2379456, + "ts": 6197201095509.754, "dur": 258.608, + "args": { + "External id": 41066,"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": 2338707, "tid": 2379456, + "ts": 6197201095590.462, "dur": 6.032, + "args": { + "External id": 41067,"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": 2338707, "tid": 2379456, + "ts": 6197201095598.306, "dur": 3.009, + "args": { + "External id": 41068,"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": 2338707, "tid": 2379456, + "ts": 6197201095602.576, "dur": 2.327, + "args": { + "External id": 41069,"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": 2338707, "tid": 2379456, + "ts": 6197201095605.798, "dur": 2.131, + "args": { + "External id": 41070,"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": 2338707, "tid": 2379456, + "ts": 6197201095651.713, "dur": 5.188, + "args": { + "External id": 41071,"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": 2338707, "tid": 2379456, + "ts": 6197201095653.768, "dur": 2.951, + "args": { + "External id": 41072,"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": 2338707, "tid": 2379456, + "ts": 6197201095659.121, "dur": 30.759, + "args": { + "External id": 41073,"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": 2338707, "tid": 2379456, + "ts": 6197201095664.985, "dur": 2.043, + "args": { + "External id": 41074,"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": 2338707, "tid": 2379456, + "ts": 6197201095691.373, "dur": 2.189, + "args": { + "External id": 41075,"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": 2338707, "tid": 2379456, + "ts": 6197201095692.591, "dur": 0.887, + "args": { + "External id": 41076,"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": 2338707, "tid": 2379456, + "ts": 6197201095694.691, "dur": 31.760, + "args": { + "External id": 41077,"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": 2338707, "tid": 2379456, + "ts": 6197201095697.055, "dur": 0.507, + "args": { + "External id": 41078,"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": 2338707, "tid": 2379456, + "ts": 6197201095803.576, "dur": 27.883, + "args": { + "External id": 41079,"kernel_hash": "cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4", "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/yk/cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4.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": 2338707, "tid": 2379456, + "ts": 6197201095848.871, "dur": 14.986, + "args": { + "External id": 41080,"kernel_hash": "ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg", "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/eu/ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg.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": 2338707, "tid": 2379456, + "ts": 6197201095871.921, "dur": 45.575, + "args": { + "External id": 41081,"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": 2338707, "tid": 2379456, + "ts": 6197201095923.937, "dur": 39.117, + "args": { + "External id": 41082,"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": 2338707, "tid": 2379456, + "ts": 6197201095975.225, "dur": 21.130, + "args": { + "External id": 41083,"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": 2338707, "tid": 2379456, + "ts": 6197201096002.250, "dur": 33.246, + "args": { + "External id": 41084,"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": 2338707, "tid": 2379456, + "ts": 6197201096042.105, "dur": 65.262, + "args": { + "External id": 41085,"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": 2338707, "tid": 2379456, + "ts": 6197201096119.010, "dur": 48.676, + "args": { + "External id": 41086,"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": 2338707, "tid": 2379456, + "ts": 6197201096201.200, "dur": 28.373, + "args": { + "External id": 41087,"kernel_hash": "c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/6w/c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7.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": 2338707, "tid": 2379456, + "ts": 6197201096252.513, "dur": 26.010, + "args": { + "External id": 41088,"kernel_hash": "ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx", "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/kj/ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx.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": 2338707, "tid": 2379456, + "ts": 6197201096294.098, "dur": 20.254, + "args": { + "External id": 41089,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197201096330.252, "dur": 14.029, + "args": { + "External id": 41090,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197201096357.678, "dur": 15.077, + "args": { + "External id": 41091,"kernel_hash": "cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/eb/cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b.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": 2338707, "tid": 2379456, + "ts": 6197201096447.033, "dur": 14.948, + "args": { + "External id": 41092,"Record function id": 0, "Ev Idx": 9347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201096450.576, "dur": 10.438, + "args": { + "External id": 41093,"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": 2338707, "tid": 2379456, + "ts": 6197201096454.353, "dur": 5.799, + "args": { + "External id": 41094,"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": 2338707, "tid": 2379456, + "ts": 6197201096456.105, "dur": 3.962, + "args": { + "External id": 41095,"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": 2338707, "tid": 2379456, + "ts": 6197201096465.900, "dur": 5.063, + "args": { + "External id": 41096,"Record function id": 0, "Ev Idx": 9351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201096467.569, "dur": 2.948, + "args": { + "External id": 41097,"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": 2338707, "tid": 2379456, + "ts": 6197201096468.481, "dur": 1.473, + "args": { + "External id": 41098,"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": 2338707, "tid": 2379456, + "ts": 6197201096469.026, "dur": 0.857, + "args": { + "External id": 41099,"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": 2338707, "tid": 2379456, + "ts": 6197201096474.472, "dur": 3.780, + "args": { + "External id": 41100,"Record function id": 0, "Ev Idx": 9355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201096475.372, "dur": 2.460, + "args": { + "External id": 41101,"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": 2338707, "tid": 2379456, + "ts": 6197201096475.863, "dur": 1.484, + "args": { + "External id": 41102,"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": 2338707, "tid": 2379456, + "ts": 6197201096476.295, "dur": 0.954, + "args": { + "External id": 41103,"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": 2338707, "tid": 2379456, + "ts": 6197201096481.526, "dur": 4.230, + "args": { + "External id": 41104,"Record function id": 0, "Ev Idx": 9359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201096482.960, "dur": 2.378, + "args": { + "External id": 41105,"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": 2338707, "tid": 2379456, + "ts": 6197201096483.762, "dur": 1.142, + "args": { + "External id": 41106,"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": 2338707, "tid": 2379456, + "ts": 6197201096484.257, "dur": 0.582, + "args": { + "External id": 41107,"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": 2338707, "tid": 2379456, + "ts": 6197201096488.996, "dur": 3.870, + "args": { + "External id": 41108,"Record function id": 0, "Ev Idx": 9363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201096490.441, "dur": 2.015, + "args": { + "External id": 41109,"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": 2338707, "tid": 2379456, + "ts": 6197201096490.956, "dur": 0.860, + "args": { + "External id": 41110,"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": 2338707, "tid": 2379456, + "ts": 6197201096491.264, "dur": 0.484, + "args": { + "External id": 41111,"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": 2338707, "tid": 2379456, + "ts": 6197201096496.118, "dur": 5.517, + "args": { + "External id": 41112,"Record function id": 0, "Ev Idx": 9367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201096497.063, "dur": 4.160, + "args": { + "External id": 41113,"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": 2338707, "tid": 2379456, + "ts": 6197201096497.613, "dur": 3.149, + "args": { + "External id": 41114,"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": 2338707, "tid": 2379456, + "ts": 6197201096500.242, "dur": 0.441, + "args": { + "External id": 41115,"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": 2338707, "tid": 2379456, + "ts": 6197201096504.941, "dur": 4.154, + "args": { + "External id": 41116,"Record function id": 0, "Ev Idx": 9371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201096506.148, "dur": 2.546, + "args": { + "External id": 41117,"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": 2338707, "tid": 2379456, + "ts": 6197201096506.634, "dur": 1.554, + "args": { + "External id": 41118,"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": 2338707, "tid": 2379456, + "ts": 6197201096507.090, "dur": 1.037, + "args": { + "External id": 41119,"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": 2338707, "tid": 2379456, + "ts": 6197201096512.252, "dur": 3.794, + "args": { + "External id": 41120,"Record function id": 0, "Ev Idx": 9375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201096513.567, "dur": 2.094, + "args": { + "External id": 41121,"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": 2338707, "tid": 2379456, + "ts": 6197201096514.097, "dur": 1.116, + "args": { + "External id": 41122,"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": 2338707, "tid": 2379456, + "ts": 6197201096514.353, "dur": 0.795, + "args": { + "External id": 41123,"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": 2338707, "tid": 2379456, + "ts": 6197201096519.190, "dur": 3.276, + "args": { + "External id": 41124,"Record function id": 0, "Ev Idx": 9379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201096520.241, "dur": 1.823, + "args": { + "External id": 41125,"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": 2338707, "tid": 2379456, + "ts": 6197201096520.731, "dur": 0.855, + "args": { + "External id": 41126,"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": 2338707, "tid": 2379456, + "ts": 6197201096521.085, "dur": 0.435, + "args": { + "External id": 41127,"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": 2338707, "tid": 2379456, + "ts": 6197201096526.872, "dur": 62483.239, + "args": { + "External id": 41128,"Record function id": 0, "Sequence number": 480024, "Fwd thread id": 1, "Ev Idx": 9383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197201096528.219, "dur": 62472.204, + "args": { + "External id": 41129,"Sequence number": 480024, "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": 2338707, "tid": 2379456, "ts": 6197201096528.219, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.14)", "pid": 2338707, "tid": 2379456, + "ts": 6197201096558.157, "dur": 37.024, + "args": { + "External id": 41130,"Record function id": 0, "Ev Idx": 9385 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.14)", "pid": 2338707, "tid": 2379456, + "ts": 6197201096602.659, "dur": 65.726, + "args": { + "External id": 41131,"Record function id": 0, "Ev Idx": 9386 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.14)", "pid": 2338707, "tid": 2379456, + "ts": 6197201096673.953, "dur": 62318.663, + "args": { + "External id": 41132,"Record function id": 0, "Ev Idx": 9387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197201096785.407, "dur": 6.848, + "args": { + "External id": 41133,"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": 2338707, "tid": 2379456, + "ts": 6197201096806.387, "dur": 5.107, + "args": { + "External id": 41134,"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": 2338707, "tid": 2379456, + "ts": 6197201096828.917, "dur": 61257.664, + "args": { + "External id": 41135,"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": 2338707, "tid": 2379456, + "ts": 6197201096842.487, "dur": 61205.504, + "args": { + "External id": 41136,"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": 2338707, "tid": 2379456, + "ts": 6197201096939.492, "dur": 17.788, + "args": { + "External id": 41137,"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": 2338707, "tid": 2379456, + "ts": 6197201096980.830, "dur": 61021.056, + "args": { + "External id": 41138,"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": 2338707, "tid": 2379456, + "ts": 6197201096983.996, "dur": 61016.939, + "args": { + "External id": 41139,"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": 2338707, "tid": 2379456, + "ts": 6197201096988.459, "dur": 8.127, + "args": { + "External id": 41140,"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": 2338707, "tid": 2379456, + "ts": 6197201096998.689, "dur": 60993.801, + "args": { + "External id": 41141,"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": 2338707, "tid": 2379456, + "ts": 6197201158203.632, "dur": 12.137, + "args": { + "External id": 41142,"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": 2338707, "tid": 2379456, + "ts": 6197201158207.204, "dur": 8.140, + "args": { + "External id": 41143,"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": 2338707, "tid": 2379456, + "ts": 6197201158246.568, "dur": 355.707, + "args": { + "External id": 41144,"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": 2338707, "tid": 2379456, + "ts": 6197201158277.894, "dur": 319.380, + "args": { + "External id": 41145,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197201158289.397, "dur": 302.454, + "args": { + "External id": 41146,"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": 2338707, "tid": 2379456, + "ts": 6197201158623.569, "dur": 2.478, + "args": { + "External id": 41147,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2379456, + "ts": 6197201158681.121, "dur": 6.387, + "args": { + "External id": 41148,"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": 2338707, "tid": 2379456, + "ts": 6197201158699.430, "dur": 49.362, + "args": { + "External id": 41149,"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": 2338707, "tid": 2379456, + "ts": 6197201158761.797, "dur": 2.179, + "args": { + "External id": 41150,"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": 2338707, "tid": 2379456, + "ts": 6197201158769.928, "dur": 11.580, + "args": { + "External id": 41151,"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": 2338707, "tid": 2379456, + "ts": 6197201158786.824, "dur": 1.348, + "args": { + "External id": 41152,"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": 2338707, "tid": 2379456, + "ts": 6197201158791.650, "dur": 13.453, + "args": { + "External id": 41153,"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": 2338707, "tid": 2379456, + "ts": 6197201158810.162, "dur": 0.911, + "args": { + "External id": 41154,"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": 2338707, "tid": 2379456, + "ts": 6197201158815.211, "dur": 10.745, + "args": { + "External id": 41155,"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": 2338707, "tid": 2379456, + "ts": 6197201158829.833, "dur": 1.135, + "args": { + "External id": 41156,"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": 2338707, "tid": 2379456, + "ts": 6197201158835.463, "dur": 13.086, + "args": { + "External id": 41157,"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": 2338707, "tid": 2379456, + "ts": 6197201158853.389, "dur": 1.113, + "args": { + "External id": 41158,"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": 2338707, "tid": 2379456, + "ts": 6197201158858.611, "dur": 10.980, + "args": { + "External id": 41159,"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": 2338707, "tid": 2379456, + "ts": 6197201158876.035, "dur": 1.007, + "args": { + "External id": 41160,"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": 2338707, "tid": 2379456, + "ts": 6197201158880.831, "dur": 11.866, + "args": { + "External id": 41161,"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": 2338707, "tid": 2379456, + "ts": 6197201158897.191, "dur": 1.077, + "args": { + "External id": 41162,"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": 2338707, "tid": 2379456, + "ts": 6197201158901.858, "dur": 10.376, + "args": { + "External id": 41163,"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": 2338707, "tid": 2379456, + "ts": 6197201158915.919, "dur": 0.712, + "args": { + "External id": 41164,"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": 2338707, "tid": 2379456, + "ts": 6197201158922.600, "dur": 12.635, + "args": { + "External id": 41165,"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": 2338707, "tid": 2379456, + "ts": 6197201159026.287, "dur": 2877.853, + "args": { + "External id": 41166,"Record function id": 0, "Ev Idx": 9421 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.13)", "pid": 2338707, "tid": 2379456, + "ts": 6197201159045.870, "dur": 1087.381, + "args": { + "External id": 41167,"Record function id": 0, "Ev Idx": 9422 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.13)", "pid": 2338707, "tid": 2379456, + "ts": 6197201159095.969, "dur": 334.967, + "args": { + "External id": 41168,"Record function id": 0, "Ev Idx": 9423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6197201159193.138, "dur": 5.882, + "args": { + "External id": 41169,"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": 2338707, "tid": 2379456, + "ts": 6197201159202.731, "dur": 0.947, + "args": { + "External id": 41170,"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": 2338707, "tid": 2379456, + "ts": 6197201159205.454, "dur": 0.885, + "args": { + "External id": 41171,"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": 2338707, "tid": 2379456, + "ts": 6197201159208.184, "dur": 0.927, + "args": { + "External id": 41172,"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": 2338707, "tid": 2379456, + "ts": 6197201159210.666, "dur": 0.893, + "args": { + "External id": 41173,"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": 2338707, "tid": 2379456, + "ts": 6197201159213.036, "dur": 0.801, + "args": { + "External id": 41174,"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": 2338707, "tid": 2379456, + "ts": 6197201159215.257, "dur": 0.905, + "args": { + "External id": 41175,"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": 2338707, "tid": 2379456, + "ts": 6197201159219.800, "dur": 1.107, + "args": { + "External id": 41176,"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": 2338707, "tid": 2379456, + "ts": 6197201159222.693, "dur": 1.025, + "args": { + "External id": 41177,"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": 2338707, "tid": 2379456, + "ts": 6197201159225.409, "dur": 1.215, + "args": { + "External id": 41178,"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": 2338707, "tid": 2379456, + "ts": 6197201159243.022, "dur": 154.314, + "args": { + "External id": 41179,"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": 2338707, "tid": 2379456, + "ts": 6197201159258.909, "dur": 133.943, + "args": { + "External id": 41180,"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": 2338707, "tid": 2379456, + "ts": 6197201159276.576, "dur": 23.880, + "args": { + "External id": 41181,"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": 2338707, "tid": 2379456, + "ts": 6197201159303.839, "dur": 61.057, + "args": { + "External id": 41182,"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": 2338707, "tid": 2379456, + "ts": 6197201159306.415, "dur": 58.066, + "args": { + "External id": 41183,"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": 2338707, "tid": 2379456, + "ts": 6197201159310.217, "dur": 5.733, + "args": { + "External id": 41184,"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": 2338707, "tid": 2379456, + "ts": 6197201159317.755, "dur": 45.630, + "args": { + "External id": 41185,"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": 2338707, "tid": 2379456, + "ts": 6197201159518.097, "dur": 608.294, + "args": { + "External id": 41186,"Record function id": 0, "Ev Idx": 9441 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.12)", "pid": 2338707, "tid": 2379456, + "ts": 6197201159532.965, "dur": 580.396, + "args": { + "External id": 41187,"Record function id": 0, "Ev Idx": 9442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197201159592.099, "dur": 4.713, + "args": { + "External id": 41188,"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": 2338707, "tid": 2379456, + "ts": 6197201159610.879, "dur": 22.988, + "args": { + "External id": 41189,"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": 2338707, "tid": 2379456, + "ts": 6197201159615.272, "dur": 1.797, + "args": { + "External id": 41190,"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": 2338707, "tid": 2379456, + "ts": 6197201159618.811, "dur": 0.372, + "args": { + "External id": 41191,"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": 2338707, "tid": 2379456, + "ts": 6197201159620.056, "dur": 0.933, + "args": { + "External id": 41192,"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": 2338707, "tid": 2379456, + "ts": 6197201159622.327, "dur": 0.282, + "args": { + "External id": 41193,"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": 2338707, "tid": 2379456, + "ts": 6197201159623.547, "dur": 0.560, + "args": { + "External id": 41194,"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": 2338707, "tid": 2379456, + "ts": 6197201159625.709, "dur": 0.466, + "args": { + "External id": 41195,"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": 2338707, "tid": 2379456, + "ts": 6197201159626.951, "dur": 0.595, + "args": { + "External id": 41196,"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": 2338707, "tid": 2379456, + "ts": 6197201159628.881, "dur": 0.332, + "args": { + "External id": 41197,"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": 2338707, "tid": 2379456, + "ts": 6197201159629.957, "dur": 0.828, + "args": { + "External id": 41198,"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": 2338707, "tid": 2379456, + "ts": 6197201159644.218, "dur": 38.643, + "args": { + "External id": 41199,"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": 2338707, "tid": 2379456, + "ts": 6197201159728.547, "dur": 117.107, + "args": { + "External id": 41200,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2379456, + "ts": 6197201159739.307, "dur": 4.546, + "args": { + "External id": 41201,"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": 2338707, "tid": 2379456, + "ts": 6197201159749.322, "dur": 10.253, + "args": { + "External id": 41202,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2379456, + "ts": 6197201159753.502, "dur": 5.668, + "args": { + "External id": 41203,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2379456, + "ts": 6197201159756.466, "dur": 0.930, + "args": { + "External id": 41204,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197201159766.192, "dur": 27.834, + "args": { + "External id": 41205,"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": 2338707, "tid": 2379456, + "ts": 6197201159768.207, "dur": 0.516, + "args": { + "External id": 41206,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197201159770.447, "dur": 0.646, + "args": { + "External id": 41207,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2379456, + "ts": 6197201159772.080, "dur": 0.420, + "args": { + "External id": 41208,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2379456, + "ts": 6197201159773.515, "dur": 0.748, + "args": { + "External id": 41209,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2379456, + "ts": 6197201159775.372, "dur": 0.491, + "args": { + "External id": 41210,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2379456, + "ts": 6197201159782.353, "dur": 0.610, + "args": { + "External id": 41211,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2379456, + "ts": 6197201159784.307, "dur": 0.545, + "args": { + "External id": 41212,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2379456, + "ts": 6197201159785.858, "dur": 0.866, + "args": { + "External id": 41213,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2379456, + "ts": 6197201159787.743, "dur": 0.228, + "args": { + "External id": 41214,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2379456, + "ts": 6197201159804.034, "dur": 33.753, + "args": { + "External id": 41215,"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": 2338707, "tid": 2379456, + "ts": 6197201159889.554, "dur": 118.774, + "args": { + "External id": 41216,"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": 2338707, "tid": 2379456, + "ts": 6197201159920.298, "dur": 84.565, + "args": { + "External id": 41217,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197201159929.461, "dur": 71.173, + "args": { + "External id": 41218,"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": 2338707, "tid": 2379456, + "ts": 6197201160024.282, "dur": 1.900, + "args": { + "External id": 41219,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197201160140.309, "dur": 1737.383, + "args": { + "External id": 41220,"Sequence number": 480023, "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": 2338707, "tid": 2379456, "ts": 6197201160140.309, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6197201160254.125, "dur": 107.239, + "args": { + "External id": 41221,"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": 2338707, "tid": 2379456, + "ts": 6197201160402.152, "dur": 40.129, + "args": { + "External id": 41222,"kernel_hash": "cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/u7/cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs.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": 2338707, "tid": 2379456, + "ts": 6197201160459.178, "dur": 49.444, + "args": { + "External id": 41223,"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": 2338707, "tid": 2379456, + "ts": 6197201160518.232, "dur": 32.653, + "args": { + "External id": 41224,"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": 2338707, "tid": 2379456, + "ts": 6197201160556.892, "dur": 33.513, + "args": { + "External id": 41225,"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": 2338707, "tid": 2379456, + "ts": 6197201160597.057, "dur": 29.129, + "args": { + "External id": 41226,"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": 2338707, "tid": 2379456, + "ts": 6197201160633.065, "dur": 29.473, + "args": { + "External id": 41227,"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": 2338707, "tid": 2379456, + "ts": 6197201160689.329, "dur": 41.677, + "args": { + "External id": 41228,"kernel_hash": "cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/wm/cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s.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": 2338707, "tid": 2379456, + "ts": 6197201160753.058, "dur": 29.636, + "args": { + "External id": 41229,"kernel_hash": "cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql", "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/qt/cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql.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": 2338707, "tid": 2379456, + "ts": 6197201160807.942, "dur": 20.553, + "args": { + "External id": 41230,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197201160841.521, "dur": 15.422, + "args": { + "External id": 41231,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197201160865.546, "dur": 41.294, + "args": { + "External id": 41232,"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": 2338707, "tid": 2379456, + "ts": 6197201160910.340, "dur": 34.047, + "args": { + "External id": 41233,"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": 2338707, "tid": 2379456, + "ts": 6197201160972.359, "dur": 291.677, + "args": { + "External id": 41234,"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": 2338707, "tid": 2379456, + "ts": 6197201161050.520, "dur": 53.521, + "args": { + "External id": 41235,"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": 2338707, "tid": 2379456, + "ts": 6197201161107.515, "dur": 2.848, + "args": { + "External id": 41236,"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": 2338707, "tid": 2379456, + "ts": 6197201161111.834, "dur": 1.730, + "args": { + "External id": 41237,"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": 2338707, "tid": 2379456, + "ts": 6197201161114.566, "dur": 1.784, + "args": { + "External id": 41238,"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": 2338707, "tid": 2379456, + "ts": 6197201161163.895, "dur": 5.287, + "args": { + "External id": 41239,"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": 2338707, "tid": 2379456, + "ts": 6197201161166.088, "dur": 2.904, + "args": { + "External id": 41240,"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": 2338707, "tid": 2379456, + "ts": 6197201161171.039, "dur": 30.442, + "args": { + "External id": 41241,"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": 2338707, "tid": 2379456, + "ts": 6197201161176.273, "dur": 1.758, + "args": { + "External id": 41242,"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": 2338707, "tid": 2379456, + "ts": 6197201161203.439, "dur": 1.683, + "args": { + "External id": 41243,"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": 2338707, "tid": 2379456, + "ts": 6197201161204.369, "dur": 0.620, + "args": { + "External id": 41244,"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": 2338707, "tid": 2379456, + "ts": 6197201161205.908, "dur": 13.708, + "args": { + "External id": 41245,"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": 2338707, "tid": 2379456, + "ts": 6197201161207.875, "dur": 0.578, + "args": { + "External id": 41246,"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": 2338707, "tid": 2379456, + "ts": 6197201161297.556, "dur": 26.867, + "args": { + "External id": 41247,"kernel_hash": "cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4", "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/yk/cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4.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": 2338707, "tid": 2379456, + "ts": 6197201161346.267, "dur": 16.232, + "args": { + "External id": 41248,"kernel_hash": "ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg", "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/eu/ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg.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": 2338707, "tid": 2379456, + "ts": 6197201161371.369, "dur": 47.177, + "args": { + "External id": 41249,"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": 2338707, "tid": 2379456, + "ts": 6197201161425.306, "dur": 38.714, + "args": { + "External id": 41250,"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": 2338707, "tid": 2379456, + "ts": 6197201161472.118, "dur": 20.675, + "args": { + "External id": 41251,"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": 2338707, "tid": 2379456, + "ts": 6197201161499.195, "dur": 36.069, + "args": { + "External id": 41252,"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": 2338707, "tid": 2379456, + "ts": 6197201161542.056, "dur": 28.490, + "args": { + "External id": 41253,"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": 2338707, "tid": 2379456, + "ts": 6197201161580.961, "dur": 30.752, + "args": { + "External id": 41254,"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": 2338707, "tid": 2379456, + "ts": 6197201161629.386, "dur": 28.056, + "args": { + "External id": 41255,"kernel_hash": "c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/6w/c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7.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": 2338707, "tid": 2379456, + "ts": 6197201161673.944, "dur": 46.408, + "args": { + "External id": 41256,"kernel_hash": "ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx", "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/kj/ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx.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": 2338707, "tid": 2379456, + "ts": 6197201161737.744, "dur": 19.901, + "args": { + "External id": 41257,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197201161774.424, "dur": 29.210, + "args": { + "External id": 41258,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197201161825.797, "dur": 20.448, + "args": { + "External id": 41259,"kernel_hash": "cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/eb/cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b.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": 2338707, "tid": 2379456, + "ts": 6197201161925.515, "dur": 14.943, + "args": { + "External id": 41260,"Record function id": 0, "Ev Idx": 9515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201161928.804, "dur": 10.712, + "args": { + "External id": 41261,"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": 2338707, "tid": 2379456, + "ts": 6197201161932.883, "dur": 5.662, + "args": { + "External id": 41262,"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": 2338707, "tid": 2379456, + "ts": 6197201161934.453, "dur": 4.002, + "args": { + "External id": 41263,"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": 2338707, "tid": 2379456, + "ts": 6197201161944.287, "dur": 4.750, + "args": { + "External id": 41264,"Record function id": 0, "Ev Idx": 9519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201161945.681, "dur": 2.921, + "args": { + "External id": 41265,"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": 2338707, "tid": 2379456, + "ts": 6197201161946.386, "dur": 1.620, + "args": { + "External id": 41266,"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": 2338707, "tid": 2379456, + "ts": 6197201161946.949, "dur": 0.975, + "args": { + "External id": 41267,"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": 2338707, "tid": 2379456, + "ts": 6197201161952.432, "dur": 7.346, + "args": { + "External id": 41268,"Record function id": 0, "Ev Idx": 9523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201161957.189, "dur": 2.157, + "args": { + "External id": 41269,"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": 2338707, "tid": 2379456, + "ts": 6197201161957.662, "dur": 1.262, + "args": { + "External id": 41270,"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": 2338707, "tid": 2379456, + "ts": 6197201161958.164, "dur": 0.694, + "args": { + "External id": 41271,"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": 2338707, "tid": 2379456, + "ts": 6197201161963.036, "dur": 3.247, + "args": { + "External id": 41272,"Record function id": 0, "Ev Idx": 9527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201161964.175, "dur": 1.699, + "args": { + "External id": 41273,"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": 2338707, "tid": 2379456, + "ts": 6197201161964.659, "dur": 0.800, + "args": { + "External id": 41274,"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": 2338707, "tid": 2379456, + "ts": 6197201161964.955, "dur": 0.429, + "args": { + "External id": 41275,"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": 2338707, "tid": 2379456, + "ts": 6197201161969.501, "dur": 5.770, + "args": { + "External id": 41276,"Record function id": 0, "Ev Idx": 9531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201161970.610, "dur": 4.181, + "args": { + "External id": 41277,"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": 2338707, "tid": 2379456, + "ts": 6197201161971.099, "dur": 3.097, + "args": { + "External id": 41278,"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": 2338707, "tid": 2379456, + "ts": 6197201161973.499, "dur": 0.581, + "args": { + "External id": 41279,"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": 2338707, "tid": 2379456, + "ts": 6197201161978.419, "dur": 4.550, + "args": { + "External id": 41280,"Record function id": 0, "Ev Idx": 9535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201161979.866, "dur": 2.676, + "args": { + "External id": 41281,"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": 2338707, "tid": 2379456, + "ts": 6197201161980.570, "dur": 1.326, + "args": { + "External id": 41282,"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": 2338707, "tid": 2379456, + "ts": 6197201161980.857, "dur": 0.963, + "args": { + "External id": 41283,"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": 2338707, "tid": 2379456, + "ts": 6197201161986.184, "dur": 3.736, + "args": { + "External id": 41284,"Record function id": 0, "Ev Idx": 9539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201161987.303, "dur": 2.197, + "args": { + "External id": 41285,"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": 2338707, "tid": 2379456, + "ts": 6197201161987.947, "dur": 1.126, + "args": { + "External id": 41286,"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": 2338707, "tid": 2379456, + "ts": 6197201161988.229, "dur": 0.780, + "args": { + "External id": 41287,"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": 2338707, "tid": 2379456, + "ts": 6197201161993.014, "dur": 4.219, + "args": { + "External id": 41288,"Record function id": 0, "Ev Idx": 9543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201161994.092, "dur": 2.741, + "args": { + "External id": 41289,"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": 2338707, "tid": 2379456, + "ts": 6197201161994.910, "dur": 1.524, + "args": { + "External id": 41290,"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": 2338707, "tid": 2379456, + "ts": 6197201161995.398, "dur": 0.973, + "args": { + "External id": 41291,"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": 2338707, "tid": 2379456, + "ts": 6197201162000.428, "dur": 5.741, + "args": { + "External id": 41292,"Record function id": 0, "Ev Idx": 9547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201162001.519, "dur": 4.261, + "args": { + "External id": 41293,"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": 2338707, "tid": 2379456, + "ts": 6197201162001.984, "dur": 3.115, + "args": { + "External id": 41294,"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": 2338707, "tid": 2379456, + "ts": 6197201162004.353, "dur": 0.657, + "args": { + "External id": 41295,"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": 2338707, "tid": 2379456, + "ts": 6197201162010.506, "dur": 63476.112, + "args": { + "External id": 41296,"Record function id": 0, "Sequence number": 480022, "Fwd thread id": 1, "Ev Idx": 9551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197201162011.927, "dur": 63465.144, + "args": { + "External id": 41297,"Sequence number": 480022, "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": 2338707, "tid": 2379456, "ts": 6197201162011.927, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.13)", "pid": 2338707, "tid": 2379456, + "ts": 6197201162040.731, "dur": 76.587, + "args": { + "External id": 41298,"Record function id": 0, "Ev Idx": 9553 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.13)", "pid": 2338707, "tid": 2379456, + "ts": 6197201162126.445, "dur": 68.289, + "args": { + "External id": 41299,"Record function id": 0, "Ev Idx": 9554 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.13)", "pid": 2338707, "tid": 2379456, + "ts": 6197201162200.168, "dur": 63269.322, + "args": { + "External id": 41300,"Record function id": 0, "Ev Idx": 9555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197201162285.655, "dur": 7.340, + "args": { + "External id": 41301,"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": 2338707, "tid": 2379456, + "ts": 6197201162304.906, "dur": 4.977, + "args": { + "External id": 41302,"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": 2338707, "tid": 2379456, + "ts": 6197201162324.616, "dur": 62196.909, + "args": { + "External id": 41303,"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": 2338707, "tid": 2379456, + "ts": 6197201162337.967, "dur": 62171.121, + "args": { + "External id": 41304,"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": 2338707, "tid": 2379456, + "ts": 6197201162431.620, "dur": 17.120, + "args": { + "External id": 41305,"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": 2338707, "tid": 2379456, + "ts": 6197201162468.887, "dur": 61995.223, + "args": { + "External id": 41306,"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": 2338707, "tid": 2379456, + "ts": 6197201162471.747, "dur": 61991.532, + "args": { + "External id": 41307,"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": 2338707, "tid": 2379456, + "ts": 6197201162476.877, "dur": 11.947, + "args": { + "External id": 41308,"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": 2338707, "tid": 2379456, + "ts": 6197201162492.740, "dur": 61966.168, + "args": { + "External id": 41309,"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": 2338707, "tid": 2379456, + "ts": 6197201224628.498, "dur": 12.312, + "args": { + "External id": 41310,"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": 2338707, "tid": 2379456, + "ts": 6197201224632.363, "dur": 8.130, + "args": { + "External id": 41311,"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": 2338707, "tid": 2379456, + "ts": 6197201224669.762, "dur": 417.874, + "args": { + "External id": 41312,"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": 2338707, "tid": 2379456, + "ts": 6197201224714.788, "dur": 337.095, + "args": { + "External id": 41313,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197201224727.528, "dur": 319.004, + "args": { + "External id": 41314,"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": 2338707, "tid": 2379456, + "ts": 6197201225113.159, "dur": 3.149, + "args": { + "External id": 41315,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2379456, + "ts": 6197201225177.953, "dur": 6.640, + "args": { + "External id": 41316,"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": 2338707, "tid": 2379456, + "ts": 6197201225196.895, "dur": 35.998, + "args": { + "External id": 41317,"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": 2338707, "tid": 2379456, + "ts": 6197201225243.300, "dur": 1.576, + "args": { + "External id": 41318,"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": 2338707, "tid": 2379456, + "ts": 6197201225251.003, "dur": 12.130, + "args": { + "External id": 41319,"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": 2338707, "tid": 2379456, + "ts": 6197201225268.720, "dur": 1.094, + "args": { + "External id": 41320,"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": 2338707, "tid": 2379456, + "ts": 6197201225273.624, "dur": 11.013, + "args": { + "External id": 41321,"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": 2338707, "tid": 2379456, + "ts": 6197201225291.244, "dur": 0.989, + "args": { + "External id": 41322,"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": 2338707, "tid": 2379456, + "ts": 6197201225296.434, "dur": 10.158, + "args": { + "External id": 41323,"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": 2338707, "tid": 2379456, + "ts": 6197201225310.650, "dur": 0.974, + "args": { + "External id": 41324,"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": 2338707, "tid": 2379456, + "ts": 6197201225315.457, "dur": 10.211, + "args": { + "External id": 41325,"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": 2338707, "tid": 2379456, + "ts": 6197201225330.458, "dur": 0.991, + "args": { + "External id": 41326,"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": 2338707, "tid": 2379456, + "ts": 6197201225335.621, "dur": 10.475, + "args": { + "External id": 41327,"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": 2338707, "tid": 2379456, + "ts": 6197201225350.067, "dur": 0.854, + "args": { + "External id": 41328,"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": 2338707, "tid": 2379456, + "ts": 6197201225356.629, "dur": 13.192, + "args": { + "External id": 41329,"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": 2338707, "tid": 2379456, + "ts": 6197201225374.038, "dur": 1.203, + "args": { + "External id": 41330,"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": 2338707, "tid": 2379456, + "ts": 6197201225379.215, "dur": 11.220, + "args": { + "External id": 41331,"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": 2338707, "tid": 2379456, + "ts": 6197201225394.411, "dur": 1.014, + "args": { + "External id": 41332,"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": 2338707, "tid": 2379456, + "ts": 6197201225399.317, "dur": 12.429, + "args": { + "External id": 41333,"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": 2338707, "tid": 2379456, + "ts": 6197201225502.102, "dur": 2921.228, + "args": { + "External id": 41334,"Record function id": 0, "Ev Idx": 9589 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.12)", "pid": 2338707, "tid": 2379456, + "ts": 6197201225522.820, "dur": 1062.082, + "args": { + "External id": 41335,"Record function id": 0, "Ev Idx": 9590 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.12)", "pid": 2338707, "tid": 2379456, + "ts": 6197201225542.133, "dur": 348.596, + "args": { + "External id": 41336,"Record function id": 0, "Ev Idx": 9591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6197201225637.181, "dur": 4.739, + "args": { + "External id": 41337,"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": 2338707, "tid": 2379456, + "ts": 6197201225645.468, "dur": 0.949, + "args": { + "External id": 41338,"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": 2338707, "tid": 2379456, + "ts": 6197201225648.249, "dur": 1.037, + "args": { + "External id": 41339,"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": 2338707, "tid": 2379456, + "ts": 6197201225650.985, "dur": 1.032, + "args": { + "External id": 41340,"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": 2338707, "tid": 2379456, + "ts": 6197201225655.882, "dur": 0.847, + "args": { + "External id": 41341,"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": 2338707, "tid": 2379456, + "ts": 6197201225658.157, "dur": 1.013, + "args": { + "External id": 41342,"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": 2338707, "tid": 2379456, + "ts": 6197201225660.536, "dur": 1.026, + "args": { + "External id": 41343,"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": 2338707, "tid": 2379456, + "ts": 6197201225662.778, "dur": 1.124, + "args": { + "External id": 41344,"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": 2338707, "tid": 2379456, + "ts": 6197201225667.907, "dur": 0.759, + "args": { + "External id": 41345,"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": 2338707, "tid": 2379456, + "ts": 6197201225669.992, "dur": 1.177, + "args": { + "External id": 41346,"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": 2338707, "tid": 2379456, + "ts": 6197201225687.330, "dur": 172.310, + "args": { + "External id": 41347,"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": 2338707, "tid": 2379456, + "ts": 6197201225718.638, "dur": 136.432, + "args": { + "External id": 41348,"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": 2338707, "tid": 2379456, + "ts": 6197201225734.836, "dur": 24.834, + "args": { + "External id": 41349,"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": 2338707, "tid": 2379456, + "ts": 6197201225763.267, "dur": 63.380, + "args": { + "External id": 41350,"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": 2338707, "tid": 2379456, + "ts": 6197201225767.883, "dur": 58.378, + "args": { + "External id": 41351,"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": 2338707, "tid": 2379456, + "ts": 6197201225772.149, "dur": 6.155, + "args": { + "External id": 41352,"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": 2338707, "tid": 2379456, + "ts": 6197201225779.968, "dur": 45.773, + "args": { + "External id": 41353,"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": 2338707, "tid": 2379456, + "ts": 6197201225980.044, "dur": 597.433, + "args": { + "External id": 41354,"Record function id": 0, "Ev Idx": 9609 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.11)", "pid": 2338707, "tid": 2379456, + "ts": 6197201225996.958, "dur": 568.243, + "args": { + "External id": 41355,"Record function id": 0, "Ev Idx": 9610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197201226098.156, "dur": 7.083, + "args": { + "External id": 41356,"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": 2338707, "tid": 2379456, + "ts": 6197201226120.772, "dur": 24.828, + "args": { + "External id": 41357,"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": 2338707, "tid": 2379456, + "ts": 6197201226125.596, "dur": 1.792, + "args": { + "External id": 41358,"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": 2338707, "tid": 2379456, + "ts": 6197201226129.745, "dur": 0.262, + "args": { + "External id": 41359,"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": 2338707, "tid": 2379456, + "ts": 6197201226131.725, "dur": 0.408, + "args": { + "External id": 41360,"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": 2338707, "tid": 2379456, + "ts": 6197201226133.020, "dur": 0.727, + "args": { + "External id": 41361,"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": 2338707, "tid": 2379456, + "ts": 6197201226134.825, "dur": 0.396, + "args": { + "External id": 41362,"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": 2338707, "tid": 2379456, + "ts": 6197201226136.125, "dur": 0.940, + "args": { + "External id": 41363,"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": 2338707, "tid": 2379456, + "ts": 6197201226138.415, "dur": 0.621, + "args": { + "External id": 41364,"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": 2338707, "tid": 2379456, + "ts": 6197201226140.114, "dur": 0.475, + "args": { + "External id": 41365,"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": 2338707, "tid": 2379456, + "ts": 6197201226141.372, "dur": 0.379, + "args": { + "External id": 41366,"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": 2338707, "tid": 2379456, + "ts": 6197201226156.361, "dur": 42.303, + "args": { + "External id": 41367,"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": 2338707, "tid": 2379456, + "ts": 6197201226229.686, "dur": 104.247, + "args": { + "External id": 41368,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2379456, + "ts": 6197201226240.340, "dur": 2.781, + "args": { + "External id": 41369,"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": 2338707, "tid": 2379456, + "ts": 6197201226247.978, "dur": 9.901, + "args": { + "External id": 41370,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2379456, + "ts": 6197201226252.356, "dur": 5.108, + "args": { + "External id": 41371,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2379456, + "ts": 6197201226255.646, "dur": 0.506, + "args": { + "External id": 41372,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197201226264.151, "dur": 22.183, + "args": { + "External id": 41373,"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": 2338707, "tid": 2379456, + "ts": 6197201226265.564, "dur": 0.544, + "args": { + "External id": 41374,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197201226267.736, "dur": 0.625, + "args": { + "External id": 41375,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2379456, + "ts": 6197201226269.539, "dur": 0.472, + "args": { + "External id": 41376,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2379456, + "ts": 6197201226271.108, "dur": 0.290, + "args": { + "External id": 41377,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2379456, + "ts": 6197201226273.132, "dur": 0.519, + "args": { + "External id": 41378,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2379456, + "ts": 6197201226274.538, "dur": 0.361, + "args": { + "External id": 41379,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2379456, + "ts": 6197201226275.920, "dur": 1.008, + "args": { + "External id": 41380,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2379456, + "ts": 6197201226278.209, "dur": 0.356, + "args": { + "External id": 41381,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2379456, + "ts": 6197201226279.649, "dur": 0.535, + "args": { + "External id": 41382,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2379456, + "ts": 6197201226296.154, "dur": 30.506, + "args": { + "External id": 41383,"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": 2338707, "tid": 2379456, + "ts": 6197201226377.949, "dur": 117.556, + "args": { + "External id": 41384,"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": 2338707, "tid": 2379456, + "ts": 6197201226405.379, "dur": 86.956, + "args": { + "External id": 41385,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197201226414.318, "dur": 73.791, + "args": { + "External id": 41386,"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": 2338707, "tid": 2379456, + "ts": 6197201226512.074, "dur": 1.911, + "args": { + "External id": 41387,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197201226591.854, "dur": 1809.396, + "args": { + "External id": 41388,"Sequence number": 480021, "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": 2338707, "tid": 2379456, "ts": 6197201226591.854, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6197201226721.726, "dur": 109.576, + "args": { + "External id": 41389,"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": 2338707, "tid": 2379456, + "ts": 6197201226874.836, "dur": 42.690, + "args": { + "External id": 41390,"kernel_hash": "cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/u7/cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs.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": 2338707, "tid": 2379456, + "ts": 6197201226935.273, "dur": 51.344, + "args": { + "External id": 41391,"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": 2338707, "tid": 2379456, + "ts": 6197201226996.651, "dur": 32.884, + "args": { + "External id": 41392,"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": 2338707, "tid": 2379456, + "ts": 6197201227035.372, "dur": 72.852, + "args": { + "External id": 41393,"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": 2338707, "tid": 2379456, + "ts": 6197201227119.355, "dur": 33.384, + "args": { + "External id": 41394,"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": 2338707, "tid": 2379456, + "ts": 6197201227161.038, "dur": 29.816, + "args": { + "External id": 41395,"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": 2338707, "tid": 2379456, + "ts": 6197201227220.159, "dur": 24.706, + "args": { + "External id": 41396,"kernel_hash": "cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/wm/cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s.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": 2338707, "tid": 2379456, + "ts": 6197201227263.890, "dur": 28.431, + "args": { + "External id": 41397,"kernel_hash": "cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql", "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/qt/cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql.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": 2338707, "tid": 2379456, + "ts": 6197201227315.552, "dur": 21.185, + "args": { + "External id": 41398,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197201227349.521, "dur": 16.527, + "args": { + "External id": 41399,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197201227374.274, "dur": 38.976, + "args": { + "External id": 41400,"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": 2338707, "tid": 2379456, + "ts": 6197201227417.226, "dur": 34.452, + "args": { + "External id": 41401,"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": 2338707, "tid": 2379456, + "ts": 6197201227479.703, "dur": 269.180, + "args": { + "External id": 41402,"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": 2338707, "tid": 2379456, + "ts": 6197201227562.921, "dur": 9.814, + "args": { + "External id": 41403,"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": 2338707, "tid": 2379456, + "ts": 6197201227574.837, "dur": 2.743, + "args": { + "External id": 41404,"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": 2338707, "tid": 2379456, + "ts": 6197201227578.881, "dur": 1.660, + "args": { + "External id": 41405,"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": 2338707, "tid": 2379456, + "ts": 6197201227581.480, "dur": 2.283, + "args": { + "External id": 41406,"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": 2338707, "tid": 2379456, + "ts": 6197201227630.040, "dur": 4.864, + "args": { + "External id": 41407,"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": 2338707, "tid": 2379456, + "ts": 6197201227631.810, "dur": 2.892, + "args": { + "External id": 41408,"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": 2338707, "tid": 2379456, + "ts": 6197201227636.697, "dur": 33.850, + "args": { + "External id": 41409,"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": 2338707, "tid": 2379456, + "ts": 6197201227642.359, "dur": 2.011, + "args": { + "External id": 41410,"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": 2338707, "tid": 2379456, + "ts": 6197201227671.899, "dur": 1.884, + "args": { + "External id": 41411,"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": 2338707, "tid": 2379456, + "ts": 6197201227673.045, "dur": 0.664, + "args": { + "External id": 41412,"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": 2338707, "tid": 2379456, + "ts": 6197201227674.960, "dur": 15.178, + "args": { + "External id": 41413,"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": 2338707, "tid": 2379456, + "ts": 6197201227676.528, "dur": 0.324, + "args": { + "External id": 41414,"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": 2338707, "tid": 2379456, + "ts": 6197201227789.837, "dur": 33.183, + "args": { + "External id": 41415,"kernel_hash": "cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4", "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/yk/cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4.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": 2338707, "tid": 2379456, + "ts": 6197201227841.119, "dur": 18.185, + "args": { + "External id": 41416,"kernel_hash": "ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg", "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/eu/ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg.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": 2338707, "tid": 2379456, + "ts": 6197201227868.096, "dur": 47.547, + "args": { + "External id": 41417,"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": 2338707, "tid": 2379456, + "ts": 6197201227921.191, "dur": 39.021, + "args": { + "External id": 41418,"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": 2338707, "tid": 2379456, + "ts": 6197201227968.489, "dur": 23.754, + "args": { + "External id": 41419,"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": 2338707, "tid": 2379456, + "ts": 6197201227998.146, "dur": 31.582, + "args": { + "External id": 41420,"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": 2338707, "tid": 2379456, + "ts": 6197201228037.039, "dur": 64.744, + "args": { + "External id": 41421,"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": 2338707, "tid": 2379456, + "ts": 6197201228113.056, "dur": 37.275, + "args": { + "External id": 41422,"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": 2338707, "tid": 2379456, + "ts": 6197201228170.781, "dur": 30.016, + "args": { + "External id": 41423,"kernel_hash": "c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/6w/c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7.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": 2338707, "tid": 2379456, + "ts": 6197201228219.022, "dur": 25.888, + "args": { + "External id": 41424,"kernel_hash": "ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx", "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/kj/ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx.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": 2338707, "tid": 2379456, + "ts": 6197201228260.101, "dur": 18.939, + "args": { + "External id": 41425,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197201228308.424, "dur": 15.869, + "args": { + "External id": 41426,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197201228335.675, "dur": 15.051, + "args": { + "External id": 41427,"kernel_hash": "cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/eb/cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b.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": 2338707, "tid": 2379456, + "ts": 6197201228449.732, "dur": 15.262, + "args": { + "External id": 41428,"Record function id": 0, "Ev Idx": 9683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201228453.166, "dur": 10.784, + "args": { + "External id": 41429,"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": 2338707, "tid": 2379456, + "ts": 6197201228457.463, "dur": 5.629, + "args": { + "External id": 41430,"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": 2338707, "tid": 2379456, + "ts": 6197201228458.958, "dur": 4.047, + "args": { + "External id": 41431,"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": 2338707, "tid": 2379456, + "ts": 6197201228469.070, "dur": 4.688, + "args": { + "External id": 41432,"Record function id": 0, "Ev Idx": 9687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201228470.483, "dur": 2.836, + "args": { + "External id": 41433,"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": 2338707, "tid": 2379456, + "ts": 6197201228471.359, "dur": 1.501, + "args": { + "External id": 41434,"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": 2338707, "tid": 2379456, + "ts": 6197201228471.942, "dur": 0.856, + "args": { + "External id": 41435,"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": 2338707, "tid": 2379456, + "ts": 6197201228477.225, "dur": 4.081, + "args": { + "External id": 41436,"Record function id": 0, "Ev Idx": 9691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201228478.528, "dur": 2.344, + "args": { + "External id": 41437,"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": 2338707, "tid": 2379456, + "ts": 6197201228479.005, "dur": 1.457, + "args": { + "External id": 41438,"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": 2338707, "tid": 2379456, + "ts": 6197201228479.688, "dur": 0.691, + "args": { + "External id": 41439,"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": 2338707, "tid": 2379456, + "ts": 6197201228484.472, "dur": 4.066, + "args": { + "External id": 41440,"Record function id": 0, "Ev Idx": 9695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201228485.500, "dur": 2.608, + "args": { + "External id": 41441,"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": 2338707, "tid": 2379456, + "ts": 6197201228486.122, "dur": 1.581, + "args": { + "External id": 41442,"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": 2338707, "tid": 2379456, + "ts": 6197201228486.638, "dur": 0.987, + "args": { + "External id": 41443,"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": 2338707, "tid": 2379456, + "ts": 6197201228491.567, "dur": 3.717, + "args": { + "External id": 41444,"Record function id": 0, "Ev Idx": 9699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201228492.782, "dur": 2.102, + "args": { + "External id": 41445,"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": 2338707, "tid": 2379456, + "ts": 6197201228493.345, "dur": 1.108, + "args": { + "External id": 41446,"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": 2338707, "tid": 2379456, + "ts": 6197201228493.650, "dur": 0.740, + "args": { + "External id": 41447,"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": 2338707, "tid": 2379456, + "ts": 6197201228498.275, "dur": 5.917, + "args": { + "External id": 41448,"Record function id": 0, "Ev Idx": 9703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201228499.370, "dur": 4.387, + "args": { + "External id": 41449,"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": 2338707, "tid": 2379456, + "ts": 6197201228499.990, "dur": 3.229, + "args": { + "External id": 41450,"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": 2338707, "tid": 2379456, + "ts": 6197201228502.526, "dur": 0.576, + "args": { + "External id": 41451,"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": 2338707, "tid": 2379456, + "ts": 6197201228507.493, "dur": 3.331, + "args": { + "External id": 41452,"Record function id": 0, "Ev Idx": 9707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201228508.683, "dur": 1.734, + "args": { + "External id": 41453,"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": 2338707, "tid": 2379456, + "ts": 6197201228509.157, "dur": 0.861, + "args": { + "External id": 41454,"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": 2338707, "tid": 2379456, + "ts": 6197201228509.412, "dur": 0.540, + "args": { + "External id": 41455,"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": 2338707, "tid": 2379456, + "ts": 6197201228514.079, "dur": 6.813, + "args": { + "External id": 41456,"Record function id": 0, "Ev Idx": 9711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201228515.123, "dur": 5.323, + "args": { + "External id": 41457,"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": 2338707, "tid": 2379456, + "ts": 6197201228515.570, "dur": 1.093, + "args": { + "External id": 41458,"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": 2338707, "tid": 2379456, + "ts": 6197201228515.911, "dur": 0.687, + "args": { + "External id": 41459,"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": 2338707, "tid": 2379456, + "ts": 6197201228523.920, "dur": 3.387, + "args": { + "External id": 41460,"Record function id": 0, "Ev Idx": 9715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201228524.981, "dur": 1.931, + "args": { + "External id": 41461,"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": 2338707, "tid": 2379456, + "ts": 6197201228525.403, "dur": 1.005, + "args": { + "External id": 41462,"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": 2338707, "tid": 2379456, + "ts": 6197201228525.768, "dur": 0.575, + "args": { + "External id": 41463,"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": 2338707, "tid": 2379456, + "ts": 6197201228531.137, "dur": 63903.646, + "args": { + "External id": 41464,"Record function id": 0, "Sequence number": 480020, "Fwd thread id": 1, "Ev Idx": 9719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197201228532.487, "dur": 63891.995, + "args": { + "External id": 41465,"Sequence number": 480020, "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": 2338707, "tid": 2379456, "ts": 6197201228532.487, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.12)", "pid": 2338707, "tid": 2379456, + "ts": 6197201228561.978, "dur": 43.839, + "args": { + "External id": 41466,"Record function id": 0, "Ev Idx": 9721 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.12)", "pid": 2338707, "tid": 2379456, + "ts": 6197201228613.324, "dur": 67.110, + "args": { + "External id": 41467,"Record function id": 0, "Ev Idx": 9722 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.12)", "pid": 2338707, "tid": 2379456, + "ts": 6197201228685.887, "dur": 63731.147, + "args": { + "External id": 41468,"Record function id": 0, "Ev Idx": 9723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197201228793.505, "dur": 6.888, + "args": { + "External id": 41469,"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": 2338707, "tid": 2379456, + "ts": 6197201228810.822, "dur": 4.842, + "args": { + "External id": 41470,"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": 2338707, "tid": 2379456, + "ts": 6197201228832.454, "dur": 62594.536, + "args": { + "External id": 41471,"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": 2338707, "tid": 2379456, + "ts": 6197201228846.066, "dur": 62568.364, + "args": { + "External id": 41472,"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": 2338707, "tid": 2379456, + "ts": 6197201228974.540, "dur": 17.829, + "args": { + "External id": 41473,"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": 2338707, "tid": 2379456, + "ts": 6197201229014.075, "dur": 62356.743, + "args": { + "External id": 41474,"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": 2338707, "tid": 2379456, + "ts": 6197201229016.897, "dur": 62352.851, + "args": { + "External id": 41475,"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": 2338707, "tid": 2379456, + "ts": 6197201229021.135, "dur": 8.761, + "args": { + "External id": 41476,"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": 2338707, "tid": 2379456, + "ts": 6197201229032.252, "dur": 62332.748, + "args": { + "External id": 41477,"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": 2338707, "tid": 2379456, + "ts": 6197201291530.807, "dur": 11.685, + "args": { + "External id": 41478,"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": 2338707, "tid": 2379456, + "ts": 6197201291534.389, "dur": 7.651, + "args": { + "External id": 41479,"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": 2338707, "tid": 2379456, + "ts": 6197201291571.764, "dur": 426.090, + "args": { + "External id": 41480,"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": 2338707, "tid": 2379456, + "ts": 6197201291603.721, "dur": 388.619, + "args": { + "External id": 41481,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197201291614.482, "dur": 371.810, + "args": { + "External id": 41482,"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": 2338707, "tid": 2379456, + "ts": 6197201292021.797, "dur": 2.497, + "args": { + "External id": 41483,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2379456, + "ts": 6197201292117.648, "dur": 7.184, + "args": { + "External id": 41484,"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": 2338707, "tid": 2379456, + "ts": 6197201292136.625, "dur": 42.849, + "args": { + "External id": 41485,"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": 2338707, "tid": 2379456, + "ts": 6197201292189.099, "dur": 2.100, + "args": { + "External id": 41486,"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": 2338707, "tid": 2379456, + "ts": 6197201292197.250, "dur": 13.354, + "args": { + "External id": 41487,"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": 2338707, "tid": 2379456, + "ts": 6197201292218.853, "dur": 0.923, + "args": { + "External id": 41488,"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": 2338707, "tid": 2379456, + "ts": 6197201292224.173, "dur": 13.466, + "args": { + "External id": 41489,"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": 2338707, "tid": 2379456, + "ts": 6197201292242.258, "dur": 1.012, + "args": { + "External id": 41490,"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": 2338707, "tid": 2379456, + "ts": 6197201292248.752, "dur": 11.003, + "args": { + "External id": 41491,"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": 2338707, "tid": 2379456, + "ts": 6197201292264.484, "dur": 1.235, + "args": { + "External id": 41492,"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": 2338707, "tid": 2379456, + "ts": 6197201292269.812, "dur": 11.354, + "args": { + "External id": 41493,"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": 2338707, "tid": 2379456, + "ts": 6197201292285.045, "dur": 1.372, + "args": { + "External id": 41494,"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": 2338707, "tid": 2379456, + "ts": 6197201292290.761, "dur": 9.485, + "args": { + "External id": 41495,"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": 2338707, "tid": 2379456, + "ts": 6197201292304.049, "dur": 1.129, + "args": { + "External id": 41496,"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": 2338707, "tid": 2379456, + "ts": 6197201292309.297, "dur": 10.115, + "args": { + "External id": 41497,"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": 2338707, "tid": 2379456, + "ts": 6197201292325.606, "dur": 0.938, + "args": { + "External id": 41498,"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": 2338707, "tid": 2379456, + "ts": 6197201292330.462, "dur": 9.669, + "args": { + "External id": 41499,"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": 2338707, "tid": 2379456, + "ts": 6197201292343.962, "dur": 0.848, + "args": { + "External id": 41500,"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": 2338707, "tid": 2379456, + "ts": 6197201292348.895, "dur": 10.695, + "args": { + "External id": 41501,"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": 2338707, "tid": 2379456, + "ts": 6197201292450.239, "dur": 2894.081, + "args": { + "External id": 41502,"Record function id": 0, "Ev Idx": 9757 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.11)", "pid": 2338707, "tid": 2379456, + "ts": 6197201292470.203, "dur": 1061.991, + "args": { + "External id": 41503,"Record function id": 0, "Ev Idx": 9758 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.11)", "pid": 2338707, "tid": 2379456, + "ts": 6197201292486.288, "dur": 345.630, + "args": { + "External id": 41504,"Record function id": 0, "Ev Idx": 9759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6197201292569.700, "dur": 4.268, + "args": { + "External id": 41505,"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": 2338707, "tid": 2379456, + "ts": 6197201292577.477, "dur": 0.905, + "args": { + "External id": 41506,"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": 2338707, "tid": 2379456, + "ts": 6197201292580.052, "dur": 0.947, + "args": { + "External id": 41507,"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": 2338707, "tid": 2379456, + "ts": 6197201292583.043, "dur": 1.416, + "args": { + "External id": 41508,"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": 2338707, "tid": 2379456, + "ts": 6197201292588.378, "dur": 1.049, + "args": { + "External id": 41509,"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": 2338707, "tid": 2379456, + "ts": 6197201292590.899, "dur": 0.874, + "args": { + "External id": 41510,"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": 2338707, "tid": 2379456, + "ts": 6197201292593.449, "dur": 0.970, + "args": { + "External id": 41511,"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": 2338707, "tid": 2379456, + "ts": 6197201292596.000, "dur": 1.096, + "args": { + "External id": 41512,"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": 2338707, "tid": 2379456, + "ts": 6197201292600.659, "dur": 1.285, + "args": { + "External id": 41513,"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": 2338707, "tid": 2379456, + "ts": 6197201292603.366, "dur": 0.935, + "args": { + "External id": 41514,"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": 2338707, "tid": 2379456, + "ts": 6197201292624.862, "dur": 174.119, + "args": { + "External id": 41515,"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": 2338707, "tid": 2379456, + "ts": 6197201292639.724, "dur": 153.695, + "args": { + "External id": 41516,"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": 2338707, "tid": 2379456, + "ts": 6197201292663.057, "dur": 15.440, + "args": { + "External id": 41517,"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": 2338707, "tid": 2379456, + "ts": 6197201292681.951, "dur": 82.534, + "args": { + "External id": 41518,"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": 2338707, "tid": 2379456, + "ts": 6197201292684.697, "dur": 79.316, + "args": { + "External id": 41519,"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": 2338707, "tid": 2379456, + "ts": 6197201292688.792, "dur": 5.659, + "args": { + "External id": 41520,"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": 2338707, "tid": 2379456, + "ts": 6197201292696.338, "dur": 66.658, + "args": { + "External id": 41521,"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": 2338707, "tid": 2379456, + "ts": 6197201292921.626, "dur": 599.277, + "args": { + "External id": 41522,"Record function id": 0, "Ev Idx": 9777 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.10)", "pid": 2338707, "tid": 2379456, + "ts": 6197201292938.435, "dur": 569.911, + "args": { + "External id": 41523,"Record function id": 0, "Ev Idx": 9778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197201293001.539, "dur": 5.605, + "args": { + "External id": 41524,"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": 2338707, "tid": 2379456, + "ts": 6197201293022.279, "dur": 23.414, + "args": { + "External id": 41525,"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": 2338707, "tid": 2379456, + "ts": 6197201293027.108, "dur": 1.734, + "args": { + "External id": 41526,"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": 2338707, "tid": 2379456, + "ts": 6197201293030.811, "dur": 0.309, + "args": { + "External id": 41527,"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": 2338707, "tid": 2379456, + "ts": 6197201293032.390, "dur": 0.684, + "args": { + "External id": 41528,"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": 2338707, "tid": 2379456, + "ts": 6197201293034.051, "dur": 0.605, + "args": { + "External id": 41529,"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": 2338707, "tid": 2379456, + "ts": 6197201293035.621, "dur": 0.395, + "args": { + "External id": 41530,"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": 2338707, "tid": 2379456, + "ts": 6197201293036.687, "dur": 0.844, + "args": { + "External id": 41531,"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": 2338707, "tid": 2379456, + "ts": 6197201293038.655, "dur": 0.291, + "args": { + "External id": 41532,"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": 2338707, "tid": 2379456, + "ts": 6197201293040.157, "dur": 0.630, + "args": { + "External id": 41533,"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": 2338707, "tid": 2379456, + "ts": 6197201293041.978, "dur": 0.292, + "args": { + "External id": 41534,"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": 2338707, "tid": 2379456, + "ts": 6197201293091.985, "dur": 46.187, + "args": { + "External id": 41535,"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": 2338707, "tid": 2379456, + "ts": 6197201293170.895, "dur": 107.027, + "args": { + "External id": 41536,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2379456, + "ts": 6197201293181.685, "dur": 4.292, + "args": { + "External id": 41537,"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": 2338707, "tid": 2379456, + "ts": 6197201293191.239, "dur": 9.948, + "args": { + "External id": 41538,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2379456, + "ts": 6197201293195.305, "dur": 5.468, + "args": { + "External id": 41539,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2379456, + "ts": 6197201293198.500, "dur": 0.740, + "args": { + "External id": 41540,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197201293207.824, "dur": 20.421, + "args": { + "External id": 41541,"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": 2338707, "tid": 2379456, + "ts": 6197201293209.800, "dur": 0.702, + "args": { + "External id": 41542,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197201293212.168, "dur": 0.390, + "args": { + "External id": 41543,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2379456, + "ts": 6197201293213.314, "dur": 0.735, + "args": { + "External id": 41544,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2379456, + "ts": 6197201293215.126, "dur": 0.403, + "args": { + "External id": 41545,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2379456, + "ts": 6197201293216.322, "dur": 0.446, + "args": { + "External id": 41546,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2379456, + "ts": 6197201293217.958, "dur": 0.322, + "args": { + "External id": 41547,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2379456, + "ts": 6197201293219.227, "dur": 0.649, + "args": { + "External id": 41548,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2379456, + "ts": 6197201293220.712, "dur": 0.199, + "args": { + "External id": 41549,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2379456, + "ts": 6197201293221.587, "dur": 0.639, + "args": { + "External id": 41550,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2379456, + "ts": 6197201293238.985, "dur": 31.439, + "args": { + "External id": 41551,"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": 2338707, "tid": 2379456, + "ts": 6197201293323.971, "dur": 114.297, + "args": { + "External id": 41552,"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": 2338707, "tid": 2379456, + "ts": 6197201293351.859, "dur": 82.860, + "args": { + "External id": 41553,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197201293361.221, "dur": 69.421, + "args": { + "External id": 41554,"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": 2338707, "tid": 2379456, + "ts": 6197201293457.448, "dur": 1.881, + "args": { + "External id": 41555,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197201293539.442, "dur": 1783.199, + "args": { + "External id": 41556,"Sequence number": 480019, "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": 2338707, "tid": 2379456, "ts": 6197201293539.442, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6197201293652.338, "dur": 126.302, + "args": { + "External id": 41557,"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": 2338707, "tid": 2379456, + "ts": 6197201293822.368, "dur": 42.558, + "args": { + "External id": 41558,"kernel_hash": "cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/u7/cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs.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": 2338707, "tid": 2379456, + "ts": 6197201293882.931, "dur": 56.546, + "args": { + "External id": 41559,"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": 2338707, "tid": 2379456, + "ts": 6197201293952.377, "dur": 32.365, + "args": { + "External id": 41560,"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": 2338707, "tid": 2379456, + "ts": 6197201293990.844, "dur": 33.281, + "args": { + "External id": 41561,"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": 2338707, "tid": 2379456, + "ts": 6197201294030.663, "dur": 63.406, + "args": { + "External id": 41562,"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": 2338707, "tid": 2379456, + "ts": 6197201294106.181, "dur": 35.585, + "args": { + "External id": 41563,"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": 2338707, "tid": 2379456, + "ts": 6197201294170.003, "dur": 24.390, + "args": { + "External id": 41564,"kernel_hash": "cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/wm/cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s.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": 2338707, "tid": 2379456, + "ts": 6197201294211.720, "dur": 27.730, + "args": { + "External id": 41565,"kernel_hash": "cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql", "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/qt/cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql.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": 2338707, "tid": 2379456, + "ts": 6197201294259.936, "dur": 28.444, + "args": { + "External id": 41566,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197201294302.943, "dur": 16.237, + "args": { + "External id": 41567,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197201294327.397, "dur": 41.979, + "args": { + "External id": 41568,"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": 2338707, "tid": 2379456, + "ts": 6197201294372.876, "dur": 33.984, + "args": { + "External id": 41569,"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": 2338707, "tid": 2379456, + "ts": 6197201294433.254, "dur": 235.172, + "args": { + "External id": 41570,"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": 2338707, "tid": 2379456, + "ts": 6197201294509.126, "dur": 6.335, + "args": { + "External id": 41571,"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": 2338707, "tid": 2379456, + "ts": 6197201294517.584, "dur": 3.185, + "args": { + "External id": 41572,"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": 2338707, "tid": 2379456, + "ts": 6197201294522.106, "dur": 2.364, + "args": { + "External id": 41573,"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": 2338707, "tid": 2379456, + "ts": 6197201294525.273, "dur": 2.230, + "args": { + "External id": 41574,"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": 2338707, "tid": 2379456, + "ts": 6197201294569.768, "dur": 5.133, + "args": { + "External id": 41575,"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": 2338707, "tid": 2379456, + "ts": 6197201294571.855, "dur": 2.860, + "args": { + "External id": 41576,"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": 2338707, "tid": 2379456, + "ts": 6197201294576.850, "dur": 29.728, + "args": { + "External id": 41577,"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": 2338707, "tid": 2379456, + "ts": 6197201294581.906, "dur": 1.669, + "args": { + "External id": 41578,"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": 2338707, "tid": 2379456, + "ts": 6197201294607.886, "dur": 5.729, + "args": { + "External id": 41579,"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": 2338707, "tid": 2379456, + "ts": 6197201294612.777, "dur": 0.774, + "args": { + "External id": 41580,"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": 2338707, "tid": 2379456, + "ts": 6197201294614.715, "dur": 13.667, + "args": { + "External id": 41581,"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": 2338707, "tid": 2379456, + "ts": 6197201294616.686, "dur": 0.462, + "args": { + "External id": 41582,"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": 2338707, "tid": 2379456, + "ts": 6197201294720.431, "dur": 29.615, + "args": { + "External id": 41583,"kernel_hash": "cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4", "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/yk/cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4.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": 2338707, "tid": 2379456, + "ts": 6197201294770.846, "dur": 17.570, + "args": { + "External id": 41584,"kernel_hash": "ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg", "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/eu/ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg.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": 2338707, "tid": 2379456, + "ts": 6197201294796.976, "dur": 46.138, + "args": { + "External id": 41585,"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": 2338707, "tid": 2379456, + "ts": 6197201294848.992, "dur": 39.312, + "args": { + "External id": 41586,"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": 2338707, "tid": 2379456, + "ts": 6197201294896.563, "dur": 23.118, + "args": { + "External id": 41587,"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": 2338707, "tid": 2379456, + "ts": 6197201294925.332, "dur": 31.761, + "args": { + "External id": 41588,"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": 2338707, "tid": 2379456, + "ts": 6197201294964.184, "dur": 27.716, + "args": { + "External id": 41589,"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": 2338707, "tid": 2379456, + "ts": 6197201294999.018, "dur": 30.264, + "args": { + "External id": 41590,"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": 2338707, "tid": 2379456, + "ts": 6197201295049.972, "dur": 62.764, + "args": { + "External id": 41591,"kernel_hash": "c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/6w/c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7.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": 2338707, "tid": 2379456, + "ts": 6197201295133.249, "dur": 43.590, + "args": { + "External id": 41592,"kernel_hash": "ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx", "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/kj/ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx.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": 2338707, "tid": 2379456, + "ts": 6197201295201.164, "dur": 19.585, + "args": { + "External id": 41593,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197201295240.041, "dur": 20.026, + "args": { + "External id": 41594,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197201295274.016, "dur": 15.527, + "args": { + "External id": 41595,"kernel_hash": "cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/eb/cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b.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": 2338707, "tid": 2379456, + "ts": 6197201295365.838, "dur": 14.877, + "args": { + "External id": 41596,"Record function id": 0, "Ev Idx": 9851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201295369.165, "dur": 10.575, + "args": { + "External id": 41597,"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": 2338707, "tid": 2379456, + "ts": 6197201295373.268, "dur": 5.634, + "args": { + "External id": 41598,"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": 2338707, "tid": 2379456, + "ts": 6197201295374.844, "dur": 3.967, + "args": { + "External id": 41599,"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": 2338707, "tid": 2379456, + "ts": 6197201295384.799, "dur": 5.656, + "args": { + "External id": 41600,"Record function id": 0, "Ev Idx": 9855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201295386.237, "dur": 3.724, + "args": { + "External id": 41601,"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": 2338707, "tid": 2379456, + "ts": 6197201295387.173, "dur": 2.349, + "args": { + "External id": 41602,"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": 2338707, "tid": 2379456, + "ts": 6197201295387.889, "dur": 1.557, + "args": { + "External id": 41603,"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": 2338707, "tid": 2379456, + "ts": 6197201295393.817, "dur": 4.882, + "args": { + "External id": 41604,"Record function id": 0, "Ev Idx": 9859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201295395.024, "dur": 3.235, + "args": { + "External id": 41605,"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": 2338707, "tid": 2379456, + "ts": 6197201295395.813, "dur": 1.787, + "args": { + "External id": 41606,"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": 2338707, "tid": 2379456, + "ts": 6197201295396.614, "dur": 0.896, + "args": { + "External id": 41607,"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": 2338707, "tid": 2379456, + "ts": 6197201295401.978, "dur": 3.553, + "args": { + "External id": 41608,"Record function id": 0, "Ev Idx": 9863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201295403.063, "dur": 2.042, + "args": { + "External id": 41609,"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": 2338707, "tid": 2379456, + "ts": 6197201295403.555, "dur": 1.122, + "args": { + "External id": 41610,"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": 2338707, "tid": 2379456, + "ts": 6197201295404.014, "dur": 0.569, + "args": { + "External id": 41611,"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": 2338707, "tid": 2379456, + "ts": 6197201295408.803, "dur": 4.146, + "args": { + "External id": 41612,"Record function id": 0, "Ev Idx": 9867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201295410.298, "dur": 2.226, + "args": { + "External id": 41613,"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": 2338707, "tid": 2379456, + "ts": 6197201295410.812, "dur": 1.152, + "args": { + "External id": 41614,"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": 2338707, "tid": 2379456, + "ts": 6197201295411.081, "dur": 0.814, + "args": { + "External id": 41615,"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": 2338707, "tid": 2379456, + "ts": 6197201295416.108, "dur": 4.122, + "args": { + "External id": 41616,"Record function id": 0, "Ev Idx": 9871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201295417.133, "dur": 2.686, + "args": { + "External id": 41617,"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": 2338707, "tid": 2379456, + "ts": 6197201295417.932, "dur": 1.453, + "args": { + "External id": 41618,"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": 2338707, "tid": 2379456, + "ts": 6197201295418.474, "dur": 0.844, + "args": { + "External id": 41619,"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": 2338707, "tid": 2379456, + "ts": 6197201295423.613, "dur": 4.073, + "args": { + "External id": 41620,"Record function id": 0, "Ev Idx": 9875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201295424.926, "dur": 2.340, + "args": { + "External id": 41621,"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": 2338707, "tid": 2379456, + "ts": 6197201295425.621, "dur": 1.207, + "args": { + "External id": 41622,"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": 2338707, "tid": 2379456, + "ts": 6197201295426.104, "dur": 0.656, + "args": { + "External id": 41623,"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": 2338707, "tid": 2379456, + "ts": 6197201295430.773, "dur": 6.755, + "args": { + "External id": 41624,"Record function id": 0, "Ev Idx": 9879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201295431.993, "dur": 5.131, + "args": { + "External id": 41625,"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": 2338707, "tid": 2379456, + "ts": 6197201295432.476, "dur": 3.970, + "args": { + "External id": 41626,"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": 2338707, "tid": 2379456, + "ts": 6197201295435.426, "dur": 0.920, + "args": { + "External id": 41627,"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": 2338707, "tid": 2379456, + "ts": 6197201295440.625, "dur": 3.485, + "args": { + "External id": 41628,"Record function id": 0, "Ev Idx": 9883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201295441.653, "dur": 2.030, + "args": { + "External id": 41629,"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": 2338707, "tid": 2379456, + "ts": 6197201295442.128, "dur": 1.000, + "args": { + "External id": 41630,"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": 2338707, "tid": 2379456, + "ts": 6197201295442.416, "dur": 0.646, + "args": { + "External id": 41631,"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": 2338707, "tid": 2379456, + "ts": 6197201295448.123, "dur": 62231.438, + "args": { + "External id": 41632,"Record function id": 0, "Sequence number": 480018, "Fwd thread id": 1, "Ev Idx": 9887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197201295449.617, "dur": 62216.711, + "args": { + "External id": 41633,"Sequence number": 480018, "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": 2338707, "tid": 2379456, "ts": 6197201295449.617, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.11)", "pid": 2338707, "tid": 2379456, + "ts": 6197201295478.073, "dur": 38.387, + "args": { + "External id": 41634,"Record function id": 0, "Ev Idx": 9889 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.11)", "pid": 2338707, "tid": 2379456, + "ts": 6197201295523.877, "dur": 65.374, + "args": { + "External id": 41635,"Record function id": 0, "Ev Idx": 9890 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.11)", "pid": 2338707, "tid": 2379456, + "ts": 6197201295598.548, "dur": 62060.358, + "args": { + "External id": 41636,"Record function id": 0, "Ev Idx": 9891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197201295687.976, "dur": 6.319, + "args": { + "External id": 41637,"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": 2338707, "tid": 2379456, + "ts": 6197201295721.208, "dur": 5.290, + "args": { + "External id": 41638,"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": 2338707, "tid": 2379456, + "ts": 6197201295742.321, "dur": 60982.106, + "args": { + "External id": 41639,"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": 2338707, "tid": 2379456, + "ts": 6197201295756.082, "dur": 60955.321, + "args": { + "External id": 41640,"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": 2338707, "tid": 2379456, + "ts": 6197201295843.732, "dur": 18.757, + "args": { + "External id": 41641,"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": 2338707, "tid": 2379456, + "ts": 6197201295882.440, "dur": 60775.610, + "args": { + "External id": 41642,"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": 2338707, "tid": 2379456, + "ts": 6197201295889.159, "dur": 60767.961, + "args": { + "External id": 41643,"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": 2338707, "tid": 2379456, + "ts": 6197201295894.194, "dur": 9.008, + "args": { + "External id": 41644,"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": 2338707, "tid": 2379456, + "ts": 6197201295905.085, "dur": 60747.108, + "args": { + "External id": 41645,"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": 2338707, "tid": 2379456, + "ts": 6197201356834.323, "dur": 12.120, + "args": { + "External id": 41646,"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": 2338707, "tid": 2379456, + "ts": 6197201356838.059, "dur": 8.049, + "args": { + "External id": 41647,"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": 2338707, "tid": 2379456, + "ts": 6197201356875.677, "dur": 404.117, + "args": { + "External id": 41648,"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": 2338707, "tid": 2379456, + "ts": 6197201356910.699, "dur": 363.450, + "args": { + "External id": 41649,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197201356922.045, "dur": 346.300, + "args": { + "External id": 41650,"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": 2338707, "tid": 2379456, + "ts": 6197201357304.527, "dur": 2.691, + "args": { + "External id": 41651,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2379456, + "ts": 6197201357368.294, "dur": 6.527, + "args": { + "External id": 41652,"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": 2338707, "tid": 2379456, + "ts": 6197201357387.011, "dur": 34.049, + "args": { + "External id": 41653,"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": 2338707, "tid": 2379456, + "ts": 6197201357431.565, "dur": 1.784, + "args": { + "External id": 41654,"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": 2338707, "tid": 2379456, + "ts": 6197201357439.376, "dur": 11.999, + "args": { + "External id": 41655,"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": 2338707, "tid": 2379456, + "ts": 6197201357456.231, "dur": 1.083, + "args": { + "External id": 41656,"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": 2338707, "tid": 2379456, + "ts": 6197201357461.229, "dur": 10.164, + "args": { + "External id": 41657,"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": 2338707, "tid": 2379456, + "ts": 6197201357476.088, "dur": 1.301, + "args": { + "External id": 41658,"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": 2338707, "tid": 2379456, + "ts": 6197201357481.500, "dur": 10.107, + "args": { + "External id": 41659,"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": 2338707, "tid": 2379456, + "ts": 6197201357496.209, "dur": 1.112, + "args": { + "External id": 41660,"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": 2338707, "tid": 2379456, + "ts": 6197201357501.305, "dur": 12.929, + "args": { + "External id": 41661,"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": 2338707, "tid": 2379456, + "ts": 6197201357518.720, "dur": 1.013, + "args": { + "External id": 41662,"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": 2338707, "tid": 2379456, + "ts": 6197201357523.999, "dur": 9.759, + "args": { + "External id": 41663,"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": 2338707, "tid": 2379456, + "ts": 6197201357540.759, "dur": 1.132, + "args": { + "External id": 41664,"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": 2338707, "tid": 2379456, + "ts": 6197201357545.414, "dur": 10.538, + "args": { + "External id": 41665,"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": 2338707, "tid": 2379456, + "ts": 6197201357559.762, "dur": 0.618, + "args": { + "External id": 41666,"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": 2338707, "tid": 2379456, + "ts": 6197201357567.797, "dur": 10.439, + "args": { + "External id": 41667,"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": 2338707, "tid": 2379456, + "ts": 6197201357582.081, "dur": 0.774, + "args": { + "External id": 41668,"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": 2338707, "tid": 2379456, + "ts": 6197201357588.505, "dur": 12.893, + "args": { + "External id": 41669,"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": 2338707, "tid": 2379456, + "ts": 6197201357694.213, "dur": 2890.876, + "args": { + "External id": 41670,"Record function id": 0, "Ev Idx": 9925 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.10)", "pid": 2338707, "tid": 2379456, + "ts": 6197201357731.638, "dur": 1071.250, + "args": { + "External id": 41671,"Record function id": 0, "Ev Idx": 9926 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.10)", "pid": 2338707, "tid": 2379456, + "ts": 6197201357748.861, "dur": 368.830, + "args": { + "External id": 41672,"Record function id": 0, "Ev Idx": 9927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6197201357836.988, "dur": 4.634, + "args": { + "External id": 41673,"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": 2338707, "tid": 2379456, + "ts": 6197201357845.317, "dur": 1.024, + "args": { + "External id": 41674,"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": 2338707, "tid": 2379456, + "ts": 6197201357848.001, "dur": 1.250, + "args": { + "External id": 41675,"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": 2338707, "tid": 2379456, + "ts": 6197201357851.070, "dur": 1.332, + "args": { + "External id": 41676,"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": 2338707, "tid": 2379456, + "ts": 6197201357853.818, "dur": 0.984, + "args": { + "External id": 41677,"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": 2338707, "tid": 2379456, + "ts": 6197201357856.081, "dur": 0.937, + "args": { + "External id": 41678,"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": 2338707, "tid": 2379456, + "ts": 6197201357858.446, "dur": 1.782, + "args": { + "External id": 41679,"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": 2338707, "tid": 2379456, + "ts": 6197201357863.491, "dur": 0.985, + "args": { + "External id": 41680,"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": 2338707, "tid": 2379456, + "ts": 6197201357865.957, "dur": 0.928, + "args": { + "External id": 41681,"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": 2338707, "tid": 2379456, + "ts": 6197201357868.339, "dur": 0.789, + "args": { + "External id": 41682,"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": 2338707, "tid": 2379456, + "ts": 6197201357886.310, "dur": 158.132, + "args": { + "External id": 41683,"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": 2338707, "tid": 2379456, + "ts": 6197201357902.588, "dur": 137.532, + "args": { + "External id": 41684,"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": 2338707, "tid": 2379456, + "ts": 6197201357920.487, "dur": 25.762, + "args": { + "External id": 41685,"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": 2338707, "tid": 2379456, + "ts": 6197201357949.812, "dur": 63.568, + "args": { + "External id": 41686,"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": 2338707, "tid": 2379456, + "ts": 6197201357952.416, "dur": 60.592, + "args": { + "External id": 41687,"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": 2338707, "tid": 2379456, + "ts": 6197201357956.142, "dur": 5.848, + "args": { + "External id": 41688,"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": 2338707, "tid": 2379456, + "ts": 6197201357963.614, "dur": 48.523, + "args": { + "External id": 41689,"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": 2338707, "tid": 2379456, + "ts": 6197201358212.557, "dur": 582.968, + "args": { + "External id": 41690,"Record function id": 0, "Ev Idx": 9945 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.9)", "pid": 2338707, "tid": 2379456, + "ts": 6197201358230.834, "dur": 552.567, + "args": { + "External id": 41691,"Record function id": 0, "Ev Idx": 9946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197201358294.452, "dur": 6.438, + "args": { + "External id": 41692,"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": 2338707, "tid": 2379456, + "ts": 6197201358315.934, "dur": 23.950, + "args": { + "External id": 41693,"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": 2338707, "tid": 2379456, + "ts": 6197201358321.201, "dur": 1.757, + "args": { + "External id": 41694,"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": 2338707, "tid": 2379456, + "ts": 6197201358325.003, "dur": 0.452, + "args": { + "External id": 41695,"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": 2338707, "tid": 2379456, + "ts": 6197201358326.700, "dur": 0.762, + "args": { + "External id": 41696,"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": 2338707, "tid": 2379456, + "ts": 6197201358328.934, "dur": 0.307, + "args": { + "External id": 41697,"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": 2338707, "tid": 2379456, + "ts": 6197201358330.341, "dur": 0.503, + "args": { + "External id": 41698,"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": 2338707, "tid": 2379456, + "ts": 6197201358331.851, "dur": 0.470, + "args": { + "External id": 41699,"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": 2338707, "tid": 2379456, + "ts": 6197201358333.080, "dur": 0.881, + "args": { + "External id": 41700,"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": 2338707, "tid": 2379456, + "ts": 6197201358335.157, "dur": 0.376, + "args": { + "External id": 41701,"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": 2338707, "tid": 2379456, + "ts": 6197201358336.141, "dur": 0.562, + "args": { + "External id": 41702,"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": 2338707, "tid": 2379456, + "ts": 6197201358349.795, "dur": 44.879, + "args": { + "External id": 41703,"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": 2338707, "tid": 2379456, + "ts": 6197201358423.960, "dur": 106.483, + "args": { + "External id": 41704,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2379456, + "ts": 6197201358433.742, "dur": 3.147, + "args": { + "External id": 41705,"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": 2338707, "tid": 2379456, + "ts": 6197201358441.833, "dur": 9.576, + "args": { + "External id": 41706,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2379456, + "ts": 6197201358446.203, "dur": 4.795, + "args": { + "External id": 41707,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2379456, + "ts": 6197201358448.994, "dur": 0.803, + "args": { + "External id": 41708,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197201358460.296, "dur": 21.954, + "args": { + "External id": 41709,"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": 2338707, "tid": 2379456, + "ts": 6197201358462.068, "dur": 0.438, + "args": { + "External id": 41710,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197201358463.699, "dur": 0.697, + "args": { + "External id": 41711,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2379456, + "ts": 6197201358465.499, "dur": 0.395, + "args": { + "External id": 41712,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2379456, + "ts": 6197201358466.759, "dur": 0.643, + "args": { + "External id": 41713,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2379456, + "ts": 6197201358468.748, "dur": 0.484, + "args": { + "External id": 41714,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2379456, + "ts": 6197201358470.451, "dur": 0.713, + "args": { + "External id": 41715,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2379456, + "ts": 6197201358472.024, "dur": 0.453, + "args": { + "External id": 41716,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2379456, + "ts": 6197201358473.515, "dur": 0.822, + "args": { + "External id": 41717,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2379456, + "ts": 6197201358475.630, "dur": 0.570, + "args": { + "External id": 41718,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2379456, + "ts": 6197201358492.252, "dur": 31.179, + "args": { + "External id": 41719,"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": 2338707, "tid": 2379456, + "ts": 6197201358574.843, "dur": 113.885, + "args": { + "External id": 41720,"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": 2338707, "tid": 2379456, + "ts": 6197201358601.949, "dur": 83.272, + "args": { + "External id": 41721,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197201358610.626, "dur": 70.728, + "args": { + "External id": 41722,"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": 2338707, "tid": 2379456, + "ts": 6197201358725.853, "dur": 2.757, + "args": { + "External id": 41723,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197201358810.550, "dur": 1751.669, + "args": { + "External id": 41724,"Sequence number": 480017, "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": 2338707, "tid": 2379456, "ts": 6197201358810.550, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6197201358918.326, "dur": 108.000, + "args": { + "External id": 41725,"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": 2338707, "tid": 2379456, + "ts": 6197201359105.720, "dur": 43.780, + "args": { + "External id": 41726,"kernel_hash": "cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/u7/cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs.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": 2338707, "tid": 2379456, + "ts": 6197201359169.890, "dur": 61.790, + "args": { + "External id": 41727,"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": 2338707, "tid": 2379456, + "ts": 6197201359242.323, "dur": 35.214, + "args": { + "External id": 41728,"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": 2338707, "tid": 2379456, + "ts": 6197201359284.197, "dur": 33.540, + "args": { + "External id": 41729,"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": 2338707, "tid": 2379456, + "ts": 6197201359324.957, "dur": 29.647, + "args": { + "External id": 41730,"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": 2338707, "tid": 2379456, + "ts": 6197201359362.367, "dur": 29.766, + "args": { + "External id": 41731,"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": 2338707, "tid": 2379456, + "ts": 6197201359420.707, "dur": 21.764, + "args": { + "External id": 41732,"kernel_hash": "cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/wm/cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s.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": 2338707, "tid": 2379456, + "ts": 6197201359460.305, "dur": 30.928, + "args": { + "External id": 41733,"kernel_hash": "cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql", "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/qt/cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql.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": 2338707, "tid": 2379456, + "ts": 6197201359514.093, "dur": 22.033, + "args": { + "External id": 41734,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197201359548.307, "dur": 13.191, + "args": { + "External id": 41735,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197201359570.105, "dur": 37.129, + "args": { + "External id": 41736,"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": 2338707, "tid": 2379456, + "ts": 6197201359610.402, "dur": 33.112, + "args": { + "External id": 41737,"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": 2338707, "tid": 2379456, + "ts": 6197201359670.639, "dur": 266.089, + "args": { + "External id": 41738,"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": 2338707, "tid": 2379456, + "ts": 6197201359764.015, "dur": 6.418, + "args": { + "External id": 41739,"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": 2338707, "tid": 2379456, + "ts": 6197201359772.426, "dur": 2.557, + "args": { + "External id": 41740,"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": 2338707, "tid": 2379456, + "ts": 6197201359776.509, "dur": 1.793, + "args": { + "External id": 41741,"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": 2338707, "tid": 2379456, + "ts": 6197201359779.344, "dur": 2.332, + "args": { + "External id": 41742,"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": 2338707, "tid": 2379456, + "ts": 6197201359828.218, "dur": 5.010, + "args": { + "External id": 41743,"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": 2338707, "tid": 2379456, + "ts": 6197201359829.972, "dur": 3.078, + "args": { + "External id": 41744,"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": 2338707, "tid": 2379456, + "ts": 6197201359838.208, "dur": 33.005, + "args": { + "External id": 41745,"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": 2338707, "tid": 2379456, + "ts": 6197201359843.972, "dur": 1.782, + "args": { + "External id": 41746,"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": 2338707, "tid": 2379456, + "ts": 6197201359872.634, "dur": 3.746, + "args": { + "External id": 41747,"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": 2338707, "tid": 2379456, + "ts": 6197201359875.724, "dur": 0.573, + "args": { + "External id": 41748,"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": 2338707, "tid": 2379456, + "ts": 6197201359877.668, "dur": 16.659, + "args": { + "External id": 41749,"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": 2338707, "tid": 2379456, + "ts": 6197201359880.367, "dur": 0.604, + "args": { + "External id": 41750,"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": 2338707, "tid": 2379456, + "ts": 6197201359973.867, "dur": 27.235, + "args": { + "External id": 41751,"kernel_hash": "cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4", "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/yk/cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4.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": 2338707, "tid": 2379456, + "ts": 6197201360017.968, "dur": 16.703, + "args": { + "External id": 41752,"kernel_hash": "ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg", "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/eu/ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg.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": 2338707, "tid": 2379456, + "ts": 6197201360041.992, "dur": 83.135, + "args": { + "External id": 41753,"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": 2338707, "tid": 2379456, + "ts": 6197201360134.426, "dur": 41.922, + "args": { + "External id": 41754,"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": 2338707, "tid": 2379456, + "ts": 6197201360185.444, "dur": 21.611, + "args": { + "External id": 41755,"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": 2338707, "tid": 2379456, + "ts": 6197201360212.878, "dur": 31.637, + "args": { + "External id": 41756,"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": 2338707, "tid": 2379456, + "ts": 6197201360250.822, "dur": 27.839, + "args": { + "External id": 41757,"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": 2338707, "tid": 2379456, + "ts": 6197201360285.150, "dur": 30.363, + "args": { + "External id": 41758,"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": 2338707, "tid": 2379456, + "ts": 6197201360337.383, "dur": 23.653, + "args": { + "External id": 41759,"kernel_hash": "c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/6w/c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7.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": 2338707, "tid": 2379456, + "ts": 6197201360380.168, "dur": 24.647, + "args": { + "External id": 41760,"kernel_hash": "ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx", "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/kj/ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx.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": 2338707, "tid": 2379456, + "ts": 6197201360422.400, "dur": 16.541, + "args": { + "External id": 41761,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197201360466.047, "dur": 23.202, + "args": { + "External id": 41762,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197201360511.455, "dur": 15.829, + "args": { + "External id": 41763,"kernel_hash": "cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/eb/cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b.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": 2338707, "tid": 2379456, + "ts": 6197201360606.985, "dur": 18.909, + "args": { + "External id": 41764,"Record function id": 0, "Ev Idx": 10019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201360613.936, "dur": 10.847, + "args": { + "External id": 41765,"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": 2338707, "tid": 2379456, + "ts": 6197201360617.978, "dur": 5.850, + "args": { + "External id": 41766,"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": 2338707, "tid": 2379456, + "ts": 6197201360619.583, "dur": 4.153, + "args": { + "External id": 41767,"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": 2338707, "tid": 2379456, + "ts": 6197201360629.959, "dur": 4.908, + "args": { + "External id": 41768,"Record function id": 0, "Ev Idx": 10023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201360631.599, "dur": 2.825, + "args": { + "External id": 41769,"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": 2338707, "tid": 2379456, + "ts": 6197201360632.326, "dur": 1.624, + "args": { + "External id": 41770,"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": 2338707, "tid": 2379456, + "ts": 6197201360633.063, "dur": 0.799, + "args": { + "External id": 41771,"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": 2338707, "tid": 2379456, + "ts": 6197201360638.198, "dur": 3.854, + "args": { + "External id": 41772,"Record function id": 0, "Ev Idx": 10027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201360639.504, "dur": 2.129, + "args": { + "External id": 41773,"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": 2338707, "tid": 2379456, + "ts": 6197201360640.180, "dur": 1.011, + "args": { + "External id": 41774,"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": 2338707, "tid": 2379456, + "ts": 6197201360640.583, "dur": 0.543, + "args": { + "External id": 41775,"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": 2338707, "tid": 2379456, + "ts": 6197201360645.279, "dur": 3.391, + "args": { + "External id": 41776,"Record function id": 0, "Ev Idx": 10031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201360646.158, "dur": 2.098, + "args": { + "External id": 41777,"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": 2338707, "tid": 2379456, + "ts": 6197201360646.609, "dur": 1.207, + "args": { + "External id": 41778,"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": 2338707, "tid": 2379456, + "ts": 6197201360647.264, "dur": 0.488, + "args": { + "External id": 41779,"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": 2338707, "tid": 2379456, + "ts": 6197201360651.795, "dur": 4.116, + "args": { + "External id": 41780,"Record function id": 0, "Ev Idx": 10035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201360653.078, "dur": 2.397, + "args": { + "External id": 41781,"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": 2338707, "tid": 2379456, + "ts": 6197201360653.603, "dur": 1.280, + "args": { + "External id": 41782,"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": 2338707, "tid": 2379456, + "ts": 6197201360653.958, "dur": 0.859, + "args": { + "External id": 41783,"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": 2338707, "tid": 2379456, + "ts": 6197201360659.065, "dur": 3.850, + "args": { + "External id": 41784,"Record function id": 0, "Ev Idx": 10039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201360660.249, "dur": 2.262, + "args": { + "External id": 41785,"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": 2338707, "tid": 2379456, + "ts": 6197201360660.716, "dur": 1.366, + "args": { + "External id": 41786,"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": 2338707, "tid": 2379456, + "ts": 6197201360661.204, "dur": 0.814, + "args": { + "External id": 41787,"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": 2338707, "tid": 2379456, + "ts": 6197201360666.265, "dur": 7.573, + "args": { + "External id": 41788,"Record function id": 0, "Ev Idx": 10043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201360667.674, "dur": 5.754, + "args": { + "External id": 41789,"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": 2338707, "tid": 2379456, + "ts": 6197201360668.254, "dur": 4.752, + "args": { + "External id": 41790,"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": 2338707, "tid": 2379456, + "ts": 6197201360668.751, "dur": 4.181, + "args": { + "External id": 41791,"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": 2338707, "tid": 2379456, + "ts": 6197201360676.957, "dur": 3.453, + "args": { + "External id": 41792,"Record function id": 0, "Ev Idx": 10047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201360678.265, "dur": 1.713, + "args": { + "External id": 41793,"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": 2338707, "tid": 2379456, + "ts": 6197201360678.707, "dur": 0.862, + "args": { + "External id": 41794,"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": 2338707, "tid": 2379456, + "ts": 6197201360678.985, "dur": 0.518, + "args": { + "External id": 41795,"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": 2338707, "tid": 2379456, + "ts": 6197201360683.485, "dur": 6.457, + "args": { + "External id": 41796,"Record function id": 0, "Ev Idx": 10051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201360684.780, "dur": 4.740, + "args": { + "External id": 41797,"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": 2338707, "tid": 2379456, + "ts": 6197201360685.232, "dur": 3.866, + "args": { + "External id": 41798,"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": 2338707, "tid": 2379456, + "ts": 6197201360687.629, "dur": 1.357, + "args": { + "External id": 41799,"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": 2338707, "tid": 2379456, + "ts": 6197201360693.563, "dur": 62065.889, + "args": { + "External id": 41800,"Record function id": 0, "Sequence number": 480016, "Fwd thread id": 1, "Ev Idx": 10055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197201360695.150, "dur": 62054.598, + "args": { + "External id": 41801,"Sequence number": 480016, "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": 2338707, "tid": 2379456, "ts": 6197201360695.150, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.10)", "pid": 2338707, "tid": 2379456, + "ts": 6197201360741.228, "dur": 37.637, + "args": { + "External id": 41802,"Record function id": 0, "Ev Idx": 10057 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.10)", "pid": 2338707, "tid": 2379456, + "ts": 6197201360787.072, "dur": 64.564, + "args": { + "External id": 41803,"Record function id": 0, "Ev Idx": 10058 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.10)", "pid": 2338707, "tid": 2379456, + "ts": 6197201360857.035, "dur": 61884.549, + "args": { + "External id": 41804,"Record function id": 0, "Ev Idx": 10059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197201360945.668, "dur": 7.570, + "args": { + "External id": 41805,"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": 2338707, "tid": 2379456, + "ts": 6197201360965.459, "dur": 5.241, + "args": { + "External id": 41806,"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": 2338707, "tid": 2379456, + "ts": 6197201360984.776, "dur": 60849.857, + "args": { + "External id": 41807,"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": 2338707, "tid": 2379456, + "ts": 6197201360998.390, "dur": 60823.862, + "args": { + "External id": 41808,"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": 2338707, "tid": 2379456, + "ts": 6197201361124.084, "dur": 19.355, + "args": { + "External id": 41809,"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": 2338707, "tid": 2379456, + "ts": 6197201361164.174, "dur": 60615.296, + "args": { + "External id": 41810,"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": 2338707, "tid": 2379456, + "ts": 6197201361167.076, "dur": 60611.550, + "args": { + "External id": 41811,"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": 2338707, "tid": 2379456, + "ts": 6197201361174.827, "dur": 10.956, + "args": { + "External id": 41812,"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": 2338707, "tid": 2379456, + "ts": 6197201361188.159, "dur": 60585.763, + "args": { + "External id": 41813,"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": 2338707, "tid": 2379456, + "ts": 6197201421940.423, "dur": 12.350, + "args": { + "External id": 41814,"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": 2338707, "tid": 2379456, + "ts": 6197201421943.912, "dur": 8.238, + "args": { + "External id": 41815,"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": 2338707, "tid": 2379456, + "ts": 6197201421982.887, "dur": 356.055, + "args": { + "External id": 41816,"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": 2338707, "tid": 2379456, + "ts": 6197201422014.774, "dur": 318.598, + "args": { + "External id": 41817,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197201422025.907, "dur": 301.172, + "args": { + "External id": 41818,"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": 2338707, "tid": 2379456, + "ts": 6197201422371.287, "dur": 2.394, + "args": { + "External id": 41819,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2379456, + "ts": 6197201422434.070, "dur": 6.681, + "args": { + "External id": 41820,"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": 2338707, "tid": 2379456, + "ts": 6197201422452.428, "dur": 34.238, + "args": { + "External id": 41821,"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": 2338707, "tid": 2379456, + "ts": 6197201422496.796, "dur": 1.480, + "args": { + "External id": 41822,"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": 2338707, "tid": 2379456, + "ts": 6197201422503.770, "dur": 13.622, + "args": { + "External id": 41823,"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": 2338707, "tid": 2379456, + "ts": 6197201422522.114, "dur": 1.103, + "args": { + "External id": 41824,"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": 2338707, "tid": 2379456, + "ts": 6197201422527.364, "dur": 12.084, + "args": { + "External id": 41825,"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": 2338707, "tid": 2379456, + "ts": 6197201422544.489, "dur": 1.225, + "args": { + "External id": 41826,"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": 2338707, "tid": 2379456, + "ts": 6197201422549.233, "dur": 11.804, + "args": { + "External id": 41827,"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": 2338707, "tid": 2379456, + "ts": 6197201422565.216, "dur": 0.945, + "args": { + "External id": 41828,"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": 2338707, "tid": 2379456, + "ts": 6197201422569.733, "dur": 13.378, + "args": { + "External id": 41829,"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": 2338707, "tid": 2379456, + "ts": 6197201422587.116, "dur": 1.146, + "args": { + "External id": 41830,"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": 2338707, "tid": 2379456, + "ts": 6197201422592.258, "dur": 11.124, + "args": { + "External id": 41831,"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": 2338707, "tid": 2379456, + "ts": 6197201422609.905, "dur": 1.094, + "args": { + "External id": 41832,"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": 2338707, "tid": 2379456, + "ts": 6197201422614.619, "dur": 13.272, + "args": { + "External id": 41833,"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": 2338707, "tid": 2379456, + "ts": 6197201422631.661, "dur": 0.863, + "args": { + "External id": 41834,"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": 2338707, "tid": 2379456, + "ts": 6197201422635.864, "dur": 11.327, + "args": { + "External id": 41835,"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": 2338707, "tid": 2379456, + "ts": 6197201422650.834, "dur": 0.923, + "args": { + "External id": 41836,"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": 2338707, "tid": 2379456, + "ts": 6197201422657.650, "dur": 12.778, + "args": { + "External id": 41837,"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": 2338707, "tid": 2379456, + "ts": 6197201422775.419, "dur": 2792.355, + "args": { + "External id": 41838,"Record function id": 0, "Ev Idx": 10093 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.9)", "pid": 2338707, "tid": 2379456, + "ts": 6197201422796.170, "dur": 1036.032, + "args": { + "External id": 41839,"Record function id": 0, "Ev Idx": 10094 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.9)", "pid": 2338707, "tid": 2379456, + "ts": 6197201422810.704, "dur": 352.550, + "args": { + "External id": 41840,"Record function id": 0, "Ev Idx": 10095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6197201422897.770, "dur": 5.040, + "args": { + "External id": 41841,"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": 2338707, "tid": 2379456, + "ts": 6197201422906.386, "dur": 0.577, + "args": { + "External id": 41842,"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": 2338707, "tid": 2379456, + "ts": 6197201422908.787, "dur": 0.979, + "args": { + "External id": 41843,"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": 2338707, "tid": 2379456, + "ts": 6197201422911.548, "dur": 1.279, + "args": { + "External id": 41844,"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": 2338707, "tid": 2379456, + "ts": 6197201422914.408, "dur": 0.711, + "args": { + "External id": 41845,"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": 2338707, "tid": 2379456, + "ts": 6197201422916.567, "dur": 1.326, + "args": { + "External id": 41846,"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": 2338707, "tid": 2379456, + "ts": 6197201422919.409, "dur": 1.024, + "args": { + "External id": 41847,"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": 2338707, "tid": 2379456, + "ts": 6197201422924.004, "dur": 1.220, + "args": { + "External id": 41848,"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": 2338707, "tid": 2379456, + "ts": 6197201422926.721, "dur": 1.065, + "args": { + "External id": 41849,"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": 2338707, "tid": 2379456, + "ts": 6197201422929.313, "dur": 0.800, + "args": { + "External id": 41850,"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": 2338707, "tid": 2379456, + "ts": 6197201422946.697, "dur": 184.004, + "args": { + "External id": 41851,"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": 2338707, "tid": 2379456, + "ts": 6197201422961.800, "dur": 163.536, + "args": { + "External id": 41852,"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": 2338707, "tid": 2379456, + "ts": 6197201422977.221, "dur": 25.087, + "args": { + "External id": 41853,"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": 2338707, "tid": 2379456, + "ts": 6197201423005.833, "dur": 93.903, + "args": { + "External id": 41854,"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": 2338707, "tid": 2379456, + "ts": 6197201423008.221, "dur": 91.089, + "args": { + "External id": 41855,"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": 2338707, "tid": 2379456, + "ts": 6197201423012.200, "dur": 5.228, + "args": { + "External id": 41856,"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": 2338707, "tid": 2379456, + "ts": 6197201423018.899, "dur": 79.211, + "args": { + "External id": 41857,"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": 2338707, "tid": 2379456, + "ts": 6197201423250.001, "dur": 573.888, + "args": { + "External id": 41858,"Record function id": 0, "Ev Idx": 10113 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.8)", "pid": 2338707, "tid": 2379456, + "ts": 6197201423266.423, "dur": 545.443, + "args": { + "External id": 41859,"Record function id": 0, "Ev Idx": 10114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197201423330.186, "dur": 5.926, + "args": { + "External id": 41860,"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": 2338707, "tid": 2379456, + "ts": 6197201423354.151, "dur": 22.019, + "args": { + "External id": 41861,"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": 2338707, "tid": 2379456, + "ts": 6197201423358.595, "dur": 1.760, + "args": { + "External id": 41862,"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": 2338707, "tid": 2379456, + "ts": 6197201423361.915, "dur": 0.254, + "args": { + "External id": 41863,"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": 2338707, "tid": 2379456, + "ts": 6197201423363.462, "dur": 0.738, + "args": { + "External id": 41864,"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": 2338707, "tid": 2379456, + "ts": 6197201423365.467, "dur": 0.302, + "args": { + "External id": 41865,"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": 2338707, "tid": 2379456, + "ts": 6197201423366.602, "dur": 0.597, + "args": { + "External id": 41866,"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": 2338707, "tid": 2379456, + "ts": 6197201423368.220, "dur": 0.410, + "args": { + "External id": 41867,"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": 2338707, "tid": 2379456, + "ts": 6197201423369.417, "dur": 0.549, + "args": { + "External id": 41868,"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": 2338707, "tid": 2379456, + "ts": 6197201423371.149, "dur": 0.276, + "args": { + "External id": 41869,"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": 2338707, "tid": 2379456, + "ts": 6197201423372.219, "dur": 0.579, + "args": { + "External id": 41870,"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": 2338707, "tid": 2379456, + "ts": 6197201423386.733, "dur": 46.162, + "args": { + "External id": 41871,"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": 2338707, "tid": 2379456, + "ts": 6197201423461.040, "dur": 103.261, + "args": { + "External id": 41872,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2379456, + "ts": 6197201423474.636, "dur": 3.210, + "args": { + "External id": 41873,"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": 2338707, "tid": 2379456, + "ts": 6197201423482.456, "dur": 9.970, + "args": { + "External id": 41874,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2379456, + "ts": 6197201423486.876, "dur": 5.129, + "args": { + "External id": 41875,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2379456, + "ts": 6197201423489.967, "dur": 0.596, + "args": { + "External id": 41876,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197201423498.291, "dur": 20.531, + "args": { + "External id": 41877,"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": 2338707, "tid": 2379456, + "ts": 6197201423499.955, "dur": 0.694, + "args": { + "External id": 41878,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197201423502.141, "dur": 0.405, + "args": { + "External id": 41879,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2379456, + "ts": 6197201423503.615, "dur": 0.513, + "args": { + "External id": 41880,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2379456, + "ts": 6197201423505.193, "dur": 0.539, + "args": { + "External id": 41881,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2379456, + "ts": 6197201423506.542, "dur": 0.727, + "args": { + "External id": 41882,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2379456, + "ts": 6197201423508.472, "dur": 0.384, + "args": { + "External id": 41883,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2379456, + "ts": 6197201423509.365, "dur": 0.678, + "args": { + "External id": 41884,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2379456, + "ts": 6197201423510.996, "dur": 0.408, + "args": { + "External id": 41885,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2379456, + "ts": 6197201423512.064, "dur": 0.675, + "args": { + "External id": 41886,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2379456, + "ts": 6197201423527.524, "dur": 29.608, + "args": { + "External id": 41887,"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": 2338707, "tid": 2379456, + "ts": 6197201423605.939, "dur": 133.141, + "args": { + "External id": 41888,"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": 2338707, "tid": 2379456, + "ts": 6197201423632.803, "dur": 102.186, + "args": { + "External id": 41889,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197201423641.437, "dur": 88.943, + "args": { + "External id": 41890,"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": 2338707, "tid": 2379456, + "ts": 6197201423759.251, "dur": 2.222, + "args": { + "External id": 41891,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197201423839.185, "dur": 1708.469, + "args": { + "External id": 41892,"Sequence number": 480015, "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": 2338707, "tid": 2379456, "ts": 6197201423839.185, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6197201423950.665, "dur": 144.508, + "args": { + "External id": 41893,"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": 2338707, "tid": 2379456, + "ts": 6197201424137.052, "dur": 42.275, + "args": { + "External id": 41894,"kernel_hash": "cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/u7/cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs.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": 2338707, "tid": 2379456, + "ts": 6197201424197.811, "dur": 59.400, + "args": { + "External id": 41895,"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": 2338707, "tid": 2379456, + "ts": 6197201424267.601, "dur": 32.811, + "args": { + "External id": 41896,"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": 2338707, "tid": 2379456, + "ts": 6197201424309.975, "dur": 33.267, + "args": { + "External id": 41897,"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": 2338707, "tid": 2379456, + "ts": 6197201424350.038, "dur": 27.879, + "args": { + "External id": 41898,"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": 2338707, "tid": 2379456, + "ts": 6197201424384.978, "dur": 29.682, + "args": { + "External id": 41899,"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": 2338707, "tid": 2379456, + "ts": 6197201424441.296, "dur": 21.655, + "args": { + "External id": 41900,"kernel_hash": "cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/wm/cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s.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": 2338707, "tid": 2379456, + "ts": 6197201424486.276, "dur": 27.572, + "args": { + "External id": 41901,"kernel_hash": "cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql", "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/qt/cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql.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": 2338707, "tid": 2379456, + "ts": 6197201424533.461, "dur": 19.541, + "args": { + "External id": 41902,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197201424565.435, "dur": 14.719, + "args": { + "External id": 41903,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197201424587.400, "dur": 37.147, + "args": { + "External id": 41904,"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": 2338707, "tid": 2379456, + "ts": 6197201424627.942, "dur": 32.949, + "args": { + "External id": 41905,"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": 2338707, "tid": 2379456, + "ts": 6197201424694.746, "dur": 258.250, + "args": { + "External id": 41906,"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": 2338707, "tid": 2379456, + "ts": 6197201424792.186, "dur": 6.605, + "args": { + "External id": 41907,"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": 2338707, "tid": 2379456, + "ts": 6197201424801.043, "dur": 2.614, + "args": { + "External id": 41908,"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": 2338707, "tid": 2379456, + "ts": 6197201424804.716, "dur": 2.697, + "args": { + "External id": 41909,"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": 2338707, "tid": 2379456, + "ts": 6197201424808.243, "dur": 2.416, + "args": { + "External id": 41910,"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": 2338707, "tid": 2379456, + "ts": 6197201424856.372, "dur": 5.188, + "args": { + "External id": 41911,"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": 2338707, "tid": 2379456, + "ts": 6197201424858.335, "dur": 3.015, + "args": { + "External id": 41912,"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": 2338707, "tid": 2379456, + "ts": 6197201424863.138, "dur": 30.248, + "args": { + "External id": 41913,"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": 2338707, "tid": 2379456, + "ts": 6197201424868.278, "dur": 1.746, + "args": { + "External id": 41914,"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": 2338707, "tid": 2379456, + "ts": 6197201424895.074, "dur": 1.511, + "args": { + "External id": 41915,"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": 2338707, "tid": 2379456, + "ts": 6197201424895.965, "dur": 0.544, + "args": { + "External id": 41916,"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": 2338707, "tid": 2379456, + "ts": 6197201424897.535, "dur": 14.795, + "args": { + "External id": 41917,"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": 2338707, "tid": 2379456, + "ts": 6197201424899.464, "dur": 1.527, + "args": { + "External id": 41918,"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": 2338707, "tid": 2379456, + "ts": 6197201424984.774, "dur": 24.484, + "args": { + "External id": 41919,"kernel_hash": "cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4", "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/yk/cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4.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": 2338707, "tid": 2379456, + "ts": 6197201425028.318, "dur": 18.821, + "args": { + "External id": 41920,"kernel_hash": "ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg", "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/eu/ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg.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": 2338707, "tid": 2379456, + "ts": 6197201425093.994, "dur": 50.782, + "args": { + "External id": 41921,"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": 2338707, "tid": 2379456, + "ts": 6197201425152.610, "dur": 40.789, + "args": { + "External id": 41922,"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": 2338707, "tid": 2379456, + "ts": 6197201425202.802, "dur": 20.454, + "args": { + "External id": 41923,"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": 2338707, "tid": 2379456, + "ts": 6197201425228.759, "dur": 31.648, + "args": { + "External id": 41924,"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": 2338707, "tid": 2379456, + "ts": 6197201425266.870, "dur": 27.711, + "args": { + "External id": 41925,"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": 2338707, "tid": 2379456, + "ts": 6197201425301.501, "dur": 30.346, + "args": { + "External id": 41926,"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": 2338707, "tid": 2379456, + "ts": 6197201425353.192, "dur": 26.109, + "args": { + "External id": 41927,"kernel_hash": "c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/6w/c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7.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": 2338707, "tid": 2379456, + "ts": 6197201425395.397, "dur": 27.396, + "args": { + "External id": 41928,"kernel_hash": "ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx", "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/kj/ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx.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": 2338707, "tid": 2379456, + "ts": 6197201425437.710, "dur": 17.733, + "args": { + "External id": 41929,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197201425472.551, "dur": 14.738, + "args": { + "External id": 41930,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197201425501.061, "dur": 16.403, + "args": { + "External id": 41931,"kernel_hash": "cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/eb/cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b.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": 2338707, "tid": 2379456, + "ts": 6197201425589.320, "dur": 14.370, + "args": { + "External id": 41932,"Record function id": 0, "Ev Idx": 10187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201425592.558, "dur": 10.198, + "args": { + "External id": 41933,"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": 2338707, "tid": 2379456, + "ts": 6197201425596.490, "dur": 5.462, + "args": { + "External id": 41934,"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": 2338707, "tid": 2379456, + "ts": 6197201425597.943, "dur": 3.914, + "args": { + "External id": 41935,"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": 2338707, "tid": 2379456, + "ts": 6197201425607.595, "dur": 4.809, + "args": { + "External id": 41936,"Record function id": 0, "Ev Idx": 10191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201425609.037, "dur": 2.952, + "args": { + "External id": 41937,"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": 2338707, "tid": 2379456, + "ts": 6197201425609.732, "dur": 1.771, + "args": { + "External id": 41938,"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": 2338707, "tid": 2379456, + "ts": 6197201425610.241, "dur": 1.200, + "args": { + "External id": 41939,"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": 2338707, "tid": 2379456, + "ts": 6197201425615.721, "dur": 4.394, + "args": { + "External id": 41940,"Record function id": 0, "Ev Idx": 10195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201425617.023, "dur": 2.668, + "args": { + "External id": 41941,"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": 2338707, "tid": 2379456, + "ts": 6197201425617.599, "dur": 1.653, + "args": { + "External id": 41942,"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": 2338707, "tid": 2379456, + "ts": 6197201425618.235, "dur": 0.939, + "args": { + "External id": 41943,"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": 2338707, "tid": 2379456, + "ts": 6197201425623.335, "dur": 4.173, + "args": { + "External id": 41944,"Record function id": 0, "Ev Idx": 10199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201425624.828, "dur": 2.193, + "args": { + "External id": 41945,"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": 2338707, "tid": 2379456, + "ts": 6197201425625.396, "dur": 1.189, + "args": { + "External id": 41946,"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": 2338707, "tid": 2379456, + "ts": 6197201425626.032, "dur": 0.487, + "args": { + "External id": 41947,"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": 2338707, "tid": 2379456, + "ts": 6197201425630.712, "dur": 4.480, + "args": { + "External id": 41948,"Record function id": 0, "Ev Idx": 10203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201425632.048, "dur": 2.748, + "args": { + "External id": 41949,"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": 2338707, "tid": 2379456, + "ts": 6197201425632.952, "dur": 1.273, + "args": { + "External id": 41950,"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": 2338707, "tid": 2379456, + "ts": 6197201425633.376, "dur": 0.782, + "args": { + "External id": 41951,"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": 2338707, "tid": 2379456, + "ts": 6197201425638.318, "dur": 6.521, + "args": { + "External id": 41952,"Record function id": 0, "Ev Idx": 10207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201425639.646, "dur": 4.752, + "args": { + "External id": 41953,"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": 2338707, "tid": 2379456, + "ts": 6197201425640.151, "dur": 3.829, + "args": { + "External id": 41954,"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": 2338707, "tid": 2379456, + "ts": 6197201425642.746, "dur": 1.122, + "args": { + "External id": 41955,"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": 2338707, "tid": 2379456, + "ts": 6197201425648.101, "dur": 3.818, + "args": { + "External id": 41956,"Record function id": 0, "Ev Idx": 10211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201425649.368, "dur": 2.143, + "args": { + "External id": 41957,"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": 2338707, "tid": 2379456, + "ts": 6197201425649.868, "dur": 1.225, + "args": { + "External id": 41958,"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": 2338707, "tid": 2379456, + "ts": 6197201425650.360, "dur": 0.652, + "args": { + "External id": 41959,"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": 2338707, "tid": 2379456, + "ts": 6197201425655.006, "dur": 4.302, + "args": { + "External id": 41960,"Record function id": 0, "Ev Idx": 10215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201425656.392, "dur": 2.503, + "args": { + "External id": 41961,"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": 2338707, "tid": 2379456, + "ts": 6197201425657.099, "dur": 1.384, + "args": { + "External id": 41962,"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": 2338707, "tid": 2379456, + "ts": 6197201425657.598, "dur": 0.819, + "args": { + "External id": 41963,"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": 2338707, "tid": 2379456, + "ts": 6197201425662.360, "dur": 3.752, + "args": { + "External id": 41964,"Record function id": 0, "Ev Idx": 10219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201425663.686, "dur": 2.033, + "args": { + "External id": 41965,"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": 2338707, "tid": 2379456, + "ts": 6197201425664.187, "dur": 1.035, + "args": { + "External id": 41966,"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": 2338707, "tid": 2379456, + "ts": 6197201425664.536, "dur": 0.619, + "args": { + "External id": 41967,"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": 2338707, "tid": 2379456, + "ts": 6197201425670.095, "dur": 64203.503, + "args": { + "External id": 41968,"Record function id": 0, "Sequence number": 480014, "Fwd thread id": 1, "Ev Idx": 10223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197201425671.318, "dur": 64192.416, + "args": { + "External id": 41969,"Sequence number": 480014, "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": 2338707, "tid": 2379456, "ts": 6197201425671.318, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.9)", "pid": 2338707, "tid": 2379456, + "ts": 6197201425730.437, "dur": 41.001, + "args": { + "External id": 41970,"Record function id": 0, "Ev Idx": 10225 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.9)", "pid": 2338707, "tid": 2379456, + "ts": 6197201425779.742, "dur": 70.583, + "args": { + "External id": 41971,"Record function id": 0, "Ev Idx": 10226 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.9)", "pid": 2338707, "tid": 2379456, + "ts": 6197201425859.343, "dur": 63996.081, + "args": { + "External id": 41972,"Record function id": 0, "Ev Idx": 10227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197201425950.887, "dur": 7.264, + "args": { + "External id": 41973,"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": 2338707, "tid": 2379456, + "ts": 6197201425968.615, "dur": 5.430, + "args": { + "External id": 41974,"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": 2338707, "tid": 2379456, + "ts": 6197201425988.473, "dur": 62862.916, + "args": { + "External id": 41975,"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": 2338707, "tid": 2379456, + "ts": 6197201426002.377, "dur": 62836.618, + "args": { + "External id": 41976,"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": 2338707, "tid": 2379456, + "ts": 6197201426126.705, "dur": 19.457, + "args": { + "External id": 41977,"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": 2338707, "tid": 2379456, + "ts": 6197201426170.072, "dur": 62624.999, + "args": { + "External id": 41978,"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": 2338707, "tid": 2379456, + "ts": 6197201426175.301, "dur": 62618.944, + "args": { + "External id": 41979,"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": 2338707, "tid": 2379456, + "ts": 6197201426179.595, "dur": 8.943, + "args": { + "External id": 41980,"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": 2338707, "tid": 2379456, + "ts": 6197201426190.965, "dur": 62598.723, + "args": { + "External id": 41981,"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": 2338707, "tid": 2379456, + "ts": 6197201488955.699, "dur": 11.789, + "args": { + "External id": 41982,"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": 2338707, "tid": 2379456, + "ts": 6197201488959.341, "dur": 7.738, + "args": { + "External id": 41983,"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": 2338707, "tid": 2379456, + "ts": 6197201488996.138, "dur": 442.039, + "args": { + "External id": 41984,"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": 2338707, "tid": 2379456, + "ts": 6197201489100.472, "dur": 332.140, + "args": { + "External id": 41985,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197201489115.178, "dur": 312.130, + "args": { + "External id": 41986,"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": 2338707, "tid": 2379456, + "ts": 6197201489460.493, "dur": 2.593, + "args": { + "External id": 41987,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2379456, + "ts": 6197201489528.062, "dur": 6.388, + "args": { + "External id": 41988,"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": 2338707, "tid": 2379456, + "ts": 6197201489546.811, "dur": 36.312, + "args": { + "External id": 41989,"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": 2338707, "tid": 2379456, + "ts": 6197201489594.193, "dur": 1.666, + "args": { + "External id": 41990,"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": 2338707, "tid": 2379456, + "ts": 6197201489601.524, "dur": 13.382, + "args": { + "External id": 41991,"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": 2338707, "tid": 2379456, + "ts": 6197201489620.611, "dur": 0.940, + "args": { + "External id": 41992,"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": 2338707, "tid": 2379456, + "ts": 6197201489625.386, "dur": 13.677, + "args": { + "External id": 41993,"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": 2338707, "tid": 2379456, + "ts": 6197201489644.286, "dur": 0.979, + "args": { + "External id": 41994,"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": 2338707, "tid": 2379456, + "ts": 6197201489648.746, "dur": 10.961, + "args": { + "External id": 41995,"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": 2338707, "tid": 2379456, + "ts": 6197201489663.848, "dur": 0.789, + "args": { + "External id": 41996,"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": 2338707, "tid": 2379456, + "ts": 6197201489668.537, "dur": 12.637, + "args": { + "External id": 41997,"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": 2338707, "tid": 2379456, + "ts": 6197201489685.643, "dur": 1.148, + "args": { + "External id": 41998,"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": 2338707, "tid": 2379456, + "ts": 6197201489691.163, "dur": 32.140, + "args": { + "External id": 41999,"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": 2338707, "tid": 2379456, + "ts": 6197201489731.150, "dur": 1.451, + "args": { + "External id": 42000,"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": 2338707, "tid": 2379456, + "ts": 6197201489739.535, "dur": 16.844, + "args": { + "External id": 42001,"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": 2338707, "tid": 2379456, + "ts": 6197201489760.399, "dur": 0.720, + "args": { + "External id": 42002,"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": 2338707, "tid": 2379456, + "ts": 6197201489764.619, "dur": 11.149, + "args": { + "External id": 42003,"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": 2338707, "tid": 2379456, + "ts": 6197201489779.631, "dur": 0.994, + "args": { + "External id": 42004,"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": 2338707, "tid": 2379456, + "ts": 6197201489784.513, "dur": 11.631, + "args": { + "External id": 42005,"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": 2338707, "tid": 2379456, + "ts": 6197201489889.814, "dur": 2881.931, + "args": { + "External id": 42006,"Record function id": 0, "Ev Idx": 10261 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.8)", "pid": 2338707, "tid": 2379456, + "ts": 6197201489912.205, "dur": 1046.678, + "args": { + "External id": 42007,"Record function id": 0, "Ev Idx": 10262 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.8)", "pid": 2338707, "tid": 2379456, + "ts": 6197201489927.995, "dur": 363.155, + "args": { + "External id": 42008,"Record function id": 0, "Ev Idx": 10263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6197201490012.388, "dur": 4.051, + "args": { + "External id": 42009,"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": 2338707, "tid": 2379456, + "ts": 6197201490020.108, "dur": 1.096, + "args": { + "External id": 42010,"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": 2338707, "tid": 2379456, + "ts": 6197201490023.065, "dur": 0.748, + "args": { + "External id": 42011,"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": 2338707, "tid": 2379456, + "ts": 6197201490025.939, "dur": 1.323, + "args": { + "External id": 42012,"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": 2338707, "tid": 2379456, + "ts": 6197201490030.702, "dur": 0.767, + "args": { + "External id": 42013,"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": 2338707, "tid": 2379456, + "ts": 6197201490032.948, "dur": 1.193, + "args": { + "External id": 42014,"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": 2338707, "tid": 2379456, + "ts": 6197201490035.841, "dur": 1.046, + "args": { + "External id": 42015,"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": 2338707, "tid": 2379456, + "ts": 6197201490038.231, "dur": 0.777, + "args": { + "External id": 42016,"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": 2338707, "tid": 2379456, + "ts": 6197201490042.661, "dur": 1.736, + "args": { + "External id": 42017,"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": 2338707, "tid": 2379456, + "ts": 6197201490045.915, "dur": 1.328, + "args": { + "External id": 42018,"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": 2338707, "tid": 2379456, + "ts": 6197201490099.105, "dur": 160.537, + "args": { + "External id": 42019,"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": 2338707, "tid": 2379456, + "ts": 6197201490114.863, "dur": 140.289, + "args": { + "External id": 42020,"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": 2338707, "tid": 2379456, + "ts": 6197201490140.718, "dur": 17.022, + "args": { + "External id": 42021,"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": 2338707, "tid": 2379456, + "ts": 6197201490161.695, "dur": 64.967, + "args": { + "External id": 42022,"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": 2338707, "tid": 2379456, + "ts": 6197201490164.675, "dur": 61.602, + "args": { + "External id": 42023,"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": 2338707, "tid": 2379456, + "ts": 6197201490168.919, "dur": 6.878, + "args": { + "External id": 42024,"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": 2338707, "tid": 2379456, + "ts": 6197201490177.319, "dur": 48.382, + "args": { + "External id": 42025,"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": 2338707, "tid": 2379456, + "ts": 6197201490376.600, "dur": 575.307, + "args": { + "External id": 42026,"Record function id": 0, "Ev Idx": 10281 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.7)", "pid": 2338707, "tid": 2379456, + "ts": 6197201490393.683, "dur": 545.981, + "args": { + "External id": 42027,"Record function id": 0, "Ev Idx": 10282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197201490456.609, "dur": 5.348, + "args": { + "External id": 42028,"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": 2338707, "tid": 2379456, + "ts": 6197201490475.956, "dur": 24.998, + "args": { + "External id": 42029,"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": 2338707, "tid": 2379456, + "ts": 6197201490481.335, "dur": 1.818, + "args": { + "External id": 42030,"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": 2338707, "tid": 2379456, + "ts": 6197201490484.841, "dur": 0.502, + "args": { + "External id": 42031,"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": 2338707, "tid": 2379456, + "ts": 6197201490486.958, "dur": 0.570, + "args": { + "External id": 42032,"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": 2338707, "tid": 2379456, + "ts": 6197201490488.969, "dur": 0.409, + "args": { + "External id": 42033,"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": 2338707, "tid": 2379456, + "ts": 6197201490490.243, "dur": 0.821, + "args": { + "External id": 42034,"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": 2338707, "tid": 2379456, + "ts": 6197201490492.350, "dur": 0.194, + "args": { + "External id": 42035,"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": 2338707, "tid": 2379456, + "ts": 6197201490493.519, "dur": 0.652, + "args": { + "External id": 42036,"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": 2338707, "tid": 2379456, + "ts": 6197201490495.515, "dur": 0.522, + "args": { + "External id": 42037,"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": 2338707, "tid": 2379456, + "ts": 6197201490496.950, "dur": 0.874, + "args": { + "External id": 42038,"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": 2338707, "tid": 2379456, + "ts": 6197201490516.278, "dur": 41.013, + "args": { + "External id": 42039,"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": 2338707, "tid": 2379456, + "ts": 6197201490589.735, "dur": 100.086, + "args": { + "External id": 42040,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2379456, + "ts": 6197201490598.598, "dur": 3.373, + "args": { + "External id": 42041,"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": 2338707, "tid": 2379456, + "ts": 6197201490607.452, "dur": 9.660, + "args": { + "External id": 42042,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2379456, + "ts": 6197201490611.716, "dur": 5.006, + "args": { + "External id": 42043,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2379456, + "ts": 6197201490614.711, "dur": 0.667, + "args": { + "External id": 42044,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197201490623.165, "dur": 20.073, + "args": { + "External id": 42045,"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": 2338707, "tid": 2379456, + "ts": 6197201490625.064, "dur": 0.534, + "args": { + "External id": 42046,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197201490626.882, "dur": 0.587, + "args": { + "External id": 42047,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2379456, + "ts": 6197201490628.218, "dur": 0.474, + "args": { + "External id": 42048,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2379456, + "ts": 6197201490629.638, "dur": 0.593, + "args": { + "External id": 42049,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2379456, + "ts": 6197201490631.093, "dur": 0.598, + "args": { + "External id": 42050,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2379456, + "ts": 6197201490632.960, "dur": 0.184, + "args": { + "External id": 42051,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2379456, + "ts": 6197201490633.668, "dur": 0.743, + "args": { + "External id": 42052,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2379456, + "ts": 6197201490635.429, "dur": 0.273, + "args": { + "External id": 42053,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2379456, + "ts": 6197201490636.424, "dur": 0.585, + "args": { + "External id": 42054,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2379456, + "ts": 6197201490652.417, "dur": 30.608, + "args": { + "External id": 42055,"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": 2338707, "tid": 2379456, + "ts": 6197201490752.862, "dur": 117.564, + "args": { + "External id": 42056,"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": 2338707, "tid": 2379456, + "ts": 6197201490780.411, "dur": 86.658, + "args": { + "External id": 42057,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197201490790.916, "dur": 71.757, + "args": { + "External id": 42058,"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": 2338707, "tid": 2379456, + "ts": 6197201490885.824, "dur": 1.642, + "args": { + "External id": 42059,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197201490965.351, "dur": 1785.754, + "args": { + "External id": 42060,"Sequence number": 480013, "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": 2338707, "tid": 2379456, "ts": 6197201490965.351, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6197201491118.339, "dur": 110.552, + "args": { + "External id": 42061,"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": 2338707, "tid": 2379456, + "ts": 6197201491270.695, "dur": 41.928, + "args": { + "External id": 42062,"kernel_hash": "cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/u7/cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs.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": 2338707, "tid": 2379456, + "ts": 6197201491329.919, "dur": 50.945, + "args": { + "External id": 42063,"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": 2338707, "tid": 2379456, + "ts": 6197201491391.234, "dur": 31.743, + "args": { + "External id": 42064,"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": 2338707, "tid": 2379456, + "ts": 6197201491429.109, "dur": 32.350, + "args": { + "External id": 42065,"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": 2338707, "tid": 2379456, + "ts": 6197201491467.583, "dur": 27.936, + "args": { + "External id": 42066,"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": 2338707, "tid": 2379456, + "ts": 6197201491503.519, "dur": 29.852, + "args": { + "External id": 42067,"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": 2338707, "tid": 2379456, + "ts": 6197201491557.562, "dur": 24.276, + "args": { + "External id": 42068,"kernel_hash": "cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/wm/cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s.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": 2338707, "tid": 2379456, + "ts": 6197201491599.190, "dur": 29.305, + "args": { + "External id": 42069,"kernel_hash": "cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql", "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/qt/cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql.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": 2338707, "tid": 2379456, + "ts": 6197201491650.764, "dur": 20.801, + "args": { + "External id": 42070,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197201491684.480, "dur": 30.056, + "args": { + "External id": 42071,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197201491726.444, "dur": 44.279, + "args": { + "External id": 42072,"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": 2338707, "tid": 2379456, + "ts": 6197201491775.000, "dur": 34.283, + "args": { + "External id": 42073,"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": 2338707, "tid": 2379456, + "ts": 6197201491840.690, "dur": 279.522, + "args": { + "External id": 42074,"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": 2338707, "tid": 2379456, + "ts": 6197201491919.246, "dur": 6.399, + "args": { + "External id": 42075,"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": 2338707, "tid": 2379456, + "ts": 6197201491927.639, "dur": 2.755, + "args": { + "External id": 42076,"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": 2338707, "tid": 2379456, + "ts": 6197201491931.332, "dur": 1.738, + "args": { + "External id": 42077,"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": 2338707, "tid": 2379456, + "ts": 6197201491933.968, "dur": 2.064, + "args": { + "External id": 42078,"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": 2338707, "tid": 2379456, + "ts": 6197201491983.573, "dur": 4.887, + "args": { + "External id": 42079,"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": 2338707, "tid": 2379456, + "ts": 6197201491985.450, "dur": 2.826, + "args": { + "External id": 42080,"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": 2338707, "tid": 2379456, + "ts": 6197201491990.251, "dur": 32.082, + "args": { + "External id": 42081,"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": 2338707, "tid": 2379456, + "ts": 6197201491995.379, "dur": 1.866, + "args": { + "External id": 42082,"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": 2338707, "tid": 2379456, + "ts": 6197201492024.031, "dur": 1.585, + "args": { + "External id": 42083,"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": 2338707, "tid": 2379456, + "ts": 6197201492025.024, "dur": 0.484, + "args": { + "External id": 42084,"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": 2338707, "tid": 2379456, + "ts": 6197201492026.486, "dur": 15.870, + "args": { + "External id": 42085,"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": 2338707, "tid": 2379456, + "ts": 6197201492028.646, "dur": 0.457, + "args": { + "External id": 42086,"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": 2338707, "tid": 2379456, + "ts": 6197201492159.979, "dur": 33.721, + "args": { + "External id": 42087,"kernel_hash": "cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4", "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/yk/cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4.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": 2338707, "tid": 2379456, + "ts": 6197201492211.442, "dur": 17.390, + "args": { + "External id": 42088,"kernel_hash": "ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg", "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/eu/ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg.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": 2338707, "tid": 2379456, + "ts": 6197201492236.834, "dur": 53.660, + "args": { + "External id": 42089,"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": 2338707, "tid": 2379456, + "ts": 6197201492300.108, "dur": 40.507, + "args": { + "External id": 42090,"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": 2338707, "tid": 2379456, + "ts": 6197201492349.046, "dur": 26.704, + "args": { + "External id": 42091,"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": 2338707, "tid": 2379456, + "ts": 6197201492381.885, "dur": 32.816, + "args": { + "External id": 42092,"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": 2338707, "tid": 2379456, + "ts": 6197201492421.425, "dur": 27.982, + "args": { + "External id": 42093,"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": 2338707, "tid": 2379456, + "ts": 6197201492456.163, "dur": 30.656, + "args": { + "External id": 42094,"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": 2338707, "tid": 2379456, + "ts": 6197201492518.823, "dur": 30.931, + "args": { + "External id": 42095,"kernel_hash": "c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/6w/c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7.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": 2338707, "tid": 2379456, + "ts": 6197201492567.507, "dur": 29.119, + "args": { + "External id": 42096,"kernel_hash": "ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx", "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/kj/ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx.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": 2338707, "tid": 2379456, + "ts": 6197201492616.615, "dur": 18.122, + "args": { + "External id": 42097,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197201492649.510, "dur": 19.151, + "args": { + "External id": 42098,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197201492684.490, "dur": 31.633, + "args": { + "External id": 42099,"kernel_hash": "cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/eb/cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b.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": 2338707, "tid": 2379456, + "ts": 6197201492794.724, "dur": 15.228, + "args": { + "External id": 42100,"Record function id": 0, "Ev Idx": 10355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201492797.835, "dur": 11.129, + "args": { + "External id": 42101,"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": 2338707, "tid": 2379456, + "ts": 6197201492802.185, "dur": 5.991, + "args": { + "External id": 42102,"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": 2338707, "tid": 2379456, + "ts": 6197201492803.912, "dur": 4.177, + "args": { + "External id": 42103,"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": 2338707, "tid": 2379456, + "ts": 6197201492813.970, "dur": 4.553, + "args": { + "External id": 42104,"Record function id": 0, "Ev Idx": 10359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201492815.364, "dur": 2.693, + "args": { + "External id": 42105,"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": 2338707, "tid": 2379456, + "ts": 6197201492816.195, "dur": 1.362, + "args": { + "External id": 42106,"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": 2338707, "tid": 2379456, + "ts": 6197201492816.564, "dur": 0.901, + "args": { + "External id": 42107,"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": 2338707, "tid": 2379456, + "ts": 6197201492821.811, "dur": 3.726, + "args": { + "External id": 42108,"Record function id": 0, "Ev Idx": 10363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201492822.933, "dur": 2.164, + "args": { + "External id": 42109,"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": 2338707, "tid": 2379456, + "ts": 6197201492823.461, "dur": 1.205, + "args": { + "External id": 42110,"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": 2338707, "tid": 2379456, + "ts": 6197201492823.977, "dur": 0.586, + "args": { + "External id": 42111,"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": 2338707, "tid": 2379456, + "ts": 6197201492828.821, "dur": 3.283, + "args": { + "External id": 42112,"Record function id": 0, "Ev Idx": 10367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201492829.818, "dur": 1.839, + "args": { + "External id": 42113,"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": 2338707, "tid": 2379456, + "ts": 6197201492830.375, "dur": 0.856, + "args": { + "External id": 42114,"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": 2338707, "tid": 2379456, + "ts": 6197201492830.669, "dur": 0.488, + "args": { + "External id": 42115,"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": 2338707, "tid": 2379456, + "ts": 6197201492835.208, "dur": 3.721, + "args": { + "External id": 42116,"Record function id": 0, "Ev Idx": 10371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201492836.471, "dur": 2.028, + "args": { + "External id": 42117,"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": 2338707, "tid": 2379456, + "ts": 6197201492837.017, "dur": 1.067, + "args": { + "External id": 42118,"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": 2338707, "tid": 2379456, + "ts": 6197201492837.526, "dur": 0.490, + "args": { + "External id": 42119,"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": 2338707, "tid": 2379456, + "ts": 6197201492842.345, "dur": 4.254, + "args": { + "External id": 42120,"Record function id": 0, "Ev Idx": 10375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201492843.552, "dur": 2.618, + "args": { + "External id": 42121,"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": 2338707, "tid": 2379456, + "ts": 6197201492844.335, "dur": 1.410, + "args": { + "External id": 42122,"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": 2338707, "tid": 2379456, + "ts": 6197201492844.826, "dur": 0.856, + "args": { + "External id": 42123,"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": 2338707, "tid": 2379456, + "ts": 6197201492849.893, "dur": 4.158, + "args": { + "External id": 42124,"Record function id": 0, "Ev Idx": 10379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201492851.076, "dur": 2.547, + "args": { + "External id": 42125,"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": 2338707, "tid": 2379456, + "ts": 6197201492851.713, "dur": 1.326, + "args": { + "External id": 42126,"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": 2338707, "tid": 2379456, + "ts": 6197201492852.194, "dur": 0.781, + "args": { + "External id": 42127,"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": 2338707, "tid": 2379456, + "ts": 6197201492857.161, "dur": 5.743, + "args": { + "External id": 42128,"Record function id": 0, "Ev Idx": 10383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201492858.367, "dur": 4.057, + "args": { + "External id": 42129,"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": 2338707, "tid": 2379456, + "ts": 6197201492858.950, "dur": 3.036, + "args": { + "External id": 42130,"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": 2338707, "tid": 2379456, + "ts": 6197201492861.299, "dur": 0.598, + "args": { + "External id": 42131,"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": 2338707, "tid": 2379456, + "ts": 6197201492866.125, "dur": 3.456, + "args": { + "External id": 42132,"Record function id": 0, "Ev Idx": 10387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201492867.058, "dur": 2.109, + "args": { + "External id": 42133,"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": 2338707, "tid": 2379456, + "ts": 6197201492867.505, "dur": 1.093, + "args": { + "External id": 42134,"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": 2338707, "tid": 2379456, + "ts": 6197201492867.776, "dur": 0.741, + "args": { + "External id": 42135,"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": 2338707, "tid": 2379456, + "ts": 6197201492873.686, "dur": 65495.837, + "args": { + "External id": 42136,"Record function id": 0, "Sequence number": 480012, "Fwd thread id": 1, "Ev Idx": 10391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197201492875.275, "dur": 65485.360, + "args": { + "External id": 42137,"Sequence number": 480012, "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": 2338707, "tid": 2379456, "ts": 6197201492875.275, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.8)", "pid": 2338707, "tid": 2379456, + "ts": 6197201492903.571, "dur": 36.965, + "args": { + "External id": 42138,"Record function id": 0, "Ev Idx": 10393 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.8)", "pid": 2338707, "tid": 2379456, + "ts": 6197201492947.961, "dur": 64.387, + "args": { + "External id": 42139,"Record function id": 0, "Ev Idx": 10394 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.8)", "pid": 2338707, "tid": 2379456, + "ts": 6197201493018.046, "dur": 65334.602, + "args": { + "External id": 42140,"Record function id": 0, "Ev Idx": 10395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197201493142.717, "dur": 7.367, + "args": { + "External id": 42141,"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": 2338707, "tid": 2379456, + "ts": 6197201493160.721, "dur": 5.066, + "args": { + "External id": 42142,"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": 2338707, "tid": 2379456, + "ts": 6197201493180.610, "dur": 64235.498, + "args": { + "External id": 42143,"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": 2338707, "tid": 2379456, + "ts": 6197201493194.791, "dur": 64208.257, + "args": { + "External id": 42144,"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": 2338707, "tid": 2379456, + "ts": 6197201493282.600, "dur": 18.208, + "args": { + "External id": 42145,"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": 2338707, "tid": 2379456, + "ts": 6197201493321.367, "dur": 64033.277, + "args": { + "External id": 42146,"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": 2338707, "tid": 2379456, + "ts": 6197201493326.355, "dur": 64027.243, + "args": { + "External id": 42147,"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": 2338707, "tid": 2379456, + "ts": 6197201493330.545, "dur": 8.451, + "args": { + "External id": 42148,"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": 2338707, "tid": 2379456, + "ts": 6197201493340.966, "dur": 64006.911, + "args": { + "External id": 42149,"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": 2338707, "tid": 2379456, + "ts": 6197201557528.918, "dur": 13.542, + "args": { + "External id": 42150,"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": 2338707, "tid": 2379456, + "ts": 6197201557532.945, "dur": 9.121, + "args": { + "External id": 42151,"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": 2338707, "tid": 2379456, + "ts": 6197201557572.089, "dur": 369.451, + "args": { + "External id": 42152,"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": 2338707, "tid": 2379456, + "ts": 6197201557603.338, "dur": 332.830, + "args": { + "External id": 42153,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197201557614.084, "dur": 316.613, + "args": { + "External id": 42154,"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": 2338707, "tid": 2379456, + "ts": 6197201557963.640, "dur": 2.198, + "args": { + "External id": 42155,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2379456, + "ts": 6197201558025.639, "dur": 6.848, + "args": { + "External id": 42156,"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": 2338707, "tid": 2379456, + "ts": 6197201558044.444, "dur": 66.619, + "args": { + "External id": 42157,"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": 2338707, "tid": 2379456, + "ts": 6197201558125.025, "dur": 2.459, + "args": { + "External id": 42158,"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": 2338707, "tid": 2379456, + "ts": 6197201558133.716, "dur": 14.406, + "args": { + "External id": 42159,"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": 2338707, "tid": 2379456, + "ts": 6197201558153.504, "dur": 1.139, + "args": { + "External id": 42160,"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": 2338707, "tid": 2379456, + "ts": 6197201558158.771, "dur": 12.520, + "args": { + "External id": 42161,"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": 2338707, "tid": 2379456, + "ts": 6197201558176.403, "dur": 0.919, + "args": { + "External id": 42162,"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": 2338707, "tid": 2379456, + "ts": 6197201558182.443, "dur": 10.294, + "args": { + "External id": 42163,"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": 2338707, "tid": 2379456, + "ts": 6197201558196.947, "dur": 0.996, + "args": { + "External id": 42164,"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": 2338707, "tid": 2379456, + "ts": 6197201558201.957, "dur": 10.667, + "args": { + "External id": 42165,"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": 2338707, "tid": 2379456, + "ts": 6197201558216.616, "dur": 1.453, + "args": { + "External id": 42166,"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": 2338707, "tid": 2379456, + "ts": 6197201558222.425, "dur": 10.046, + "args": { + "External id": 42167,"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": 2338707, "tid": 2379456, + "ts": 6197201558236.463, "dur": 1.060, + "args": { + "External id": 42168,"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": 2338707, "tid": 2379456, + "ts": 6197201558241.500, "dur": 9.998, + "args": { + "External id": 42169,"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": 2338707, "tid": 2379456, + "ts": 6197201558257.304, "dur": 0.726, + "args": { + "External id": 42170,"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": 2338707, "tid": 2379456, + "ts": 6197201558261.564, "dur": 8.743, + "args": { + "External id": 42171,"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": 2338707, "tid": 2379456, + "ts": 6197201558274.410, "dur": 0.772, + "args": { + "External id": 42172,"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": 2338707, "tid": 2379456, + "ts": 6197201558279.503, "dur": 10.406, + "args": { + "External id": 42173,"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": 2338707, "tid": 2379456, + "ts": 6197201558384.931, "dur": 2892.859, + "args": { + "External id": 42174,"Record function id": 0, "Ev Idx": 10429 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.7)", "pid": 2338707, "tid": 2379456, + "ts": 6197201558408.889, "dur": 1069.355, + "args": { + "External id": 42175,"Record function id": 0, "Ev Idx": 10430 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.7)", "pid": 2338707, "tid": 2379456, + "ts": 6197201558425.526, "dur": 348.237, + "args": { + "External id": 42176,"Record function id": 0, "Ev Idx": 10431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6197201558519.391, "dur": 4.306, + "args": { + "External id": 42177,"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": 2338707, "tid": 2379456, + "ts": 6197201558527.065, "dur": 0.904, + "args": { + "External id": 42178,"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": 2338707, "tid": 2379456, + "ts": 6197201558529.827, "dur": 0.976, + "args": { + "External id": 42179,"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": 2338707, "tid": 2379456, + "ts": 6197201558532.703, "dur": 1.074, + "args": { + "External id": 42180,"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": 2338707, "tid": 2379456, + "ts": 6197201558535.232, "dur": 0.522, + "args": { + "External id": 42181,"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": 2338707, "tid": 2379456, + "ts": 6197201558539.006, "dur": 1.172, + "args": { + "External id": 42182,"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": 2338707, "tid": 2379456, + "ts": 6197201558541.892, "dur": 1.183, + "args": { + "External id": 42183,"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": 2338707, "tid": 2379456, + "ts": 6197201558544.549, "dur": 1.404, + "args": { + "External id": 42184,"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": 2338707, "tid": 2379456, + "ts": 6197201558547.265, "dur": 1.244, + "args": { + "External id": 42185,"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": 2338707, "tid": 2379456, + "ts": 6197201558551.569, "dur": 1.238, + "args": { + "External id": 42186,"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": 2338707, "tid": 2379456, + "ts": 6197201558569.305, "dur": 170.943, + "args": { + "External id": 42187,"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": 2338707, "tid": 2379456, + "ts": 6197201558585.125, "dur": 149.762, + "args": { + "External id": 42188,"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": 2338707, "tid": 2379456, + "ts": 6197201558600.353, "dur": 23.840, + "args": { + "External id": 42189,"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": 2338707, "tid": 2379456, + "ts": 6197201558627.639, "dur": 60.587, + "args": { + "External id": 42190,"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": 2338707, "tid": 2379456, + "ts": 6197201558630.225, "dur": 57.634, + "args": { + "External id": 42191,"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": 2338707, "tid": 2379456, + "ts": 6197201558634.189, "dur": 5.642, + "args": { + "External id": 42192,"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": 2338707, "tid": 2379456, + "ts": 6197201558641.673, "dur": 45.465, + "args": { + "External id": 42193,"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": 2338707, "tid": 2379456, + "ts": 6197201558863.778, "dur": 607.286, + "args": { + "External id": 42194,"Record function id": 0, "Ev Idx": 10449 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.6)", "pid": 2338707, "tid": 2379456, + "ts": 6197201558880.150, "dur": 578.667, + "args": { + "External id": 42195,"Record function id": 0, "Ev Idx": 10450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197201558945.034, "dur": 5.765, + "args": { + "External id": 42196,"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": 2338707, "tid": 2379456, + "ts": 6197201558965.565, "dur": 27.653, + "args": { + "External id": 42197,"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": 2338707, "tid": 2379456, + "ts": 6197201558974.096, "dur": 1.504, + "args": { + "External id": 42198,"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": 2338707, "tid": 2379456, + "ts": 6197201558977.788, "dur": 0.299, + "args": { + "External id": 42199,"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": 2338707, "tid": 2379456, + "ts": 6197201558979.435, "dur": 0.979, + "args": { + "External id": 42200,"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": 2338707, "tid": 2379456, + "ts": 6197201558981.589, "dur": 0.312, + "args": { + "External id": 42201,"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": 2338707, "tid": 2379456, + "ts": 6197201558982.739, "dur": 0.855, + "args": { + "External id": 42202,"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": 2338707, "tid": 2379456, + "ts": 6197201558984.928, "dur": 0.311, + "args": { + "External id": 42203,"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": 2338707, "tid": 2379456, + "ts": 6197201558986.013, "dur": 0.743, + "args": { + "External id": 42204,"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": 2338707, "tid": 2379456, + "ts": 6197201558987.959, "dur": 0.532, + "args": { + "External id": 42205,"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": 2338707, "tid": 2379456, + "ts": 6197201558989.010, "dur": 0.664, + "args": { + "External id": 42206,"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": 2338707, "tid": 2379456, + "ts": 6197201559003.704, "dur": 44.156, + "args": { + "External id": 42207,"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": 2338707, "tid": 2379456, + "ts": 6197201559117.639, "dur": 111.680, + "args": { + "External id": 42208,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2379456, + "ts": 6197201559128.393, "dur": 5.163, + "args": { + "External id": 42209,"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": 2338707, "tid": 2379456, + "ts": 6197201559138.999, "dur": 10.094, + "args": { + "External id": 42210,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2379456, + "ts": 6197201559143.027, "dur": 5.656, + "args": { + "External id": 42211,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2379456, + "ts": 6197201559146.115, "dur": 0.993, + "args": { + "External id": 42212,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197201559155.744, "dur": 22.212, + "args": { + "External id": 42213,"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": 2338707, "tid": 2379456, + "ts": 6197201559157.403, "dur": 0.536, + "args": { + "External id": 42214,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197201559159.245, "dur": 0.526, + "args": { + "External id": 42215,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2379456, + "ts": 6197201559160.636, "dur": 0.372, + "args": { + "External id": 42216,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2379456, + "ts": 6197201559162.415, "dur": 0.450, + "args": { + "External id": 42217,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2379456, + "ts": 6197201559163.891, "dur": 0.406, + "args": { + "External id": 42218,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2379456, + "ts": 6197201559165.350, "dur": 0.722, + "args": { + "External id": 42219,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2379456, + "ts": 6197201559167.355, "dur": 0.696, + "args": { + "External id": 42220,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2379456, + "ts": 6197201559168.901, "dur": 0.824, + "args": { + "External id": 42221,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2379456, + "ts": 6197201559170.861, "dur": 0.816, + "args": { + "External id": 42222,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2379456, + "ts": 6197201559187.909, "dur": 33.703, + "args": { + "External id": 42223,"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": 2338707, "tid": 2379456, + "ts": 6197201559275.416, "dur": 114.883, + "args": { + "External id": 42224,"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": 2338707, "tid": 2379456, + "ts": 6197201559303.764, "dur": 83.167, + "args": { + "External id": 42225,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197201559313.243, "dur": 69.741, + "args": { + "External id": 42226,"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": 2338707, "tid": 2379456, + "ts": 6197201559407.088, "dur": 1.768, + "args": { + "External id": 42227,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197201559485.653, "dur": 1768.027, + "args": { + "External id": 42228,"Sequence number": 480011, "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": 2338707, "tid": 2379456, "ts": 6197201559485.653, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6197201559596.591, "dur": 124.716, + "args": { + "External id": 42229,"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": 2338707, "tid": 2379456, + "ts": 6197201559764.879, "dur": 43.532, + "args": { + "External id": 42230,"kernel_hash": "cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/u7/cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs.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": 2338707, "tid": 2379456, + "ts": 6197201559826.390, "dur": 55.200, + "args": { + "External id": 42231,"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": 2338707, "tid": 2379456, + "ts": 6197201559891.682, "dur": 32.740, + "args": { + "External id": 42232,"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": 2338707, "tid": 2379456, + "ts": 6197201559930.898, "dur": 32.974, + "args": { + "External id": 42233,"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": 2338707, "tid": 2379456, + "ts": 6197201559970.150, "dur": 27.848, + "args": { + "External id": 42234,"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": 2338707, "tid": 2379456, + "ts": 6197201560005.125, "dur": 29.250, + "args": { + "External id": 42235,"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": 2338707, "tid": 2379456, + "ts": 6197201560096.184, "dur": 25.722, + "args": { + "External id": 42236,"kernel_hash": "cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/wm/cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s.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": 2338707, "tid": 2379456, + "ts": 6197201560142.943, "dur": 28.310, + "args": { + "External id": 42237,"kernel_hash": "cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql", "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/qt/cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql.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": 2338707, "tid": 2379456, + "ts": 6197201560193.681, "dur": 18.412, + "args": { + "External id": 42238,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197201560226.484, "dur": 13.295, + "args": { + "External id": 42239,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197201560251.970, "dur": 45.224, + "args": { + "External id": 42240,"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": 2338707, "tid": 2379456, + "ts": 6197201560301.455, "dur": 33.753, + "args": { + "External id": 42241,"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": 2338707, "tid": 2379456, + "ts": 6197201560366.551, "dur": 241.638, + "args": { + "External id": 42242,"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": 2338707, "tid": 2379456, + "ts": 6197201560442.993, "dur": 5.942, + "args": { + "External id": 42243,"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": 2338707, "tid": 2379456, + "ts": 6197201560451.093, "dur": 2.631, + "args": { + "External id": 42244,"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": 2338707, "tid": 2379456, + "ts": 6197201560454.798, "dur": 1.972, + "args": { + "External id": 42245,"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": 2338707, "tid": 2379456, + "ts": 6197201560457.782, "dur": 2.370, + "args": { + "External id": 42246,"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": 2338707, "tid": 2379456, + "ts": 6197201560502.763, "dur": 5.506, + "args": { + "External id": 42247,"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": 2338707, "tid": 2379456, + "ts": 6197201560505.136, "dur": 2.943, + "args": { + "External id": 42248,"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": 2338707, "tid": 2379456, + "ts": 6197201560509.965, "dur": 34.509, + "args": { + "External id": 42249,"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": 2338707, "tid": 2379456, + "ts": 6197201560515.340, "dur": 1.718, + "args": { + "External id": 42250,"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": 2338707, "tid": 2379456, + "ts": 6197201560545.870, "dur": 2.072, + "args": { + "External id": 42251,"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": 2338707, "tid": 2379456, + "ts": 6197201560547.324, "dur": 0.542, + "args": { + "External id": 42252,"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": 2338707, "tid": 2379456, + "ts": 6197201560550.738, "dur": 16.989, + "args": { + "External id": 42253,"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": 2338707, "tid": 2379456, + "ts": 6197201560552.599, "dur": 0.721, + "args": { + "External id": 42254,"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": 2338707, "tid": 2379456, + "ts": 6197201560647.267, "dur": 25.439, + "args": { + "External id": 42255,"kernel_hash": "cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4", "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/yk/cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4.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": 2338707, "tid": 2379456, + "ts": 6197201560689.193, "dur": 31.582, + "args": { + "External id": 42256,"kernel_hash": "ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg", "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/eu/ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg.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": 2338707, "tid": 2379456, + "ts": 6197201560731.057, "dur": 46.970, + "args": { + "External id": 42257,"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": 2338707, "tid": 2379456, + "ts": 6197201560784.273, "dur": 39.204, + "args": { + "External id": 42258,"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": 2338707, "tid": 2379456, + "ts": 6197201560832.032, "dur": 22.756, + "args": { + "External id": 42259,"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": 2338707, "tid": 2379456, + "ts": 6197201560860.177, "dur": 31.573, + "args": { + "External id": 42260,"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": 2338707, "tid": 2379456, + "ts": 6197201560898.569, "dur": 27.912, + "args": { + "External id": 42261,"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": 2338707, "tid": 2379456, + "ts": 6197201560933.400, "dur": 30.789, + "args": { + "External id": 42262,"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": 2338707, "tid": 2379456, + "ts": 6197201560985.431, "dur": 25.940, + "args": { + "External id": 42263,"kernel_hash": "c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/6w/c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7.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": 2338707, "tid": 2379456, + "ts": 6197201561027.383, "dur": 58.609, + "args": { + "External id": 42264,"kernel_hash": "ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx", "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/kj/ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx.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": 2338707, "tid": 2379456, + "ts": 6197201561105.944, "dur": 36.075, + "args": { + "External id": 42265,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197201561169.344, "dur": 17.836, + "args": { + "External id": 42266,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197201561202.948, "dur": 16.632, + "args": { + "External id": 42267,"kernel_hash": "cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/eb/cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b.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": 2338707, "tid": 2379456, + "ts": 6197201561303.575, "dur": 16.179, + "args": { + "External id": 42268,"Record function id": 0, "Ev Idx": 10523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201561307.491, "dur": 11.198, + "args": { + "External id": 42269,"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": 2338707, "tid": 2379456, + "ts": 6197201561311.848, "dur": 6.043, + "args": { + "External id": 42270,"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": 2338707, "tid": 2379456, + "ts": 6197201561313.678, "dur": 4.109, + "args": { + "External id": 42271,"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": 2338707, "tid": 2379456, + "ts": 6197201561323.583, "dur": 5.245, + "args": { + "External id": 42272,"Record function id": 0, "Ev Idx": 10527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201561325.291, "dur": 3.039, + "args": { + "External id": 42273,"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": 2338707, "tid": 2379456, + "ts": 6197201561326.000, "dur": 1.747, + "args": { + "External id": 42274,"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": 2338707, "tid": 2379456, + "ts": 6197201561326.836, "dur": 0.822, + "args": { + "External id": 42275,"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": 2338707, "tid": 2379456, + "ts": 6197201561332.183, "dur": 3.868, + "args": { + "External id": 42276,"Record function id": 0, "Ev Idx": 10531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201561333.122, "dur": 2.494, + "args": { + "External id": 42277,"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": 2338707, "tid": 2379456, + "ts": 6197201561333.905, "dur": 1.183, + "args": { + "External id": 42278,"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": 2338707, "tid": 2379456, + "ts": 6197201561334.328, "dur": 0.694, + "args": { + "External id": 42279,"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": 2338707, "tid": 2379456, + "ts": 6197201561339.281, "dur": 4.130, + "args": { + "External id": 42280,"Record function id": 0, "Ev Idx": 10535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201561340.350, "dur": 2.624, + "args": { + "External id": 42281,"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": 2338707, "tid": 2379456, + "ts": 6197201561341.015, "dur": 1.560, + "args": { + "External id": 42282,"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": 2338707, "tid": 2379456, + "ts": 6197201561341.525, "dur": 0.986, + "args": { + "External id": 42283,"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": 2338707, "tid": 2379456, + "ts": 6197201561346.607, "dur": 4.262, + "args": { + "External id": 42284,"Record function id": 0, "Ev Idx": 10539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201561347.987, "dur": 2.385, + "args": { + "External id": 42285,"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": 2338707, "tid": 2379456, + "ts": 6197201561348.536, "dur": 1.300, + "args": { + "External id": 42286,"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": 2338707, "tid": 2379456, + "ts": 6197201561349.071, "dur": 0.677, + "args": { + "External id": 42287,"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": 2338707, "tid": 2379456, + "ts": 6197201561353.985, "dur": 3.595, + "args": { + "External id": 42288,"Record function id": 0, "Ev Idx": 10543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201561354.887, "dur": 2.262, + "args": { + "External id": 42289,"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": 2338707, "tid": 2379456, + "ts": 6197201561355.498, "dur": 1.224, + "args": { + "External id": 42290,"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": 2338707, "tid": 2379456, + "ts": 6197201561355.778, "dur": 0.861, + "args": { + "External id": 42291,"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": 2338707, "tid": 2379456, + "ts": 6197201561360.855, "dur": 4.423, + "args": { + "External id": 42292,"Record function id": 0, "Ev Idx": 10547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201561362.256, "dur": 2.620, + "args": { + "External id": 42293,"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": 2338707, "tid": 2379456, + "ts": 6197201561362.899, "dur": 1.423, + "args": { + "External id": 42294,"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": 2338707, "tid": 2379456, + "ts": 6197201561363.465, "dur": 0.797, + "args": { + "External id": 42295,"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": 2338707, "tid": 2379456, + "ts": 6197201561368.467, "dur": 3.734, + "args": { + "External id": 42296,"Record function id": 0, "Ev Idx": 10551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201561369.511, "dur": 2.302, + "args": { + "External id": 42297,"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": 2338707, "tid": 2379456, + "ts": 6197201561370.007, "dur": 1.412, + "args": { + "External id": 42298,"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": 2338707, "tid": 2379456, + "ts": 6197201561370.267, "dur": 1.086, + "args": { + "External id": 42299,"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": 2338707, "tid": 2379456, + "ts": 6197201561375.622, "dur": 3.969, + "args": { + "External id": 42300,"Record function id": 0, "Ev Idx": 10555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201561376.816, "dur": 2.339, + "args": { + "External id": 42301,"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": 2338707, "tid": 2379456, + "ts": 6197201561377.260, "dur": 1.274, + "args": { + "External id": 42302,"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": 2338707, "tid": 2379456, + "ts": 6197201561377.767, "dur": 0.681, + "args": { + "External id": 42303,"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": 2338707, "tid": 2379456, + "ts": 6197201561383.532, "dur": 69480.384, + "args": { + "External id": 42304,"Record function id": 0, "Sequence number": 480010, "Fwd thread id": 1, "Ev Idx": 10559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197201561384.892, "dur": 69469.838, + "args": { + "External id": 42305,"Sequence number": 480010, "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": 2338707, "tid": 2379456, "ts": 6197201561384.892, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.7)", "pid": 2338707, "tid": 2379456, + "ts": 6197201561413.108, "dur": 34.665, + "args": { + "External id": 42306,"Record function id": 0, "Ev Idx": 10561 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.7)", "pid": 2338707, "tid": 2379456, + "ts": 6197201561455.135, "dur": 65.714, + "args": { + "External id": 42307,"Record function id": 0, "Ev Idx": 10562 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.7)", "pid": 2338707, "tid": 2379456, + "ts": 6197201561526.265, "dur": 69321.030, + "args": { + "External id": 42308,"Record function id": 0, "Ev Idx": 10563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197201561610.213, "dur": 6.765, + "args": { + "External id": 42309,"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": 2338707, "tid": 2379456, + "ts": 6197201561626.640, "dur": 4.588, + "args": { + "External id": 42310,"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": 2338707, "tid": 2379456, + "ts": 6197201561646.193, "dur": 68220.961, + "args": { + "External id": 42311,"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": 2338707, "tid": 2379456, + "ts": 6197201561659.411, "dur": 68194.916, + "args": { + "External id": 42312,"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": 2338707, "tid": 2379456, + "ts": 6197201561764.843, "dur": 19.033, + "args": { + "External id": 42313,"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": 2338707, "tid": 2379456, + "ts": 6197201561804.770, "dur": 68006.651, + "args": { + "External id": 42314,"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": 2338707, "tid": 2379456, + "ts": 6197201561807.705, "dur": 68002.869, + "args": { + "External id": 42315,"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": 2338707, "tid": 2379456, + "ts": 6197201561811.999, "dur": 10.375, + "args": { + "External id": 42316,"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": 2338707, "tid": 2379456, + "ts": 6197201561824.130, "dur": 67982.140, + "args": { + "External id": 42317,"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": 2338707, "tid": 2379456, + "ts": 6197201629973.049, "dur": 12.600, + "args": { + "External id": 42318,"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": 2338707, "tid": 2379456, + "ts": 6197201629976.532, "dur": 8.742, + "args": { + "External id": 42319,"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": 2338707, "tid": 2379456, + "ts": 6197201630014.465, "dur": 431.248, + "args": { + "External id": 42320,"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": 2338707, "tid": 2379456, + "ts": 6197201630047.859, "dur": 391.965, + "args": { + "External id": 42321,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197201630088.967, "dur": 345.754, + "args": { + "External id": 42322,"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": 2338707, "tid": 2379456, + "ts": 6197201630467.620, "dur": 2.019, + "args": { + "External id": 42323,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2379456, + "ts": 6197201630531.614, "dur": 6.450, + "args": { + "External id": 42324,"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": 2338707, "tid": 2379456, + "ts": 6197201630549.370, "dur": 33.930, + "args": { + "External id": 42325,"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": 2338707, "tid": 2379456, + "ts": 6197201630593.981, "dur": 1.535, + "args": { + "External id": 42326,"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": 2338707, "tid": 2379456, + "ts": 6197201630600.406, "dur": 12.051, + "args": { + "External id": 42327,"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": 2338707, "tid": 2379456, + "ts": 6197201630618.022, "dur": 0.815, + "args": { + "External id": 42328,"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": 2338707, "tid": 2379456, + "ts": 6197201630622.443, "dur": 10.864, + "args": { + "External id": 42329,"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": 2338707, "tid": 2379456, + "ts": 6197201630637.757, "dur": 1.012, + "args": { + "External id": 42330,"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": 2338707, "tid": 2379456, + "ts": 6197201630643.068, "dur": 9.851, + "args": { + "External id": 42331,"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": 2338707, "tid": 2379456, + "ts": 6197201630657.077, "dur": 0.865, + "args": { + "External id": 42332,"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": 2338707, "tid": 2379456, + "ts": 6197201630661.518, "dur": 12.304, + "args": { + "External id": 42333,"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": 2338707, "tid": 2379456, + "ts": 6197201630678.113, "dur": 0.718, + "args": { + "External id": 42334,"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": 2338707, "tid": 2379456, + "ts": 6197201630684.317, "dur": 10.708, + "args": { + "External id": 42335,"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": 2338707, "tid": 2379456, + "ts": 6197201630699.573, "dur": 15.938, + "args": { + "External id": 42336,"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": 2338707, "tid": 2379456, + "ts": 6197201630722.149, "dur": 16.058, + "args": { + "External id": 42337,"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": 2338707, "tid": 2379456, + "ts": 6197201630747.092, "dur": 1.181, + "args": { + "External id": 42338,"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": 2338707, "tid": 2379456, + "ts": 6197201630752.046, "dur": 10.540, + "args": { + "External id": 42339,"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": 2338707, "tid": 2379456, + "ts": 6197201630768.026, "dur": 1.123, + "args": { + "External id": 42340,"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": 2338707, "tid": 2379456, + "ts": 6197201630772.903, "dur": 11.648, + "args": { + "External id": 42341,"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": 2338707, "tid": 2379456, + "ts": 6197201630880.009, "dur": 2854.439, + "args": { + "External id": 42342,"Record function id": 0, "Ev Idx": 10597 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.6)", "pid": 2338707, "tid": 2379456, + "ts": 6197201630899.563, "dur": 1025.807, + "args": { + "External id": 42343,"Record function id": 0, "Ev Idx": 10598 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.6)", "pid": 2338707, "tid": 2379456, + "ts": 6197201630913.393, "dur": 357.645, + "args": { + "External id": 42344,"Record function id": 0, "Ev Idx": 10599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6197201630998.485, "dur": 4.064, + "args": { + "External id": 42345,"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": 2338707, "tid": 2379456, + "ts": 6197201631006.317, "dur": 0.932, + "args": { + "External id": 42346,"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": 2338707, "tid": 2379456, + "ts": 6197201631009.256, "dur": 1.275, + "args": { + "External id": 42347,"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": 2338707, "tid": 2379456, + "ts": 6197201631012.419, "dur": 0.804, + "args": { + "External id": 42348,"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": 2338707, "tid": 2379456, + "ts": 6197201631014.826, "dur": 0.903, + "args": { + "External id": 42349,"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": 2338707, "tid": 2379456, + "ts": 6197201631017.190, "dur": 1.030, + "args": { + "External id": 42350,"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": 2338707, "tid": 2379456, + "ts": 6197201631021.990, "dur": 1.238, + "args": { + "External id": 42351,"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": 2338707, "tid": 2379456, + "ts": 6197201631024.599, "dur": 1.001, + "args": { + "External id": 42352,"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": 2338707, "tid": 2379456, + "ts": 6197201631027.066, "dur": 1.181, + "args": { + "External id": 42353,"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": 2338707, "tid": 2379456, + "ts": 6197201631029.742, "dur": 1.109, + "args": { + "External id": 42354,"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": 2338707, "tid": 2379456, + "ts": 6197201631049.442, "dur": 190.003, + "args": { + "External id": 42355,"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": 2338707, "tid": 2379456, + "ts": 6197201631098.796, "dur": 135.548, + "args": { + "External id": 42356,"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": 2338707, "tid": 2379456, + "ts": 6197201631123.936, "dur": 15.442, + "args": { + "External id": 42357,"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": 2338707, "tid": 2379456, + "ts": 6197201631143.032, "dur": 63.801, + "args": { + "External id": 42358,"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": 2338707, "tid": 2379456, + "ts": 6197201631145.873, "dur": 60.706, + "args": { + "External id": 42359,"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": 2338707, "tid": 2379456, + "ts": 6197201631149.298, "dur": 6.396, + "args": { + "External id": 42360,"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": 2338707, "tid": 2379456, + "ts": 6197201631157.107, "dur": 48.805, + "args": { + "External id": 42361,"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": 2338707, "tid": 2379456, + "ts": 6197201631361.051, "dur": 556.965, + "args": { + "External id": 42362,"Record function id": 0, "Ev Idx": 10617 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.5)", "pid": 2338707, "tid": 2379456, + "ts": 6197201631377.222, "dur": 525.652, + "args": { + "External id": 42363,"Record function id": 0, "Ev Idx": 10618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197201631436.763, "dur": 4.921, + "args": { + "External id": 42364,"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": 2338707, "tid": 2379456, + "ts": 6197201631455.981, "dur": 21.725, + "args": { + "External id": 42365,"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": 2338707, "tid": 2379456, + "ts": 6197201631460.687, "dur": 1.803, + "args": { + "External id": 42366,"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": 2338707, "tid": 2379456, + "ts": 6197201631463.916, "dur": 0.369, + "args": { + "External id": 42367,"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": 2338707, "tid": 2379456, + "ts": 6197201631465.911, "dur": 0.563, + "args": { + "External id": 42368,"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": 2338707, "tid": 2379456, + "ts": 6197201631467.274, "dur": 0.195, + "args": { + "External id": 42369,"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": 2338707, "tid": 2379456, + "ts": 6197201631468.657, "dur": 0.444, + "args": { + "External id": 42370,"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": 2338707, "tid": 2379456, + "ts": 6197201631470.166, "dur": 0.274, + "args": { + "External id": 42371,"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": 2338707, "tid": 2379456, + "ts": 6197201631471.195, "dur": 0.512, + "args": { + "External id": 42372,"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": 2338707, "tid": 2379456, + "ts": 6197201631472.591, "dur": 0.499, + "args": { + "External id": 42373,"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": 2338707, "tid": 2379456, + "ts": 6197201631473.863, "dur": 0.843, + "args": { + "External id": 42374,"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": 2338707, "tid": 2379456, + "ts": 6197201631487.593, "dur": 38.362, + "args": { + "External id": 42375,"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": 2338707, "tid": 2379456, + "ts": 6197201631555.567, "dur": 95.255, + "args": { + "External id": 42376,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2379456, + "ts": 6197201631564.702, "dur": 3.340, + "args": { + "External id": 42377,"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": 2338707, "tid": 2379456, + "ts": 6197201631572.800, "dur": 9.592, + "args": { + "External id": 42378,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2379456, + "ts": 6197201631576.946, "dur": 5.030, + "args": { + "External id": 42379,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2379456, + "ts": 6197201631580.237, "dur": 0.541, + "args": { + "External id": 42380,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197201631588.328, "dur": 18.102, + "args": { + "External id": 42381,"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": 2338707, "tid": 2379456, + "ts": 6197201631589.963, "dur": 0.633, + "args": { + "External id": 42382,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197201631591.749, "dur": 0.258, + "args": { + "External id": 42383,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2379456, + "ts": 6197201631593.222, "dur": 0.536, + "args": { + "External id": 42384,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2379456, + "ts": 6197201631594.909, "dur": 0.309, + "args": { + "External id": 42385,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2379456, + "ts": 6197201631595.758, "dur": 0.523, + "args": { + "External id": 42386,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2379456, + "ts": 6197201631597.322, "dur": 0.294, + "args": { + "External id": 42387,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2379456, + "ts": 6197201631598.464, "dur": 0.842, + "args": { + "External id": 42388,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2379456, + "ts": 6197201631600.409, "dur": 0.267, + "args": { + "External id": 42389,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2379456, + "ts": 6197201631601.216, "dur": 0.642, + "args": { + "External id": 42390,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2379456, + "ts": 6197201631615.023, "dur": 29.033, + "args": { + "External id": 42391,"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": 2338707, "tid": 2379456, + "ts": 6197201631692.400, "dur": 138.786, + "args": { + "External id": 42392,"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": 2338707, "tid": 2379456, + "ts": 6197201631740.360, "dur": 87.281, + "args": { + "External id": 42393,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197201631751.970, "dur": 71.482, + "args": { + "External id": 42394,"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": 2338707, "tid": 2379456, + "ts": 6197201631850.826, "dur": 1.780, + "args": { + "External id": 42395,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197201631932.648, "dur": 1757.930, + "args": { + "External id": 42396,"Sequence number": 480009, "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": 2338707, "tid": 2379456, "ts": 6197201631932.648, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6197201632051.553, "dur": 159.444, + "args": { + "External id": 42397,"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": 2338707, "tid": 2379456, + "ts": 6197201632254.989, "dur": 41.878, + "args": { + "External id": 42398,"kernel_hash": "cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/u7/cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs.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": 2338707, "tid": 2379456, + "ts": 6197201632314.912, "dur": 54.578, + "args": { + "External id": 42399,"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": 2338707, "tid": 2379456, + "ts": 6197201632380.628, "dur": 35.645, + "args": { + "External id": 42400,"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": 2338707, "tid": 2379456, + "ts": 6197201632422.531, "dur": 33.236, + "args": { + "External id": 42401,"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": 2338707, "tid": 2379456, + "ts": 6197201632462.234, "dur": 28.862, + "args": { + "External id": 42402,"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": 2338707, "tid": 2379456, + "ts": 6197201632499.032, "dur": 29.018, + "args": { + "External id": 42403,"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": 2338707, "tid": 2379456, + "ts": 6197201632552.201, "dur": 25.377, + "args": { + "External id": 42404,"kernel_hash": "cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/wm/cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s.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": 2338707, "tid": 2379456, + "ts": 6197201632597.939, "dur": 28.707, + "args": { + "External id": 42405,"kernel_hash": "cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql", "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/qt/cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql.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": 2338707, "tid": 2379456, + "ts": 6197201632649.990, "dur": 20.853, + "args": { + "External id": 42406,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197201632683.286, "dur": 14.595, + "args": { + "External id": 42407,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197201632723.518, "dur": 41.469, + "args": { + "External id": 42408,"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": 2338707, "tid": 2379456, + "ts": 6197201632768.803, "dur": 33.280, + "args": { + "External id": 42409,"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": 2338707, "tid": 2379456, + "ts": 6197201632830.297, "dur": 271.962, + "args": { + "External id": 42410,"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": 2338707, "tid": 2379456, + "ts": 6197201632909.431, "dur": 6.176, + "args": { + "External id": 42411,"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": 2338707, "tid": 2379456, + "ts": 6197201632917.510, "dur": 2.860, + "args": { + "External id": 42412,"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": 2338707, "tid": 2379456, + "ts": 6197201632921.213, "dur": 1.961, + "args": { + "External id": 42413,"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": 2338707, "tid": 2379456, + "ts": 6197201632924.338, "dur": 2.185, + "args": { + "External id": 42414,"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": 2338707, "tid": 2379456, + "ts": 6197201632969.410, "dur": 4.985, + "args": { + "External id": 42415,"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": 2338707, "tid": 2379456, + "ts": 6197201632971.140, "dur": 3.074, + "args": { + "External id": 42416,"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": 2338707, "tid": 2379456, + "ts": 6197201632976.126, "dur": 30.578, + "args": { + "External id": 42417,"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": 2338707, "tid": 2379456, + "ts": 6197201632981.915, "dur": 1.642, + "args": { + "External id": 42418,"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": 2338707, "tid": 2379456, + "ts": 6197201633008.242, "dur": 2.162, + "args": { + "External id": 42419,"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": 2338707, "tid": 2379456, + "ts": 6197201633009.586, "dur": 0.747, + "args": { + "External id": 42420,"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": 2338707, "tid": 2379456, + "ts": 6197201633011.060, "dur": 13.692, + "args": { + "External id": 42421,"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": 2338707, "tid": 2379456, + "ts": 6197201633012.905, "dur": 0.421, + "args": { + "External id": 42422,"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": 2338707, "tid": 2379456, + "ts": 6197201633139.449, "dur": 30.250, + "args": { + "External id": 42423,"kernel_hash": "cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4", "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/yk/cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4.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": 2338707, "tid": 2379456, + "ts": 6197201633185.661, "dur": 15.970, + "args": { + "External id": 42424,"kernel_hash": "ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg", "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/eu/ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg.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": 2338707, "tid": 2379456, + "ts": 6197201633210.039, "dur": 46.458, + "args": { + "External id": 42425,"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": 2338707, "tid": 2379456, + "ts": 6197201633262.763, "dur": 39.767, + "args": { + "External id": 42426,"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": 2338707, "tid": 2379456, + "ts": 6197201633309.817, "dur": 21.389, + "args": { + "External id": 42427,"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": 2338707, "tid": 2379456, + "ts": 6197201633340.019, "dur": 31.298, + "args": { + "External id": 42428,"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": 2338707, "tid": 2379456, + "ts": 6197201633378.249, "dur": 28.934, + "args": { + "External id": 42429,"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": 2338707, "tid": 2379456, + "ts": 6197201633413.493, "dur": 33.660, + "args": { + "External id": 42430,"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": 2338707, "tid": 2379456, + "ts": 6197201633466.090, "dur": 26.965, + "args": { + "External id": 42431,"kernel_hash": "c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/6w/c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7.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": 2338707, "tid": 2379456, + "ts": 6197201633510.779, "dur": 40.636, + "args": { + "External id": 42432,"kernel_hash": "ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx", "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/kj/ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx.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": 2338707, "tid": 2379456, + "ts": 6197201633577.906, "dur": 17.846, + "args": { + "External id": 42433,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197201633610.317, "dur": 19.438, + "args": { + "External id": 42434,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197201633642.346, "dur": 15.487, + "args": { + "External id": 42435,"kernel_hash": "cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/eb/cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b.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": 2338707, "tid": 2379456, + "ts": 6197201633757.304, "dur": 16.475, + "args": { + "External id": 42436,"Record function id": 0, "Ev Idx": 10691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201633761.382, "dur": 11.325, + "args": { + "External id": 42437,"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": 2338707, "tid": 2379456, + "ts": 6197201633765.646, "dur": 5.965, + "args": { + "External id": 42438,"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": 2338707, "tid": 2379456, + "ts": 6197201633767.333, "dur": 4.174, + "args": { + "External id": 42439,"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": 2338707, "tid": 2379456, + "ts": 6197201633777.921, "dur": 4.885, + "args": { + "External id": 42440,"Record function id": 0, "Ev Idx": 10695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201633779.327, "dur": 3.020, + "args": { + "External id": 42441,"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": 2338707, "tid": 2379456, + "ts": 6197201633779.993, "dur": 1.856, + "args": { + "External id": 42442,"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": 2338707, "tid": 2379456, + "ts": 6197201633780.749, "dur": 1.009, + "args": { + "External id": 42443,"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": 2338707, "tid": 2379456, + "ts": 6197201633786.139, "dur": 8.149, + "args": { + "External id": 42444,"Record function id": 0, "Ev Idx": 10699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201633791.250, "dur": 2.636, + "args": { + "External id": 42445,"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": 2338707, "tid": 2379456, + "ts": 6197201633791.783, "dur": 1.478, + "args": { + "External id": 42446,"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": 2338707, "tid": 2379456, + "ts": 6197201633792.393, "dur": 0.800, + "args": { + "External id": 42447,"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": 2338707, "tid": 2379456, + "ts": 6197201633797.405, "dur": 4.036, + "args": { + "External id": 42448,"Record function id": 0, "Ev Idx": 10703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201633798.505, "dur": 2.504, + "args": { + "External id": 42449,"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": 2338707, "tid": 2379456, + "ts": 6197201633799.431, "dur": 1.134, + "args": { + "External id": 42450,"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": 2338707, "tid": 2379456, + "ts": 6197201633799.755, "dur": 0.744, + "args": { + "External id": 42451,"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": 2338707, "tid": 2379456, + "ts": 6197201633804.561, "dur": 4.378, + "args": { + "External id": 42452,"Record function id": 0, "Ev Idx": 10707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201633805.980, "dur": 2.522, + "args": { + "External id": 42453,"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": 2338707, "tid": 2379456, + "ts": 6197201633806.564, "dur": 1.390, + "args": { + "External id": 42454,"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": 2338707, "tid": 2379456, + "ts": 6197201633807.113, "dur": 0.775, + "args": { + "External id": 42455,"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": 2338707, "tid": 2379456, + "ts": 6197201633812.210, "dur": 3.684, + "args": { + "External id": 42456,"Record function id": 0, "Ev Idx": 10711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201633813.216, "dur": 2.263, + "args": { + "External id": 42457,"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": 2338707, "tid": 2379456, + "ts": 6197201633814.061, "dur": 0.997, + "args": { + "External id": 42458,"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": 2338707, "tid": 2379456, + "ts": 6197201633814.341, "dur": 0.650, + "args": { + "External id": 42459,"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": 2338707, "tid": 2379456, + "ts": 6197201633819.124, "dur": 3.834, + "args": { + "External id": 42460,"Record function id": 0, "Ev Idx": 10715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201633820.301, "dur": 2.205, + "args": { + "External id": 42461,"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": 2338707, "tid": 2379456, + "ts": 6197201633820.765, "dur": 1.143, + "args": { + "External id": 42462,"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": 2338707, "tid": 2379456, + "ts": 6197201633821.105, "dur": 0.735, + "args": { + "External id": 42463,"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": 2338707, "tid": 2379456, + "ts": 6197201633826.133, "dur": 4.035, + "args": { + "External id": 42464,"Record function id": 0, "Ev Idx": 10719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201633827.375, "dur": 2.390, + "args": { + "External id": 42465,"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": 2338707, "tid": 2379456, + "ts": 6197201633827.957, "dur": 1.316, + "args": { + "External id": 42466,"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": 2338707, "tid": 2379456, + "ts": 6197201633828.361, "dur": 0.847, + "args": { + "External id": 42467,"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": 2338707, "tid": 2379456, + "ts": 6197201633833.355, "dur": 3.160, + "args": { + "External id": 42468,"Record function id": 0, "Ev Idx": 10723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201633834.242, "dur": 1.749, + "args": { + "External id": 42469,"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": 2338707, "tid": 2379456, + "ts": 6197201633834.698, "dur": 0.793, + "args": { + "External id": 42470,"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": 2338707, "tid": 2379456, + "ts": 6197201633834.986, "dur": 0.440, + "args": { + "External id": 42471,"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": 2338707, "tid": 2379456, + "ts": 6197201633840.224, "dur": 65457.685, + "args": { + "External id": 42472,"Record function id": 0, "Sequence number": 480008, "Fwd thread id": 1, "Ev Idx": 10727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197201633841.973, "dur": 65446.219, + "args": { + "External id": 42473,"Sequence number": 480008, "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": 2338707, "tid": 2379456, "ts": 6197201633841.973, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.6)", "pid": 2338707, "tid": 2379456, + "ts": 6197201633876.215, "dur": 38.338, + "args": { + "External id": 42474,"Record function id": 0, "Ev Idx": 10729 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.6)", "pid": 2338707, "tid": 2379456, + "ts": 6197201633921.944, "dur": 67.774, + "args": { + "External id": 42475,"Record function id": 0, "Ev Idx": 10730 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.6)", "pid": 2338707, "tid": 2379456, + "ts": 6197201633995.615, "dur": 65284.842, + "args": { + "External id": 42476,"Record function id": 0, "Ev Idx": 10731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197201634119.200, "dur": 8.287, + "args": { + "External id": 42477,"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": 2338707, "tid": 2379456, + "ts": 6197201634138.558, "dur": 5.159, + "args": { + "External id": 42478,"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": 2338707, "tid": 2379456, + "ts": 6197201634158.608, "dur": 64154.048, + "args": { + "External id": 42479,"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": 2338707, "tid": 2379456, + "ts": 6197201634174.118, "dur": 64126.257, + "args": { + "External id": 42480,"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": 2338707, "tid": 2379456, + "ts": 6197201634260.594, "dur": 17.164, + "args": { + "External id": 42481,"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": 2338707, "tid": 2379456, + "ts": 6197201634297.951, "dur": 63960.628, + "args": { + "External id": 42482,"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": 2338707, "tid": 2379456, + "ts": 6197201634301.322, "dur": 63956.471, + "args": { + "External id": 42483,"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": 2338707, "tid": 2379456, + "ts": 6197201634305.333, "dur": 8.329, + "args": { + "External id": 42484,"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": 2338707, "tid": 2379456, + "ts": 6197201634315.362, "dur": 63937.716, + "args": { + "External id": 42485,"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": 2338707, "tid": 2379456, + "ts": 6197201698419.657, "dur": 11.905, + "args": { + "External id": 42486,"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": 2338707, "tid": 2379456, + "ts": 6197201698423.291, "dur": 7.850, + "args": { + "External id": 42487,"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": 2338707, "tid": 2379456, + "ts": 6197201698459.234, "dur": 360.291, + "args": { + "External id": 42488,"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": 2338707, "tid": 2379456, + "ts": 6197201698490.060, "dur": 324.391, + "args": { + "External id": 42489,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197201698500.885, "dur": 307.636, + "args": { + "External id": 42490,"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": 2338707, "tid": 2379456, + "ts": 6197201698842.524, "dur": 2.359, + "args": { + "External id": 42491,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2379456, + "ts": 6197201698904.600, "dur": 6.672, + "args": { + "External id": 42492,"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": 2338707, "tid": 2379456, + "ts": 6197201698922.903, "dur": 31.067, + "args": { + "External id": 42493,"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": 2338707, "tid": 2379456, + "ts": 6197201698964.706, "dur": 1.355, + "args": { + "External id": 42494,"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": 2338707, "tid": 2379456, + "ts": 6197201698971.166, "dur": 11.674, + "args": { + "External id": 42495,"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": 2338707, "tid": 2379456, + "ts": 6197201698987.881, "dur": 0.916, + "args": { + "External id": 42496,"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": 2338707, "tid": 2379456, + "ts": 6197201699026.118, "dur": 11.336, + "args": { + "External id": 42497,"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": 2338707, "tid": 2379456, + "ts": 6197201699042.571, "dur": 1.370, + "args": { + "External id": 42498,"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": 2338707, "tid": 2379456, + "ts": 6197201699047.307, "dur": 49.124, + "args": { + "External id": 42499,"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": 2338707, "tid": 2379456, + "ts": 6197201699105.187, "dur": 1.488, + "args": { + "External id": 42500,"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": 2338707, "tid": 2379456, + "ts": 6197201699111.590, "dur": 12.602, + "args": { + "External id": 42501,"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": 2338707, "tid": 2379456, + "ts": 6197201699128.815, "dur": 1.201, + "args": { + "External id": 42502,"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": 2338707, "tid": 2379456, + "ts": 6197201699133.516, "dur": 15.250, + "args": { + "External id": 42503,"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": 2338707, "tid": 2379456, + "ts": 6197201699155.022, "dur": 0.826, + "args": { + "External id": 42504,"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": 2338707, "tid": 2379456, + "ts": 6197201699159.964, "dur": 12.541, + "args": { + "External id": 42505,"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": 2338707, "tid": 2379456, + "ts": 6197201699176.832, "dur": 0.666, + "args": { + "External id": 42506,"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": 2338707, "tid": 2379456, + "ts": 6197201699180.912, "dur": 11.509, + "args": { + "External id": 42507,"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": 2338707, "tid": 2379456, + "ts": 6197201699199.604, "dur": 0.949, + "args": { + "External id": 42508,"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": 2338707, "tid": 2379456, + "ts": 6197201699206.401, "dur": 12.362, + "args": { + "External id": 42509,"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": 2338707, "tid": 2379456, + "ts": 6197201699314.331, "dur": 2897.143, + "args": { + "External id": 42510,"Record function id": 0, "Ev Idx": 10765 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.5)", "pid": 2338707, "tid": 2379456, + "ts": 6197201699335.261, "dur": 1045.940, + "args": { + "External id": 42511,"Record function id": 0, "Ev Idx": 10766 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.5)", "pid": 2338707, "tid": 2379456, + "ts": 6197201699351.611, "dur": 319.855, + "args": { + "External id": 42512,"Record function id": 0, "Ev Idx": 10767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6197201699441.554, "dur": 4.233, + "args": { + "External id": 42513,"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": 2338707, "tid": 2379456, + "ts": 6197201699449.077, "dur": 0.643, + "args": { + "External id": 42514,"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": 2338707, "tid": 2379456, + "ts": 6197201699451.444, "dur": 1.054, + "args": { + "External id": 42515,"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": 2338707, "tid": 2379456, + "ts": 6197201699454.441, "dur": 1.095, + "args": { + "External id": 42516,"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": 2338707, "tid": 2379456, + "ts": 6197201699456.880, "dur": 0.739, + "args": { + "External id": 42517,"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": 2338707, "tid": 2379456, + "ts": 6197201699459.054, "dur": 0.609, + "args": { + "External id": 42518,"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": 2338707, "tid": 2379456, + "ts": 6197201699461.070, "dur": 1.520, + "args": { + "External id": 42519,"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": 2338707, "tid": 2379456, + "ts": 6197201699465.830, "dur": 0.709, + "args": { + "External id": 42520,"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": 2338707, "tid": 2379456, + "ts": 6197201699467.976, "dur": 1.217, + "args": { + "External id": 42521,"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": 2338707, "tid": 2379456, + "ts": 6197201699470.586, "dur": 0.769, + "args": { + "External id": 42522,"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": 2338707, "tid": 2379456, + "ts": 6197201699488.731, "dur": 154.984, + "args": { + "External id": 42523,"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": 2338707, "tid": 2379456, + "ts": 6197201699503.556, "dur": 132.625, + "args": { + "External id": 42524,"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": 2338707, "tid": 2379456, + "ts": 6197201699518.664, "dur": 25.988, + "args": { + "External id": 42525,"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": 2338707, "tid": 2379456, + "ts": 6197201699548.266, "dur": 60.406, + "args": { + "External id": 42526,"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": 2338707, "tid": 2379456, + "ts": 6197201699552.534, "dur": 55.809, + "args": { + "External id": 42527,"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": 2338707, "tid": 2379456, + "ts": 6197201699556.321, "dur": 5.811, + "args": { + "External id": 42528,"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": 2338707, "tid": 2379456, + "ts": 6197201699563.821, "dur": 43.929, + "args": { + "External id": 42529,"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": 2338707, "tid": 2379456, + "ts": 6197201699784.302, "dur": 589.390, + "args": { + "External id": 42530,"Record function id": 0, "Ev Idx": 10785 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.4)", "pid": 2338707, "tid": 2379456, + "ts": 6197201699801.155, "dur": 560.491, + "args": { + "External id": 42531,"Record function id": 0, "Ev Idx": 10786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197201699864.213, "dur": 6.273, + "args": { + "External id": 42532,"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": 2338707, "tid": 2379456, + "ts": 6197201699885.558, "dur": 21.451, + "args": { + "External id": 42533,"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": 2338707, "tid": 2379456, + "ts": 6197201699890.158, "dur": 1.630, + "args": { + "External id": 42534,"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": 2338707, "tid": 2379456, + "ts": 6197201699893.163, "dur": 0.610, + "args": { + "External id": 42535,"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": 2338707, "tid": 2379456, + "ts": 6197201699895.146, "dur": 0.428, + "args": { + "External id": 42536,"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": 2338707, "tid": 2379456, + "ts": 6197201699896.445, "dur": 0.177, + "args": { + "External id": 42537,"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": 2338707, "tid": 2379456, + "ts": 6197201699897.870, "dur": 0.559, + "args": { + "External id": 42538,"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": 2338707, "tid": 2379456, + "ts": 6197201699899.428, "dur": 0.244, + "args": { + "External id": 42539,"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": 2338707, "tid": 2379456, + "ts": 6197201699900.443, "dur": 0.505, + "args": { + "External id": 42540,"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": 2338707, "tid": 2379456, + "ts": 6197201699902.096, "dur": 0.305, + "args": { + "External id": 42541,"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": 2338707, "tid": 2379456, + "ts": 6197201699903.115, "dur": 0.549, + "args": { + "External id": 42542,"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": 2338707, "tid": 2379456, + "ts": 6197201699918.164, "dur": 41.326, + "args": { + "External id": 42543,"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": 2338707, "tid": 2379456, + "ts": 6197201699988.663, "dur": 142.291, + "args": { + "External id": 42544,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2379456, + "ts": 6197201699998.068, "dur": 3.508, + "args": { + "External id": 42545,"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": 2338707, "tid": 2379456, + "ts": 6197201700006.723, "dur": 9.743, + "args": { + "External id": 42546,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2379456, + "ts": 6197201700010.963, "dur": 5.086, + "args": { + "External id": 42547,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2379456, + "ts": 6197201700014.264, "dur": 0.533, + "args": { + "External id": 42548,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197201700022.966, "dur": 20.251, + "args": { + "External id": 42549,"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": 2338707, "tid": 2379456, + "ts": 6197201700024.439, "dur": 0.474, + "args": { + "External id": 42550,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197201700025.969, "dur": 0.396, + "args": { + "External id": 42551,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2379456, + "ts": 6197201700027.196, "dur": 0.968, + "args": { + "External id": 42552,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2379456, + "ts": 6197201700029.310, "dur": 0.787, + "args": { + "External id": 42553,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2379456, + "ts": 6197201700031.320, "dur": 0.798, + "args": { + "External id": 42554,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2379456, + "ts": 6197201700033.157, "dur": 0.372, + "args": { + "External id": 42555,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2379456, + "ts": 6197201700034.550, "dur": 0.873, + "args": { + "External id": 42556,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2379456, + "ts": 6197201700036.344, "dur": 0.276, + "args": { + "External id": 42557,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2379456, + "ts": 6197201700037.141, "dur": 0.722, + "args": { + "External id": 42558,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2379456, + "ts": 6197201700052.052, "dur": 69.665, + "args": { + "External id": 42559,"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": 2338707, "tid": 2379456, + "ts": 6197201700177.838, "dur": 112.988, + "args": { + "External id": 42560,"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": 2338707, "tid": 2379456, + "ts": 6197201700205.654, "dur": 81.493, + "args": { + "External id": 42561,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197201700214.694, "dur": 68.225, + "args": { + "External id": 42562,"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": 2338707, "tid": 2379456, + "ts": 6197201700309.353, "dur": 1.985, + "args": { + "External id": 42563,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197201700388.797, "dur": 1794.632, + "args": { + "External id": 42564,"Sequence number": 480007, "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": 2338707, "tid": 2379456, "ts": 6197201700388.797, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6197201700496.753, "dur": 107.754, + "args": { + "External id": 42565,"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": 2338707, "tid": 2379456, + "ts": 6197201700643.567, "dur": 42.160, + "args": { + "External id": 42566,"kernel_hash": "cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/u7/cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs.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": 2338707, "tid": 2379456, + "ts": 6197201700721.761, "dur": 62.560, + "args": { + "External id": 42567,"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": 2338707, "tid": 2379456, + "ts": 6197201700797.248, "dur": 37.726, + "args": { + "External id": 42568,"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": 2338707, "tid": 2379456, + "ts": 6197201700841.359, "dur": 33.528, + "args": { + "External id": 42569,"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": 2338707, "tid": 2379456, + "ts": 6197201700881.116, "dur": 28.337, + "args": { + "External id": 42570,"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": 2338707, "tid": 2379456, + "ts": 6197201700920.834, "dur": 30.615, + "args": { + "External id": 42571,"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": 2338707, "tid": 2379456, + "ts": 6197201700979.612, "dur": 23.920, + "args": { + "External id": 42572,"kernel_hash": "cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/wm/cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s.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": 2338707, "tid": 2379456, + "ts": 6197201701021.394, "dur": 26.918, + "args": { + "External id": 42573,"kernel_hash": "cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql", "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/qt/cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql.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": 2338707, "tid": 2379456, + "ts": 6197201701113.503, "dur": 23.221, + "args": { + "External id": 42574,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197201701150.801, "dur": 15.003, + "args": { + "External id": 42575,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197201701175.593, "dur": 43.503, + "args": { + "External id": 42576,"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": 2338707, "tid": 2379456, + "ts": 6197201701222.793, "dur": 34.133, + "args": { + "External id": 42577,"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": 2338707, "tid": 2379456, + "ts": 6197201701285.634, "dur": 242.058, + "args": { + "External id": 42578,"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": 2338707, "tid": 2379456, + "ts": 6197201701364.255, "dur": 5.749, + "args": { + "External id": 42579,"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": 2338707, "tid": 2379456, + "ts": 6197201701372.144, "dur": 2.714, + "args": { + "External id": 42580,"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": 2338707, "tid": 2379456, + "ts": 6197201701375.877, "dur": 1.856, + "args": { + "External id": 42581,"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": 2338707, "tid": 2379456, + "ts": 6197201701378.564, "dur": 2.626, + "args": { + "External id": 42582,"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": 2338707, "tid": 2379456, + "ts": 6197201701424.074, "dur": 5.511, + "args": { + "External id": 42583,"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": 2338707, "tid": 2379456, + "ts": 6197201701426.557, "dur": 2.843, + "args": { + "External id": 42584,"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": 2338707, "tid": 2379456, + "ts": 6197201701431.284, "dur": 32.953, + "args": { + "External id": 42585,"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": 2338707, "tid": 2379456, + "ts": 6197201701437.175, "dur": 1.805, + "args": { + "External id": 42586,"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": 2338707, "tid": 2379456, + "ts": 6197201701466.250, "dur": 1.833, + "args": { + "External id": 42587,"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": 2338707, "tid": 2379456, + "ts": 6197201701467.280, "dur": 0.731, + "args": { + "External id": 42588,"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": 2338707, "tid": 2379456, + "ts": 6197201701468.814, "dur": 18.244, + "args": { + "External id": 42589,"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": 2338707, "tid": 2379456, + "ts": 6197201701471.203, "dur": 0.386, + "args": { + "External id": 42590,"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": 2338707, "tid": 2379456, + "ts": 6197201701560.575, "dur": 28.817, + "args": { + "External id": 42591,"kernel_hash": "cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4", "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/yk/cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4.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": 2338707, "tid": 2379456, + "ts": 6197201701614.199, "dur": 16.902, + "args": { + "External id": 42592,"kernel_hash": "ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg", "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/eu/ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg.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": 2338707, "tid": 2379456, + "ts": 6197201701640.191, "dur": 41.956, + "args": { + "External id": 42593,"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": 2338707, "tid": 2379456, + "ts": 6197201701687.538, "dur": 59.012, + "args": { + "External id": 42594,"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": 2338707, "tid": 2379456, + "ts": 6197201701758.727, "dur": 25.093, + "args": { + "External id": 42595,"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": 2338707, "tid": 2379456, + "ts": 6197201701788.971, "dur": 31.905, + "args": { + "External id": 42596,"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": 2338707, "tid": 2379456, + "ts": 6197201701827.508, "dur": 28.057, + "args": { + "External id": 42597,"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": 2338707, "tid": 2379456, + "ts": 6197201701863.103, "dur": 31.840, + "args": { + "External id": 42598,"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": 2338707, "tid": 2379456, + "ts": 6197201701913.807, "dur": 27.068, + "args": { + "External id": 42599,"kernel_hash": "c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/6w/c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7.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": 2338707, "tid": 2379456, + "ts": 6197201701958.006, "dur": 27.508, + "args": { + "External id": 42600,"kernel_hash": "ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx", "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/kj/ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx.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": 2338707, "tid": 2379456, + "ts": 6197201702001.341, "dur": 19.207, + "args": { + "External id": 42601,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197201702036.151, "dur": 15.574, + "args": { + "External id": 42602,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197201702121.583, "dur": 28.628, + "args": { + "External id": 42603,"kernel_hash": "cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/eb/cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b.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": 2338707, "tid": 2379456, + "ts": 6197201702233.574, "dur": 15.574, + "args": { + "External id": 42604,"Record function id": 0, "Ev Idx": 10859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201702237.054, "dur": 11.099, + "args": { + "External id": 42605,"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": 2338707, "tid": 2379456, + "ts": 6197201702241.521, "dur": 5.789, + "args": { + "External id": 42606,"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": 2338707, "tid": 2379456, + "ts": 6197201702243.083, "dur": 4.131, + "args": { + "External id": 42607,"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": 2338707, "tid": 2379456, + "ts": 6197201702252.978, "dur": 7.764, + "args": { + "External id": 42608,"Record function id": 0, "Ev Idx": 10863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201702254.296, "dur": 5.972, + "args": { + "External id": 42609,"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": 2338707, "tid": 2379456, + "ts": 6197201702258.512, "dur": 1.260, + "args": { + "External id": 42610,"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": 2338707, "tid": 2379456, + "ts": 6197201702259.023, "dur": 0.630, + "args": { + "External id": 42611,"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": 2338707, "tid": 2379456, + "ts": 6197201702264.005, "dur": 3.613, + "args": { + "External id": 42612,"Record function id": 0, "Ev Idx": 10867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201702265.036, "dur": 2.191, + "args": { + "External id": 42613,"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": 2338707, "tid": 2379456, + "ts": 6197201702265.548, "dur": 1.295, + "args": { + "External id": 42614,"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": 2338707, "tid": 2379456, + "ts": 6197201702266.126, "dur": 0.650, + "args": { + "External id": 42615,"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": 2338707, "tid": 2379456, + "ts": 6197201702271.010, "dur": 4.165, + "args": { + "External id": 42616,"Record function id": 0, "Ev Idx": 10871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201702272.241, "dur": 2.527, + "args": { + "External id": 42617,"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": 2338707, "tid": 2379456, + "ts": 6197201702272.832, "dur": 1.521, + "args": { + "External id": 42618,"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": 2338707, "tid": 2379456, + "ts": 6197201702273.121, "dur": 1.164, + "args": { + "External id": 42619,"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": 2338707, "tid": 2379456, + "ts": 6197201702278.235, "dur": 4.679, + "args": { + "External id": 42620,"Record function id": 0, "Ev Idx": 10875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201702279.580, "dur": 2.890, + "args": { + "External id": 42621,"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": 2338707, "tid": 2379456, + "ts": 6197201702280.132, "dur": 1.537, + "args": { + "External id": 42622,"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": 2338707, "tid": 2379456, + "ts": 6197201702280.566, "dur": 1.015, + "args": { + "External id": 42623,"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": 2338707, "tid": 2379456, + "ts": 6197201702286.162, "dur": 3.650, + "args": { + "External id": 42624,"Record function id": 0, "Ev Idx": 10879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201702287.446, "dur": 1.960, + "args": { + "External id": 42625,"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": 2338707, "tid": 2379456, + "ts": 6197201702287.952, "dur": 0.984, + "args": { + "External id": 42626,"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": 2338707, "tid": 2379456, + "ts": 6197201702288.261, "dur": 0.607, + "args": { + "External id": 42627,"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": 2338707, "tid": 2379456, + "ts": 6197201702293.073, "dur": 3.669, + "args": { + "External id": 42628,"Record function id": 0, "Ev Idx": 10883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201702294.276, "dur": 2.061, + "args": { + "External id": 42629,"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": 2338707, "tid": 2379456, + "ts": 6197201702294.905, "dur": 1.033, + "args": { + "External id": 42630,"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": 2338707, "tid": 2379456, + "ts": 6197201702295.169, "dur": 0.705, + "args": { + "External id": 42631,"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": 2338707, "tid": 2379456, + "ts": 6197201702299.918, "dur": 4.419, + "args": { + "External id": 42632,"Record function id": 0, "Ev Idx": 10887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201702301.329, "dur": 2.587, + "args": { + "External id": 42633,"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": 2338707, "tid": 2379456, + "ts": 6197201702301.785, "dur": 1.438, + "args": { + "External id": 42634,"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": 2338707, "tid": 2379456, + "ts": 6197201702302.174, "dur": 0.983, + "args": { + "External id": 42635,"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": 2338707, "tid": 2379456, + "ts": 6197201702307.414, "dur": 3.584, + "args": { + "External id": 42636,"Record function id": 0, "Ev Idx": 10891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201702308.634, "dur": 1.978, + "args": { + "External id": 42637,"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": 2338707, "tid": 2379456, + "ts": 6197201702309.130, "dur": 1.073, + "args": { + "External id": 42638,"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": 2338707, "tid": 2379456, + "ts": 6197201702309.516, "dur": 0.620, + "args": { + "External id": 42639,"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": 2338707, "tid": 2379456, + "ts": 6197201702315.238, "dur": 63357.226, + "args": { + "External id": 42640,"Record function id": 0, "Sequence number": 480006, "Fwd thread id": 1, "Ev Idx": 10895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197201702316.363, "dur": 63347.311, + "args": { + "External id": 42641,"Sequence number": 480006, "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": 2338707, "tid": 2379456, "ts": 6197201702316.363, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.5)", "pid": 2338707, "tid": 2379456, + "ts": 6197201702346.330, "dur": 37.968, + "args": { + "External id": 42642,"Record function id": 0, "Ev Idx": 10897 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.5)", "pid": 2338707, "tid": 2379456, + "ts": 6197201702391.690, "dur": 67.052, + "args": { + "External id": 42643,"Record function id": 0, "Ev Idx": 10898 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.5)", "pid": 2338707, "tid": 2379456, + "ts": 6197201702464.094, "dur": 63191.980, + "args": { + "External id": 42644,"Record function id": 0, "Ev Idx": 10899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197201702550.611, "dur": 7.141, + "args": { + "External id": 42645,"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": 2338707, "tid": 2379456, + "ts": 6197201702567.517, "dur": 4.497, + "args": { + "External id": 42646,"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": 2338707, "tid": 2379456, + "ts": 6197201702586.288, "dur": 62154.274, + "args": { + "External id": 42647,"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": 2338707, "tid": 2379456, + "ts": 6197201702600.145, "dur": 62127.124, + "args": { + "External id": 42648,"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": 2338707, "tid": 2379456, + "ts": 6197201702690.938, "dur": 38.539, + "args": { + "External id": 42649,"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": 2338707, "tid": 2379456, + "ts": 6197201702753.989, "dur": 61919.533, + "args": { + "External id": 42650,"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": 2338707, "tid": 2379456, + "ts": 6197201702757.219, "dur": 61915.319, + "args": { + "External id": 42651,"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": 2338707, "tid": 2379456, + "ts": 6197201702762.755, "dur": 13.091, + "args": { + "External id": 42652,"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": 2338707, "tid": 2379456, + "ts": 6197201702777.524, "dur": 61890.470, + "args": { + "External id": 42653,"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": 2338707, "tid": 2379456, + "ts": 6197201764846.506, "dur": 12.801, + "args": { + "External id": 42654,"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": 2338707, "tid": 2379456, + "ts": 6197201764850.154, "dur": 8.637, + "args": { + "External id": 42655,"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": 2338707, "tid": 2379456, + "ts": 6197201764889.503, "dur": 392.417, + "args": { + "External id": 42656,"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": 2338707, "tid": 2379456, + "ts": 6197201764921.044, "dur": 355.331, + "args": { + "External id": 42657,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197201764932.386, "dur": 337.856, + "args": { + "External id": 42658,"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": 2338707, "tid": 2379456, + "ts": 6197201765306.791, "dur": 2.510, + "args": { + "External id": 42659,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2379456, + "ts": 6197201765369.763, "dur": 6.873, + "args": { + "External id": 42660,"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": 2338707, "tid": 2379456, + "ts": 6197201765389.084, "dur": 32.712, + "args": { + "External id": 42661,"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": 2338707, "tid": 2379456, + "ts": 6197201765432.742, "dur": 1.653, + "args": { + "External id": 42662,"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": 2338707, "tid": 2379456, + "ts": 6197201765439.789, "dur": 12.199, + "args": { + "External id": 42663,"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": 2338707, "tid": 2379456, + "ts": 6197201765457.407, "dur": 0.937, + "args": { + "External id": 42664,"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": 2338707, "tid": 2379456, + "ts": 6197201765462.761, "dur": 11.062, + "args": { + "External id": 42665,"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": 2338707, "tid": 2379456, + "ts": 6197201765479.279, "dur": 1.058, + "args": { + "External id": 42666,"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": 2338707, "tid": 2379456, + "ts": 6197201765484.328, "dur": 10.011, + "args": { + "External id": 42667,"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": 2338707, "tid": 2379456, + "ts": 6197201765499.092, "dur": 0.864, + "args": { + "External id": 42668,"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": 2338707, "tid": 2379456, + "ts": 6197201765503.451, "dur": 10.842, + "args": { + "External id": 42669,"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": 2338707, "tid": 2379456, + "ts": 6197201765518.856, "dur": 1.247, + "args": { + "External id": 42670,"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": 2338707, "tid": 2379456, + "ts": 6197201765523.691, "dur": 9.937, + "args": { + "External id": 42671,"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": 2338707, "tid": 2379456, + "ts": 6197201765540.154, "dur": 1.114, + "args": { + "External id": 42672,"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": 2338707, "tid": 2379456, + "ts": 6197201765545.400, "dur": 10.357, + "args": { + "External id": 42673,"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": 2338707, "tid": 2379456, + "ts": 6197201765559.744, "dur": 0.960, + "args": { + "External id": 42674,"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": 2338707, "tid": 2379456, + "ts": 6197201765564.838, "dur": 10.133, + "args": { + "External id": 42675,"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": 2338707, "tid": 2379456, + "ts": 6197201765578.883, "dur": 0.715, + "args": { + "External id": 42676,"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": 2338707, "tid": 2379456, + "ts": 6197201765584.694, "dur": 10.682, + "args": { + "External id": 42677,"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": 2338707, "tid": 2379456, + "ts": 6197201765686.635, "dur": 2874.881, + "args": { + "External id": 42678,"Record function id": 0, "Ev Idx": 10933 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.4)", "pid": 2338707, "tid": 2379456, + "ts": 6197201765730.985, "dur": 1062.351, + "args": { + "External id": 42679,"Record function id": 0, "Ev Idx": 10934 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.4)", "pid": 2338707, "tid": 2379456, + "ts": 6197201765746.763, "dur": 367.374, + "args": { + "External id": 42680,"Record function id": 0, "Ev Idx": 10935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6197201765847.507, "dur": 4.903, + "args": { + "External id": 42681,"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": 2338707, "tid": 2379456, + "ts": 6197201765856.033, "dur": 0.867, + "args": { + "External id": 42682,"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": 2338707, "tid": 2379456, + "ts": 6197201765858.755, "dur": 0.939, + "args": { + "External id": 42683,"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": 2338707, "tid": 2379456, + "ts": 6197201765861.523, "dur": 1.118, + "args": { + "External id": 42684,"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": 2338707, "tid": 2379456, + "ts": 6197201765863.898, "dur": 0.940, + "args": { + "External id": 42685,"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": 2338707, "tid": 2379456, + "ts": 6197201765866.271, "dur": 0.726, + "args": { + "External id": 42686,"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": 2338707, "tid": 2379456, + "ts": 6197201765869.956, "dur": 1.196, + "args": { + "External id": 42687,"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": 2338707, "tid": 2379456, + "ts": 6197201765872.398, "dur": 1.188, + "args": { + "External id": 42688,"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": 2338707, "tid": 2379456, + "ts": 6197201765874.848, "dur": 1.189, + "args": { + "External id": 42689,"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": 2338707, "tid": 2379456, + "ts": 6197201765877.558, "dur": 1.042, + "args": { + "External id": 42690,"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": 2338707, "tid": 2379456, + "ts": 6197201765897.397, "dur": 149.475, + "args": { + "External id": 42691,"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": 2338707, "tid": 2379456, + "ts": 6197201765912.500, "dur": 129.637, + "args": { + "External id": 42692,"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": 2338707, "tid": 2379456, + "ts": 6197201765927.565, "dur": 25.157, + "args": { + "External id": 42693,"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": 2338707, "tid": 2379456, + "ts": 6197201765956.179, "dur": 58.974, + "args": { + "External id": 42694,"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": 2338707, "tid": 2379456, + "ts": 6197201765959.076, "dur": 55.702, + "args": { + "External id": 42695,"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": 2338707, "tid": 2379456, + "ts": 6197201765962.207, "dur": 5.892, + "args": { + "External id": 42696,"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": 2338707, "tid": 2379456, + "ts": 6197201765969.678, "dur": 44.488, + "args": { + "External id": 42697,"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": 2338707, "tid": 2379456, + "ts": 6197201766202.747, "dur": 582.976, + "args": { + "External id": 42698,"Record function id": 0, "Ev Idx": 10953 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.3)", "pid": 2338707, "tid": 2379456, + "ts": 6197201766220.371, "dur": 553.037, + "args": { + "External id": 42699,"Record function id": 0, "Ev Idx": 10954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197201766282.804, "dur": 5.883, + "args": { + "External id": 42700,"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": 2338707, "tid": 2379456, + "ts": 6197201766303.874, "dur": 23.732, + "args": { + "External id": 42701,"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": 2338707, "tid": 2379456, + "ts": 6197201766308.920, "dur": 1.897, + "args": { + "External id": 42702,"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": 2338707, "tid": 2379456, + "ts": 6197201766312.354, "dur": 0.496, + "args": { + "External id": 42703,"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": 2338707, "tid": 2379456, + "ts": 6197201766313.937, "dur": 0.585, + "args": { + "External id": 42704,"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": 2338707, "tid": 2379456, + "ts": 6197201766316.036, "dur": 0.512, + "args": { + "External id": 42705,"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": 2338707, "tid": 2379456, + "ts": 6197201766317.605, "dur": 0.735, + "args": { + "External id": 42706,"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": 2338707, "tid": 2379456, + "ts": 6197201766319.211, "dur": 0.563, + "args": { + "External id": 42707,"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": 2338707, "tid": 2379456, + "ts": 6197201766320.608, "dur": 0.290, + "args": { + "External id": 42708,"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": 2338707, "tid": 2379456, + "ts": 6197201766321.830, "dur": 0.562, + "args": { + "External id": 42709,"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": 2338707, "tid": 2379456, + "ts": 6197201766323.914, "dur": 0.278, + "args": { + "External id": 42710,"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": 2338707, "tid": 2379456, + "ts": 6197201766338.610, "dur": 44.424, + "args": { + "External id": 42711,"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": 2338707, "tid": 2379456, + "ts": 6197201766412.065, "dur": 109.953, + "args": { + "External id": 42712,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2379456, + "ts": 6197201766421.610, "dur": 3.179, + "args": { + "External id": 42713,"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": 2338707, "tid": 2379456, + "ts": 6197201766429.794, "dur": 9.888, + "args": { + "External id": 42714,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2379456, + "ts": 6197201766433.899, "dur": 5.336, + "args": { + "External id": 42715,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2379456, + "ts": 6197201766437.080, "dur": 0.735, + "args": { + "External id": 42716,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197201766446.148, "dur": 26.067, + "args": { + "External id": 42717,"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": 2338707, "tid": 2379456, + "ts": 6197201766448.004, "dur": 0.519, + "args": { + "External id": 42718,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197201766449.822, "dur": 0.543, + "args": { + "External id": 42719,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2379456, + "ts": 6197201766455.130, "dur": 0.205, + "args": { + "External id": 42720,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2379456, + "ts": 6197201766455.928, "dur": 0.456, + "args": { + "External id": 42721,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2379456, + "ts": 6197201766457.533, "dur": 0.516, + "args": { + "External id": 42722,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2379456, + "ts": 6197201766458.809, "dur": 0.486, + "args": { + "External id": 42723,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2379456, + "ts": 6197201766463.159, "dur": 0.360, + "args": { + "External id": 42724,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2379456, + "ts": 6197201766464.235, "dur": 0.703, + "args": { + "External id": 42725,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2379456, + "ts": 6197201766466.082, "dur": 0.413, + "args": { + "External id": 42726,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2379456, + "ts": 6197201766482.140, "dur": 32.767, + "args": { + "External id": 42727,"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": 2338707, "tid": 2379456, + "ts": 6197201766564.919, "dur": 114.935, + "args": { + "External id": 42728,"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": 2338707, "tid": 2379456, + "ts": 6197201766590.469, "dur": 85.886, + "args": { + "External id": 42729,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197201766599.807, "dur": 72.576, + "args": { + "External id": 42730,"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": 2338707, "tid": 2379456, + "ts": 6197201766698.934, "dur": 19.353, + "args": { + "External id": 42731,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197201766801.164, "dur": 1734.772, + "args": { + "External id": 42732,"Sequence number": 480005, "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": 2338707, "tid": 2379456, "ts": 6197201766801.164, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6197201766912.659, "dur": 107.439, + "args": { + "External id": 42733,"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": 2338707, "tid": 2379456, + "ts": 6197201767098.700, "dur": 46.088, + "args": { + "External id": 42734,"kernel_hash": "cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/u7/cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs.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": 2338707, "tid": 2379456, + "ts": 6197201767165.131, "dur": 57.382, + "args": { + "External id": 42735,"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": 2338707, "tid": 2379456, + "ts": 6197201767237.715, "dur": 34.891, + "args": { + "External id": 42736,"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": 2338707, "tid": 2379456, + "ts": 6197201767279.553, "dur": 34.024, + "args": { + "External id": 42737,"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": 2338707, "tid": 2379456, + "ts": 6197201767320.133, "dur": 32.094, + "args": { + "External id": 42738,"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": 2338707, "tid": 2379456, + "ts": 6197201767359.878, "dur": 30.265, + "args": { + "External id": 42739,"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": 2338707, "tid": 2379456, + "ts": 6197201767419.399, "dur": 23.565, + "args": { + "External id": 42740,"kernel_hash": "cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/wm/cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s.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": 2338707, "tid": 2379456, + "ts": 6197201767463.634, "dur": 27.323, + "args": { + "External id": 42741,"kernel_hash": "cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql", "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/qt/cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql.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": 2338707, "tid": 2379456, + "ts": 6197201767512.191, "dur": 25.223, + "args": { + "External id": 42742,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197201767549.881, "dur": 16.367, + "args": { + "External id": 42743,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197201767573.948, "dur": 37.828, + "args": { + "External id": 42744,"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": 2338707, "tid": 2379456, + "ts": 6197201767614.780, "dur": 35.766, + "args": { + "External id": 42745,"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": 2338707, "tid": 2379456, + "ts": 6197201767679.203, "dur": 253.637, + "args": { + "External id": 42746,"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": 2338707, "tid": 2379456, + "ts": 6197201767769.917, "dur": 7.163, + "args": { + "External id": 42747,"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": 2338707, "tid": 2379456, + "ts": 6197201767779.064, "dur": 2.962, + "args": { + "External id": 42748,"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": 2338707, "tid": 2379456, + "ts": 6197201767783.269, "dur": 2.677, + "args": { + "External id": 42749,"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": 2338707, "tid": 2379456, + "ts": 6197201767787.236, "dur": 2.191, + "args": { + "External id": 42750,"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": 2338707, "tid": 2379456, + "ts": 6197201767835.243, "dur": 4.886, + "args": { + "External id": 42751,"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": 2338707, "tid": 2379456, + "ts": 6197201767837.043, "dur": 2.908, + "args": { + "External id": 42752,"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": 2338707, "tid": 2379456, + "ts": 6197201767841.969, "dur": 31.607, + "args": { + "External id": 42753,"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": 2338707, "tid": 2379456, + "ts": 6197201767848.277, "dur": 2.201, + "args": { + "External id": 42754,"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": 2338707, "tid": 2379456, + "ts": 6197201767874.838, "dur": 1.843, + "args": { + "External id": 42755,"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": 2338707, "tid": 2379456, + "ts": 6197201767875.840, "dur": 0.760, + "args": { + "External id": 42756,"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": 2338707, "tid": 2379456, + "ts": 6197201767877.564, "dur": 14.366, + "args": { + "External id": 42757,"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": 2338707, "tid": 2379456, + "ts": 6197201767880.090, "dur": 0.535, + "args": { + "External id": 42758,"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": 2338707, "tid": 2379456, + "ts": 6197201767969.415, "dur": 25.309, + "args": { + "External id": 42759,"kernel_hash": "cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4", "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/yk/cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4.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": 2338707, "tid": 2379456, + "ts": 6197201768013.649, "dur": 15.365, + "args": { + "External id": 42760,"kernel_hash": "ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg", "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/eu/ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg.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": 2338707, "tid": 2379456, + "ts": 6197201768036.398, "dur": 84.338, + "args": { + "External id": 42761,"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": 2338707, "tid": 2379456, + "ts": 6197201768129.917, "dur": 43.748, + "args": { + "External id": 42762,"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": 2338707, "tid": 2379456, + "ts": 6197201768182.946, "dur": 21.502, + "args": { + "External id": 42763,"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": 2338707, "tid": 2379456, + "ts": 6197201768210.594, "dur": 32.225, + "args": { + "External id": 42764,"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": 2338707, "tid": 2379456, + "ts": 6197201768249.466, "dur": 28.558, + "args": { + "External id": 42765,"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": 2338707, "tid": 2379456, + "ts": 6197201768285.989, "dur": 30.776, + "args": { + "External id": 42766,"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": 2338707, "tid": 2379456, + "ts": 6197201768336.176, "dur": 26.155, + "args": { + "External id": 42767,"kernel_hash": "c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/6w/c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7.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": 2338707, "tid": 2379456, + "ts": 6197201768380.784, "dur": 26.049, + "args": { + "External id": 42768,"kernel_hash": "ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx", "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/kj/ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx.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": 2338707, "tid": 2379456, + "ts": 6197201768422.999, "dur": 16.826, + "args": { + "External id": 42769,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197201768455.543, "dur": 14.042, + "args": { + "External id": 42770,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197201768480.732, "dur": 15.033, + "args": { + "External id": 42771,"kernel_hash": "cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/eb/cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b.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": 2338707, "tid": 2379456, + "ts": 6197201768584.024, "dur": 15.320, + "args": { + "External id": 42772,"Record function id": 0, "Ev Idx": 11027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201768587.076, "dur": 11.320, + "args": { + "External id": 42773,"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": 2338707, "tid": 2379456, + "ts": 6197201768591.348, "dur": 6.159, + "args": { + "External id": 42774,"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": 2338707, "tid": 2379456, + "ts": 6197201768592.994, "dur": 4.420, + "args": { + "External id": 42775,"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": 2338707, "tid": 2379456, + "ts": 6197201768603.354, "dur": 4.837, + "args": { + "External id": 42776,"Record function id": 0, "Ev Idx": 11031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201768604.522, "dur": 3.222, + "args": { + "External id": 42777,"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": 2338707, "tid": 2379456, + "ts": 6197201768605.628, "dur": 1.531, + "args": { + "External id": 42778,"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": 2338707, "tid": 2379456, + "ts": 6197201768606.166, "dur": 0.931, + "args": { + "External id": 42779,"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": 2338707, "tid": 2379456, + "ts": 6197201768611.454, "dur": 4.256, + "args": { + "External id": 42780,"Record function id": 0, "Ev Idx": 11035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201768612.546, "dur": 2.774, + "args": { + "External id": 42781,"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": 2338707, "tid": 2379456, + "ts": 6197201768613.067, "dur": 1.744, + "args": { + "External id": 42782,"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": 2338707, "tid": 2379456, + "ts": 6197201768613.920, "dur": 0.830, + "args": { + "External id": 42783,"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": 2338707, "tid": 2379456, + "ts": 6197201768618.811, "dur": 3.859, + "args": { + "External id": 42784,"Record function id": 0, "Ev Idx": 11039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201768620.032, "dur": 2.235, + "args": { + "External id": 42785,"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": 2338707, "tid": 2379456, + "ts": 6197201768620.598, "dur": 1.272, + "args": { + "External id": 42786,"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": 2338707, "tid": 2379456, + "ts": 6197201768621.107, "dur": 0.703, + "args": { + "External id": 42787,"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": 2338707, "tid": 2379456, + "ts": 6197201768625.722, "dur": 3.701, + "args": { + "External id": 42788,"Record function id": 0, "Ev Idx": 11043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201768626.860, "dur": 2.163, + "args": { + "External id": 42789,"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": 2338707, "tid": 2379456, + "ts": 6197201768627.316, "dur": 1.284, + "args": { + "External id": 42790,"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": 2338707, "tid": 2379456, + "ts": 6197201768627.591, "dur": 0.942, + "args": { + "External id": 42791,"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": 2338707, "tid": 2379456, + "ts": 6197201768632.416, "dur": 5.284, + "args": { + "External id": 42792,"Record function id": 0, "Ev Idx": 11047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201768633.284, "dur": 4.010, + "args": { + "External id": 42793,"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": 2338707, "tid": 2379456, + "ts": 6197201768633.862, "dur": 3.020, + "args": { + "External id": 42794,"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": 2338707, "tid": 2379456, + "ts": 6197201768636.205, "dur": 0.575, + "args": { + "External id": 42795,"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": 2338707, "tid": 2379456, + "ts": 6197201768640.902, "dur": 2.935, + "args": { + "External id": 42796,"Record function id": 0, "Ev Idx": 11051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201768641.846, "dur": 1.610, + "args": { + "External id": 42797,"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": 2338707, "tid": 2379456, + "ts": 6197201768642.261, "dur": 0.792, + "args": { + "External id": 42798,"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": 2338707, "tid": 2379456, + "ts": 6197201768642.556, "dur": 0.436, + "args": { + "External id": 42799,"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": 2338707, "tid": 2379456, + "ts": 6197201768646.876, "dur": 3.163, + "args": { + "External id": 42800,"Record function id": 0, "Ev Idx": 11055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201768647.714, "dur": 1.927, + "args": { + "External id": 42801,"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": 2338707, "tid": 2379456, + "ts": 6197201768648.134, "dur": 1.102, + "args": { + "External id": 42802,"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": 2338707, "tid": 2379456, + "ts": 6197201768648.414, "dur": 0.757, + "args": { + "External id": 42803,"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": 2338707, "tid": 2379456, + "ts": 6197201768653.326, "dur": 3.958, + "args": { + "External id": 42804,"Record function id": 0, "Ev Idx": 11059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201768654.440, "dur": 2.447, + "args": { + "External id": 42805,"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": 2338707, "tid": 2379456, + "ts": 6197201768654.846, "dur": 1.628, + "args": { + "External id": 42806,"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": 2338707, "tid": 2379456, + "ts": 6197201768655.179, "dur": 1.235, + "args": { + "External id": 42807,"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": 2338707, "tid": 2379456, + "ts": 6197201768661.203, "dur": 64010.188, + "args": { + "External id": 42808,"Record function id": 0, "Sequence number": 480004, "Fwd thread id": 1, "Ev Idx": 11063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197201768662.707, "dur": 63999.599, + "args": { + "External id": 42809,"Sequence number": 480004, "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": 2338707, "tid": 2379456, "ts": 6197201768662.707, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.4)", "pid": 2338707, "tid": 2379456, + "ts": 6197201768696.961, "dur": 60.661, + "args": { + "External id": 42810,"Record function id": 0, "Ev Idx": 11065 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.4)", "pid": 2338707, "tid": 2379456, + "ts": 6197201768765.889, "dur": 68.820, + "args": { + "External id": 42811,"Record function id": 0, "Ev Idx": 11066 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.4)", "pid": 2338707, "tid": 2379456, + "ts": 6197201768840.175, "dur": 63814.291, + "args": { + "External id": 42812,"Record function id": 0, "Ev Idx": 11067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197201768930.399, "dur": 7.177, + "args": { + "External id": 42813,"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": 2338707, "tid": 2379456, + "ts": 6197201768947.849, "dur": 5.043, + "args": { + "External id": 42814,"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": 2338707, "tid": 2379456, + "ts": 6197201768971.011, "dur": 62679.217, + "args": { + "External id": 42815,"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": 2338707, "tid": 2379456, + "ts": 6197201768984.355, "dur": 62653.132, + "args": { + "External id": 42816,"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": 2338707, "tid": 2379456, + "ts": 6197201769112.223, "dur": 19.673, + "args": { + "External id": 42817,"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": 2338707, "tid": 2379456, + "ts": 6197201769152.344, "dur": 62445.188, + "args": { + "External id": 42818,"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": 2338707, "tid": 2379456, + "ts": 6197201769155.372, "dur": 62441.289, + "args": { + "External id": 42819,"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": 2338707, "tid": 2379456, + "ts": 6197201769159.870, "dur": 10.367, + "args": { + "External id": 42820,"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": 2338707, "tid": 2379456, + "ts": 6197201769172.463, "dur": 62419.579, + "args": { + "External id": 42821,"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": 2338707, "tid": 2379456, + "ts": 6197201831772.547, "dur": 12.188, + "args": { + "External id": 42822,"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": 2338707, "tid": 2379456, + "ts": 6197201831775.973, "dur": 8.294, + "args": { + "External id": 42823,"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": 2338707, "tid": 2379456, + "ts": 6197201831814.576, "dur": 450.941, + "args": { + "External id": 42824,"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": 2338707, "tid": 2379456, + "ts": 6197201831843.193, "dur": 416.921, + "args": { + "External id": 42825,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197201831854.644, "dur": 398.796, + "args": { + "External id": 42826,"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": 2338707, "tid": 2379456, + "ts": 6197201832290.319, "dur": 2.648, + "args": { + "External id": 42827,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2379456, + "ts": 6197201832356.036, "dur": 6.587, + "args": { + "External id": 42828,"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": 2338707, "tid": 2379456, + "ts": 6197201832375.127, "dur": 34.237, + "args": { + "External id": 42829,"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": 2338707, "tid": 2379456, + "ts": 6197201832419.362, "dur": 1.615, + "args": { + "External id": 42830,"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": 2338707, "tid": 2379456, + "ts": 6197201832426.516, "dur": 11.475, + "args": { + "External id": 42831,"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": 2338707, "tid": 2379456, + "ts": 6197201832443.171, "dur": 1.340, + "args": { + "External id": 42832,"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": 2338707, "tid": 2379456, + "ts": 6197201832450.520, "dur": 12.167, + "args": { + "External id": 42833,"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": 2338707, "tid": 2379456, + "ts": 6197201832467.571, "dur": 0.992, + "args": { + "External id": 42834,"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": 2338707, "tid": 2379456, + "ts": 6197201832472.297, "dur": 9.686, + "args": { + "External id": 42835,"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": 2338707, "tid": 2379456, + "ts": 6197201832486.358, "dur": 0.906, + "args": { + "External id": 42836,"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": 2338707, "tid": 2379456, + "ts": 6197201832491.053, "dur": 12.563, + "args": { + "External id": 42837,"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": 2338707, "tid": 2379456, + "ts": 6197201832507.673, "dur": 1.359, + "args": { + "External id": 42838,"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": 2338707, "tid": 2379456, + "ts": 6197201832513.311, "dur": 12.052, + "args": { + "External id": 42839,"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": 2338707, "tid": 2379456, + "ts": 6197201832531.710, "dur": 1.199, + "args": { + "External id": 42840,"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": 2338707, "tid": 2379456, + "ts": 6197201832536.569, "dur": 15.811, + "args": { + "External id": 42841,"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": 2338707, "tid": 2379456, + "ts": 6197201832556.265, "dur": 1.004, + "args": { + "External id": 42842,"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": 2338707, "tid": 2379456, + "ts": 6197201832560.416, "dur": 10.696, + "args": { + "External id": 42843,"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": 2338707, "tid": 2379456, + "ts": 6197201832575.456, "dur": 1.013, + "args": { + "External id": 42844,"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": 2338707, "tid": 2379456, + "ts": 6197201832582.623, "dur": 10.332, + "args": { + "External id": 42845,"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": 2338707, "tid": 2379456, + "ts": 6197201832686.089, "dur": 2918.397, + "args": { + "External id": 42846,"Record function id": 0, "Ev Idx": 11101 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.3)", "pid": 2338707, "tid": 2379456, + "ts": 6197201832722.443, "dur": 1043.048, + "args": { + "External id": 42847,"Record function id": 0, "Ev Idx": 11102 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.3)", "pid": 2338707, "tid": 2379456, + "ts": 6197201832738.367, "dur": 355.809, + "args": { + "External id": 42848,"Record function id": 0, "Ev Idx": 11103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6197201832827.873, "dur": 4.776, + "args": { + "External id": 42849,"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": 2338707, "tid": 2379456, + "ts": 6197201832835.806, "dur": 0.738, + "args": { + "External id": 42850,"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": 2338707, "tid": 2379456, + "ts": 6197201832838.727, "dur": 0.966, + "args": { + "External id": 42851,"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": 2338707, "tid": 2379456, + "ts": 6197201832842.114, "dur": 0.640, + "args": { + "External id": 42852,"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": 2338707, "tid": 2379456, + "ts": 6197201832844.360, "dur": 0.713, + "args": { + "External id": 42853,"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": 2338707, "tid": 2379456, + "ts": 6197201832846.287, "dur": 0.808, + "args": { + "External id": 42854,"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": 2338707, "tid": 2379456, + "ts": 6197201832850.572, "dur": 0.976, + "args": { + "External id": 42855,"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": 2338707, "tid": 2379456, + "ts": 6197201832852.716, "dur": 0.702, + "args": { + "External id": 42856,"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": 2338707, "tid": 2379456, + "ts": 6197201832854.900, "dur": 1.173, + "args": { + "External id": 42857,"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": 2338707, "tid": 2379456, + "ts": 6197201832857.438, "dur": 0.875, + "args": { + "External id": 42858,"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": 2338707, "tid": 2379456, + "ts": 6197201832877.809, "dur": 150.816, + "args": { + "External id": 42859,"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": 2338707, "tid": 2379456, + "ts": 6197201832892.760, "dur": 131.201, + "args": { + "External id": 42860,"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": 2338707, "tid": 2379456, + "ts": 6197201832907.272, "dur": 25.031, + "args": { + "External id": 42861,"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": 2338707, "tid": 2379456, + "ts": 6197201832935.807, "dur": 62.584, + "args": { + "External id": 42862,"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": 2338707, "tid": 2379456, + "ts": 6197201832938.407, "dur": 59.667, + "args": { + "External id": 42863,"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": 2338707, "tid": 2379456, + "ts": 6197201832942.198, "dur": 5.803, + "args": { + "External id": 42864,"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": 2338707, "tid": 2379456, + "ts": 6197201832949.718, "dur": 47.627, + "args": { + "External id": 42865,"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": 2338707, "tid": 2379456, + "ts": 6197201833190.538, "dur": 567.696, + "args": { + "External id": 42866,"Record function id": 0, "Ev Idx": 11121 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.2)", "pid": 2338707, "tid": 2379456, + "ts": 6197201833207.319, "dur": 537.979, + "args": { + "External id": 42867,"Record function id": 0, "Ev Idx": 11122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197201833269.799, "dur": 5.746, + "args": { + "External id": 42868,"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": 2338707, "tid": 2379456, + "ts": 6197201833290.719, "dur": 24.165, + "args": { + "External id": 42869,"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": 2338707, "tid": 2379456, + "ts": 6197201833295.817, "dur": 2.171, + "args": { + "External id": 42870,"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": 2338707, "tid": 2379456, + "ts": 6197201833299.597, "dur": 0.292, + "args": { + "External id": 42871,"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": 2338707, "tid": 2379456, + "ts": 6197201833301.562, "dur": 0.484, + "args": { + "External id": 42872,"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": 2338707, "tid": 2379456, + "ts": 6197201833302.915, "dur": 0.208, + "args": { + "External id": 42873,"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": 2338707, "tid": 2379456, + "ts": 6197201833304.703, "dur": 0.645, + "args": { + "External id": 42874,"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": 2338707, "tid": 2379456, + "ts": 6197201833306.291, "dur": 0.548, + "args": { + "External id": 42875,"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": 2338707, "tid": 2379456, + "ts": 6197201833308.055, "dur": 0.516, + "args": { + "External id": 42876,"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": 2338707, "tid": 2379456, + "ts": 6197201833309.813, "dur": 0.288, + "args": { + "External id": 42877,"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": 2338707, "tid": 2379456, + "ts": 6197201833310.649, "dur": 0.854, + "args": { + "External id": 42878,"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": 2338707, "tid": 2379456, + "ts": 6197201833325.334, "dur": 42.091, + "args": { + "External id": 42879,"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": 2338707, "tid": 2379456, + "ts": 6197201833395.706, "dur": 98.854, + "args": { + "External id": 42880,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2379456, + "ts": 6197201833405.251, "dur": 3.499, + "args": { + "External id": 42881,"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": 2338707, "tid": 2379456, + "ts": 6197201833414.165, "dur": 9.660, + "args": { + "External id": 42882,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2379456, + "ts": 6197201833418.369, "dur": 5.034, + "args": { + "External id": 42883,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2379456, + "ts": 6197201833421.610, "dur": 0.533, + "args": { + "External id": 42884,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197201833429.852, "dur": 17.632, + "args": { + "External id": 42885,"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": 2338707, "tid": 2379456, + "ts": 6197201833431.216, "dur": 0.723, + "args": { + "External id": 42886,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197201833433.596, "dur": 0.467, + "args": { + "External id": 42887,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2379456, + "ts": 6197201833435.270, "dur": 0.615, + "args": { + "External id": 42888,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2379456, + "ts": 6197201833436.748, "dur": 0.184, + "args": { + "External id": 42889,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2379456, + "ts": 6197201833437.452, "dur": 0.422, + "args": { + "External id": 42890,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2379456, + "ts": 6197201833439.094, "dur": 0.277, + "args": { + "External id": 42891,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2379456, + "ts": 6197201833440.026, "dur": 0.584, + "args": { + "External id": 42892,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2379456, + "ts": 6197201833441.408, "dur": 0.180, + "args": { + "External id": 42893,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2379456, + "ts": 6197201833442.343, "dur": 0.413, + "args": { + "External id": 42894,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2379456, + "ts": 6197201833456.212, "dur": 31.118, + "args": { + "External id": 42895,"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": 2338707, "tid": 2379456, + "ts": 6197201833536.674, "dur": 122.274, + "args": { + "External id": 42896,"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": 2338707, "tid": 2379456, + "ts": 6197201833569.274, "dur": 86.433, + "args": { + "External id": 42897,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197201833578.272, "dur": 73.012, + "args": { + "External id": 42898,"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": 2338707, "tid": 2379456, + "ts": 6197201833675.878, "dur": 1.938, + "args": { + "External id": 42899,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197201833773.018, "dur": 1808.227, + "args": { + "External id": 42900,"Sequence number": 480003, "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": 2338707, "tid": 2379456, "ts": 6197201833773.018, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6197201833887.000, "dur": 107.309, + "args": { + "External id": 42901,"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": 2338707, "tid": 2379456, + "ts": 6197201834036.734, "dur": 79.897, + "args": { + "External id": 42902,"kernel_hash": "cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/u7/cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs.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": 2338707, "tid": 2379456, + "ts": 6197201834137.456, "dur": 59.138, + "args": { + "External id": 42903,"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": 2338707, "tid": 2379456, + "ts": 6197201834206.857, "dur": 33.684, + "args": { + "External id": 42904,"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": 2338707, "tid": 2379456, + "ts": 6197201834246.810, "dur": 33.292, + "args": { + "External id": 42905,"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": 2338707, "tid": 2379456, + "ts": 6197201834286.726, "dur": 28.058, + "args": { + "External id": 42906,"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": 2338707, "tid": 2379456, + "ts": 6197201834320.909, "dur": 29.152, + "args": { + "External id": 42907,"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": 2338707, "tid": 2379456, + "ts": 6197201834377.602, "dur": 22.497, + "args": { + "External id": 42908,"kernel_hash": "cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/wm/cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s.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": 2338707, "tid": 2379456, + "ts": 6197201834418.541, "dur": 29.041, + "args": { + "External id": 42909,"kernel_hash": "cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql", "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/qt/cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql.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": 2338707, "tid": 2379456, + "ts": 6197201834470.664, "dur": 18.776, + "args": { + "External id": 42910,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197201834501.507, "dur": 19.670, + "args": { + "External id": 42911,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197201834529.442, "dur": 37.987, + "args": { + "External id": 42912,"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": 2338707, "tid": 2379456, + "ts": 6197201834571.195, "dur": 32.464, + "args": { + "External id": 42913,"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": 2338707, "tid": 2379456, + "ts": 6197201834631.338, "dur": 288.221, + "args": { + "External id": 42914,"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": 2338707, "tid": 2379456, + "ts": 6197201834742.200, "dur": 7.682, + "args": { + "External id": 42915,"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": 2338707, "tid": 2379456, + "ts": 6197201834755.270, "dur": 2.405, + "args": { + "External id": 42916,"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": 2338707, "tid": 2379456, + "ts": 6197201834759.040, "dur": 2.734, + "args": { + "External id": 42917,"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": 2338707, "tid": 2379456, + "ts": 6197201834762.679, "dur": 1.631, + "args": { + "External id": 42918,"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": 2338707, "tid": 2379456, + "ts": 6197201834809.139, "dur": 4.940, + "args": { + "External id": 42919,"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": 2338707, "tid": 2379456, + "ts": 6197201834810.973, "dur": 2.804, + "args": { + "External id": 42920,"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": 2338707, "tid": 2379456, + "ts": 6197201834815.883, "dur": 33.313, + "args": { + "External id": 42921,"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": 2338707, "tid": 2379456, + "ts": 6197201834821.889, "dur": 1.857, + "args": { + "External id": 42922,"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": 2338707, "tid": 2379456, + "ts": 6197201834850.632, "dur": 1.391, + "args": { + "External id": 42923,"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": 2338707, "tid": 2379456, + "ts": 6197201834851.464, "dur": 0.491, + "args": { + "External id": 42924,"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": 2338707, "tid": 2379456, + "ts": 6197201834854.918, "dur": 16.700, + "args": { + "External id": 42925,"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": 2338707, "tid": 2379456, + "ts": 6197201834857.733, "dur": 0.476, + "args": { + "External id": 42926,"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": 2338707, "tid": 2379456, + "ts": 6197201834959.430, "dur": 31.369, + "args": { + "External id": 42927,"kernel_hash": "cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4", "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/yk/cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4.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": 2338707, "tid": 2379456, + "ts": 6197201835006.846, "dur": 16.994, + "args": { + "External id": 42928,"kernel_hash": "ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg", "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/eu/ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg.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": 2338707, "tid": 2379456, + "ts": 6197201835031.473, "dur": 91.952, + "args": { + "External id": 42929,"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": 2338707, "tid": 2379456, + "ts": 6197201835132.999, "dur": 44.252, + "args": { + "External id": 42930,"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": 2338707, "tid": 2379456, + "ts": 6197201835191.283, "dur": 22.715, + "args": { + "External id": 42931,"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": 2338707, "tid": 2379456, + "ts": 6197201835220.164, "dur": 31.461, + "args": { + "External id": 42932,"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": 2338707, "tid": 2379456, + "ts": 6197201835272.242, "dur": 40.190, + "args": { + "External id": 42933,"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": 2338707, "tid": 2379456, + "ts": 6197201835321.114, "dur": 32.332, + "args": { + "External id": 42934,"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": 2338707, "tid": 2379456, + "ts": 6197201835381.576, "dur": 27.626, + "args": { + "External id": 42935,"kernel_hash": "c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/6w/c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7.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": 2338707, "tid": 2379456, + "ts": 6197201835426.225, "dur": 31.443, + "args": { + "External id": 42936,"kernel_hash": "ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx", "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/kj/ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx.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": 2338707, "tid": 2379456, + "ts": 6197201835472.711, "dur": 19.021, + "args": { + "External id": 42937,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197201835505.334, "dur": 15.042, + "args": { + "External id": 42938,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197201835534.848, "dur": 16.443, + "args": { + "External id": 42939,"kernel_hash": "cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/eb/cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b.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": 2338707, "tid": 2379456, + "ts": 6197201835626.843, "dur": 14.950, + "args": { + "External id": 42940,"Record function id": 0, "Ev Idx": 11195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201835630.163, "dur": 10.441, + "args": { + "External id": 42941,"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": 2338707, "tid": 2379456, + "ts": 6197201835634.146, "dur": 5.654, + "args": { + "External id": 42942,"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": 2338707, "tid": 2379456, + "ts": 6197201835635.762, "dur": 3.934, + "args": { + "External id": 42943,"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": 2338707, "tid": 2379456, + "ts": 6197201835645.778, "dur": 5.191, + "args": { + "External id": 42944,"Record function id": 0, "Ev Idx": 11199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201835647.189, "dur": 3.275, + "args": { + "External id": 42945,"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": 2338707, "tid": 2379456, + "ts": 6197201835647.831, "dur": 1.963, + "args": { + "External id": 42946,"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": 2338707, "tid": 2379456, + "ts": 6197201835648.543, "dur": 1.171, + "args": { + "External id": 42947,"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": 2338707, "tid": 2379456, + "ts": 6197201835654.354, "dur": 4.178, + "args": { + "External id": 42948,"Record function id": 0, "Ev Idx": 11203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201835655.512, "dur": 2.577, + "args": { + "External id": 42949,"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": 2338707, "tid": 2379456, + "ts": 6197201835656.219, "dur": 1.420, + "args": { + "External id": 42950,"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": 2338707, "tid": 2379456, + "ts": 6197201835656.933, "dur": 0.601, + "args": { + "External id": 42951,"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": 2338707, "tid": 2379456, + "ts": 6197201835661.754, "dur": 4.248, + "args": { + "External id": 42952,"Record function id": 0, "Ev Idx": 11207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201835663.324, "dur": 2.245, + "args": { + "External id": 42953,"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": 2338707, "tid": 2379456, + "ts": 6197201835663.953, "dur": 1.223, + "args": { + "External id": 42954,"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": 2338707, "tid": 2379456, + "ts": 6197201835664.387, "dur": 0.702, + "args": { + "External id": 42955,"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": 2338707, "tid": 2379456, + "ts": 6197201835669.167, "dur": 3.494, + "args": { + "External id": 42956,"Record function id": 0, "Ev Idx": 11211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201835670.224, "dur": 2.022, + "args": { + "External id": 42957,"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": 2338707, "tid": 2379456, + "ts": 6197201835670.710, "dur": 1.051, + "args": { + "External id": 42958,"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": 2338707, "tid": 2379456, + "ts": 6197201835671.001, "dur": 0.695, + "args": { + "External id": 42959,"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": 2338707, "tid": 2379456, + "ts": 6197201835675.756, "dur": 3.877, + "args": { + "External id": 42960,"Record function id": 0, "Ev Idx": 11215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201835676.907, "dur": 2.274, + "args": { + "External id": 42961,"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": 2338707, "tid": 2379456, + "ts": 6197201835677.366, "dur": 1.402, + "args": { + "External id": 42962,"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": 2338707, "tid": 2379456, + "ts": 6197201835677.826, "dur": 0.876, + "args": { + "External id": 42963,"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": 2338707, "tid": 2379456, + "ts": 6197201835682.808, "dur": 3.658, + "args": { + "External id": 42964,"Record function id": 0, "Ev Idx": 11219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201835683.841, "dur": 2.229, + "args": { + "External id": 42965,"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": 2338707, "tid": 2379456, + "ts": 6197201835684.314, "dur": 1.318, + "args": { + "External id": 42966,"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": 2338707, "tid": 2379456, + "ts": 6197201835684.702, "dur": 0.865, + "args": { + "External id": 42967,"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": 2338707, "tid": 2379456, + "ts": 6197201835689.506, "dur": 5.590, + "args": { + "External id": 42968,"Record function id": 0, "Ev Idx": 11223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201835690.635, "dur": 4.058, + "args": { + "External id": 42969,"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": 2338707, "tid": 2379456, + "ts": 6197201835691.091, "dur": 3.010, + "args": { + "External id": 42970,"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": 2338707, "tid": 2379456, + "ts": 6197201835693.390, "dur": 0.643, + "args": { + "External id": 42971,"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": 2338707, "tid": 2379456, + "ts": 6197201835698.207, "dur": 19.364, + "args": { + "External id": 42972,"Record function id": 0, "Ev Idx": 11227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201835699.320, "dur": 17.071, + "args": { + "External id": 42973,"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": 2338707, "tid": 2379456, + "ts": 6197201835699.747, "dur": 15.542, + "args": { + "External id": 42974,"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": 2338707, "tid": 2379456, + "ts": 6197201835700.027, "dur": 14.832, + "args": { + "External id": 42975,"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": 2338707, "tid": 2379456, + "ts": 6197201835723.856, "dur": 61556.720, + "args": { + "External id": 42976,"Record function id": 0, "Sequence number": 480002, "Fwd thread id": 1, "Ev Idx": 11231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197201835725.716, "dur": 61544.662, + "args": { + "External id": 42977,"Sequence number": 480002, "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": 2338707, "tid": 2379456, "ts": 6197201835725.716, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.3)", "pid": 2338707, "tid": 2379456, + "ts": 6197201835755.969, "dur": 41.206, + "args": { + "External id": 42978,"Record function id": 0, "Ev Idx": 11233 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.3)", "pid": 2338707, "tid": 2379456, + "ts": 6197201835805.101, "dur": 64.986, + "args": { + "External id": 42979,"Record function id": 0, "Ev Idx": 11234 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.3)", "pid": 2338707, "tid": 2379456, + "ts": 6197201835876.012, "dur": 61386.555, + "args": { + "External id": 42980,"Record function id": 0, "Ev Idx": 11235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197201835963.914, "dur": 6.953, + "args": { + "External id": 42981,"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": 2338707, "tid": 2379456, + "ts": 6197201835980.459, "dur": 4.735, + "args": { + "External id": 42982,"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": 2338707, "tid": 2379456, + "ts": 6197201835998.707, "dur": 60270.442, + "args": { + "External id": 42983,"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": 2338707, "tid": 2379456, + "ts": 6197201836012.327, "dur": 60243.816, + "args": { + "External id": 42984,"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": 2338707, "tid": 2379456, + "ts": 6197201836137.022, "dur": 19.353, + "args": { + "External id": 42985,"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": 2338707, "tid": 2379456, + "ts": 6197201836177.609, "dur": 60035.659, + "args": { + "External id": 42986,"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": 2338707, "tid": 2379456, + "ts": 6197201836182.626, "dur": 60029.821, + "args": { + "External id": 42987,"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": 2338707, "tid": 2379456, + "ts": 6197201836186.718, "dur": 11.101, + "args": { + "External id": 42988,"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": 2338707, "tid": 2379456, + "ts": 6197201836199.985, "dur": 60007.776, + "args": { + "External id": 42989,"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": 2338707, "tid": 2379456, + "ts": 6197201896375.591, "dur": 12.620, + "args": { + "External id": 42990,"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": 2338707, "tid": 2379456, + "ts": 6197201896379.215, "dur": 8.559, + "args": { + "External id": 42991,"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": 2338707, "tid": 2379456, + "ts": 6197201896419.605, "dur": 374.077, + "args": { + "External id": 42992,"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": 2338707, "tid": 2379456, + "ts": 6197201896451.029, "dur": 336.951, + "args": { + "External id": 42993,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197201896462.264, "dur": 319.953, + "args": { + "External id": 42994,"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": 2338707, "tid": 2379456, + "ts": 6197201896819.330, "dur": 2.337, + "args": { + "External id": 42995,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2379456, + "ts": 6197201896884.690, "dur": 6.508, + "args": { + "External id": 42996,"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": 2338707, "tid": 2379456, + "ts": 6197201896903.041, "dur": 33.275, + "args": { + "External id": 42997,"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": 2338707, "tid": 2379456, + "ts": 6197201896946.880, "dur": 1.455, + "args": { + "External id": 42998,"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": 2338707, "tid": 2379456, + "ts": 6197201896953.488, "dur": 13.483, + "args": { + "External id": 42999,"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": 2338707, "tid": 2379456, + "ts": 6197201896972.041, "dur": 1.041, + "args": { + "External id": 43000,"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": 2338707, "tid": 2379456, + "ts": 6197201896976.779, "dur": 13.315, + "args": { + "External id": 43001,"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": 2338707, "tid": 2379456, + "ts": 6197201897002.276, "dur": 0.991, + "args": { + "External id": 43002,"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": 2338707, "tid": 2379456, + "ts": 6197201897006.752, "dur": 11.798, + "args": { + "External id": 43003,"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": 2338707, "tid": 2379456, + "ts": 6197201897022.920, "dur": 0.940, + "args": { + "External id": 43004,"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": 2338707, "tid": 2379456, + "ts": 6197201897029.322, "dur": 12.650, + "args": { + "External id": 43005,"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": 2338707, "tid": 2379456, + "ts": 6197201897046.039, "dur": 0.951, + "args": { + "External id": 43006,"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": 2338707, "tid": 2379456, + "ts": 6197201897051.185, "dur": 47.919, + "args": { + "External id": 43007,"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": 2338707, "tid": 2379456, + "ts": 6197201897107.293, "dur": 1.824, + "args": { + "External id": 43008,"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": 2338707, "tid": 2379456, + "ts": 6197201897130.524, "dur": 15.408, + "args": { + "External id": 43009,"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": 2338707, "tid": 2379456, + "ts": 6197201897158.607, "dur": 0.879, + "args": { + "External id": 43010,"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": 2338707, "tid": 2379456, + "ts": 6197201897163.286, "dur": 11.841, + "args": { + "External id": 43011,"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": 2338707, "tid": 2379456, + "ts": 6197201897181.800, "dur": 0.722, + "args": { + "External id": 43012,"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": 2338707, "tid": 2379456, + "ts": 6197201897186.694, "dur": 13.247, + "args": { + "External id": 43013,"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": 2338707, "tid": 2379456, + "ts": 6197201897297.306, "dur": 2861.363, + "args": { + "External id": 43014,"Record function id": 0, "Ev Idx": 11269 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.2)", "pid": 2338707, "tid": 2379456, + "ts": 6197201897319.218, "dur": 1054.524, + "args": { + "External id": 43015,"Record function id": 0, "Ev Idx": 11270 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.2)", "pid": 2338707, "tid": 2379456, + "ts": 6197201897335.350, "dur": 319.767, + "args": { + "External id": 43016,"Record function id": 0, "Ev Idx": 11271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6197201897428.094, "dur": 4.135, + "args": { + "External id": 43017,"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": 2338707, "tid": 2379456, + "ts": 6197201897435.554, "dur": 0.702, + "args": { + "External id": 43018,"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": 2338707, "tid": 2379456, + "ts": 6197201897438.003, "dur": 0.697, + "args": { + "External id": 43019,"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": 2338707, "tid": 2379456, + "ts": 6197201897440.493, "dur": 0.545, + "args": { + "External id": 43020,"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": 2338707, "tid": 2379456, + "ts": 6197201897442.883, "dur": 1.016, + "args": { + "External id": 43021,"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": 2338707, "tid": 2379456, + "ts": 6197201897447.239, "dur": 0.642, + "args": { + "External id": 43022,"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": 2338707, "tid": 2379456, + "ts": 6197201897449.292, "dur": 0.895, + "args": { + "External id": 43023,"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": 2338707, "tid": 2379456, + "ts": 6197201897451.315, "dur": 1.468, + "args": { + "External id": 43024,"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": 2338707, "tid": 2379456, + "ts": 6197201897454.424, "dur": 0.824, + "args": { + "External id": 43025,"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": 2338707, "tid": 2379456, + "ts": 6197201897458.493, "dur": 1.028, + "args": { + "External id": 43026,"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": 2338707, "tid": 2379456, + "ts": 6197201897475.306, "dur": 151.129, + "args": { + "External id": 43027,"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": 2338707, "tid": 2379456, + "ts": 6197201897490.411, "dur": 131.735, + "args": { + "External id": 43028,"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": 2338707, "tid": 2379456, + "ts": 6197201897515.004, "dur": 15.077, + "args": { + "External id": 43029,"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": 2338707, "tid": 2379456, + "ts": 6197201897533.644, "dur": 61.452, + "args": { + "External id": 43030,"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": 2338707, "tid": 2379456, + "ts": 6197201897536.356, "dur": 58.319, + "args": { + "External id": 43031,"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": 2338707, "tid": 2379456, + "ts": 6197201897539.568, "dur": 9.333, + "args": { + "External id": 43032,"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": 2338707, "tid": 2379456, + "ts": 6197201897550.444, "dur": 43.649, + "args": { + "External id": 43033,"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": 2338707, "tid": 2379456, + "ts": 6197201897770.499, "dur": 596.187, + "args": { + "External id": 43034,"Record function id": 0, "Ev Idx": 11289 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.1)", "pid": 2338707, "tid": 2379456, + "ts": 6197201897787.030, "dur": 567.546, + "args": { + "External id": 43035,"Record function id": 0, "Ev Idx": 11290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197201897850.030, "dur": 6.146, + "args": { + "External id": 43036,"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": 2338707, "tid": 2379456, + "ts": 6197201897872.546, "dur": 23.002, + "args": { + "External id": 43037,"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": 2338707, "tid": 2379456, + "ts": 6197201897877.316, "dur": 1.925, + "args": { + "External id": 43038,"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": 2338707, "tid": 2379456, + "ts": 6197201897881.583, "dur": 0.404, + "args": { + "External id": 43039,"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": 2338707, "tid": 2379456, + "ts": 6197201897882.709, "dur": 0.479, + "args": { + "External id": 43040,"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": 2338707, "tid": 2379456, + "ts": 6197201897884.351, "dur": 0.515, + "args": { + "External id": 43041,"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": 2338707, "tid": 2379456, + "ts": 6197201897885.653, "dur": 0.322, + "args": { + "External id": 43042,"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": 2338707, "tid": 2379456, + "ts": 6197201897886.717, "dur": 0.481, + "args": { + "External id": 43043,"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": 2338707, "tid": 2379456, + "ts": 6197201897888.491, "dur": 0.407, + "args": { + "External id": 43044,"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": 2338707, "tid": 2379456, + "ts": 6197201897889.772, "dur": 0.301, + "args": { + "External id": 43045,"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": 2338707, "tid": 2379456, + "ts": 6197201897890.975, "dur": 0.506, + "args": { + "External id": 43046,"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": 2338707, "tid": 2379456, + "ts": 6197201897905.497, "dur": 44.606, + "args": { + "External id": 43047,"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": 2338707, "tid": 2379456, + "ts": 6197201897978.675, "dur": 138.696, + "args": { + "External id": 43048,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2379456, + "ts": 6197201897988.284, "dur": 2.966, + "args": { + "External id": 43049,"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": 2338707, "tid": 2379456, + "ts": 6197201897995.951, "dur": 9.835, + "args": { + "External id": 43050,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2379456, + "ts": 6197201898000.196, "dur": 5.192, + "args": { + "External id": 43051,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2379456, + "ts": 6197201898003.577, "dur": 0.526, + "args": { + "External id": 43052,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197201898012.082, "dur": 18.147, + "args": { + "External id": 43053,"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": 2338707, "tid": 2379456, + "ts": 6197201898013.424, "dur": 0.693, + "args": { + "External id": 43054,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197201898015.271, "dur": 0.258, + "args": { + "External id": 43055,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2379456, + "ts": 6197201898016.175, "dur": 0.776, + "args": { + "External id": 43056,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2379456, + "ts": 6197201898018.284, "dur": 0.378, + "args": { + "External id": 43057,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2379456, + "ts": 6197201898019.218, "dur": 0.592, + "args": { + "External id": 43058,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2379456, + "ts": 6197201898020.812, "dur": 0.274, + "args": { + "External id": 43059,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2379456, + "ts": 6197201898021.631, "dur": 0.857, + "args": { + "External id": 43060,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2379456, + "ts": 6197201898023.731, "dur": 0.230, + "args": { + "External id": 43061,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2379456, + "ts": 6197201898024.474, "dur": 0.600, + "args": { + "External id": 43062,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2379456, + "ts": 6197201898039.501, "dur": 68.183, + "args": { + "External id": 43063,"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": 2338707, "tid": 2379456, + "ts": 6197201898165.639, "dur": 122.036, + "args": { + "External id": 43064,"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": 2338707, "tid": 2379456, + "ts": 6197201898193.115, "dur": 91.030, + "args": { + "External id": 43065,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197201898203.529, "dur": 76.037, + "args": { + "External id": 43066,"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": 2338707, "tid": 2379456, + "ts": 6197201898303.022, "dur": 1.933, + "args": { + "External id": 43067,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197201898380.819, "dur": 1751.915, + "args": { + "External id": 43068,"Sequence number": 480001, "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": 2338707, "tid": 2379456, "ts": 6197201898380.819, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6197201898490.019, "dur": 105.137, + "args": { + "External id": 43069,"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": 2338707, "tid": 2379456, + "ts": 6197201898634.429, "dur": 40.882, + "args": { + "External id": 43070,"kernel_hash": "cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/u7/cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs.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": 2338707, "tid": 2379456, + "ts": 6197201898692.124, "dur": 73.990, + "args": { + "External id": 43071,"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": 2338707, "tid": 2379456, + "ts": 6197201898779.835, "dur": 34.767, + "args": { + "External id": 43072,"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": 2338707, "tid": 2379456, + "ts": 6197201898820.902, "dur": 34.220, + "args": { + "External id": 43073,"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": 2338707, "tid": 2379456, + "ts": 6197201898861.802, "dur": 28.107, + "args": { + "External id": 43074,"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": 2338707, "tid": 2379456, + "ts": 6197201898896.923, "dur": 29.390, + "args": { + "External id": 43075,"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": 2338707, "tid": 2379456, + "ts": 6197201898952.683, "dur": 25.677, + "args": { + "External id": 43076,"kernel_hash": "cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/wm/cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s.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": 2338707, "tid": 2379456, + "ts": 6197201898995.402, "dur": 28.085, + "args": { + "External id": 43077,"kernel_hash": "cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql", "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/qt/cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql.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": 2338707, "tid": 2379456, + "ts": 6197201899045.012, "dur": 59.242, + "args": { + "External id": 43078,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197201899121.267, "dur": 18.119, + "args": { + "External id": 43079,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197201899148.273, "dur": 48.323, + "args": { + "External id": 43080,"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": 2338707, "tid": 2379456, + "ts": 6197201899200.249, "dur": 34.438, + "args": { + "External id": 43081,"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": 2338707, "tid": 2379456, + "ts": 6197201899264.913, "dur": 230.508, + "args": { + "External id": 43082,"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": 2338707, "tid": 2379456, + "ts": 6197201899339.712, "dur": 6.081, + "args": { + "External id": 43083,"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": 2338707, "tid": 2379456, + "ts": 6197201899347.782, "dur": 2.545, + "args": { + "External id": 43084,"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": 2338707, "tid": 2379456, + "ts": 6197201899351.152, "dur": 2.299, + "args": { + "External id": 43085,"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": 2338707, "tid": 2379456, + "ts": 6197201899354.301, "dur": 2.439, + "args": { + "External id": 43086,"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": 2338707, "tid": 2379456, + "ts": 6197201899399.952, "dur": 4.950, + "args": { + "External id": 43087,"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": 2338707, "tid": 2379456, + "ts": 6197201899401.985, "dur": 2.735, + "args": { + "External id": 43088,"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": 2338707, "tid": 2379456, + "ts": 6197201899406.472, "dur": 30.246, + "args": { + "External id": 43089,"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": 2338707, "tid": 2379456, + "ts": 6197201899411.832, "dur": 1.741, + "args": { + "External id": 43090,"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": 2338707, "tid": 2379456, + "ts": 6197201899438.382, "dur": 1.484, + "args": { + "External id": 43091,"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": 2338707, "tid": 2379456, + "ts": 6197201899439.309, "dur": 0.483, + "args": { + "External id": 43092,"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": 2338707, "tid": 2379456, + "ts": 6197201899440.795, "dur": 14.003, + "args": { + "External id": 43093,"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": 2338707, "tid": 2379456, + "ts": 6197201899442.394, "dur": 0.911, + "args": { + "External id": 43094,"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": 2338707, "tid": 2379456, + "ts": 6197201899531.993, "dur": 26.883, + "args": { + "External id": 43095,"kernel_hash": "cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4", "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/yk/cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4.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": 2338707, "tid": 2379456, + "ts": 6197201899575.820, "dur": 15.885, + "args": { + "External id": 43096,"kernel_hash": "ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg", "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/eu/ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg.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": 2338707, "tid": 2379456, + "ts": 6197201899599.574, "dur": 42.202, + "args": { + "External id": 43097,"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": 2338707, "tid": 2379456, + "ts": 6197201899648.160, "dur": 39.432, + "args": { + "External id": 43098,"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": 2338707, "tid": 2379456, + "ts": 6197201899695.123, "dur": 39.918, + "args": { + "External id": 43099,"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": 2338707, "tid": 2379456, + "ts": 6197201899743.507, "dur": 33.296, + "args": { + "External id": 43100,"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": 2338707, "tid": 2379456, + "ts": 6197201899784.152, "dur": 28.597, + "args": { + "External id": 43101,"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": 2338707, "tid": 2379456, + "ts": 6197201899819.171, "dur": 32.163, + "args": { + "External id": 43102,"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": 2338707, "tid": 2379456, + "ts": 6197201899871.961, "dur": 23.941, + "args": { + "External id": 43103,"kernel_hash": "c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/6w/c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7.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": 2338707, "tid": 2379456, + "ts": 6197201899915.957, "dur": 25.205, + "args": { + "External id": 43104,"kernel_hash": "ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx", "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/kj/ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx.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": 2338707, "tid": 2379456, + "ts": 6197201899967.485, "dur": 28.987, + "args": { + "External id": 43105,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197201900017.483, "dur": 14.909, + "args": { + "External id": 43106,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197201900045.989, "dur": 53.956, + "args": { + "External id": 43107,"kernel_hash": "cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/eb/cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b.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": 2338707, "tid": 2379456, + "ts": 6197201900181.178, "dur": 16.349, + "args": { + "External id": 43108,"Record function id": 0, "Ev Idx": 11363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201900184.992, "dur": 11.410, + "args": { + "External id": 43109,"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": 2338707, "tid": 2379456, + "ts": 6197201900189.534, "dur": 6.007, + "args": { + "External id": 43110,"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": 2338707, "tid": 2379456, + "ts": 6197201900191.215, "dur": 4.197, + "args": { + "External id": 43111,"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": 2338707, "tid": 2379456, + "ts": 6197201900201.525, "dur": 4.716, + "args": { + "External id": 43112,"Record function id": 0, "Ev Idx": 11367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201900203.188, "dur": 2.589, + "args": { + "External id": 43113,"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": 2338707, "tid": 2379456, + "ts": 6197201900203.806, "dur": 1.525, + "args": { + "External id": 43114,"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": 2338707, "tid": 2379456, + "ts": 6197201900204.348, "dur": 0.876, + "args": { + "External id": 43115,"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": 2338707, "tid": 2379456, + "ts": 6197201900209.558, "dur": 4.341, + "args": { + "External id": 43116,"Record function id": 0, "Ev Idx": 11371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201900210.870, "dur": 2.593, + "args": { + "External id": 43117,"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": 2338707, "tid": 2379456, + "ts": 6197201900211.648, "dur": 1.234, + "args": { + "External id": 43118,"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": 2338707, "tid": 2379456, + "ts": 6197201900212.165, "dur": 0.653, + "args": { + "External id": 43119,"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": 2338707, "tid": 2379456, + "ts": 6197201900217.053, "dur": 4.157, + "args": { + "External id": 43120,"Record function id": 0, "Ev Idx": 11375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201900218.023, "dur": 2.785, + "args": { + "External id": 43121,"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": 2338707, "tid": 2379456, + "ts": 6197201900218.479, "dur": 1.672, + "args": { + "External id": 43122,"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": 2338707, "tid": 2379456, + "ts": 6197201900218.993, "dur": 1.090, + "args": { + "External id": 43123,"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": 2338707, "tid": 2379456, + "ts": 6197201900227.253, "dur": 5.657, + "args": { + "External id": 43124,"Record function id": 0, "Ev Idx": 11379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201900228.337, "dur": 4.096, + "args": { + "External id": 43125,"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": 2338707, "tid": 2379456, + "ts": 6197201900228.774, "dur": 3.022, + "args": { + "External id": 43126,"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": 2338707, "tid": 2379456, + "ts": 6197201900230.916, "dur": 0.781, + "args": { + "External id": 43127,"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": 2338707, "tid": 2379456, + "ts": 6197201900236.037, "dur": 3.508, + "args": { + "External id": 43128,"Record function id": 0, "Ev Idx": 11383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201900237.276, "dur": 1.862, + "args": { + "External id": 43129,"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": 2338707, "tid": 2379456, + "ts": 6197201900237.744, "dur": 0.999, + "args": { + "External id": 43130,"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": 2338707, "tid": 2379456, + "ts": 6197201900238.064, "dur": 0.597, + "args": { + "External id": 43131,"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": 2338707, "tid": 2379456, + "ts": 6197201900242.754, "dur": 3.385, + "args": { + "External id": 43132,"Record function id": 0, "Ev Idx": 11387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201900243.723, "dur": 2.022, + "args": { + "External id": 43133,"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": 2338707, "tid": 2379456, + "ts": 6197201900244.152, "dur": 1.202, + "args": { + "External id": 43134,"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": 2338707, "tid": 2379456, + "ts": 6197201900244.545, "dur": 0.743, + "args": { + "External id": 43135,"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": 2338707, "tid": 2379456, + "ts": 6197201900249.308, "dur": 4.052, + "args": { + "External id": 43136,"Record function id": 0, "Ev Idx": 11391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201900250.354, "dur": 2.611, + "args": { + "External id": 43137,"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": 2338707, "tid": 2379456, + "ts": 6197201900250.803, "dur": 1.771, + "args": { + "External id": 43138,"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": 2338707, "tid": 2379456, + "ts": 6197201900251.228, "dur": 1.281, + "args": { + "External id": 43139,"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": 2338707, "tid": 2379456, + "ts": 6197201900256.426, "dur": 3.839, + "args": { + "External id": 43140,"Record function id": 0, "Ev Idx": 11395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201900257.515, "dur": 2.321, + "args": { + "External id": 43141,"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": 2338707, "tid": 2379456, + "ts": 6197201900258.119, "dur": 1.145, + "args": { + "External id": 43142,"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": 2338707, "tid": 2379456, + "ts": 6197201900258.511, "dur": 0.687, + "args": { + "External id": 43143,"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": 2338707, "tid": 2379456, + "ts": 6197201900264.188, "dur": 62632.899, + "args": { + "External id": 43144,"Record function id": 0, "Sequence number": 480000, "Fwd thread id": 1, "Ev Idx": 11399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197201900265.764, "dur": 62621.506, + "args": { + "External id": 43145,"Sequence number": 480000, "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": 2338707, "tid": 2379456, "ts": 6197201900265.764, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.2)", "pid": 2338707, "tid": 2379456, + "ts": 6197201900295.044, "dur": 39.065, + "args": { + "External id": 43146,"Record function id": 0, "Ev Idx": 11401 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.2)", "pid": 2338707, "tid": 2379456, + "ts": 6197201900342.063, "dur": 65.115, + "args": { + "External id": 43147,"Record function id": 0, "Ev Idx": 11402 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.2)", "pid": 2338707, "tid": 2379456, + "ts": 6197201900412.922, "dur": 62466.669, + "args": { + "External id": 43148,"Record function id": 0, "Ev Idx": 11403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197201900504.218, "dur": 6.743, + "args": { + "External id": 43149,"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": 2338707, "tid": 2379456, + "ts": 6197201900520.518, "dur": 4.431, + "args": { + "External id": 43150,"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": 2338707, "tid": 2379456, + "ts": 6197201900538.933, "dur": 61427.077, + "args": { + "External id": 43151,"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": 2338707, "tid": 2379456, + "ts": 6197201900552.359, "dur": 61401.512, + "args": { + "External id": 43152,"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": 2338707, "tid": 2379456, + "ts": 6197201900651.149, "dur": 16.937, + "args": { + "External id": 43153,"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": 2338707, "tid": 2379456, + "ts": 6197201900688.561, "dur": 61221.005, + "args": { + "External id": 43154,"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": 2338707, "tid": 2379456, + "ts": 6197201900691.213, "dur": 61217.478, + "args": { + "External id": 43155,"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": 2338707, "tid": 2379456, + "ts": 6197201900695.711, "dur": 28.662, + "args": { + "External id": 43156,"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": 2338707, "tid": 2379456, + "ts": 6197201900727.283, "dur": 61176.263, + "args": { + "External id": 43157,"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": 2338707, "tid": 2379456, + "ts": 6197201962107.630, "dur": 12.605, + "args": { + "External id": 43158,"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": 2338707, "tid": 2379456, + "ts": 6197201962110.933, "dur": 8.644, + "args": { + "External id": 43159,"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": 2338707, "tid": 2379456, + "ts": 6197201962151.545, "dur": 324.830, + "args": { + "External id": 43160,"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": 2338707, "tid": 2379456, + "ts": 6197201962181.473, "dur": 290.139, + "args": { + "External id": 43161,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197201962192.539, "dur": 273.955, + "args": { + "External id": 43162,"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": 2338707, "tid": 2379456, + "ts": 6197201962496.426, "dur": 2.141, + "args": { + "External id": 43163,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2379456, + "ts": 6197201962555.269, "dur": 6.323, + "args": { + "External id": 43164,"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": 2338707, "tid": 2379456, + "ts": 6197201962573.089, "dur": 35.679, + "args": { + "External id": 43165,"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": 2338707, "tid": 2379456, + "ts": 6197201962619.455, "dur": 2.164, + "args": { + "External id": 43166,"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": 2338707, "tid": 2379456, + "ts": 6197201962627.033, "dur": 13.505, + "args": { + "External id": 43167,"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": 2338707, "tid": 2379456, + "ts": 6197201962645.853, "dur": 0.958, + "args": { + "External id": 43168,"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": 2338707, "tid": 2379456, + "ts": 6197201962650.828, "dur": 17.183, + "args": { + "External id": 43169,"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": 2338707, "tid": 2379456, + "ts": 6197201962673.066, "dur": 0.847, + "args": { + "External id": 43170,"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": 2338707, "tid": 2379456, + "ts": 6197201962677.251, "dur": 11.026, + "args": { + "External id": 43171,"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": 2338707, "tid": 2379456, + "ts": 6197201962694.004, "dur": 1.054, + "args": { + "External id": 43172,"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": 2338707, "tid": 2379456, + "ts": 6197201962699.093, "dur": 31.260, + "args": { + "External id": 43173,"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": 2338707, "tid": 2379456, + "ts": 6197201962738.168, "dur": 1.550, + "args": { + "External id": 43174,"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": 2338707, "tid": 2379456, + "ts": 6197201962743.828, "dur": 12.687, + "args": { + "External id": 43175,"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": 2338707, "tid": 2379456, + "ts": 6197201962760.337, "dur": 0.744, + "args": { + "External id": 43176,"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": 2338707, "tid": 2379456, + "ts": 6197201962764.273, "dur": 12.098, + "args": { + "External id": 43177,"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": 2338707, "tid": 2379456, + "ts": 6197201962782.006, "dur": 0.934, + "args": { + "External id": 43178,"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": 2338707, "tid": 2379456, + "ts": 6197201962786.307, "dur": 12.137, + "args": { + "External id": 43179,"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": 2338707, "tid": 2379456, + "ts": 6197201962802.375, "dur": 0.868, + "args": { + "External id": 43180,"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": 2338707, "tid": 2379456, + "ts": 6197201962806.724, "dur": 12.502, + "args": { + "External id": 43181,"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": 2338707, "tid": 2379456, + "ts": 6197201962912.940, "dur": 2834.302, + "args": { + "External id": 43182,"Record function id": 0, "Ev Idx": 11437 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.1)", "pid": 2338707, "tid": 2379456, + "ts": 6197201962936.432, "dur": 1058.273, + "args": { + "External id": 43183,"Record function id": 0, "Ev Idx": 11438 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.1)", "pid": 2338707, "tid": 2379456, + "ts": 6197201962950.510, "dur": 369.494, + "args": { + "External id": 43184,"Record function id": 0, "Ev Idx": 11439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6197201963040.025, "dur": 4.580, + "args": { + "External id": 43185,"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": 2338707, "tid": 2379456, + "ts": 6197201963048.248, "dur": 0.850, + "args": { + "External id": 43186,"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": 2338707, "tid": 2379456, + "ts": 6197201963051.224, "dur": 0.838, + "args": { + "External id": 43187,"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": 2338707, "tid": 2379456, + "ts": 6197201963089.946, "dur": 1.471, + "args": { + "External id": 43188,"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": 2338707, "tid": 2379456, + "ts": 6197201963093.371, "dur": 0.970, + "args": { + "External id": 43189,"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": 2338707, "tid": 2379456, + "ts": 6197201963095.788, "dur": 0.733, + "args": { + "External id": 43190,"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": 2338707, "tid": 2379456, + "ts": 6197201963098.084, "dur": 0.878, + "args": { + "External id": 43191,"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": 2338707, "tid": 2379456, + "ts": 6197201963101.968, "dur": 0.836, + "args": { + "External id": 43192,"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": 2338707, "tid": 2379456, + "ts": 6197201963104.141, "dur": 0.638, + "args": { + "External id": 43193,"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": 2338707, "tid": 2379456, + "ts": 6197201963105.948, "dur": 0.854, + "args": { + "External id": 43194,"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": 2338707, "tid": 2379456, + "ts": 6197201963132.815, "dur": 154.937, + "args": { + "External id": 43195,"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": 2338707, "tid": 2379456, + "ts": 6197201963148.419, "dur": 134.459, + "args": { + "External id": 43196,"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": 2338707, "tid": 2379456, + "ts": 6197201963163.060, "dur": 24.904, + "args": { + "External id": 43197,"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": 2338707, "tid": 2379456, + "ts": 6197201963192.822, "dur": 62.694, + "args": { + "External id": 43198,"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": 2338707, "tid": 2379456, + "ts": 6197201963195.427, "dur": 59.749, + "args": { + "External id": 43199,"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": 2338707, "tid": 2379456, + "ts": 6197201963199.043, "dur": 6.857, + "args": { + "External id": 43200,"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": 2338707, "tid": 2379456, + "ts": 6197201963207.440, "dur": 47.060, + "args": { + "External id": 43201,"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": 2338707, "tid": 2379456, + "ts": 6197201963412.472, "dur": 575.054, + "args": { + "External id": 43202,"Record function id": 0, "Ev Idx": 11457 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.0)", "pid": 2338707, "tid": 2379456, + "ts": 6197201963430.603, "dur": 545.021, + "args": { + "External id": 43203,"Record function id": 0, "Ev Idx": 11458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197201963497.244, "dur": 5.120, + "args": { + "External id": 43204,"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": 2338707, "tid": 2379456, + "ts": 6197201963517.058, "dur": 23.951, + "args": { + "External id": 43205,"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": 2338707, "tid": 2379456, + "ts": 6197201963521.465, "dur": 1.827, + "args": { + "External id": 43206,"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": 2338707, "tid": 2379456, + "ts": 6197201963525.409, "dur": 0.589, + "args": { + "External id": 43207,"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": 2338707, "tid": 2379456, + "ts": 6197201963527.256, "dur": 0.460, + "args": { + "External id": 43208,"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": 2338707, "tid": 2379456, + "ts": 6197201963529.281, "dur": 0.586, + "args": { + "External id": 43209,"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": 2338707, "tid": 2379456, + "ts": 6197201963530.931, "dur": 0.752, + "args": { + "External id": 43210,"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": 2338707, "tid": 2379456, + "ts": 6197201963533.236, "dur": 0.638, + "args": { + "External id": 43211,"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": 2338707, "tid": 2379456, + "ts": 6197201963534.879, "dur": 0.355, + "args": { + "External id": 43212,"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": 2338707, "tid": 2379456, + "ts": 6197201963536.257, "dur": 0.667, + "args": { + "External id": 43213,"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": 2338707, "tid": 2379456, + "ts": 6197201963537.821, "dur": 0.198, + "args": { + "External id": 43214,"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": 2338707, "tid": 2379456, + "ts": 6197201963550.847, "dur": 42.210, + "args": { + "External id": 43215,"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": 2338707, "tid": 2379456, + "ts": 6197201963621.440, "dur": 126.572, + "args": { + "External id": 43216,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2379456, + "ts": 6197201963630.427, "dur": 3.022, + "args": { + "External id": 43217,"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": 2338707, "tid": 2379456, + "ts": 6197201963638.289, "dur": 9.350, + "args": { + "External id": 43218,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2379456, + "ts": 6197201963642.397, "dur": 4.822, + "args": { + "External id": 43219,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2379456, + "ts": 6197201963645.197, "dur": 0.572, + "args": { + "External id": 43220,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197201963653.532, "dur": 22.938, + "args": { + "External id": 43221,"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": 2338707, "tid": 2379456, + "ts": 6197201963654.843, "dur": 0.255, + "args": { + "External id": 43222,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2379456, + "ts": 6197201963656.423, "dur": 4.151, + "args": { + "External id": 43223,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2379456, + "ts": 6197201963661.834, "dur": 0.242, + "args": { + "External id": 43224,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2379456, + "ts": 6197201963662.707, "dur": 0.862, + "args": { + "External id": 43225,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2379456, + "ts": 6197201963664.892, "dur": 0.560, + "args": { + "External id": 43226,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2379456, + "ts": 6197201963666.652, "dur": 0.455, + "args": { + "External id": 43227,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2379456, + "ts": 6197201963668.301, "dur": 0.344, + "args": { + "External id": 43228,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2379456, + "ts": 6197201963669.341, "dur": 0.918, + "args": { + "External id": 43229,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2379456, + "ts": 6197201963671.211, "dur": 0.345, + "args": { + "External id": 43230,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2379456, + "ts": 6197201963688.282, "dur": 50.662, + "args": { + "External id": 43231,"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": 2338707, "tid": 2379456, + "ts": 6197201963793.941, "dur": 114.351, + "args": { + "External id": 43232,"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": 2338707, "tid": 2379456, + "ts": 6197201963821.102, "dur": 83.292, + "args": { + "External id": 43233,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197201963830.256, "dur": 70.091, + "args": { + "External id": 43234,"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": 2338707, "tid": 2379456, + "ts": 6197201963924.380, "dur": 1.879, + "args": { + "External id": 43235,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197201964001.594, "dur": 1721.477, + "args": { + "External id": 43236,"Sequence number": 479999, "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": 2338707, "tid": 2379456, "ts": 6197201964001.594, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6197201964153.726, "dur": 118.413, + "args": { + "External id": 43237,"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": 2338707, "tid": 2379456, + "ts": 6197201964313.599, "dur": 43.922, + "args": { + "External id": 43238,"kernel_hash": "cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/u7/cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs.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": 2338707, "tid": 2379456, + "ts": 6197201964374.661, "dur": 51.017, + "args": { + "External id": 43239,"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": 2338707, "tid": 2379456, + "ts": 6197201964435.209, "dur": 32.375, + "args": { + "External id": 43240,"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": 2338707, "tid": 2379456, + "ts": 6197201964474.250, "dur": 33.338, + "args": { + "External id": 43241,"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": 2338707, "tid": 2379456, + "ts": 6197201964513.996, "dur": 29.319, + "args": { + "External id": 43242,"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": 2338707, "tid": 2379456, + "ts": 6197201964550.812, "dur": 29.051, + "args": { + "External id": 43243,"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": 2338707, "tid": 2379456, + "ts": 6197201964602.230, "dur": 22.866, + "args": { + "External id": 43244,"kernel_hash": "cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/wm/cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s.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": 2338707, "tid": 2379456, + "ts": 6197201964643.468, "dur": 27.931, + "args": { + "External id": 43245,"kernel_hash": "cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql", "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/qt/cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql.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": 2338707, "tid": 2379456, + "ts": 6197201964693.429, "dur": 36.760, + "args": { + "External id": 43246,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197201964746.535, "dur": 17.802, + "args": { + "External id": 43247,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197201964772.719, "dur": 41.547, + "args": { + "External id": 43248,"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": 2338707, "tid": 2379456, + "ts": 6197201964817.905, "dur": 34.119, + "args": { + "External id": 43249,"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": 2338707, "tid": 2379456, + "ts": 6197201964878.623, "dur": 283.897, + "args": { + "External id": 43250,"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": 2338707, "tid": 2379456, + "ts": 6197201964952.441, "dur": 9.587, + "args": { + "External id": 43251,"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": 2338707, "tid": 2379456, + "ts": 6197201964963.866, "dur": 2.473, + "args": { + "External id": 43252,"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": 2338707, "tid": 2379456, + "ts": 6197201964967.648, "dur": 1.675, + "args": { + "External id": 43253,"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": 2338707, "tid": 2379456, + "ts": 6197201964970.167, "dur": 1.926, + "args": { + "External id": 43254,"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": 2338707, "tid": 2379456, + "ts": 6197201965020.067, "dur": 4.564, + "args": { + "External id": 43255,"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": 2338707, "tid": 2379456, + "ts": 6197201965021.753, "dur": 2.693, + "args": { + "External id": 43256,"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": 2338707, "tid": 2379456, + "ts": 6197201965026.197, "dur": 67.867, + "args": { + "External id": 43257,"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": 2338707, "tid": 2379456, + "ts": 6197201965031.533, "dur": 1.766, + "args": { + "External id": 43258,"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": 2338707, "tid": 2379456, + "ts": 6197201965096.964, "dur": 2.132, + "args": { + "External id": 43259,"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": 2338707, "tid": 2379456, + "ts": 6197201965097.876, "dur": 1.097, + "args": { + "External id": 43260,"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": 2338707, "tid": 2379456, + "ts": 6197201965100.115, "dur": 17.769, + "args": { + "External id": 43261,"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": 2338707, "tid": 2379456, + "ts": 6197201965102.683, "dur": 1.496, + "args": { + "External id": 43262,"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": 2338707, "tid": 2379456, + "ts": 6197201965200.889, "dur": 27.542, + "args": { + "External id": 43263,"kernel_hash": "cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4", "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/yk/cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4.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": 2338707, "tid": 2379456, + "ts": 6197201965245.538, "dur": 15.030, + "args": { + "External id": 43264,"kernel_hash": "ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg", "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/eu/ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg.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": 2338707, "tid": 2379456, + "ts": 6197201965268.221, "dur": 50.000, + "args": { + "External id": 43265,"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": 2338707, "tid": 2379456, + "ts": 6197201965325.084, "dur": 43.557, + "args": { + "External id": 43266,"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": 2338707, "tid": 2379456, + "ts": 6197201965376.104, "dur": 22.104, + "args": { + "External id": 43267,"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": 2338707, "tid": 2379456, + "ts": 6197201965403.625, "dur": 31.795, + "args": { + "External id": 43268,"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": 2338707, "tid": 2379456, + "ts": 6197201965442.346, "dur": 28.064, + "args": { + "External id": 43269,"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": 2338707, "tid": 2379456, + "ts": 6197201965477.041, "dur": 30.915, + "args": { + "External id": 43270,"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": 2338707, "tid": 2379456, + "ts": 6197201965528.406, "dur": 23.589, + "args": { + "External id": 43271,"kernel_hash": "c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/6w/c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7.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": 2338707, "tid": 2379456, + "ts": 6197201965567.989, "dur": 23.528, + "args": { + "External id": 43272,"kernel_hash": "ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx", "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/kj/ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx.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": 2338707, "tid": 2379456, + "ts": 6197201965607.923, "dur": 16.322, + "args": { + "External id": 43273,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197201965637.467, "dur": 14.229, + "args": { + "External id": 43274,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197201965664.902, "dur": 15.302, + "args": { + "External id": 43275,"kernel_hash": "cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/eb/cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b.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": 2338707, "tid": 2379456, + "ts": 6197201965769.024, "dur": 15.414, + "args": { + "External id": 43276,"Record function id": 0, "Ev Idx": 11531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201965772.790, "dur": 10.756, + "args": { + "External id": 43277,"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": 2338707, "tid": 2379456, + "ts": 6197201965776.736, "dur": 5.906, + "args": { + "External id": 43278,"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": 2338707, "tid": 2379456, + "ts": 6197201965778.577, "dur": 3.959, + "args": { + "External id": 43279,"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": 2338707, "tid": 2379456, + "ts": 6197201965788.302, "dur": 3.874, + "args": { + "External id": 43280,"Record function id": 0, "Ev Idx": 11535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201965789.456, "dur": 2.293, + "args": { + "External id": 43281,"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": 2338707, "tid": 2379456, + "ts": 6197201965790.073, "dur": 1.216, + "args": { + "External id": 43282,"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": 2338707, "tid": 2379456, + "ts": 6197201965790.528, "dur": 0.694, + "args": { + "External id": 43283,"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": 2338707, "tid": 2379456, + "ts": 6197201965795.489, "dur": 20.113, + "args": { + "External id": 43284,"Record function id": 0, "Ev Idx": 11539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201965808.783, "dur": 5.954, + "args": { + "External id": 43285,"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": 2338707, "tid": 2379456, + "ts": 6197201965810.495, "dur": 2.503, + "args": { + "External id": 43286,"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": 2338707, "tid": 2379456, + "ts": 6197201965811.504, "dur": 1.255, + "args": { + "External id": 43287,"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": 2338707, "tid": 2379456, + "ts": 6197201965820.704, "dur": 3.832, + "args": { + "External id": 43288,"Record function id": 0, "Ev Idx": 11543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201965822.090, "dur": 2.057, + "args": { + "External id": 43289,"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": 2338707, "tid": 2379456, + "ts": 6197201965822.583, "dur": 1.076, + "args": { + "External id": 43290,"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": 2338707, "tid": 2379456, + "ts": 6197201965822.956, "dur": 0.641, + "args": { + "External id": 43291,"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": 2338707, "tid": 2379456, + "ts": 6197201965827.677, "dur": 4.800, + "args": { + "External id": 43292,"Record function id": 0, "Ev Idx": 11547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201965828.997, "dur": 3.080, + "args": { + "External id": 43293,"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": 2338707, "tid": 2379456, + "ts": 6197201965829.630, "dur": 1.912, + "args": { + "External id": 43294,"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": 2338707, "tid": 2379456, + "ts": 6197201965830.201, "dur": 1.279, + "args": { + "External id": 43295,"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": 2338707, "tid": 2379456, + "ts": 6197201965835.559, "dur": 4.163, + "args": { + "External id": 43296,"Record function id": 0, "Ev Idx": 11551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201965836.538, "dur": 2.804, + "args": { + "External id": 43297,"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": 2338707, "tid": 2379456, + "ts": 6197201965837.244, "dur": 1.491, + "args": { + "External id": 43298,"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": 2338707, "tid": 2379456, + "ts": 6197201965838.071, "dur": 0.575, + "args": { + "External id": 43299,"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": 2338707, "tid": 2379456, + "ts": 6197201965842.931, "dur": 3.220, + "args": { + "External id": 43300,"Record function id": 0, "Ev Idx": 11555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201965843.844, "dur": 1.908, + "args": { + "External id": 43301,"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": 2338707, "tid": 2379456, + "ts": 6197201965844.450, "dur": 0.897, + "args": { + "External id": 43302,"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": 2338707, "tid": 2379456, + "ts": 6197201965844.740, "dur": 0.529, + "args": { + "External id": 43303,"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": 2338707, "tid": 2379456, + "ts": 6197201965849.097, "dur": 2.996, + "args": { + "External id": 43304,"Record function id": 0, "Ev Idx": 11559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201965850.081, "dur": 1.602, + "args": { + "External id": 43305,"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": 2338707, "tid": 2379456, + "ts": 6197201965850.482, "dur": 0.755, + "args": { + "External id": 43306,"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": 2338707, "tid": 2379456, + "ts": 6197201965850.711, "dur": 0.460, + "args": { + "External id": 43307,"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": 2338707, "tid": 2379456, + "ts": 6197201965855.166, "dur": 4.165, + "args": { + "External id": 43308,"Record function id": 0, "Ev Idx": 11563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197201965856.707, "dur": 2.250, + "args": { + "External id": 43309,"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": 2338707, "tid": 2379456, + "ts": 6197201965857.131, "dur": 1.187, + "args": { + "External id": 43310,"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": 2338707, "tid": 2379456, + "ts": 6197201965857.557, "dur": 0.698, + "args": { + "External id": 43311,"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": 2338707, "tid": 2379456, + "ts": 6197201965863.537, "dur": 64813.512, + "args": { + "External id": 43312,"Record function id": 0, "Sequence number": 479998, "Fwd thread id": 1, "Ev Idx": 11567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197201965865.015, "dur": 64803.119, + "args": { + "External id": 43313,"Sequence number": 479998, "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": 2338707, "tid": 2379456, "ts": 6197201965865.015, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.1)", "pid": 2338707, "tid": 2379456, + "ts": 6197201965897.613, "dur": 39.118, + "args": { + "External id": 43314,"Record function id": 0, "Ev Idx": 11569 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.1)", "pid": 2338707, "tid": 2379456, + "ts": 6197201965943.442, "dur": 73.568, + "args": { + "External id": 43315,"Record function id": 0, "Ev Idx": 11570 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.1)", "pid": 2338707, "tid": 2379456, + "ts": 6197201966024.525, "dur": 64636.712, + "args": { + "External id": 43316,"Record function id": 0, "Ev Idx": 11571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197201966148.349, "dur": 7.717, + "args": { + "External id": 43317,"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": 2338707, "tid": 2379456, + "ts": 6197201966166.472, "dur": 4.817, + "args": { + "External id": 43318,"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": 2338707, "tid": 2379456, + "ts": 6197201966185.859, "dur": 63571.583, + "args": { + "External id": 43319,"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": 2338707, "tid": 2379456, + "ts": 6197201966199.616, "dur": 63545.044, + "args": { + "External id": 43320,"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": 2338707, "tid": 2379456, + "ts": 6197201966294.060, "dur": 17.522, + "args": { + "External id": 43321,"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": 2338707, "tid": 2379456, + "ts": 6197201966331.813, "dur": 63357.662, + "args": { + "External id": 43322,"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": 2338707, "tid": 2379456, + "ts": 6197201966334.699, "dur": 63353.757, + "args": { + "External id": 43323,"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": 2338707, "tid": 2379456, + "ts": 6197201966339.278, "dur": 8.989, + "args": { + "External id": 43324,"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": 2338707, "tid": 2379456, + "ts": 6197201966350.176, "dur": 63333.571, + "args": { + "External id": 43325,"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": 2338707, "tid": 2379456, + "ts": 6197202029860.452, "dur": 11.830, + "args": { + "External id": 43326,"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": 2338707, "tid": 2379456, + "ts": 6197202029863.787, "dur": 8.062, + "args": { + "External id": 43327,"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": 2338707, "tid": 2379456, + "ts": 6197202029900.236, "dur": 382.416, + "args": { + "External id": 43328,"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": 2338707, "tid": 2379456, + "ts": 6197202029930.660, "dur": 347.023, + "args": { + "External id": 43329,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197202029941.780, "dur": 329.936, + "args": { + "External id": 43330,"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": 2338707, "tid": 2379456, + "ts": 6197202030306.129, "dur": 2.270, + "args": { + "External id": 43331,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2379456, + "ts": 6197202030366.736, "dur": 6.615, + "args": { + "External id": 43332,"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": 2338707, "tid": 2379456, + "ts": 6197202030385.035, "dur": 32.964, + "args": { + "External id": 43333,"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": 2338707, "tid": 2379456, + "ts": 6197202030428.482, "dur": 1.368, + "args": { + "External id": 43334,"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": 2338707, "tid": 2379456, + "ts": 6197202030439.625, "dur": 13.386, + "args": { + "External id": 43335,"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": 2338707, "tid": 2379456, + "ts": 6197202030458.312, "dur": 0.861, + "args": { + "External id": 43336,"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": 2338707, "tid": 2379456, + "ts": 6197202030462.799, "dur": 12.523, + "args": { + "External id": 43337,"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": 2338707, "tid": 2379456, + "ts": 6197202030481.183, "dur": 1.415, + "args": { + "External id": 43338,"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": 2338707, "tid": 2379456, + "ts": 6197202030486.112, "dur": 12.140, + "args": { + "External id": 43339,"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": 2338707, "tid": 2379456, + "ts": 6197202030502.469, "dur": 0.798, + "args": { + "External id": 43340,"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": 2338707, "tid": 2379456, + "ts": 6197202030507.693, "dur": 12.520, + "args": { + "External id": 43341,"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": 2338707, "tid": 2379456, + "ts": 6197202030524.946, "dur": 0.766, + "args": { + "External id": 43342,"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": 2338707, "tid": 2379456, + "ts": 6197202030528.926, "dur": 11.563, + "args": { + "External id": 43343,"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": 2338707, "tid": 2379456, + "ts": 6197202030546.247, "dur": 1.342, + "args": { + "External id": 43344,"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": 2338707, "tid": 2379456, + "ts": 6197202030551.285, "dur": 12.757, + "args": { + "External id": 43345,"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": 2338707, "tid": 2379456, + "ts": 6197202030568.018, "dur": 0.722, + "args": { + "External id": 43346,"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": 2338707, "tid": 2379456, + "ts": 6197202030572.383, "dur": 11.770, + "args": { + "External id": 43347,"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": 2338707, "tid": 2379456, + "ts": 6197202030588.406, "dur": 0.865, + "args": { + "External id": 43348,"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": 2338707, "tid": 2379456, + "ts": 6197202030592.813, "dur": 12.193, + "args": { + "External id": 43349,"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": 2338707, "tid": 2379456, + "ts": 6197202030690.732, "dur": 2233.817, + "args": { + "External id": 43350,"Record function id": 0, "Ev Idx": 11605 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.0)", "pid": 2338707, "tid": 2379456, + "ts": 6197202030727.860, "dur": 484.083, + "args": { + "External id": 43351,"Record function id": 0, "Ev Idx": 11606 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.0)", "pid": 2338707, "tid": 2379456, + "ts": 6197202030742.872, "dur": 363.113, + "args": { + "External id": 43352,"Record function id": 0, "Ev Idx": 11607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6197202030836.394, "dur": 5.100, + "args": { + "External id": 43353,"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": 2338707, "tid": 2379456, + "ts": 6197202030845.026, "dur": 1.008, + "args": { + "External id": 43354,"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": 2338707, "tid": 2379456, + "ts": 6197202030847.617, "dur": 1.230, + "args": { + "External id": 43355,"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": 2338707, "tid": 2379456, + "ts": 6197202030850.343, "dur": 1.454, + "args": { + "External id": 43356,"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": 2338707, "tid": 2379456, + "ts": 6197202030853.474, "dur": 0.894, + "args": { + "External id": 43357,"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": 2338707, "tid": 2379456, + "ts": 6197202030856.972, "dur": 0.903, + "args": { + "External id": 43358,"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": 2338707, "tid": 2379456, + "ts": 6197202030859.412, "dur": 4.322, + "args": { + "External id": 43359,"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": 2338707, "tid": 2379456, + "ts": 6197202030865.130, "dur": 1.275, + "args": { + "External id": 43360,"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": 2338707, "tid": 2379456, + "ts": 6197202030867.954, "dur": 1.119, + "args": { + "External id": 43361,"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": 2338707, "tid": 2379456, + "ts": 6197202030871.794, "dur": 1.109, + "args": { + "External id": 43362,"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": 2338707, "tid": 2379456, + "ts": 6197202030889.006, "dur": 148.172, + "args": { + "External id": 43363,"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": 2338707, "tid": 2379456, + "ts": 6197202030903.717, "dur": 129.147, + "args": { + "External id": 43364,"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": 2338707, "tid": 2379456, + "ts": 6197202030917.625, "dur": 27.347, + "args": { + "External id": 43365,"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": 2338707, "tid": 2379456, + "ts": 6197202030948.574, "dur": 58.876, + "args": { + "External id": 43366,"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": 2338707, "tid": 2379456, + "ts": 6197202030950.910, "dur": 56.182, + "args": { + "External id": 43367,"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": 2338707, "tid": 2379456, + "ts": 6197202030954.503, "dur": 5.438, + "args": { + "External id": 43368,"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": 2338707, "tid": 2379456, + "ts": 6197202030961.458, "dur": 44.988, + "args": { + "External id": 43369,"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": 2338707, "tid": 2379456, + "ts": 6197202031220.541, "dur": 1680.061, + "args": { + "External id": 43370,"Sequence number": 479997, "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": 2338707, "tid": 2379456, "ts": 6197202031220.541, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6197202031330.436, "dur": 108.763, + "args": { + "External id": 43371,"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": 2338707, "tid": 2379456, + "ts": 6197202031478.506, "dur": 40.421, + "args": { + "External id": 43372,"kernel_hash": "cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/u7/cu73slalpcimolzdcsth5yc2bffweqdrn5mjolw7iwdski5pzujs.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": 2338707, "tid": 2379456, + "ts": 6197202031535.612, "dur": 50.733, + "args": { + "External id": 43373,"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": 2338707, "tid": 2379456, + "ts": 6197202031599.132, "dur": 31.129, + "args": { + "External id": 43374,"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": 2338707, "tid": 2379456, + "ts": 6197202031637.204, "dur": 34.135, + "args": { + "External id": 43375,"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": 2338707, "tid": 2379456, + "ts": 6197202031678.486, "dur": 45.186, + "args": { + "External id": 43376,"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": 2338707, "tid": 2379456, + "ts": 6197202031734.241, "dur": 33.143, + "args": { + "External id": 43377,"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": 2338707, "tid": 2379456, + "ts": 6197202031794.167, "dur": 25.984, + "args": { + "External id": 43378,"kernel_hash": "cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/wm/cwmdtyuwgj7j3fxg57ckso72wqi2qzdp23gsirbcv7772zguon5s.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": 2338707, "tid": 2379456, + "ts": 6197202031839.477, "dur": 27.265, + "args": { + "External id": 43379,"kernel_hash": "cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql", "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/qt/cqtkq7myps3bnwtywqmkcfinhjn2cq7yyi2rklvdi3lxtis2knql.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": 2338707, "tid": 2379456, + "ts": 6197202031887.020, "dur": 19.954, + "args": { + "External id": 43380,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197202031921.259, "dur": 17.495, + "args": { + "External id": 43381,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197202031946.667, "dur": 39.628, + "args": { + "External id": 43382,"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": 2338707, "tid": 2379456, + "ts": 6197202031989.606, "dur": 32.702, + "args": { + "External id": 43383,"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": 2338707, "tid": 2379456, + "ts": 6197202032049.522, "dur": 277.326, + "args": { + "External id": 43384,"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": 2338707, "tid": 2379456, + "ts": 6197202032159.875, "dur": 6.989, + "args": { + "External id": 43385,"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": 2338707, "tid": 2379456, + "ts": 6197202032168.982, "dur": 6.206, + "args": { + "External id": 43386,"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": 2338707, "tid": 2379456, + "ts": 6197202032176.140, "dur": 1.915, + "args": { + "External id": 43387,"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": 2338707, "tid": 2379456, + "ts": 6197202032178.866, "dur": 2.264, + "args": { + "External id": 43388,"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": 2338707, "tid": 2379456, + "ts": 6197202032226.695, "dur": 8.308, + "args": { + "External id": 43389,"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": 2338707, "tid": 2379456, + "ts": 6197202032231.772, "dur": 3.049, + "args": { + "External id": 43390,"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": 2338707, "tid": 2379456, + "ts": 6197202032236.482, "dur": 31.602, + "args": { + "External id": 43391,"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": 2338707, "tid": 2379456, + "ts": 6197202032242.295, "dur": 1.949, + "args": { + "External id": 43392,"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": 2338707, "tid": 2379456, + "ts": 6197202032269.316, "dur": 1.566, + "args": { + "External id": 43393,"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": 2338707, "tid": 2379456, + "ts": 6197202032270.081, "dur": 0.729, + "args": { + "External id": 43394,"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": 2338707, "tid": 2379456, + "ts": 6197202032272.329, "dur": 13.043, + "args": { + "External id": 43395,"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": 2338707, "tid": 2379456, + "ts": 6197202032273.830, "dur": 0.851, + "args": { + "External id": 43396,"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": 2338707, "tid": 2379456, + "ts": 6197202032363.382, "dur": 28.387, + "args": { + "External id": 43397,"kernel_hash": "cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4", "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/yk/cyklfqyq3ruewgyv73sfwklyujhcs5pkt5uoemzhq5k47tccech4.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": 2338707, "tid": 2379456, + "ts": 6197202032410.222, "dur": 16.130, + "args": { + "External id": 43398,"kernel_hash": "ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg", "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/eu/ceuzvztw4yvdvos35uwgo5c2k6tiuymkspbfjem2pq5pqcfmcgjg.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": 2338707, "tid": 2379456, + "ts": 6197202032434.209, "dur": 49.191, + "args": { + "External id": 43399,"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": 2338707, "tid": 2379456, + "ts": 6197202032491.044, "dur": 40.286, + "args": { + "External id": 43400,"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": 2338707, "tid": 2379456, + "ts": 6197202032538.995, "dur": 23.092, + "args": { + "External id": 43401,"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": 2338707, "tid": 2379456, + "ts": 6197202032567.732, "dur": 31.556, + "args": { + "External id": 43402,"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": 2338707, "tid": 2379456, + "ts": 6197202032605.728, "dur": 28.223, + "args": { + "External id": 43403,"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": 2338707, "tid": 2379456, + "ts": 6197202032640.984, "dur": 29.880, + "args": { + "External id": 43404,"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": 2338707, "tid": 2379456, + "ts": 6197202032690.456, "dur": 43.710, + "args": { + "External id": 43405,"kernel_hash": "c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/6w/c6w57dwqlavni5blikci5m4csat5hnlhey5taj7vfkseu26zork7.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": 2338707, "tid": 2379456, + "ts": 6197202032752.958, "dur": 24.377, + "args": { + "External id": 43406,"kernel_hash": "ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx", "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/kj/ckjppy65bf3dvikk7c5b6blgzdmfgaljxyfbqmudoshkdutvtokx.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": 2338707, "tid": 2379456, + "ts": 6197202032795.064, "dur": 17.869, + "args": { + "External id": 43407,"kernel_hash": "c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5", "grid": "grid(8192,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "8192", "66"], "kernel_file": "/tmp/torchinductor_cvm/4m/c4mjgau2yanfqumxpspcb2s3xxxwzlinzlyupgfzaooqh5zvt5h5.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": 2338707, "tid": 2379456, + "ts": 6197202032829.752, "dur": 13.467, + "args": { + "External id": 43408,"kernel_hash": "cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "2"], "kernel_file": "/tmp/torchinductor_cvm/y5/cy5n6jvcqjg4gnbvuoozi4zmjzoyes5m2wtuaitwk3cpetqueido.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": 2338707, "tid": 2379456, + "ts": 6197202032855.547, "dur": 15.743, + "args": { + "External id": 43409,"kernel_hash": "cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/eb/cebp6425kwg6qjs7vc5dpxqx2tgnwzzcolkzg6q26v5rzluozz5b.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": 2338707, "tid": 2379456, + "ts": 6197202032946.166, "dur": 16.903, + "args": { + "External id": 43410,"Record function id": 0, "Ev Idx": 11665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197202032950.344, "dur": 11.709, + "args": { + "External id": 43411,"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": 2338707, "tid": 2379456, + "ts": 6197202032955.157, "dur": 5.892, + "args": { + "External id": 43412,"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": 2338707, "tid": 2379456, + "ts": 6197202032956.695, "dur": 4.252, + "args": { + "External id": 43413,"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": 2338707, "tid": 2379456, + "ts": 6197202032967.092, "dur": 5.414, + "args": { + "External id": 43414,"Record function id": 0, "Ev Idx": 11669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197202032968.938, "dur": 3.141, + "args": { + "External id": 43415,"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": 2338707, "tid": 2379456, + "ts": 6197202032969.825, "dur": 1.676, + "args": { + "External id": 43416,"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": 2338707, "tid": 2379456, + "ts": 6197202032970.693, "dur": 0.733, + "args": { + "External id": 43417,"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": 2338707, "tid": 2379456, + "ts": 6197202032975.770, "dur": 4.525, + "args": { + "External id": 43418,"Record function id": 0, "Ev Idx": 11673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197202032977.213, "dur": 2.688, + "args": { + "External id": 43419,"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": 2338707, "tid": 2379456, + "ts": 6197202032977.967, "dur": 1.486, + "args": { + "External id": 43420,"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": 2338707, "tid": 2379456, + "ts": 6197202032978.633, "dur": 0.753, + "args": { + "External id": 43421,"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": 2338707, "tid": 2379456, + "ts": 6197202032983.526, "dur": 4.324, + "args": { + "External id": 43422,"Record function id": 0, "Ev Idx": 11677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197202032985.053, "dur": 2.399, + "args": { + "External id": 43423,"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": 2338707, "tid": 2379456, + "ts": 6197202032985.840, "dur": 1.181, + "args": { + "External id": 43424,"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": 2338707, "tid": 2379456, + "ts": 6197202032986.373, "dur": 0.587, + "args": { + "External id": 43425,"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": 2338707, "tid": 2379456, + "ts": 6197202032990.940, "dur": 5.035, + "args": { + "External id": 43426,"Record function id": 0, "Ev Idx": 11681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197202032992.490, "dur": 3.053, + "args": { + "External id": 43427,"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": 2338707, "tid": 2379456, + "ts": 6197202032993.158, "dur": 1.987, + "args": { + "External id": 43428,"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": 2338707, "tid": 2379456, + "ts": 6197202032993.640, "dur": 1.401, + "args": { + "External id": 43429,"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": 2338707, "tid": 2379456, + "ts": 6197202032999.080, "dur": 3.589, + "args": { + "External id": 43430,"Record function id": 0, "Ev Idx": 11685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197202033000.353, "dur": 1.909, + "args": { + "External id": 43431,"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": 2338707, "tid": 2379456, + "ts": 6197202033000.831, "dur": 1.045, + "args": { + "External id": 43432,"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": 2338707, "tid": 2379456, + "ts": 6197202033001.104, "dur": 0.696, + "args": { + "External id": 43433,"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": 2338707, "tid": 2379456, + "ts": 6197202033005.802, "dur": 3.443, + "args": { + "External id": 43434,"Record function id": 0, "Ev Idx": 11689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197202033006.686, "dur": 2.166, + "args": { + "External id": 43435,"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": 2338707, "tid": 2379456, + "ts": 6197202033007.373, "dur": 1.061, + "args": { + "External id": 43436,"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": 2338707, "tid": 2379456, + "ts": 6197202033007.627, "dur": 0.739, + "args": { + "External id": 43437,"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": 2338707, "tid": 2379456, + "ts": 6197202033012.606, "dur": 4.603, + "args": { + "External id": 43438,"Record function id": 0, "Ev Idx": 11693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197202033014.061, "dur": 2.740, + "args": { + "External id": 43439,"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": 2338707, "tid": 2379456, + "ts": 6197202033014.813, "dur": 1.414, + "args": { + "External id": 43440,"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": 2338707, "tid": 2379456, + "ts": 6197202033015.459, "dur": 0.704, + "args": { + "External id": 43441,"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": 2338707, "tid": 2379456, + "ts": 6197202033020.406, "dur": 4.420, + "args": { + "External id": 43442,"Record function id": 0, "Ev Idx": 11697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197202033021.785, "dur": 2.539, + "args": { + "External id": 43443,"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": 2338707, "tid": 2379456, + "ts": 6197202033022.292, "dur": 1.581, + "args": { + "External id": 43444,"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": 2338707, "tid": 2379456, + "ts": 6197202033022.942, "dur": 0.847, + "args": { + "External id": 43445,"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": 2338707, "tid": 2379456, + "ts": 6197202033028.689, "dur": 61795.676, + "args": { + "External id": 43446,"Record function id": 0, "Sequence number": 479996, "Fwd thread id": 1, "Ev Idx": 11701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197202033030.233, "dur": 61784.446, + "args": { + "External id": 43447,"Sequence number": 479996, "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": 2338707, "tid": 2379456, "ts": 6197202033030.233, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.0)", "pid": 2338707, "tid": 2379456, + "ts": 6197202033094.714, "dur": 38.600, + "args": { + "External id": 43448,"Record function id": 0, "Ev Idx": 11703 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.0)", "pid": 2338707, "tid": 2379456, + "ts": 6197202033141.171, "dur": 72.961, + "args": { + "External id": 43449,"Record function id": 0, "Ev Idx": 11704 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.0)", "pid": 2338707, "tid": 2379456, + "ts": 6197202033219.803, "dur": 61587.456, + "args": { + "External id": 43450,"Record function id": 0, "Ev Idx": 11705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197202033310.732, "dur": 7.466, + "args": { + "External id": 43451,"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": 2338707, "tid": 2379456, + "ts": 6197202033341.647, "dur": 6.015, + "args": { + "External id": 43452,"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": 2338707, "tid": 2379456, + "ts": 6197202033364.590, "dur": 60483.434, + "args": { + "External id": 43453,"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": 2338707, "tid": 2379456, + "ts": 6197202033378.735, "dur": 60456.236, + "args": { + "External id": 43454,"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": 2338707, "tid": 2379456, + "ts": 6197202033477.382, "dur": 22.019, + "args": { + "External id": 43455,"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": 2338707, "tid": 2379456, + "ts": 6197202033518.989, "dur": 60267.562, + "args": { + "External id": 43456,"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": 2338707, "tid": 2379456, + "ts": 6197202033521.561, "dur": 60263.790, + "args": { + "External id": 43457,"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": 2338707, "tid": 2379456, + "ts": 6197202033525.751, "dur": 8.701, + "args": { + "External id": 43458,"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": 2338707, "tid": 2379456, + "ts": 6197202033536.260, "dur": 60243.126, + "args": { + "External id": 43459,"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": 2338707, "tid": 2379456, + "ts": 6197202093959.061, "dur": 12.175, + "args": { + "External id": 43460,"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": 2338707, "tid": 2379456, + "ts": 6197202093962.834, "dur": 8.066, + "args": { + "External id": 43461,"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": 2338707, "tid": 2379456, + "ts": 6197202094000.512, "dur": 400.392, + "args": { + "External id": 43462,"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": 2338707, "tid": 2379456, + "ts": 6197202094029.632, "dur": 365.564, + "args": { + "External id": 43463,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197202094040.408, "dur": 348.828, + "args": { + "External id": 43464,"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": 2338707, "tid": 2379456, + "ts": 6197202094426.337, "dur": 2.292, + "args": { + "External id": 43465,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2379456, + "ts": 6197202094492.234, "dur": 6.628, + "args": { + "External id": 43466,"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": 2338707, "tid": 2379456, + "ts": 6197202094510.047, "dur": 35.128, + "args": { + "External id": 43467,"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": 2338707, "tid": 2379456, + "ts": 6197202094556.136, "dur": 1.660, + "args": { + "External id": 43468,"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": 2338707, "tid": 2379456, + "ts": 6197202094563.469, "dur": 12.689, + "args": { + "External id": 43469,"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": 2338707, "tid": 2379456, + "ts": 6197202094581.305, "dur": 0.969, + "args": { + "External id": 43470,"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": 2338707, "tid": 2379456, + "ts": 6197202094587.383, "dur": 10.760, + "args": { + "External id": 43471,"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": 2338707, "tid": 2379456, + "ts": 6197202094603.178, "dur": 0.858, + "args": { + "External id": 43472,"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": 2338707, "tid": 2379456, + "ts": 6197202094608.889, "dur": 10.691, + "args": { + "External id": 43473,"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": 2338707, "tid": 2379456, + "ts": 6197202094623.531, "dur": 0.920, + "args": { + "External id": 43474,"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": 2338707, "tid": 2379456, + "ts": 6197202094628.146, "dur": 12.736, + "args": { + "External id": 43475,"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": 2338707, "tid": 2379456, + "ts": 6197202094645.031, "dur": 1.383, + "args": { + "External id": 43476,"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": 2338707, "tid": 2379456, + "ts": 6197202094650.975, "dur": 11.199, + "args": { + "External id": 43477,"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": 2338707, "tid": 2379456, + "ts": 6197202094666.171, "dur": 0.831, + "args": { + "External id": 43478,"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": 2338707, "tid": 2379456, + "ts": 6197202094671.901, "dur": 12.619, + "args": { + "External id": 43479,"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": 2338707, "tid": 2379456, + "ts": 6197202094689.075, "dur": 0.754, + "args": { + "External id": 43480,"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": 2338707, "tid": 2379456, + "ts": 6197202094693.582, "dur": 26.185, + "args": { + "External id": 43481,"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": 2338707, "tid": 2379456, + "ts": 6197202094727.754, "dur": 1.860, + "args": { + "External id": 43482,"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": 2338707, "tid": 2379456, + "ts": 6197202094734.074, "dur": 13.349, + "args": { + "External id": 43483,"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": 2338707, "tid": 2379456, + "ts": 6197202094840.484, "dur": 310.995, + "args": { + "External id": 43484,"Record function id": 0, "Sequence number": 479995, "Fwd thread id": 1, "Ev Idx": 11739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6197202094843.228, "dur": 298.646, + "args": { + "External id": 43485,"Sequence number": 479995, "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": 2338707, "tid": 2379456, "ts": 6197202094843.228, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_embedding_dense_backward_0", "pid": 2338707, "tid": 2379456, + "ts": 6197202094969.677, "dur": 38.791, + "args": { + "External id": 43486,"kernel_hash": "cylhmuu3q4lld7ngapzsx2q3nsghgiylz3hysdrztph5rn33kr3r", "grid": "grid(131072000,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "131072000"], "kernel_file": "/tmp/torchinductor_cvm/yl/cylhmuu3q4lld7ngapzsx2q3nsghgiylz3hysdrztph5rn33kr3r.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": 2338707, "tid": 2379456, + "ts": 6197202095022.742, "dur": 22.149, + "args": { + "External id": 43487,"kernel_hash": "cqovkpvfazf4uawh526mshntxf6zr2towc3gbwazqnfjbhqiu3u5", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/qo/cqovkpvfazf4uawh526mshntxf6zr2towc3gbwazqnfjbhqiu3u5.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": 2338707, "tid": 2379456, + "ts": 6197202095100.939, "dur": 23.018, + "args": { + "External id": 43488,"kernel_hash": "cxsh2jiwiopwz5eatuiwkxhwp4pcrm5kca3w7qyj3ojcu3sw473n", "grid": "grid(131072000,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "131072000"], "kernel_file": "/tmp/torchinductor_cvm/xs/cxsh2jiwiopwz5eatuiwkxhwp4pcrm5kca3w7qyj3ojcu3sw473n.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": 2338707, "tid": 2379456, + "ts": 6197202095163.884, "dur": 14.475, + "args": { + "External id": 43489,"Record function id": 0, "Ev Idx": 11744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6197202095166.714, "dur": 10.565, + "args": { + "External id": 43490,"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": 2338707, "tid": 2379456, + "ts": 6197202095170.615, "dur": 5.613, + "args": { + "External id": 43491,"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": 2338707, "tid": 2379456, + "ts": 6197202095171.891, "dur": 4.222, + "args": { + "External id": 43492,"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": 2338707, "tid": 2379456, + "ts": 6197202095201.156, "dur": 11455.902, + "args": { + "External id": 43493,"Record function id": 0, "Ev Idx": 11748 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate", "pid": 2338707, "tid": 2379456, + "ts": 6197202095219.520, "dur": 41.379, + "args": { + "External id": 43494,"Record function id": 0, "Ev Idx": 11749 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard", "pid": 2338707, "tid": 2379456, + "ts": 6197202095267.152, "dur": 276.732, + "args": { + "External id": 43495,"Record function id": 0, "Ev Idx": 11750 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce", "pid": 2338707, "tid": 2379456, + "ts": 6197202095550.030, "dur": 10857.878, + "args": { + "External id": 43496,"Record function id": 0, "Ev Idx": 11751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6197202095673.918, "dur": 7.363, + "args": { + "External id": 43497,"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": 2338707, "tid": 2379456, + "ts": 6197202095694.852, "dur": 4.761, + "args": { + "External id": 43498,"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": 2338707, "tid": 2379456, + "ts": 6197202095735.578, "dur": 9002.072, + "args": { + "External id": 43499,"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": 2338707, "tid": 2379456, + "ts": 6197202095763.904, "dur": 8959.412, + "args": { + "External id": 43500,"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": 2338707, "tid": 2379456, + "ts": 6197202096450.856, "dur": 23.232, + "args": { + "External id": 43501,"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": 2338707, "tid": 2379456, + "ts": 6197202096678.437, "dur": 7977.641, + "args": { + "External id": 43502,"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": 2338707, "tid": 2379456, + "ts": 6197202096681.768, "dur": 7973.001, + "args": { + "External id": 43503,"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": 2338707, "tid": 2379456, + "ts": 6197202096686.937, "dur": 35.446, + "args": { + "External id": 43504,"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": 2338707, "tid": 2379456, + "ts": 6197202096726.374, "dur": 7921.720, + "args": { + "External id": 43505,"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": 2338707, "tid": 2379456, + "ts": 6197202104890.079, "dur": 11.595, + "args": { + "External id": 43506,"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": 2338707, "tid": 2379456, + "ts": 6197202104893.668, "dur": 7.674, + "args": { + "External id": 43507,"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": 2338707, "tid": 2379456, + "ts": 6197202104931.018, "dur": 402.735, + "args": { + "External id": 43508,"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": 2338707, "tid": 2379456, + "ts": 6197202104956.739, "dur": 371.159, + "args": { + "External id": 43509,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2379456, + "ts": 6197202104969.428, "dur": 352.357, + "args": { + "External id": 43510,"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": 2338707, "tid": 2379456, + "ts": 6197202105357.449, "dur": 2.339, + "args": { + "External id": 43511,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2379456, + "ts": 6197202105421.416, "dur": 6.855, + "args": { + "External id": 43512,"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": 2338707, "tid": 2379456, + "ts": 6197202105440.340, "dur": 32.469, + "args": { + "External id": 43513,"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": 2338707, "tid": 2379456, + "ts": 6197202105482.956, "dur": 1.472, + "args": { + "External id": 43514,"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": 2338707, "tid": 2379456, + "ts": 6197202105490.194, "dur": 12.201, + "args": { + "External id": 43515,"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": 2338707, "tid": 2379456, + "ts": 6197202105507.448, "dur": 0.904, + "args": { + "External id": 43516,"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": 2338707, "tid": 2379456, + "ts": 6197202105513.315, "dur": 11.330, + "args": { + "External id": 43517,"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": 2338707, "tid": 2379456, + "ts": 6197202105530.319, "dur": 0.921, + "args": { + "External id": 43518,"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": 2338707, "tid": 2379456, + "ts": 6197202105535.343, "dur": 10.722, + "args": { + "External id": 43519,"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": 2338707, "tid": 2379456, + "ts": 6197202105552.512, "dur": 0.774, + "args": { + "External id": 43520,"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": 2338707, "tid": 2379456, + "ts": 6197202105588.248, "dur": 11.585, + "args": { + "External id": 43521,"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": 2338707, "tid": 2379456, + "ts": 6197202105604.666, "dur": 0.833, + "args": { + "External id": 43522,"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": 2338707, "tid": 2379456, + "ts": 6197202105609.566, "dur": 10.838, + "args": { + "External id": 43523,"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": 2338707, "tid": 2379456, + "ts": 6197202105624.795, "dur": 0.859, + "args": { + "External id": 43524,"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": 2338707, "tid": 2379456, + "ts": 6197202105629.568, "dur": 10.304, + "args": { + "External id": 43525,"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": 2338707, "tid": 2379456, + "ts": 6197202105644.813, "dur": 0.953, + "args": { + "External id": 43526,"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": 2338707, "tid": 2379456, + "ts": 6197202105651.048, "dur": 9.702, + "args": { + "External id": 43527,"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": 2338707, "tid": 2379456, + "ts": 6197202105665.476, "dur": 0.678, + "args": { + "External id": 43528,"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": 2338707, "tid": 2379456, + "ts": 6197202105670.134, "dur": 10.322, + "args": { + "External id": 43529,"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": 2338707, "tid": 2379456, + "ts": 6197202105685.119, "dur": 0.667, + "args": { + "External id": 43530,"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": 2338707, "tid": 2379456, + "ts": 6197202105689.969, "dur": 9.974, + "args": { + "External id": 43531,"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": 2338707, "tid": 2379456, + "ts": 6197202105722.358, "dur": 1.360, + "args": { + "External id": 43532,"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": 2338707, "tid": 2379456, + "ts": 6197202105729.047, "dur": 13.254, + "args": { + "External id": 43533,"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": 2338707, "tid": 2379456, + "ts": 6197202105747.501, "dur": 0.806, + "args": { + "External id": 43534,"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": 2338707, "tid": 2379456, + "ts": 6197202105752.876, "dur": 9.734, + "args": { + "External id": 43535,"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": 2338707, "tid": 2379456, + "ts": 6197202105766.927, "dur": 0.774, + "args": { + "External id": 43536,"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": 2338707, "tid": 2379456, + "ts": 6197202105772.380, "dur": 10.314, + "args": { + "External id": 43537,"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": 2338707, "tid": 2379456, + "ts": 6197202105787.475, "dur": 0.992, + "args": { + "External id": 43538,"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": 2338707, "tid": 2379456, + "ts": 6197202105794.181, "dur": 15.406, + "args": { + "External id": 43539,"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": 2338707, "tid": 2379456, + "ts": 6197202105813.613, "dur": 0.854, + "args": { + "External id": 43540,"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": 2338707, "tid": 2379456, + "ts": 6197202105820.367, "dur": 10.027, + "args": { + "External id": 43541,"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": 2338707, "tid": 2379456, + "ts": 6197202105834.831, "dur": 0.905, + "args": { + "External id": 43542,"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": 2338707, "tid": 2379456, + "ts": 6197202105839.389, "dur": 10.096, + "args": { + "External id": 43543,"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": 2338707, "tid": 2379456, + "ts": 6197202105853.943, "dur": 1.025, + "args": { + "External id": 43544,"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": 2338707, "tid": 2379456, + "ts": 6197202105858.899, "dur": 9.568, + "args": { + "External id": 43545,"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": 2338707, "tid": 2379456, + "ts": 6197202105873.562, "dur": 0.726, + "args": { + "External id": 43546,"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": 2338707, "tid": 2379456, + "ts": 6197202105878.368, "dur": 9.472, + "args": { + "External id": 43547,"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": 2338707, "tid": 2379456, + "ts": 6197202105892.080, "dur": 0.710, + "args": { + "External id": 43548,"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": 2338707, "tid": 2379456, + "ts": 6197202105896.700, "dur": 10.274, + "args": { + "External id": 43549,"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": 2338707, "tid": 2379456, + "ts": 6197202105911.240, "dur": 1.034, + "args": { + "External id": 43550,"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": 2338707, "tid": 2379456, + "ts": 6197202105916.308, "dur": 9.029, + "args": { + "External id": 43551,"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": 2338707, "tid": 2379456, + "ts": 6197202105930.918, "dur": 0.909, + "args": { + "External id": 43552,"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": 2338707, "tid": 2379456, + "ts": 6197202105936.138, "dur": 10.764, + "args": { + "External id": 43553,"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": 2338707, "tid": 2379456, + "ts": 6197202105951.152, "dur": 0.772, + "args": { + "External id": 43554,"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": 2338707, "tid": 2379456, + "ts": 6197202105956.008, "dur": 8.815, + "args": { + "External id": 43555,"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": 2338707, "tid": 2379456, + "ts": 6197202105968.650, "dur": 0.974, + "args": { + "External id": 43556,"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": 2338707, "tid": 2379456, + "ts": 6197202105973.842, "dur": 9.871, + "args": { + "External id": 43557,"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": 2338707, "tid": 2379456, + "ts": 6197202105989.203, "dur": 0.876, + "args": { + "External id": 43558,"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": 2338707, "tid": 2379456, + "ts": 6197202105994.038, "dur": 9.313, + "args": { + "External id": 43559,"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": 2338707, "tid": 2379456, + "ts": 6197202106007.808, "dur": 0.914, + "args": { + "External id": 43560,"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": 2338707, "tid": 2379456, + "ts": 6197202106012.891, "dur": 10.030, + "args": { + "External id": 43561,"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": 2338707, "tid": 2379456, + "ts": 6197202106027.048, "dur": 0.976, + "args": { + "External id": 43562,"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": 2338707, "tid": 2379456, + "ts": 6197202106032.562, "dur": 10.022, + "args": { + "External id": 43563,"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": 2338707, "tid": 2379456, + "ts": 6197202106048.145, "dur": 0.726, + "args": { + "External id": 43564,"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": 2338707, "tid": 2379456, + "ts": 6197202106092.330, "dur": 14.663, + "args": { + "External id": 43565,"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": 2338707, "tid": 2379456, + "ts": 6197202106114.643, "dur": 1.137, + "args": { + "External id": 43566,"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": 2338707, "tid": 2379456, + "ts": 6197202106120.838, "dur": 10.241, + "args": { + "External id": 43567,"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": 2338707, "tid": 2379456, + "ts": 6197202106135.282, "dur": 1.000, + "args": { + "External id": 43568,"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": 2338707, "tid": 2379456, + "ts": 6197202106140.827, "dur": 10.333, + "args": { + "External id": 43569,"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": 2338707, "tid": 2379456, + "ts": 6197202106154.931, "dur": 0.742, + "args": { + "External id": 43570,"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": 2338707, "tid": 2379456, + "ts": 6197202106160.724, "dur": 9.537, + "args": { + "External id": 43571,"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": 2338707, "tid": 2379456, + "ts": 6197202106174.362, "dur": 0.804, + "args": { + "External id": 43572,"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": 2338707, "tid": 2379456, + "ts": 6197202106179.430, "dur": 12.270, + "args": { + "External id": 43573,"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": 2338707, "tid": 2379456, + "ts": 6197202106195.630, "dur": 1.181, + "args": { + "External id": 43574,"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": 2338707, "tid": 2379456, + "ts": 6197202106200.789, "dur": 10.148, + "args": { + "External id": 43575,"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": 2338707, "tid": 2379456, + "ts": 6197202106215.811, "dur": 0.696, + "args": { + "External id": 43576,"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": 2338707, "tid": 2379456, + "ts": 6197202106220.869, "dur": 11.626, + "args": { + "External id": 43577,"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": 2338707, "tid": 2379456, + "ts": 6197202106236.496, "dur": 0.776, + "args": { + "External id": 43578,"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": 2338707, "tid": 2379456, + "ts": 6197202106241.845, "dur": 9.351, + "args": { + "External id": 43579,"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": 2338707, "tid": 2379456, + "ts": 6197202106255.449, "dur": 0.880, + "args": { + "External id": 43580,"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": 2338707, "tid": 2379456, + "ts": 6197202106260.256, "dur": 9.646, + "args": { + "External id": 43581,"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": 2338707, "tid": 2379456, + "ts": 6197202106274.386, "dur": 0.723, + "args": { + "External id": 43582,"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": 2338707, "tid": 2379456, + "ts": 6197202106280.137, "dur": 10.046, + "args": { + "External id": 43583,"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": 2338707, "tid": 2379456, + "ts": 6197202106294.288, "dur": 0.774, + "args": { + "External id": 43584,"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": 2338707, "tid": 2379456, + "ts": 6197202106299.090, "dur": 9.767, + "args": { + "External id": 43585,"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": 2338707, "tid": 2379456, + "ts": 6197202106312.536, "dur": 1.077, + "args": { + "External id": 43586,"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": 2338707, "tid": 2379456, + "ts": 6197202106317.723, "dur": 10.053, + "args": { + "External id": 43587,"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": 2338707, "tid": 2379456, + "ts": 6197202106331.654, "dur": 0.776, + "args": { + "External id": 43588,"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": 2338707, "tid": 2379456, + "ts": 6197202106336.663, "dur": 9.888, + "args": { + "External id": 43589,"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#1023", "pid": 2338707, "tid": 2338707, + "ts": 6197195554125.794, "dur": 6581849.896, + "args": { + "External id": 22529,"Record function id": 0, "Ev Idx": 11845 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "Optimizer.zero_grad#AdamW.zero_grad", "pid": 2338707, "tid": 2338707, + "ts": 6197195554169.775, "dur": 1000.089, + "args": { + "External id": 22530,"Record function id": 0, "Ev Idx": 11846 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "enumerate(DataLoader)#_StatefulMultiProcessingDataLoaderIter.__next__", "pid": 2338707, "tid": 2338707, + "ts": 6197195555235.316, "dur": 2371.807, + "args": { + "External id": 22531,"Record function id": 0, "Ev Idx": 11847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6197195556449.545, "dur": 9.124, + "args": { + "External id": 22532,"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": 2338707, "tid": 2338707, + "ts": 6197195556482.514, "dur": 8.438, + "args": { + "External id": 22533,"Sequence number": 479766, "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": 2338707, "tid": 2338707, + "ts": 6197195557007.271, "dur": 2.666, + "args": { + "External id": 22534,"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": 2338707, "tid": 2338707, + "ts": 6197195557021.660, "dur": 3.604, + "args": { + "External id": 22535,"Sequence number": 479766, "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": 2338707, "tid": 2338707, + "ts": 6197195557471.766, "dur": 1.980, + "args": { + "External id": 22536,"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": 2338707, "tid": 2338707, + "ts": 6197195557478.971, "dur": 2.427, + "args": { + "External id": 22537,"Sequence number": 479766, "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": 2338707, "tid": 2338707, + "ts": 6197195557970.907, "dur": 20.162, + "args": { + "External id": 22538,"Sequence number": 479766, "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": 2338707, "tid": 2338707, + "ts": 6197195557983.198, "dur": 3.021, + "args": { + "External id": 22539,"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": 2338707, "tid": 2338707, + "ts": 6197195557992.964, "dur": 5.245, + "args": { + "External id": 22540,"Sequence number": 479766, "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": 2338707, "tid": 2338707, + "ts": 6197195557995.733, "dur": 1.180, + "args": { + "External id": 22541,"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": 2338707, "tid": 2338707, + "ts": 6197195558032.097, "dur": 2309.918, + "args": { + "External id": 22542,"Sequence number": 479766, "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": 2338707, "tid": 2338707, + "ts": 6197195558041.042, "dur": 2300.145, + "args": { + "External id": 22543,"Sequence number": 479766, "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": 2338707, "tid": 2338707, + "ts": 6197195558053.025, "dur": 47.800, + "args": { + "External id": 22544,"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": 2338707, "tid": 2338707, + "ts": 6197195558104.685, "dur": 2235.010, + "args": { + "External id": 22545,"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": 2338707, "tid": 2338707, + "ts": 6197195558116.800, "dur": 0.507, + "args": { + "External id": 22546,"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": 2338707, "tid": 2338707, + "ts": 6197195558121.008, "dur": 8.100, + "args": { + "External id": 22547,"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": 2338707, "tid": 2338707, + "ts": 6197195558124.354, "dur": 4.564, + "args": { + "External id": 22548,"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": 2338707, "tid": 2338707, + "ts": 6197195558127.811, "dur": 0.776, + "args": { + "External id": 22549,"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": 2338707, "tid": 2338707, + "ts": 6197195558131.891, "dur": 154.429, + "args": { + "External id": 22550,"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": 2338707, "tid": 2338707, + "ts": 6197195558134.622, "dur": 151.404, + "args": { + "External id": 22551,"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": 2338707, "tid": 2338707, + "ts": 6197195558137.535, "dur": 23.043, + "args": { + "External id": 22552,"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": 2338707, "tid": 2338707, + "ts": 6197195558143.263, "dur": 16.682, + "args": { + "External id": 22553,"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": 2338707, "tid": 2338707, + "ts": 6197195558161.672, "dur": 123.759, + "args": { + "External id": 22554,"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": 2338707, "tid": 2338707, + "ts": 6197195558288.598, "dur": 2047.045, + "args": { + "External id": 22555,"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": 2338707, "tid": 2338707, + "ts": 6197195560358.553, "dur": 370.638, + "args": { + "External id": 22556,"Sequence number": 479766, "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": 2338707, "tid": 2338707, + "ts": 6197195560360.866, "dur": 367.597, + "args": { + "External id": 22557,"Sequence number": 479766, "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": 2338707, "tid": 2338707, + "ts": 6197195560367.890, "dur": 9.265, + "args": { + "External id": 22558,"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": 2338707, "tid": 2338707, + "ts": 6197195560381.185, "dur": 345.079, + "args": { + "External id": 22559,"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": 2338707, "tid": 2338707, + "ts": 6197195560758.275, "dur": 62.768, + "args": { + "External id": 22560,"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": 2338707, "tid": 2338707, + "ts": 6197195560764.089, "dur": 5.973, + "args": { + "External id": 22561,"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": 2338707, "tid": 2338707, + "ts": 6197195560773.019, "dur": 47.637, + "args": { + "External id": 22562,"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": 2338707, "tid": 2338707, + "ts": 6197195560778.648, "dur": 9.077, + "args": { + "External id": 22563,"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": 2338707, "tid": 2338707, + "ts": 6197195560834.770, "dur": 84.635, + "args": { + "External id": 22564,"Sequence number": 479766, "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": 2338707, "tid": 2338707, + "ts": 6197195560842.676, "dur": 7.724, + "args": { + "External id": 22565,"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": 2338707, "tid": 2338707, + "ts": 6197195560847.832, "dur": 2.275, + "args": { + "External id": 22566,"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": 2338707, "tid": 2338707, + "ts": 6197195560851.797, "dur": 3.563, + "args": { + "External id": 22567,"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": 2338707, "tid": 2338707, + "ts": 6197195560858.454, "dur": 5.317, + "args": { + "External id": 22568,"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": 2338707, "tid": 2338707, + "ts": 6197195560867.271, "dur": 6.310, + "args": { + "External id": 22569,"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": 2338707, "tid": 2338707, + "ts": 6197195560872.387, "dur": 0.813, + "args": { + "External id": 22570,"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": 2338707, "tid": 2338707, + "ts": 6197195560874.430, "dur": 4.923, + "args": { + "External id": 22571,"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": 2338707, "tid": 2338707, + "ts": 6197195560878.186, "dur": 1.048, + "args": { + "External id": 22572,"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": 2338707, "tid": 2338707, + "ts": 6197195560881.656, "dur": 6.583, + "args": { + "External id": 22573,"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": 2338707, "tid": 2338707, + "ts": 6197195560885.188, "dur": 2.911, + "args": { + "External id": 22574,"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": 2338707, "tid": 2338707, + "ts": 6197195560886.794, "dur": 1.200, + "args": { + "External id": 22575,"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": 2338707, "tid": 2338707, + "ts": 6197195560889.369, "dur": 29.130, + "args": { + "External id": 22576,"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": 2338707, "tid": 2338707, + "ts": 6197195560929.247, "dur": 35.102, + "args": { + "External id": 22577,"Sequence number": 479766, "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": 2338707, "tid": 2338707, + "ts": 6197195560931.303, "dur": 32.809, + "args": { + "External id": 22578,"Sequence number": 479766, "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": 2338707, "tid": 2338707, + "ts": 6197195560936.366, "dur": 4.097, + "args": { + "External id": 22579,"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": 2338707, "tid": 2338707, + "ts": 6197195560941.449, "dur": 22.094, + "args": { + "External id": 22580,"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": 2338707, "tid": 2338707, + "ts": 6197195561143.664, "dur": 192.313, + "args": { + "External id": 22581,"Record function id": 0, "Ev Idx": 11897 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::inputs_to_device", "pid": 2338707, "tid": 2338707, + "ts": 6197195561251.807, "dur": 70.823, + "args": { + "External id": 22582,"Record function id": 0, "Ev Idx": 11898 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6197195561344.908, "dur": 58.790, + "args": { + "External id": 22583,"Record function id": 0, "Ev Idx": 11899 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward", "pid": 2338707, "tid": 2338707, + "ts": 6197195561416.048, "dur": 13455.087, + "args": { + "External id": 22584,"Record function id": 0, "Ev Idx": 11900 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather", "pid": 2338707, "tid": 2338707, + "ts": 6197195561428.544, "dur": 1791.750, + "args": { + "External id": 22585,"Record function id": 0, "Ev Idx": 11901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6197195561583.823, "dur": 10.642, + "args": { + "External id": 22586,"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": 2338707, "tid": 2338707, + "ts": 6197195561615.651, "dur": 171.609, + "args": { + "External id": 22587,"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": 2338707, "tid": 2338707, + "ts": 6197195561622.540, "dur": 2.216, + "args": { + "External id": 22588,"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": 2338707, "tid": 2338707, + "ts": 6197195561631.687, "dur": 0.610, + "args": { + "External id": 22589,"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": 2338707, "tid": 2338707, + "ts": 6197195561633.248, "dur": 0.419, + "args": { + "External id": 22590,"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": 2338707, "tid": 2338707, + "ts": 6197195561634.578, "dur": 3.865, + "args": { + "External id": 22591,"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": 2338707, "tid": 2338707, + "ts": 6197195561643.410, "dur": 0.445, + "args": { + "External id": 22592,"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": 2338707, "tid": 2338707, + "ts": 6197195561644.527, "dur": 0.604, + "args": { + "External id": 22593,"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": 2338707, "tid": 2338707, + "ts": 6197195561646.172, "dur": 2.443, + "args": { + "External id": 22594,"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": 2338707, "tid": 2338707, + "ts": 6197195561651.473, "dur": 0.678, + "args": { + "External id": 22595,"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": 2338707, "tid": 2338707, + "ts": 6197195561652.878, "dur": 0.614, + "args": { + "External id": 22596,"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": 2338707, "tid": 2338707, + "ts": 6197195561658.704, "dur": 0.338, + "args": { + "External id": 22597,"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": 2338707, "tid": 2338707, + "ts": 6197195561659.844, "dur": 0.481, + "args": { + "External id": 22598,"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": 2338707, "tid": 2338707, + "ts": 6197195561661.048, "dur": 2.672, + "args": { + "External id": 22599,"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": 2338707, "tid": 2338707, + "ts": 6197195561667.682, "dur": 0.526, + "args": { + "External id": 22600,"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": 2338707, "tid": 2338707, + "ts": 6197195561668.927, "dur": 0.604, + "args": { + "External id": 22601,"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": 2338707, "tid": 2338707, + "ts": 6197195561670.283, "dur": 3.887, + "args": { + "External id": 22602,"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": 2338707, "tid": 2338707, + "ts": 6197195561676.891, "dur": 0.474, + "args": { + "External id": 22603,"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": 2338707, "tid": 2338707, + "ts": 6197195561678.065, "dur": 0.533, + "args": { + "External id": 22604,"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": 2338707, "tid": 2338707, + "ts": 6197195561684.077, "dur": 0.344, + "args": { + "External id": 22605,"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": 2338707, "tid": 2338707, + "ts": 6197195561685.387, "dur": 0.580, + "args": { + "External id": 22606,"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": 2338707, "tid": 2338707, + "ts": 6197195561687.179, "dur": 3.163, + "args": { + "External id": 22607,"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": 2338707, "tid": 2338707, + "ts": 6197195561693.974, "dur": 0.641, + "args": { + "External id": 22608,"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": 2338707, "tid": 2338707, + "ts": 6197195561695.369, "dur": 1.020, + "args": { + "External id": 22609,"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": 2338707, "tid": 2338707, + "ts": 6197195561697.524, "dur": 19.150, + "args": { + "External id": 22610,"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": 2338707, "tid": 2338707, + "ts": 6197195561721.325, "dur": 0.405, + "args": { + "External id": 22611,"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": 2338707, "tid": 2338707, + "ts": 6197195561722.737, "dur": 0.457, + "args": { + "External id": 22612,"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": 2338707, "tid": 2338707, + "ts": 6197195561727.462, "dur": 0.367, + "args": { + "External id": 22613,"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": 2338707, "tid": 2338707, + "ts": 6197195561728.672, "dur": 0.588, + "args": { + "External id": 22614,"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": 2338707, "tid": 2338707, + "ts": 6197195561730.034, "dur": 3.051, + "args": { + "External id": 22615,"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": 2338707, "tid": 2338707, + "ts": 6197195561738.447, "dur": 0.597, + "args": { + "External id": 22616,"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": 2338707, "tid": 2338707, + "ts": 6197195561739.883, "dur": 0.545, + "args": { + "External id": 22617,"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": 2338707, "tid": 2338707, + "ts": 6197195561741.276, "dur": 2.630, + "args": { + "External id": 22618,"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": 2338707, "tid": 2338707, + "ts": 6197195561747.054, "dur": 0.665, + "args": { + "External id": 22619,"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": 2338707, "tid": 2338707, + "ts": 6197195561748.299, "dur": 0.381, + "args": { + "External id": 22620,"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": 2338707, "tid": 2338707, + "ts": 6197195561753.339, "dur": 0.378, + "args": { + "External id": 22621,"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": 2338707, "tid": 2338707, + "ts": 6197195561754.494, "dur": 0.596, + "args": { + "External id": 22622,"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": 2338707, "tid": 2338707, + "ts": 6197195561756.206, "dur": 2.408, + "args": { + "External id": 22623,"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": 2338707, "tid": 2338707, + "ts": 6197195561763.459, "dur": 0.360, + "args": { + "External id": 22624,"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": 2338707, "tid": 2338707, + "ts": 6197195561764.553, "dur": 0.469, + "args": { + "External id": 22625,"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": 2338707, "tid": 2338707, + "ts": 6197195561766.151, "dur": 2.911, + "args": { + "External id": 22626,"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": 2338707, "tid": 2338707, + "ts": 6197195561849.959, "dur": 172.499, + "args": { + "External id": 22627,"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": 2338707, "tid": 2338707, + "ts": 6197195562163.952, "dur": 385.730, + "args": { + "External id": 22628,"Record function id": 0, "Concrete Inputs": ["", "", "141824512", "8", "1", "15", ""], "Input type": ["TensorList", "", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], []], "Ev Idx": 11944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6197195562186.165, "dur": 8.621, + "args": { + "External id": 22629,"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": 2338707, "tid": 2338707, + "ts": 6197195562204.075, "dur": 19.053, + "args": { + "External id": 22630,"Record function id": 0, "Concrete Inputs": ["", "0", "141824512", "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": 2338707, "tid": 2338707, + "ts": 6197195562209.967, "dur": 12.627, + "args": { + "External id": 22631,"Record function id": 0, "Concrete Inputs": ["", "0", "141824512", "283649024", "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": 2338707, "tid": 2338707, + "ts": 6197195562216.394, "dur": 1.328, + "args": { + "External id": 22632,"Record function id": 0, "Concrete Inputs": ["", "[141824512]", "[1]", "141824512"], "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": 2338707, "tid": 2338707, + "ts": 6197195562234.601, "dur": 144.064, + "args": { + "External id": 22633,"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": 2338707, "tid": 2338707, + "ts": 6197195562237.408, "dur": 0.675, + "args": { + "External id": 22634,"Record function id": 0, "Concrete Inputs": ["", "[16384000]", "[1]", "141824512"], "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": 2338707, "tid": 2338707, + "ts": 6197195562239.713, "dur": 0.655, + "args": { + "External id": 22635,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "158208512"], "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": 2338707, "tid": 2338707, + "ts": 6197195562243.337, "dur": 2.957, + "args": { + "External id": 22636,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "158209024"], "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": 2338707, "tid": 2338707, + "ts": 6197195562247.168, "dur": 0.969, + "args": { + "External id": 22637,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "160306176"], "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": 2338707, "tid": 2338707, + "ts": 6197195562250.043, "dur": 0.479, + "args": { + "External id": 22638,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "160830464"], "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": 2338707, "tid": 2338707, + "ts": 6197195562251.500, "dur": 0.513, + "args": { + "External id": 22639,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "161354752"], "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": 2338707, "tid": 2338707, + "ts": 6197195562253.444, "dur": 0.534, + "args": { + "External id": 22640,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "163451904"], "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": 2338707, "tid": 2338707, + "ts": 6197195562256.027, "dur": 0.557, + "args": { + "External id": 22641,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "163452416"], "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": 2338707, "tid": 2338707, + "ts": 6197195562257.481, "dur": 0.949, + "args": { + "External id": 22642,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "170792448"], "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": 2338707, "tid": 2338707, + "ts": 6197195562259.564, "dur": 0.558, + "args": { + "External id": 22643,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "178132480"], "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": 2338707, "tid": 2338707, + "ts": 6197195562262.611, "dur": 3.356, + "args": { + "External id": 22644,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "185472512"], "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": 2338707, "tid": 2338707, + "ts": 6197195562267.224, "dur": 0.324, + "args": { + "External id": 22645,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "185473024"], "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": 2338707, "tid": 2338707, + "ts": 6197195562268.661, "dur": 2.791, + "args": { + "External id": 22646,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "187570176"], "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": 2338707, "tid": 2338707, + "ts": 6197195562274.195, "dur": 0.285, + "args": { + "External id": 22647,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "188094464"], "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": 2338707, "tid": 2338707, + "ts": 6197195562275.950, "dur": 0.574, + "args": { + "External id": 22648,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "188618752"], "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": 2338707, "tid": 2338707, + "ts": 6197195562281.146, "dur": 0.348, + "args": { + "External id": 22649,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "190715904"], "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": 2338707, "tid": 2338707, + "ts": 6197195562283.115, "dur": 0.667, + "args": { + "External id": 22650,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "190716416"], "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": 2338707, "tid": 2338707, + "ts": 6197195562285.662, "dur": 0.686, + "args": { + "External id": 22651,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "198056448"], "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": 2338707, "tid": 2338707, + "ts": 6197195562290.232, "dur": 2.700, + "args": { + "External id": 22652,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "205396480"], "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": 2338707, "tid": 2338707, + "ts": 6197195562294.951, "dur": 0.360, + "args": { + "External id": 22653,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "212736512"], "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": 2338707, "tid": 2338707, + "ts": 6197195562296.775, "dur": 2.412, + "args": { + "External id": 22654,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "212737024"], "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": 2338707, "tid": 2338707, + "ts": 6197195562300.602, "dur": 0.466, + "args": { + "External id": 22655,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "214834176"], "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": 2338707, "tid": 2338707, + "ts": 6197195562302.749, "dur": 0.299, + "args": { + "External id": 22656,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "215358464"], "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": 2338707, "tid": 2338707, + "ts": 6197195562306.916, "dur": 0.459, + "args": { + "External id": 22657,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "215882752"], "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": 2338707, "tid": 2338707, + "ts": 6197195562308.942, "dur": 0.339, + "args": { + "External id": 22658,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "217979904"], "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": 2338707, "tid": 2338707, + "ts": 6197195562311.030, "dur": 0.468, + "args": { + "External id": 22659,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "217980416"], "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": 2338707, "tid": 2338707, + "ts": 6197195562315.182, "dur": 2.466, + "args": { + "External id": 22660,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "225320448"], "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": 2338707, "tid": 2338707, + "ts": 6197195562319.227, "dur": 0.662, + "args": { + "External id": 22661,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "232660480"], "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": 2338707, "tid": 2338707, + "ts": 6197195562321.258, "dur": 2.486, + "args": { + "External id": 22662,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "240000512"], "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": 2338707, "tid": 2338707, + "ts": 6197195562325.229, "dur": 0.935, + "args": { + "External id": 22663,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "240001024"], "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": 2338707, "tid": 2338707, + "ts": 6197195562328.141, "dur": 0.389, + "args": { + "External id": 22664,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "242098176"], "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": 2338707, "tid": 2338707, + "ts": 6197195562332.528, "dur": 0.362, + "args": { + "External id": 22665,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "242622464"], "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": 2338707, "tid": 2338707, + "ts": 6197195562334.290, "dur": 0.679, + "args": { + "External id": 22666,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "243146752"], "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": 2338707, "tid": 2338707, + "ts": 6197195562336.539, "dur": 0.405, + "args": { + "External id": 22667,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "245243904"], "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": 2338707, "tid": 2338707, + "ts": 6197195562340.621, "dur": 2.427, + "args": { + "External id": 22668,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "245244416"], "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": 2338707, "tid": 2338707, + "ts": 6197195562344.632, "dur": 0.437, + "args": { + "External id": 22669,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "252584448"], "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": 2338707, "tid": 2338707, + "ts": 6197195562346.712, "dur": 2.344, + "args": { + "External id": 22670,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "259924480"], "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": 2338707, "tid": 2338707, + "ts": 6197195562350.817, "dur": 0.342, + "args": { + "External id": 22671,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "267264512"], "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": 2338707, "tid": 2338707, + "ts": 6197195562352.940, "dur": 0.254, + "args": { + "External id": 22672,"Record function id": 0, "Concrete Inputs": ["", "[16384000]", "[1]", "267265024"], "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": 2338707, "tid": 2338707, + "ts": 6197195562404.622, "dur": 126.215, + "args": { + "External id": 22673,"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": 2338707, "tid": 2338707, + "ts": 6197195562630.820, "dur": 401.926, + "args": { + "External id": 22674,"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": 2338707, "tid": 2338707, + "ts": 6197195562671.870, "dur": 353.404, + "args": { + "External id": 22675,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2338707, + "ts": 6197195562685.503, "dur": 333.078, + "args": { + "External id": 22676,"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": 2338707, "tid": 2338707, + "ts": 6197195563103.677, "dur": 4.160, + "args": { + "External id": 22677,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out", "pid": 2338707, "tid": 2338707, + "ts": 6197195563243.227, "dur": 11336.645, + "args": { + "External id": 22678,"Record function id": 0, "Ev Idx": 11994 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6197195563513.609, "dur": 7.946, + "args": { + "External id": 22679,"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": 2338707, "tid": 2338707, + "ts": 6197195563528.428, "dur": 1.640, + "args": { + "External id": 22680,"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": 2338707, "tid": 2338707, + "ts": 6197195563532.474, "dur": 1.694, + "args": { + "External id": 22681,"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": 2338707, "tid": 2338707, + "ts": 6197195563537.017, "dur": 3.923, + "args": { + "External id": 22682,"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": 2338707, "tid": 2338707, + "ts": 6197195563542.829, "dur": 1.108, + "args": { + "External id": 22683,"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": 2338707, "tid": 2338707, + "ts": 6197195563545.757, "dur": 1.251, + "args": { + "External id": 22684,"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": 2338707, "tid": 2338707, + "ts": 6197195563551.582, "dur": 1.380, + "args": { + "External id": 22685,"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": 2338707, "tid": 2338707, + "ts": 6197195563554.884, "dur": 3.362, + "args": { + "External id": 22686,"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": 2338707, "tid": 2338707, + "ts": 6197195563560.112, "dur": 1.037, + "args": { + "External id": 22687,"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": 2338707, "tid": 2338707, + "ts": 6197195563563.166, "dur": 1.199, + "args": { + "External id": 22688,"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": 2338707, "tid": 2338707, + "ts": 6197195563568.743, "dur": 1.256, + "args": { + "External id": 22689,"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": 2338707, "tid": 2338707, + "ts": 6197195563571.912, "dur": 3.439, + "args": { + "External id": 22690,"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": 2338707, "tid": 2338707, + "ts": 6197195563577.074, "dur": 1.355, + "args": { + "External id": 22691,"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": 2338707, "tid": 2338707, + "ts": 6197195563580.403, "dur": 1.279, + "args": { + "External id": 22692,"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": 2338707, "tid": 2338707, + "ts": 6197195563585.787, "dur": 0.982, + "args": { + "External id": 22693,"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": 2338707, "tid": 2338707, + "ts": 6197195563588.823, "dur": 2.605, + "args": { + "External id": 22694,"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": 2338707, "tid": 2338707, + "ts": 6197195563593.430, "dur": 0.613, + "args": { + "External id": 22695,"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": 2338707, "tid": 2338707, + "ts": 6197195563595.770, "dur": 0.959, + "args": { + "External id": 22696,"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": 2338707, "tid": 2338707, + "ts": 6197195563601.326, "dur": 1.163, + "args": { + "External id": 22697,"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": 2338707, "tid": 2338707, + "ts": 6197195563604.519, "dur": 3.930, + "args": { + "External id": 22698,"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": 2338707, "tid": 2338707, + "ts": 6197195563610.302, "dur": 1.386, + "args": { + "External id": 22699,"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": 2338707, "tid": 2338707, + "ts": 6197195563613.899, "dur": 1.077, + "args": { + "External id": 22700,"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": 2338707, "tid": 2338707, + "ts": 6197195563618.965, "dur": 0.991, + "args": { + "External id": 22701,"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": 2338707, "tid": 2338707, + "ts": 6197195563621.730, "dur": 2.531, + "args": { + "External id": 22702,"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": 2338707, "tid": 2338707, + "ts": 6197195563636.161, "dur": 1.352, + "args": { + "External id": 22703,"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": 2338707, "tid": 2338707, + "ts": 6197195563639.519, "dur": 1.043, + "args": { + "External id": 22704,"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": 2338707, "tid": 2338707, + "ts": 6197195563644.377, "dur": 0.969, + "args": { + "External id": 22705,"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": 2338707, "tid": 2338707, + "ts": 6197195563647.141, "dur": 3.467, + "args": { + "External id": 22706,"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": 2338707, "tid": 2338707, + "ts": 6197195563652.379, "dur": 0.918, + "args": { + "External id": 22707,"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": 2338707, "tid": 2338707, + "ts": 6197195563654.968, "dur": 1.011, + "args": { + "External id": 22708,"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": 2338707, "tid": 2338707, + "ts": 6197195563659.610, "dur": 1.066, + "args": { + "External id": 22709,"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": 2338707, "tid": 2338707, + "ts": 6197195563662.459, "dur": 1.855, + "args": { + "External id": 22710,"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": 2338707, "tid": 2338707, + "ts": 6197195563666.015, "dur": 1.029, + "args": { + "External id": 22711,"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": 2338707, "tid": 2338707, + "ts": 6197195563668.682, "dur": 0.952, + "args": { + "External id": 22712,"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": 2338707, "tid": 2338707, + "ts": 6197195563673.609, "dur": 1.122, + "args": { + "External id": 22713,"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": 2338707, "tid": 2338707, + "ts": 6197195563676.412, "dur": 3.403, + "args": { + "External id": 22714,"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": 2338707, "tid": 2338707, + "ts": 6197195563681.297, "dur": 1.151, + "args": { + "External id": 22715,"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": 2338707, "tid": 2338707, + "ts": 6197195563684.214, "dur": 1.208, + "args": { + "External id": 22716,"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": 2338707, "tid": 2338707, + "ts": 6197195563689.764, "dur": 0.989, + "args": { + "External id": 22717,"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": 2338707, "tid": 2338707, + "ts": 6197195563692.842, "dur": 1.576, + "args": { + "External id": 22718,"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": 2338707, "tid": 2338707, + "ts": 6197195563745.163, "dur": 10757.665, + "args": { + "External id": 22719,"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": 2338707, "tid": 2338707, + "ts": 6197195563776.642, "dur": 10713.313, + "args": { + "External id": 22720,"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": 2338707, "tid": 2338707, + "ts": 6197195563802.927, "dur": 7.863, + "args": { + "External id": 22721,"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": 2338707, "tid": 2338707, + "ts": 6197195563818.681, "dur": 10616.329, + "args": { + "External id": 22722,"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": 2338707, "tid": 2338707, + "ts": 6197195563824.125, "dur": 10610.055, + "args": { + "External id": 22723,"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": 2338707, "tid": 2338707, + "ts": 6197195563831.918, "dur": 7.613, + "args": { + "External id": 22724,"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": 2338707, "tid": 2338707, + "ts": 6197195563841.517, "dur": 10588.559, + "args": { + "External id": 22725,"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": 2338707, "tid": 2338707, + "ts": 6197195574979.177, "dur": 42.809, + "args": { + "External id": 22726,"Record function id": 0, "Ev Idx": 12042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 0/0", "pid": 2338707, "tid": 2338707, + "ts": 6197195575024.003, "dur": 314.069, + "args": { + "External id": 22727,"Record function id": 0, "Ev Idx": 12043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197195575123.212, "dur": 202.861, + "args": { + "External id": 22728,"Sequence number": 479766, "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": 2338707, "tid": 2338707, "ts": 6197195575123.212, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_embedding_0", "pid": 2338707, "tid": 2338707, + "ts": 6197195575212.387, "dur": 66.253, + "args": { + "External id": 22729,"kernel_hash": "coj4cw2xx67czwyji56kkta4pwcipuxvxsnrrkf7vsjjhsb6mejv", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/oj/coj4cw2xx67czwyji56kkta4pwcipuxvxsnrrkf7vsjjhsb6mejv.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": 2338707, "tid": 2338707, + "ts": 6197195575415.795, "dur": 67.690, + "args": { + "External id": 22730,"Record function id": 0, "Ev Idx": 12046 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.0)", "pid": 2338707, "tid": 2338707, + "ts": 6197195575497.806, "dur": 9192.177, + "args": { + "External id": 22731,"Record function id": 0, "Ev Idx": 12047 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.0)", "pid": 2338707, "tid": 2338707, + "ts": 6197195575509.543, "dur": 1063.339, + "args": { + "External id": 22732,"Record function id": 0, "Ev Idx": 12048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6197195575605.584, "dur": 13.195, + "args": { + "External id": 22733,"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": 2338707, "tid": 2338707, + "ts": 6197195575635.713, "dur": 49.344, + "args": { + "External id": 22734,"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": 2338707, "tid": 2338707, + "ts": 6197195575645.165, "dur": 3.019, + "args": { + "External id": 22735,"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": 2338707, "tid": 2338707, + "ts": 6197195575651.060, "dur": 0.610, + "args": { + "External id": 22736,"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": 2338707, "tid": 2338707, + "ts": 6197195575653.558, "dur": 2.894, + "args": { + "External id": 22737,"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": 2338707, "tid": 2338707, + "ts": 6197195575658.337, "dur": 0.533, + "args": { + "External id": 22738,"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": 2338707, "tid": 2338707, + "ts": 6197195575660.581, "dur": 0.656, + "args": { + "External id": 22739,"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": 2338707, "tid": 2338707, + "ts": 6197195575665.617, "dur": 0.692, + "args": { + "External id": 22740,"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": 2338707, "tid": 2338707, + "ts": 6197195575668.021, "dur": 0.362, + "args": { + "External id": 22741,"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": 2338707, "tid": 2338707, + "ts": 6197195575669.833, "dur": 3.046, + "args": { + "External id": 22742,"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": 2338707, "tid": 2338707, + "ts": 6197195575676.537, "dur": 0.538, + "args": { + "External id": 22743,"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": 2338707, "tid": 2338707, + "ts": 6197195575698.390, "dur": 96.117, + "args": { + "External id": 22744,"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": 2338707, "tid": 2338707, + "ts": 6197195575837.598, "dur": 146.024, + "args": { + "External id": 22745,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2338707, + "ts": 6197195575851.604, "dur": 8.014, + "args": { + "External id": 22746,"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": 2338707, "tid": 2338707, + "ts": 6197195575866.549, "dur": 13.149, + "args": { + "External id": 22747,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2338707, + "ts": 6197195575871.956, "dur": 7.209, + "args": { + "External id": 22748,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2338707, + "ts": 6197195575876.356, "dur": 0.760, + "args": { + "External id": 22749,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197195575887.845, "dur": 34.333, + "args": { + "External id": 22750,"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": 2338707, "tid": 2338707, + "ts": 6197195575890.430, "dur": 0.641, + "args": { + "External id": 22751,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197195575893.030, "dur": 0.555, + "args": { + "External id": 22752,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2338707, + "ts": 6197195575897.698, "dur": 0.494, + "args": { + "External id": 22753,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2338707, + "ts": 6197195575899.679, "dur": 0.584, + "args": { + "External id": 22754,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2338707, + "ts": 6197195575902.238, "dur": 3.637, + "args": { + "External id": 22755,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2338707, + "ts": 6197195575907.643, "dur": 0.628, + "args": { + "External id": 22756,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2338707, + "ts": 6197195575909.866, "dur": 0.376, + "args": { + "External id": 22757,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2338707, + "ts": 6197195575914.774, "dur": 0.405, + "args": { + "External id": 22758,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2338707, + "ts": 6197195575916.696, "dur": 0.602, + "args": { + "External id": 22759,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2338707, + "ts": 6197195575935.249, "dur": 37.422, + "args": { + "External id": 22760,"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": 2338707, "tid": 2338707, + "ts": 6197195576049.032, "dur": 411.129, + "args": { + "External id": 22761,"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": 2338707, "tid": 2338707, + "ts": 6197195576149.729, "dur": 304.279, + "args": { + "External id": 22762,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2338707, + "ts": 6197195576162.889, "dur": 284.085, + "args": { + "External id": 22763,"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": 2338707, "tid": 2338707, + "ts": 6197195576488.340, "dur": 2.651, + "args": { + "External id": 22764,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.0)", "pid": 2338707, "tid": 2338707, + "ts": 6197195576598.321, "dur": 7828.064, + "args": { + "External id": 22765,"Record function id": 0, "Ev Idx": 12081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6197195576757.423, "dur": 8.235, + "args": { + "External id": 22766,"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": 2338707, "tid": 2338707, + "ts": 6197195576771.799, "dur": 1.442, + "args": { + "External id": 22767,"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": 2338707, "tid": 2338707, + "ts": 6197195576775.673, "dur": 1.243, + "args": { + "External id": 22768,"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": 2338707, "tid": 2338707, + "ts": 6197195576779.028, "dur": 3.802, + "args": { + "External id": 22769,"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": 2338707, "tid": 2338707, + "ts": 6197195576787.048, "dur": 1.254, + "args": { + "External id": 22770,"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": 2338707, "tid": 2338707, + "ts": 6197195576789.963, "dur": 1.023, + "args": { + "External id": 22771,"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": 2338707, "tid": 2338707, + "ts": 6197195576792.993, "dur": 1.219, + "args": { + "External id": 22772,"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": 2338707, "tid": 2338707, + "ts": 6197195576796.151, "dur": 2.466, + "args": { + "External id": 22773,"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": 2338707, "tid": 2338707, + "ts": 6197195576802.909, "dur": 0.896, + "args": { + "External id": 22774,"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": 2338707, "tid": 2338707, + "ts": 6197195576805.651, "dur": 1.380, + "args": { + "External id": 22775,"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": 2338707, "tid": 2338707, + "ts": 6197195576828.140, "dur": 7544.663, + "args": { + "External id": 22776,"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": 2338707, "tid": 2338707, + "ts": 6197195576846.511, "dur": 7515.753, + "args": { + "External id": 22777,"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": 2338707, "tid": 2338707, + "ts": 6197195576871.136, "dur": 17.848, + "args": { + "External id": 22778,"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": 2338707, "tid": 2338707, + "ts": 6197195576896.337, "dur": 7419.448, + "args": { + "External id": 22779,"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": 2338707, "tid": 2338707, + "ts": 6197195576902.277, "dur": 7412.782, + "args": { + "External id": 22780,"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": 2338707, "tid": 2338707, + "ts": 6197195576909.415, "dur": 8.055, + "args": { + "External id": 22781,"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": 2338707, "tid": 2338707, + "ts": 6197195576919.584, "dur": 7391.492, + "args": { + "External id": 22782,"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": 2338707, "tid": 2338707, + "ts": 6197195584620.710, "dur": 39.717, + "args": { + "External id": 22783,"Sequence number": 479767, "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": 2338707, "tid": 2338707, "ts": 6197195584620.710, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6197195584643.816, "dur": 10.578, + "args": { + "External id": 22784,"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": 2338707, "tid": 2338707, + "ts": 6197195584648.440, "dur": 5.658, + "args": { + "External id": 22785,"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": 2338707, "tid": 2338707, + "ts": 6197195584781.611, "dur": 107.938, + "args": { + "External id": 22786,"Record function id": 0, "Ev Idx": 12102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6197195584892.026, "dur": 1494.495, + "args": { + "External id": 22787,"Record function id": 0, "Ev Idx": 12103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197195584946.391, "dur": 1423.038, + "args": { + "External id": 22788,"Sequence number": 479768, "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": 2338707, "tid": 2338707, "ts": 6197195584946.391, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6197195585036.491, "dur": 130.201, + "args": { + "External id": 22789,"kernel_hash": "cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/du/cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs.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": 2338707, "tid": 2338707, + "ts": 6197195585188.057, "dur": 122.924, + "args": { + "External id": 22790,"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": 2338707, "tid": 2338707, + "ts": 6197195585326.480, "dur": 45.769, + "args": { + "External id": 22791,"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": 2338707, "tid": 2338707, + "ts": 6197195585383.164, "dur": 34.181, + "args": { + "External id": 22792,"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": 2338707, "tid": 2338707, + "ts": 6197195585449.390, "dur": 34.695, + "args": { + "External id": 22793,"kernel_hash": "cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5", "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/jw/cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5.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": 2338707, "tid": 2338707, + "ts": 6197195585510.791, "dur": 23.523, + "args": { + "External id": 22794,"kernel_hash": "cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi", "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/xw/cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi.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": 2338707, "tid": 2338707, + "ts": 6197195585563.477, "dur": 191.248, + "args": { + "External id": 22795,"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": 2338707, "tid": 2338707, + "ts": 6197195585626.291, "dur": 15.801, + "args": { + "External id": 22796,"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": 2338707, "tid": 2338707, + "ts": 6197195585632.529, "dur": 8.596, + "args": { + "External id": 22797,"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": 2338707, "tid": 2338707, + "ts": 6197195585645.375, "dur": 4.417, + "args": { + "External id": 22798,"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": 2338707, "tid": 2338707, + "ts": 6197195585651.644, "dur": 1.059, + "args": { + "External id": 22799,"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": 2338707, "tid": 2338707, + "ts": 6197195585655.980, "dur": 3.838, + "args": { + "External id": 22800,"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": 2338707, "tid": 2338707, + "ts": 6197195585769.613, "dur": 68.339, + "args": { + "External id": 22801,"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": 2338707, "tid": 2338707, + "ts": 6197195585881.779, "dur": 41.331, + "args": { + "External id": 22802,"kernel_hash": "cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/dm/cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43.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": 2338707, "tid": 2338707, + "ts": 6197195585932.712, "dur": 52.064, + "args": { + "External id": 22803,"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": 2338707, "tid": 2338707, + "ts": 6197195585996.309, "dur": 42.026, + "args": { + "External id": 22804,"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": 2338707, "tid": 2338707, + "ts": 6197195586116.555, "dur": 37.730, + "args": { + "External id": 22805,"kernel_hash": "cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/b7/cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu.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": 2338707, "tid": 2338707, + "ts": 6197195586165.529, "dur": 51.082, + "args": { + "External id": 22806,"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": 2338707, "tid": 2338707, + "ts": 6197195586245.581, "dur": 24.848, + "args": { + "External id": 22807,"kernel_hash": "cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/gi/cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb.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": 2338707, "tid": 2338707, + "ts": 6197195586467.601, "dur": 110.580, + "args": { + "External id": 22808,"Record function id": 0, "Ev Idx": 12124 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6197195586669.846, "dur": 99.056, + "args": { + "External id": 22809,"Record function id": 0, "Ev Idx": 12125 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.1)", "pid": 2338707, "tid": 2338707, + "ts": 6197195586783.164, "dur": 27603.082, + "args": { + "External id": 22810,"Record function id": 0, "Ev Idx": 12126 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.1)", "pid": 2338707, "tid": 2338707, + "ts": 6197195586793.672, "dur": 1259.398, + "args": { + "External id": 22811,"Record function id": 0, "Ev Idx": 12127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6197195586901.245, "dur": 11.755, + "args": { + "External id": 22812,"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": 2338707, "tid": 2338707, + "ts": 6197195586934.845, "dur": 47.993, + "args": { + "External id": 22813,"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": 2338707, "tid": 2338707, + "ts": 6197195586941.847, "dur": 5.619, + "args": { + "External id": 22814,"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": 2338707, "tid": 2338707, + "ts": 6197195586950.359, "dur": 0.532, + "args": { + "External id": 22815,"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": 2338707, "tid": 2338707, + "ts": 6197195586952.740, "dur": 0.646, + "args": { + "External id": 22816,"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": 2338707, "tid": 2338707, + "ts": 6197195586958.107, "dur": 0.482, + "args": { + "External id": 22817,"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": 2338707, "tid": 2338707, + "ts": 6197195586960.146, "dur": 0.579, + "args": { + "External id": 22818,"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": 2338707, "tid": 2338707, + "ts": 6197195586962.248, "dur": 2.699, + "args": { + "External id": 22819,"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": 2338707, "tid": 2338707, + "ts": 6197195586969.227, "dur": 0.492, + "args": { + "External id": 22820,"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": 2338707, "tid": 2338707, + "ts": 6197195586971.480, "dur": 0.361, + "args": { + "External id": 22821,"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": 2338707, "tid": 2338707, + "ts": 6197195586973.222, "dur": 2.324, + "args": { + "External id": 22822,"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": 2338707, "tid": 2338707, + "ts": 6197195586997.326, "dur": 138.334, + "args": { + "External id": 22823,"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": 2338707, "tid": 2338707, + "ts": 6197195587182.815, "dur": 163.696, + "args": { + "External id": 22824,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2338707, + "ts": 6197195587198.993, "dur": 6.431, + "args": { + "External id": 22825,"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": 2338707, "tid": 2338707, + "ts": 6197195587212.266, "dur": 13.027, + "args": { + "External id": 22826,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2338707, + "ts": 6197195587217.876, "dur": 6.899, + "args": { + "External id": 22827,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2338707, + "ts": 6197195587221.868, "dur": 0.745, + "args": { + "External id": 22828,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197195587233.975, "dur": 34.113, + "args": { + "External id": 22829,"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": 2338707, "tid": 2338707, + "ts": 6197195587236.546, "dur": 0.622, + "args": { + "External id": 22830,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197195587239.433, "dur": 0.556, + "args": { + "External id": 22831,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2338707, + "ts": 6197195587241.208, "dur": 5.719, + "args": { + "External id": 22832,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2338707, + "ts": 6197195587248.938, "dur": 0.472, + "args": { + "External id": 22833,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2338707, + "ts": 6197195587250.847, "dur": 0.505, + "args": { + "External id": 22834,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2338707, + "ts": 6197195587255.316, "dur": 0.428, + "args": { + "External id": 22835,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2338707, + "ts": 6197195587257.225, "dur": 0.425, + "args": { + "External id": 22836,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2338707, + "ts": 6197195587259.226, "dur": 0.567, + "args": { + "External id": 22837,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2338707, + "ts": 6197195587263.321, "dur": 0.347, + "args": { + "External id": 22838,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2338707, + "ts": 6197195587284.165, "dur": 51.249, + "args": { + "External id": 22839,"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": 2338707, "tid": 2338707, + "ts": 6197195587434.288, "dur": 496.351, + "args": { + "External id": 22840,"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": 2338707, "tid": 2338707, + "ts": 6197195587473.568, "dur": 449.663, + "args": { + "External id": 22841,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2338707, + "ts": 6197195587486.479, "dur": 428.819, + "args": { + "External id": 22842,"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": 2338707, "tid": 2338707, + "ts": 6197195587962.037, "dur": 2.819, + "args": { + "External id": 22843,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.1)", "pid": 2338707, "tid": 2338707, + "ts": 6197195588126.846, "dur": 26017.527, + "args": { + "External id": 22844,"Record function id": 0, "Ev Idx": 12160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6197195588263.570, "dur": 8.170, + "args": { + "External id": 22845,"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": 2338707, "tid": 2338707, + "ts": 6197195588276.820, "dur": 3.771, + "args": { + "External id": 22846,"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": 2338707, "tid": 2338707, + "ts": 6197195588282.910, "dur": 0.969, + "args": { + "External id": 22847,"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": 2338707, "tid": 2338707, + "ts": 6197195588285.944, "dur": 0.883, + "args": { + "External id": 22848,"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": 2338707, "tid": 2338707, + "ts": 6197195588289.012, "dur": 1.052, + "args": { + "External id": 22849,"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": 2338707, "tid": 2338707, + "ts": 6197195588294.663, "dur": 0.980, + "args": { + "External id": 22850,"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": 2338707, "tid": 2338707, + "ts": 6197195588297.322, "dur": 1.059, + "args": { + "External id": 22851,"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": 2338707, "tid": 2338707, + "ts": 6197195588300.120, "dur": 2.501, + "args": { + "External id": 22852,"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": 2338707, "tid": 2338707, + "ts": 6197195588304.322, "dur": 0.576, + "args": { + "External id": 22853,"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": 2338707, "tid": 2338707, + "ts": 6197195588309.046, "dur": 3.089, + "args": { + "External id": 22854,"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": 2338707, "tid": 2338707, + "ts": 6197195588333.726, "dur": 25758.462, + "args": { + "External id": 22855,"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": 2338707, "tid": 2338707, + "ts": 6197195588352.436, "dur": 25729.789, + "args": { + "External id": 22856,"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": 2338707, "tid": 2338707, + "ts": 6197195588376.296, "dur": 18.352, + "args": { + "External id": 22857,"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": 2338707, "tid": 2338707, + "ts": 6197195588399.361, "dur": 25607.488, + "args": { + "External id": 22858,"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": 2338707, "tid": 2338707, + "ts": 6197195588402.408, "dur": 25603.692, + "args": { + "External id": 22859,"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": 2338707, "tid": 2338707, + "ts": 6197195588409.314, "dur": 7.614, + "args": { + "External id": 22860,"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": 2338707, "tid": 2338707, + "ts": 6197195588418.975, "dur": 25583.725, + "args": { + "External id": 22861,"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": 2338707, "tid": 2338707, + "ts": 6197195614320.206, "dur": 36.087, + "args": { + "External id": 22862,"Sequence number": 479769, "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": 2338707, "tid": 2338707, "ts": 6197195614320.206, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6197195614340.744, "dur": 9.688, + "args": { + "External id": 22863,"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": 2338707, "tid": 2338707, + "ts": 6197195614344.866, "dur": 5.268, + "args": { + "External id": 22864,"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": 2338707, "tid": 2338707, + "ts": 6197195614438.010, "dur": 95.414, + "args": { + "External id": 22865,"Record function id": 0, "Ev Idx": 12181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6197195614534.979, "dur": 1355.306, + "args": { + "External id": 22866,"Record function id": 0, "Ev Idx": 12182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197195614582.286, "dur": 1291.827, + "args": { + "External id": 22867,"Sequence number": 479770, "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": 2338707, "tid": 2338707, "ts": 6197195614582.286, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6197195614672.462, "dur": 76.812, + "args": { + "External id": 22868,"kernel_hash": "cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/du/cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs.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": 2338707, "tid": 2338707, + "ts": 6197195614770.154, "dur": 119.776, + "args": { + "External id": 22869,"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": 2338707, "tid": 2338707, + "ts": 6197195614905.377, "dur": 42.247, + "args": { + "External id": 22870,"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": 2338707, "tid": 2338707, + "ts": 6197195614954.609, "dur": 39.601, + "args": { + "External id": 22871,"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": 2338707, "tid": 2338707, + "ts": 6197195615026.742, "dur": 72.949, + "args": { + "External id": 22872,"kernel_hash": "cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5", "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/jw/cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5.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": 2338707, "tid": 2338707, + "ts": 6197195615131.499, "dur": 27.707, + "args": { + "External id": 22873,"kernel_hash": "cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi", "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/xw/cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi.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": 2338707, "tid": 2338707, + "ts": 6197195615184.591, "dur": 159.805, + "args": { + "External id": 22874,"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": 2338707, "tid": 2338707, + "ts": 6197195615247.411, "dur": 13.972, + "args": { + "External id": 22875,"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": 2338707, "tid": 2338707, + "ts": 6197195615253.934, "dur": 6.416, + "args": { + "External id": 22876,"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": 2338707, "tid": 2338707, + "ts": 6197195615264.809, "dur": 4.544, + "args": { + "External id": 22877,"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": 2338707, "tid": 2338707, + "ts": 6197195615270.993, "dur": 3.591, + "args": { + "External id": 22878,"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": 2338707, "tid": 2338707, + "ts": 6197195615277.278, "dur": 6.205, + "args": { + "External id": 22879,"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": 2338707, "tid": 2338707, + "ts": 6197195615357.815, "dur": 65.293, + "args": { + "External id": 22880,"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": 2338707, "tid": 2338707, + "ts": 6197195615462.269, "dur": 35.546, + "args": { + "External id": 22881,"kernel_hash": "cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/dm/cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43.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": 2338707, "tid": 2338707, + "ts": 6197195615509.282, "dur": 50.026, + "args": { + "External id": 22882,"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": 2338707, "tid": 2338707, + "ts": 6197195615568.472, "dur": 40.049, + "args": { + "External id": 22883,"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": 2338707, "tid": 2338707, + "ts": 6197195615638.486, "dur": 31.665, + "args": { + "External id": 22884,"kernel_hash": "cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/b7/cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu.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": 2338707, "tid": 2338707, + "ts": 6197195615676.320, "dur": 63.619, + "args": { + "External id": 22885,"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": 2338707, "tid": 2338707, + "ts": 6197195615767.641, "dur": 25.530, + "args": { + "External id": 22886,"kernel_hash": "cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/gi/cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb.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": 2338707, "tid": 2338707, + "ts": 6197195615967.619, "dur": 135.880, + "args": { + "External id": 22887,"Record function id": 0, "Ev Idx": 12203 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6197195616199.331, "dur": 60.211, + "args": { + "External id": 22888,"Record function id": 0, "Ev Idx": 12204 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.2)", "pid": 2338707, "tid": 2338707, + "ts": 6197195616270.488, "dur": 27623.312, + "args": { + "External id": 22889,"Record function id": 0, "Ev Idx": 12205 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.2)", "pid": 2338707, "tid": 2338707, + "ts": 6197195616279.700, "dur": 1165.548, + "args": { + "External id": 22890,"Record function id": 0, "Ev Idx": 12206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6197195616382.024, "dur": 11.114, + "args": { + "External id": 22891,"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": 2338707, "tid": 2338707, + "ts": 6197195616408.919, "dur": 45.621, + "args": { + "External id": 22892,"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": 2338707, "tid": 2338707, + "ts": 6197195616416.253, "dur": 2.574, + "args": { + "External id": 22893,"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": 2338707, "tid": 2338707, + "ts": 6197195616424.551, "dur": 0.393, + "args": { + "External id": 22894,"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": 2338707, "tid": 2338707, + "ts": 6197195616426.711, "dur": 0.575, + "args": { + "External id": 22895,"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": 2338707, "tid": 2338707, + "ts": 6197195616428.454, "dur": 0.579, + "args": { + "External id": 22896,"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": 2338707, "tid": 2338707, + "ts": 6197195616433.594, "dur": 0.549, + "args": { + "External id": 22897,"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": 2338707, "tid": 2338707, + "ts": 6197195616435.471, "dur": 0.628, + "args": { + "External id": 22898,"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": 2338707, "tid": 2338707, + "ts": 6197195616437.577, "dur": 4.858, + "args": { + "External id": 22899,"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": 2338707, "tid": 2338707, + "ts": 6197195616443.854, "dur": 0.480, + "args": { + "External id": 22900,"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": 2338707, "tid": 2338707, + "ts": 6197195616446.337, "dur": 0.410, + "args": { + "External id": 22901,"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": 2338707, "tid": 2338707, + "ts": 6197195616467.552, "dur": 67.321, + "args": { + "External id": 22902,"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": 2338707, "tid": 2338707, + "ts": 6197195616575.322, "dur": 170.754, + "args": { + "External id": 22903,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2338707, + "ts": 6197195616593.139, "dur": 4.201, + "args": { + "External id": 22904,"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": 2338707, "tid": 2338707, + "ts": 6197195616603.746, "dur": 11.981, + "args": { + "External id": 22905,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2338707, + "ts": 6197195616609.279, "dur": 5.936, + "args": { + "External id": 22906,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2338707, + "ts": 6197195616613.222, "dur": 0.498, + "args": { + "External id": 22907,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197195616623.486, "dur": 35.914, + "args": { + "External id": 22908,"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": 2338707, "tid": 2338707, + "ts": 6197195616625.586, "dur": 2.740, + "args": { + "External id": 22909,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197195616630.167, "dur": 0.792, + "args": { + "External id": 22910,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2338707, + "ts": 6197195616632.366, "dur": 0.420, + "args": { + "External id": 22911,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2338707, + "ts": 6197195616636.587, "dur": 2.672, + "args": { + "External id": 22912,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2338707, + "ts": 6197195616640.896, "dur": 0.539, + "args": { + "External id": 22913,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2338707, + "ts": 6197195616642.760, "dur": 0.530, + "args": { + "External id": 22914,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2338707, + "ts": 6197195616647.149, "dur": 0.618, + "args": { + "External id": 22915,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2338707, + "ts": 6197195616649.418, "dur": 0.544, + "args": { + "External id": 22916,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2338707, + "ts": 6197195616651.817, "dur": 2.013, + "args": { + "External id": 22917,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2338707, + "ts": 6197195616673.292, "dur": 61.060, + "args": { + "External id": 22918,"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": 2338707, "tid": 2338707, + "ts": 6197195616813.234, "dur": 508.150, + "args": { + "External id": 22919,"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": 2338707, "tid": 2338707, + "ts": 6197195616853.047, "dur": 460.934, + "args": { + "External id": 22920,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2338707, + "ts": 6197195616867.400, "dur": 435.899, + "args": { + "External id": 22921,"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": 2338707, "tid": 2338707, + "ts": 6197195617352.999, "dur": 3.022, + "args": { + "External id": 22922,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.2)", "pid": 2338707, "tid": 2338707, + "ts": 6197195617470.581, "dur": 26162.189, + "args": { + "External id": 22923,"Record function id": 0, "Ev Idx": 12239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6197195617603.671, "dur": 7.864, + "args": { + "External id": 22924,"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": 2338707, "tid": 2338707, + "ts": 6197195617617.028, "dur": 1.667, + "args": { + "External id": 22925,"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": 2338707, "tid": 2338707, + "ts": 6197195617621.082, "dur": 4.147, + "args": { + "External id": 22926,"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": 2338707, "tid": 2338707, + "ts": 6197195617627.477, "dur": 1.001, + "args": { + "External id": 22927,"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": 2338707, "tid": 2338707, + "ts": 6197195617630.177, "dur": 1.122, + "args": { + "External id": 22928,"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": 2338707, "tid": 2338707, + "ts": 6197195617632.913, "dur": 1.045, + "args": { + "External id": 22929,"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": 2338707, "tid": 2338707, + "ts": 6197195617638.391, "dur": 1.110, + "args": { + "External id": 22930,"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": 2338707, "tid": 2338707, + "ts": 6197195617641.106, "dur": 3.066, + "args": { + "External id": 22931,"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": 2338707, "tid": 2338707, + "ts": 6197195617645.778, "dur": 1.056, + "args": { + "External id": 22932,"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": 2338707, "tid": 2338707, + "ts": 6197195617648.596, "dur": 1.010, + "args": { + "External id": 22933,"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": 2338707, "tid": 2338707, + "ts": 6197195617673.473, "dur": 25900.338, + "args": { + "External id": 22934,"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": 2338707, "tid": 2338707, + "ts": 6197195617692.557, "dur": 25871.093, + "args": { + "External id": 22935,"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": 2338707, "tid": 2338707, + "ts": 6197195617736.195, "dur": 20.920, + "args": { + "External id": 22936,"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": 2338707, "tid": 2338707, + "ts": 6197195617761.881, "dur": 25757.209, + "args": { + "External id": 22937,"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": 2338707, "tid": 2338707, + "ts": 6197195617764.739, "dur": 25753.526, + "args": { + "External id": 22938,"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": 2338707, "tid": 2338707, + "ts": 6197195617772.248, "dur": 6.364, + "args": { + "External id": 22939,"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": 2338707, "tid": 2338707, + "ts": 6197195617780.861, "dur": 25733.325, + "args": { + "External id": 22940,"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": 2338707, "tid": 2338707, + "ts": 6197195643825.336, "dur": 36.898, + "args": { + "External id": 22941,"Sequence number": 479771, "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": 2338707, "tid": 2338707, "ts": 6197195643825.336, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6197195643845.420, "dur": 10.976, + "args": { + "External id": 22942,"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": 2338707, "tid": 2338707, + "ts": 6197195643849.946, "dur": 6.016, + "args": { + "External id": 22943,"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": 2338707, "tid": 2338707, + "ts": 6197195643945.493, "dur": 98.591, + "args": { + "External id": 22944,"Record function id": 0, "Ev Idx": 12260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6197195644045.509, "dur": 1397.125, + "args": { + "External id": 22945,"Record function id": 0, "Ev Idx": 12261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197195644134.362, "dur": 1290.521, + "args": { + "External id": 22946,"Sequence number": 479772, "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": 2338707, "tid": 2338707, "ts": 6197195644134.362, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6197195644217.802, "dur": 63.095, + "args": { + "External id": 22947,"kernel_hash": "cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/du/cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs.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": 2338707, "tid": 2338707, + "ts": 6197195644297.680, "dur": 122.535, + "args": { + "External id": 22948,"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": 2338707, "tid": 2338707, + "ts": 6197195644435.167, "dur": 42.979, + "args": { + "External id": 22949,"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": 2338707, "tid": 2338707, + "ts": 6197195644489.786, "dur": 34.622, + "args": { + "External id": 22950,"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": 2338707, "tid": 2338707, + "ts": 6197195644553.949, "dur": 34.791, + "args": { + "External id": 22951,"kernel_hash": "cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5", "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/jw/cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5.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": 2338707, "tid": 2338707, + "ts": 6197195644612.327, "dur": 23.168, + "args": { + "External id": 22952,"kernel_hash": "cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi", "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/xw/cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi.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": 2338707, "tid": 2338707, + "ts": 6197195644662.725, "dur": 179.830, + "args": { + "External id": 22953,"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": 2338707, "tid": 2338707, + "ts": 6197195644744.663, "dur": 14.839, + "args": { + "External id": 22954,"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": 2338707, "tid": 2338707, + "ts": 6197195644751.296, "dur": 7.123, + "args": { + "External id": 22955,"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": 2338707, "tid": 2338707, + "ts": 6197195644762.788, "dur": 6.161, + "args": { + "External id": 22956,"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": 2338707, "tid": 2338707, + "ts": 6197195644770.504, "dur": 1.051, + "args": { + "External id": 22957,"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": 2338707, "tid": 2338707, + "ts": 6197195644774.580, "dur": 5.660, + "args": { + "External id": 22958,"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": 2338707, "tid": 2338707, + "ts": 6197195644857.257, "dur": 64.475, + "args": { + "External id": 22959,"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": 2338707, "tid": 2338707, + "ts": 6197195644961.972, "dur": 38.176, + "args": { + "External id": 22960,"kernel_hash": "cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/dm/cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43.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": 2338707, "tid": 2338707, + "ts": 6197195645012.695, "dur": 91.664, + "args": { + "External id": 22961,"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": 2338707, "tid": 2338707, + "ts": 6197195645120.539, "dur": 48.798, + "args": { + "External id": 22962,"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": 2338707, "tid": 2338707, + "ts": 6197195645196.296, "dur": 37.367, + "args": { + "External id": 22963,"kernel_hash": "cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/b7/cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu.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": 2338707, "tid": 2338707, + "ts": 6197195645242.924, "dur": 44.822, + "args": { + "External id": 22964,"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": 2338707, "tid": 2338707, + "ts": 6197195645311.706, "dur": 24.317, + "args": { + "External id": 22965,"kernel_hash": "cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/gi/cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb.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": 2338707, "tid": 2338707, + "ts": 6197195645524.439, "dur": 101.595, + "args": { + "External id": 22966,"Record function id": 0, "Ev Idx": 12282 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6197195645738.976, "dur": 59.381, + "args": { + "External id": 22967,"Record function id": 0, "Ev Idx": 12283 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.3)", "pid": 2338707, "tid": 2338707, + "ts": 6197195645810.629, "dur": 29326.345, + "args": { + "External id": 22968,"Record function id": 0, "Ev Idx": 12284 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.3)", "pid": 2338707, "tid": 2338707, + "ts": 6197195645821.682, "dur": 1286.540, + "args": { + "External id": 22969,"Record function id": 0, "Ev Idx": 12285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6197195645924.716, "dur": 12.232, + "args": { + "External id": 22970,"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": 2338707, "tid": 2338707, + "ts": 6197195645952.890, "dur": 48.695, + "args": { + "External id": 22971,"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": 2338707, "tid": 2338707, + "ts": 6197195645959.797, "dur": 2.953, + "args": { + "External id": 22972,"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": 2338707, "tid": 2338707, + "ts": 6197195645967.679, "dur": 0.684, + "args": { + "External id": 22973,"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": 2338707, "tid": 2338707, + "ts": 6197195645969.679, "dur": 0.484, + "args": { + "External id": 22974,"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": 2338707, "tid": 2338707, + "ts": 6197195645977.074, "dur": 0.523, + "args": { + "External id": 22975,"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": 2338707, "tid": 2338707, + "ts": 6197195645981.005, "dur": 0.471, + "args": { + "External id": 22976,"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": 2338707, "tid": 2338707, + "ts": 6197195645982.640, "dur": 0.636, + "args": { + "External id": 22977,"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": 2338707, "tid": 2338707, + "ts": 6197195645984.518, "dur": 5.420, + "args": { + "External id": 22978,"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": 2338707, "tid": 2338707, + "ts": 6197195645991.135, "dur": 0.348, + "args": { + "External id": 22979,"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": 2338707, "tid": 2338707, + "ts": 6197195645992.640, "dur": 0.442, + "args": { + "External id": 22980,"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": 2338707, "tid": 2338707, + "ts": 6197195646017.005, "dur": 122.010, + "args": { + "External id": 22981,"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": 2338707, "tid": 2338707, + "ts": 6197195646184.573, "dur": 163.866, + "args": { + "External id": 22982,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2338707, + "ts": 6197195646201.104, "dur": 6.758, + "args": { + "External id": 22983,"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": 2338707, "tid": 2338707, + "ts": 6197195646214.322, "dur": 13.823, + "args": { + "External id": 22984,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2338707, + "ts": 6197195646220.172, "dur": 7.477, + "args": { + "External id": 22985,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2338707, + "ts": 6197195646224.430, "dur": 1.188, + "args": { + "External id": 22986,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197195646236.547, "dur": 33.838, + "args": { + "External id": 22987,"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": 2338707, "tid": 2338707, + "ts": 6197195646238.932, "dur": 2.847, + "args": { + "External id": 22988,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197195646243.349, "dur": 0.336, + "args": { + "External id": 22989,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2338707, + "ts": 6197195646244.712, "dur": 0.502, + "args": { + "External id": 22990,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2338707, + "ts": 6197195646248.425, "dur": 2.704, + "args": { + "External id": 22991,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2338707, + "ts": 6197195646252.145, "dur": 0.502, + "args": { + "External id": 22992,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2338707, + "ts": 6197195646254.240, "dur": 0.565, + "args": { + "External id": 22993,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2338707, + "ts": 6197195646258.552, "dur": 0.658, + "args": { + "External id": 22994,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2338707, + "ts": 6197195646260.197, "dur": 0.534, + "args": { + "External id": 22995,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2338707, + "ts": 6197195646262.229, "dur": 2.790, + "args": { + "External id": 22996,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2338707, + "ts": 6197195646294.239, "dur": 44.405, + "args": { + "External id": 22997,"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": 2338707, "tid": 2338707, + "ts": 6197195646416.985, "dur": 524.791, + "args": { + "External id": 22998,"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": 2338707, "tid": 2338707, + "ts": 6197195646457.066, "dur": 476.938, + "args": { + "External id": 22999,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2338707, + "ts": 6197195646472.350, "dur": 454.170, + "args": { + "External id": 23000,"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": 2338707, "tid": 2338707, + "ts": 6197195646976.037, "dur": 3.778, + "args": { + "External id": 23001,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.3)", "pid": 2338707, "tid": 2338707, + "ts": 6197195647137.462, "dur": 27728.444, + "args": { + "External id": 23002,"Record function id": 0, "Ev Idx": 12318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6197195647272.212, "dur": 8.414, + "args": { + "External id": 23003,"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": 2338707, "tid": 2338707, + "ts": 6197195647285.141, "dur": 0.970, + "args": { + "External id": 23004,"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": 2338707, "tid": 2338707, + "ts": 6197195647288.464, "dur": 3.505, + "args": { + "External id": 23005,"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": 2338707, "tid": 2338707, + "ts": 6197195647294.577, "dur": 1.280, + "args": { + "External id": 23006,"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": 2338707, "tid": 2338707, + "ts": 6197195647297.543, "dur": 0.888, + "args": { + "External id": 23007,"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": 2338707, "tid": 2338707, + "ts": 6197195647300.371, "dur": 0.990, + "args": { + "External id": 23008,"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": 2338707, "tid": 2338707, + "ts": 6197195647306.094, "dur": 1.023, + "args": { + "External id": 23009,"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": 2338707, "tid": 2338707, + "ts": 6197195647308.905, "dur": 2.364, + "args": { + "External id": 23010,"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": 2338707, "tid": 2338707, + "ts": 6197195647313.158, "dur": 1.157, + "args": { + "External id": 23011,"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": 2338707, "tid": 2338707, + "ts": 6197195647316.235, "dur": 0.991, + "args": { + "External id": 23012,"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": 2338707, "tid": 2338707, + "ts": 6197195647341.183, "dur": 27475.035, + "args": { + "External id": 23013,"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": 2338707, "tid": 2338707, + "ts": 6197195647360.439, "dur": 27446.106, + "args": { + "External id": 23014,"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": 2338707, "tid": 2338707, + "ts": 6197195647381.403, "dur": 19.786, + "args": { + "External id": 23015,"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": 2338707, "tid": 2338707, + "ts": 6197195647405.738, "dur": 27357.258, + "args": { + "External id": 23016,"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": 2338707, "tid": 2338707, + "ts": 6197195647409.058, "dur": 27353.308, + "args": { + "External id": 23017,"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": 2338707, "tid": 2338707, + "ts": 6197195647417.592, "dur": 6.314, + "args": { + "External id": 23018,"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": 2338707, "tid": 2338707, + "ts": 6197195647426.058, "dur": 27332.433, + "args": { + "External id": 23019,"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": 2338707, "tid": 2338707, + "ts": 6197195675030.577, "dur": 74.154, + "args": { + "External id": 23020,"Sequence number": 479773, "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": 2338707, "tid": 2338707, "ts": 6197195675030.577, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6197195675087.201, "dur": 10.687, + "args": { + "External id": 23021,"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": 2338707, "tid": 2338707, + "ts": 6197195675091.330, "dur": 6.160, + "args": { + "External id": 23022,"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": 2338707, "tid": 2338707, + "ts": 6197195675186.369, "dur": 92.889, + "args": { + "External id": 23023,"Record function id": 0, "Ev Idx": 12339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6197195675280.577, "dur": 1388.560, + "args": { + "External id": 23024,"Record function id": 0, "Ev Idx": 12340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197195675327.969, "dur": 1324.034, + "args": { + "External id": 23025,"Sequence number": 479774, "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": 2338707, "tid": 2338707, "ts": 6197195675327.969, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6197195675409.755, "dur": 60.442, + "args": { + "External id": 23026,"kernel_hash": "cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/du/cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs.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": 2338707, "tid": 2338707, + "ts": 6197195675485.866, "dur": 123.058, + "args": { + "External id": 23027,"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": 2338707, "tid": 2338707, + "ts": 6197195675626.863, "dur": 45.040, + "args": { + "External id": 23028,"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": 2338707, "tid": 2338707, + "ts": 6197195675680.552, "dur": 55.633, + "args": { + "External id": 23029,"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": 2338707, "tid": 2338707, + "ts": 6197195675778.330, "dur": 34.787, + "args": { + "External id": 23030,"kernel_hash": "cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5", "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/jw/cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5.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": 2338707, "tid": 2338707, + "ts": 6197195675834.934, "dur": 22.340, + "args": { + "External id": 23031,"kernel_hash": "cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi", "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/xw/cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi.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": 2338707, "tid": 2338707, + "ts": 6197195675884.455, "dur": 160.994, + "args": { + "External id": 23032,"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": 2338707, "tid": 2338707, + "ts": 6197195675947.451, "dur": 14.144, + "args": { + "External id": 23033,"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": 2338707, "tid": 2338707, + "ts": 6197195675953.892, "dur": 6.708, + "args": { + "External id": 23034,"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": 2338707, "tid": 2338707, + "ts": 6197195675965.212, "dur": 5.286, + "args": { + "External id": 23035,"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": 2338707, "tid": 2338707, + "ts": 6197195675972.245, "dur": 1.776, + "args": { + "External id": 23036,"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": 2338707, "tid": 2338707, + "ts": 6197195675979.258, "dur": 4.989, + "args": { + "External id": 23037,"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": 2338707, "tid": 2338707, + "ts": 6197195676101.579, "dur": 74.300, + "args": { + "External id": 23038,"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": 2338707, "tid": 2338707, + "ts": 6197195676222.365, "dur": 38.937, + "args": { + "External id": 23039,"kernel_hash": "cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/dm/cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43.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": 2338707, "tid": 2338707, + "ts": 6197195676274.884, "dur": 52.885, + "args": { + "External id": 23040,"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": 2338707, "tid": 2338707, + "ts": 6197195676368.290, "dur": 42.689, + "args": { + "External id": 23041,"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": 2338707, "tid": 2338707, + "ts": 6197195676444.844, "dur": 31.037, + "args": { + "External id": 23042,"kernel_hash": "cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/b7/cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu.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": 2338707, "tid": 2338707, + "ts": 6197195676482.531, "dur": 41.827, + "args": { + "External id": 23043,"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": 2338707, "tid": 2338707, + "ts": 6197195676545.895, "dur": 23.002, + "args": { + "External id": 23044,"kernel_hash": "cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/gi/cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb.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": 2338707, "tid": 2338707, + "ts": 6197195676772.008, "dur": 102.803, + "args": { + "External id": 23045,"Record function id": 0, "Ev Idx": 12361 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6197195676970.641, "dur": 57.190, + "args": { + "External id": 23046,"Record function id": 0, "Ev Idx": 12362 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.4)", "pid": 2338707, "tid": 2338707, + "ts": 6197195677040.411, "dur": 30849.235, + "args": { + "External id": 23047,"Record function id": 0, "Ev Idx": 12363 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.4)", "pid": 2338707, "tid": 2338707, + "ts": 6197195677051.174, "dur": 1193.685, + "args": { + "External id": 23048,"Record function id": 0, "Ev Idx": 12364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6197195677200.611, "dur": 11.644, + "args": { + "External id": 23049,"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": 2338707, "tid": 2338707, + "ts": 6197195677231.629, "dur": 48.623, + "args": { + "External id": 23050,"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": 2338707, "tid": 2338707, + "ts": 6197195677239.160, "dur": 3.000, + "args": { + "External id": 23051,"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": 2338707, "tid": 2338707, + "ts": 6197195677248.131, "dur": 0.481, + "args": { + "External id": 23052,"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": 2338707, "tid": 2338707, + "ts": 6197195677250.563, "dur": 0.392, + "args": { + "External id": 23053,"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": 2338707, "tid": 2338707, + "ts": 6197195677252.870, "dur": 0.675, + "args": { + "External id": 23054,"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": 2338707, "tid": 2338707, + "ts": 6197195677257.313, "dur": 0.819, + "args": { + "External id": 23055,"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": 2338707, "tid": 2338707, + "ts": 6197195677259.798, "dur": 0.553, + "args": { + "External id": 23056,"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": 2338707, "tid": 2338707, + "ts": 6197195677261.876, "dur": 5.842, + "args": { + "External id": 23057,"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": 2338707, "tid": 2338707, + "ts": 6197195677269.674, "dur": 0.588, + "args": { + "External id": 23058,"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": 2338707, "tid": 2338707, + "ts": 6197195677272.035, "dur": 0.564, + "args": { + "External id": 23059,"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": 2338707, "tid": 2338707, + "ts": 6197195677295.339, "dur": 71.597, + "args": { + "External id": 23060,"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": 2338707, "tid": 2338707, + "ts": 6197195677410.211, "dur": 149.254, + "args": { + "External id": 23061,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2338707, + "ts": 6197195677423.339, "dur": 4.823, + "args": { + "External id": 23062,"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": 2338707, "tid": 2338707, + "ts": 6197195677434.058, "dur": 12.967, + "args": { + "External id": 23063,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2338707, + "ts": 6197195677439.952, "dur": 6.551, + "args": { + "External id": 23064,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2338707, + "ts": 6197195677444.259, "dur": 0.597, + "args": { + "External id": 23065,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197195677455.979, "dur": 39.184, + "args": { + "External id": 23066,"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": 2338707, "tid": 2338707, + "ts": 6197195677458.733, "dur": 3.179, + "args": { + "External id": 23067,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197195677463.625, "dur": 0.631, + "args": { + "External id": 23068,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2338707, + "ts": 6197195677466.407, "dur": 0.511, + "args": { + "External id": 23069,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2338707, + "ts": 6197195677471.453, "dur": 3.091, + "args": { + "External id": 23070,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2338707, + "ts": 6197195677476.139, "dur": 0.657, + "args": { + "External id": 23071,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2338707, + "ts": 6197195677478.536, "dur": 0.647, + "args": { + "External id": 23072,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2338707, + "ts": 6197195677482.911, "dur": 0.271, + "args": { + "External id": 23073,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2338707, + "ts": 6197195677485.052, "dur": 0.599, + "args": { + "External id": 23074,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2338707, + "ts": 6197195677487.564, "dur": 3.102, + "args": { + "External id": 23075,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2338707, + "ts": 6197195677507.206, "dur": 42.858, + "args": { + "External id": 23076,"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": 2338707, "tid": 2338707, + "ts": 6197195677624.072, "dur": 495.159, + "args": { + "External id": 23077,"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": 2338707, "tid": 2338707, + "ts": 6197195677664.429, "dur": 447.892, + "args": { + "External id": 23078,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2338707, + "ts": 6197195677677.505, "dur": 426.273, + "args": { + "External id": 23079,"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": 2338707, "tid": 2338707, + "ts": 6197195678152.832, "dur": 3.276, + "args": { + "External id": 23080,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.4)", "pid": 2338707, "tid": 2338707, + "ts": 6197195678270.525, "dur": 29365.478, + "args": { + "External id": 23081,"Record function id": 0, "Ev Idx": 12397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6197195678402.349, "dur": 8.268, + "args": { + "External id": 23082,"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": 2338707, "tid": 2338707, + "ts": 6197195678414.904, "dur": 1.194, + "args": { + "External id": 23083,"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": 2338707, "tid": 2338707, + "ts": 6197195678418.032, "dur": 3.866, + "args": { + "External id": 23084,"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": 2338707, "tid": 2338707, + "ts": 6197195678424.121, "dur": 1.063, + "args": { + "External id": 23085,"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": 2338707, "tid": 2338707, + "ts": 6197195678426.778, "dur": 1.012, + "args": { + "External id": 23086,"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": 2338707, "tid": 2338707, + "ts": 6197195678429.231, "dur": 1.134, + "args": { + "External id": 23087,"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": 2338707, "tid": 2338707, + "ts": 6197195678435.098, "dur": 1.118, + "args": { + "External id": 23088,"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": 2338707, "tid": 2338707, + "ts": 6197195678438.062, "dur": 2.172, + "args": { + "External id": 23089,"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": 2338707, "tid": 2338707, + "ts": 6197195678442.038, "dur": 0.731, + "args": { + "External id": 23090,"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": 2338707, "tid": 2338707, + "ts": 6197195678444.472, "dur": 0.830, + "args": { + "External id": 23091,"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": 2338707, "tid": 2338707, + "ts": 6197195678470.152, "dur": 29116.823, + "args": { + "External id": 23092,"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": 2338707, "tid": 2338707, + "ts": 6197195678489.164, "dur": 29088.391, + "args": { + "External id": 23093,"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": 2338707, "tid": 2338707, + "ts": 6197195678515.757, "dur": 20.772, + "args": { + "External id": 23094,"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": 2338707, "tid": 2338707, + "ts": 6197195678540.783, "dur": 28994.493, + "args": { + "External id": 23095,"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": 2338707, "tid": 2338707, + "ts": 6197195678544.105, "dur": 28990.551, + "args": { + "External id": 23096,"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": 2338707, "tid": 2338707, + "ts": 6197195678552.109, "dur": 6.293, + "args": { + "External id": 23097,"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": 2338707, "tid": 2338707, + "ts": 6197195678560.507, "dur": 28970.191, + "args": { + "External id": 23098,"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": 2338707, "tid": 2338707, + "ts": 6197195707821.061, "dur": 37.383, + "args": { + "External id": 23099,"Sequence number": 479775, "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": 2338707, "tid": 2338707, "ts": 6197195707821.061, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6197195707842.162, "dur": 10.445, + "args": { + "External id": 23100,"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": 2338707, "tid": 2338707, + "ts": 6197195707846.616, "dur": 5.638, + "args": { + "External id": 23101,"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": 2338707, "tid": 2338707, + "ts": 6197195707940.635, "dur": 92.449, + "args": { + "External id": 23102,"Record function id": 0, "Ev Idx": 12418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6197195708034.904, "dur": 1384.523, + "args": { + "External id": 23103,"Record function id": 0, "Ev Idx": 12419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197195708121.536, "dur": 1281.096, + "args": { + "External id": 23104,"Sequence number": 479776, "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": 2338707, "tid": 2338707, "ts": 6197195708121.536, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6197195708203.311, "dur": 63.260, + "args": { + "External id": 23105,"kernel_hash": "cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/du/cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs.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": 2338707, "tid": 2338707, + "ts": 6197195708282.808, "dur": 122.173, + "args": { + "External id": 23106,"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": 2338707, "tid": 2338707, + "ts": 6197195708419.211, "dur": 43.876, + "args": { + "External id": 23107,"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": 2338707, "tid": 2338707, + "ts": 6197195708474.213, "dur": 35.374, + "args": { + "External id": 23108,"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": 2338707, "tid": 2338707, + "ts": 6197195708538.907, "dur": 33.594, + "args": { + "External id": 23109,"kernel_hash": "cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5", "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/jw/cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5.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": 2338707, "tid": 2338707, + "ts": 6197195708596.824, "dur": 21.112, + "args": { + "External id": 23110,"kernel_hash": "cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi", "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/xw/cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi.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": 2338707, "tid": 2338707, + "ts": 6197195708645.405, "dur": 181.823, + "args": { + "External id": 23111,"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": 2338707, "tid": 2338707, + "ts": 6197195708724.295, "dur": 15.966, + "args": { + "External id": 23112,"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": 2338707, "tid": 2338707, + "ts": 6197195708730.982, "dur": 8.169, + "args": { + "External id": 23113,"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": 2338707, "tid": 2338707, + "ts": 6197195708743.731, "dur": 4.703, + "args": { + "External id": 23114,"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": 2338707, "tid": 2338707, + "ts": 6197195708749.922, "dur": 1.139, + "args": { + "External id": 23115,"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": 2338707, "tid": 2338707, + "ts": 6197195708754.088, "dur": 8.424, + "args": { + "External id": 23116,"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": 2338707, "tid": 2338707, + "ts": 6197195708841.857, "dur": 64.953, + "args": { + "External id": 23117,"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": 2338707, "tid": 2338707, + "ts": 6197195708944.986, "dur": 36.859, + "args": { + "External id": 23118,"kernel_hash": "cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/dm/cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43.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": 2338707, "tid": 2338707, + "ts": 6197195708993.468, "dur": 51.310, + "args": { + "External id": 23119,"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": 2338707, "tid": 2338707, + "ts": 6197195709100.186, "dur": 50.214, + "args": { + "External id": 23120,"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": 2338707, "tid": 2338707, + "ts": 6197195709181.373, "dur": 34.430, + "args": { + "External id": 23121,"kernel_hash": "cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/b7/cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu.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": 2338707, "tid": 2338707, + "ts": 6197195709225.730, "dur": 44.700, + "args": { + "External id": 23122,"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": 2338707, "tid": 2338707, + "ts": 6197195709292.210, "dur": 23.257, + "args": { + "External id": 23123,"kernel_hash": "cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/gi/cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb.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": 2338707, "tid": 2338707, + "ts": 6197195709499.398, "dur": 102.874, + "args": { + "External id": 23124,"Record function id": 0, "Ev Idx": 12440 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6197195709689.400, "dur": 82.128, + "args": { + "External id": 23125,"Record function id": 0, "Ev Idx": 12441 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.5)", "pid": 2338707, "tid": 2338707, + "ts": 6197195709785.180, "dur": 31889.960, + "args": { + "External id": 23126,"Record function id": 0, "Ev Idx": 12442 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.5)", "pid": 2338707, "tid": 2338707, + "ts": 6197195709797.596, "dur": 1156.333, + "args": { + "External id": 23127,"Record function id": 0, "Ev Idx": 12443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6197195709898.930, "dur": 11.786, + "args": { + "External id": 23128,"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": 2338707, "tid": 2338707, + "ts": 6197195709927.727, "dur": 46.331, + "args": { + "External id": 23129,"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": 2338707, "tid": 2338707, + "ts": 6197195709934.823, "dur": 2.801, + "args": { + "External id": 23130,"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": 2338707, "tid": 2338707, + "ts": 6197195709943.101, "dur": 0.529, + "args": { + "External id": 23131,"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": 2338707, "tid": 2338707, + "ts": 6197195709945.781, "dur": 0.711, + "args": { + "External id": 23132,"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": 2338707, "tid": 2338707, + "ts": 6197195709948.101, "dur": 0.694, + "args": { + "External id": 23133,"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": 2338707, "tid": 2338707, + "ts": 6197195709952.879, "dur": 0.683, + "args": { + "External id": 23134,"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": 2338707, "tid": 2338707, + "ts": 6197195709955.296, "dur": 0.717, + "args": { + "External id": 23135,"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": 2338707, "tid": 2338707, + "ts": 6197195709957.741, "dur": 4.990, + "args": { + "External id": 23136,"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": 2338707, "tid": 2338707, + "ts": 6197195709964.450, "dur": 0.360, + "args": { + "External id": 23137,"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": 2338707, "tid": 2338707, + "ts": 6197195709966.824, "dur": 0.418, + "args": { + "External id": 23138,"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": 2338707, "tid": 2338707, + "ts": 6197195709988.311, "dur": 108.215, + "args": { + "External id": 23139,"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": 2338707, "tid": 2338707, + "ts": 6197195710143.352, "dur": 165.089, + "args": { + "External id": 23140,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2338707, + "ts": 6197195710158.079, "dur": 6.844, + "args": { + "External id": 23141,"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": 2338707, "tid": 2338707, + "ts": 6197195710171.243, "dur": 13.996, + "args": { + "External id": 23142,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2338707, + "ts": 6197195710177.019, "dur": 7.730, + "args": { + "External id": 23143,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2338707, + "ts": 6197195710181.833, "dur": 0.886, + "args": { + "External id": 23144,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197195710193.662, "dur": 37.810, + "args": { + "External id": 23145,"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": 2338707, "tid": 2338707, + "ts": 6197195710196.439, "dur": 2.584, + "args": { + "External id": 23146,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197195710200.863, "dur": 0.586, + "args": { + "External id": 23147,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2338707, + "ts": 6197195710203.218, "dur": 0.531, + "args": { + "External id": 23148,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2338707, + "ts": 6197195710208.189, "dur": 2.883, + "args": { + "External id": 23149,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2338707, + "ts": 6197195710212.750, "dur": 0.646, + "args": { + "External id": 23150,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2338707, + "ts": 6197195710215.158, "dur": 0.465, + "args": { + "External id": 23151,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2338707, + "ts": 6197195710219.563, "dur": 0.680, + "args": { + "External id": 23152,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2338707, + "ts": 6197195710221.741, "dur": 0.349, + "args": { + "External id": 23153,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2338707, + "ts": 6197195710224.149, "dur": 2.660, + "args": { + "External id": 23154,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2338707, + "ts": 6197195710251.389, "dur": 47.230, + "args": { + "External id": 23155,"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": 2338707, "tid": 2338707, + "ts": 6197195710374.912, "dur": 456.570, + "args": { + "External id": 23156,"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": 2338707, "tid": 2338707, + "ts": 6197195710412.483, "dur": 411.831, + "args": { + "External id": 23157,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2338707, + "ts": 6197195710426.512, "dur": 389.546, + "args": { + "External id": 23158,"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": 2338707, "tid": 2338707, + "ts": 6197195710862.417, "dur": 3.085, + "args": { + "External id": 23159,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.5)", "pid": 2338707, "tid": 2338707, + "ts": 6197195710981.157, "dur": 30453.887, + "args": { + "External id": 23160,"Record function id": 0, "Ev Idx": 12476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6197195711155.674, "dur": 8.116, + "args": { + "External id": 23161,"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": 2338707, "tid": 2338707, + "ts": 6197195711168.459, "dur": 1.306, + "args": { + "External id": 23162,"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": 2338707, "tid": 2338707, + "ts": 6197195711171.682, "dur": 3.660, + "args": { + "External id": 23163,"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": 2338707, "tid": 2338707, + "ts": 6197195711177.628, "dur": 0.847, + "args": { + "External id": 23164,"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": 2338707, "tid": 2338707, + "ts": 6197195711180.074, "dur": 0.942, + "args": { + "External id": 23165,"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": 2338707, "tid": 2338707, + "ts": 6197195711185.240, "dur": 1.179, + "args": { + "External id": 23166,"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": 2338707, "tid": 2338707, + "ts": 6197195711188.482, "dur": 0.908, + "args": { + "External id": 23167,"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": 2338707, "tid": 2338707, + "ts": 6197195711191.178, "dur": 2.591, + "args": { + "External id": 23168,"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": 2338707, "tid": 2338707, + "ts": 6197195711195.776, "dur": 0.867, + "args": { + "External id": 23169,"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": 2338707, "tid": 2338707, + "ts": 6197195711201.416, "dur": 0.841, + "args": { + "External id": 23170,"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": 2338707, "tid": 2338707, + "ts": 6197195711226.914, "dur": 30155.257, + "args": { + "External id": 23171,"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": 2338707, "tid": 2338707, + "ts": 6197195711260.179, "dur": 30111.875, + "args": { + "External id": 23172,"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": 2338707, "tid": 2338707, + "ts": 6197195711279.270, "dur": 22.004, + "args": { + "External id": 23173,"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": 2338707, "tid": 2338707, + "ts": 6197195711305.468, "dur": 30020.994, + "args": { + "External id": 23174,"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": 2338707, "tid": 2338707, + "ts": 6197195711308.456, "dur": 30017.454, + "args": { + "External id": 23175,"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": 2338707, "tid": 2338707, + "ts": 6197195711315.640, "dur": 6.297, + "args": { + "External id": 23176,"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": 2338707, "tid": 2338707, + "ts": 6197195711324.383, "dur": 29997.625, + "args": { + "External id": 23177,"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": 2338707, "tid": 2338707, + "ts": 6197195741603.622, "dur": 38.385, + "args": { + "External id": 23178,"Sequence number": 479777, "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": 2338707, "tid": 2338707, "ts": 6197195741603.622, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6197195741626.247, "dur": 9.985, + "args": { + "External id": 23179,"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": 2338707, "tid": 2338707, + "ts": 6197195741630.370, "dur": 5.581, + "args": { + "External id": 23180,"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": 2338707, "tid": 2338707, + "ts": 6197195741741.359, "dur": 91.816, + "args": { + "External id": 23181,"Record function id": 0, "Ev Idx": 12497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6197195741835.449, "dur": 1376.740, + "args": { + "External id": 23182,"Record function id": 0, "Ev Idx": 12498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197195741881.633, "dur": 1313.992, + "args": { + "External id": 23183,"Sequence number": 479778, "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": 2338707, "tid": 2338707, "ts": 6197195741881.633, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6197195741965.285, "dur": 61.053, + "args": { + "External id": 23184,"kernel_hash": "cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/du/cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs.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": 2338707, "tid": 2338707, + "ts": 6197195742042.619, "dur": 163.851, + "args": { + "External id": 23185,"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": 2338707, "tid": 2338707, + "ts": 6197195742225.832, "dur": 45.354, + "args": { + "External id": 23186,"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": 2338707, "tid": 2338707, + "ts": 6197195742282.130, "dur": 33.372, + "args": { + "External id": 23187,"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": 2338707, "tid": 2338707, + "ts": 6197195742347.365, "dur": 32.075, + "args": { + "External id": 23188,"kernel_hash": "cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5", "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/jw/cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5.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": 2338707, "tid": 2338707, + "ts": 6197195742402.821, "dur": 19.884, + "args": { + "External id": 23189,"kernel_hash": "cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi", "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/xw/cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi.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": 2338707, "tid": 2338707, + "ts": 6197195742457.950, "dur": 156.589, + "args": { + "External id": 23190,"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": 2338707, "tid": 2338707, + "ts": 6197195742520.320, "dur": 13.747, + "args": { + "External id": 23191,"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": 2338707, "tid": 2338707, + "ts": 6197195742526.728, "dur": 6.420, + "args": { + "External id": 23192,"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": 2338707, "tid": 2338707, + "ts": 6197195742538.155, "dur": 5.096, + "args": { + "External id": 23193,"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": 2338707, "tid": 2338707, + "ts": 6197195742545.155, "dur": 1.295, + "args": { + "External id": 23194,"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": 2338707, "tid": 2338707, + "ts": 6197195742549.736, "dur": 4.834, + "args": { + "External id": 23195,"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": 2338707, "tid": 2338707, + "ts": 6197195742627.529, "dur": 58.423, + "args": { + "External id": 23196,"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": 2338707, "tid": 2338707, + "ts": 6197195742749.905, "dur": 39.069, + "args": { + "External id": 23197,"kernel_hash": "cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/dm/cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43.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": 2338707, "tid": 2338707, + "ts": 6197195742800.792, "dur": 55.607, + "args": { + "External id": 23198,"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": 2338707, "tid": 2338707, + "ts": 6197195742866.989, "dur": 41.000, + "args": { + "External id": 23199,"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": 2338707, "tid": 2338707, + "ts": 6197195742934.686, "dur": 34.951, + "args": { + "External id": 23200,"kernel_hash": "cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/b7/cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu.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": 2338707, "tid": 2338707, + "ts": 6197195742978.635, "dur": 41.165, + "args": { + "External id": 23201,"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": 2338707, "tid": 2338707, + "ts": 6197195743043.980, "dur": 62.571, + "args": { + "External id": 23202,"kernel_hash": "cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/gi/cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb.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": 2338707, "tid": 2338707, + "ts": 6197195743294.381, "dur": 99.649, + "args": { + "External id": 23203,"Record function id": 0, "Ev Idx": 12519 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6197195743484.101, "dur": 56.739, + "args": { + "External id": 23204,"Record function id": 0, "Ev Idx": 12520 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.6)", "pid": 2338707, "tid": 2338707, + "ts": 6197195743553.021, "dur": 33030.383, + "args": { + "External id": 23205,"Record function id": 0, "Ev Idx": 12521 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.6)", "pid": 2338707, "tid": 2338707, + "ts": 6197195743562.761, "dur": 1156.220, + "args": { + "External id": 23206,"Record function id": 0, "Ev Idx": 12522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6197195743663.688, "dur": 10.970, + "args": { + "External id": 23207,"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": 2338707, "tid": 2338707, + "ts": 6197195743690.991, "dur": 66.049, + "args": { + "External id": 23208,"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": 2338707, "tid": 2338707, + "ts": 6197195743697.871, "dur": 20.379, + "args": { + "External id": 23209,"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": 2338707, "tid": 2338707, + "ts": 6197195743725.010, "dur": 0.549, + "args": { + "External id": 23210,"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": 2338707, "tid": 2338707, + "ts": 6197195743727.161, "dur": 0.632, + "args": { + "External id": 23211,"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": 2338707, "tid": 2338707, + "ts": 6197195743729.917, "dur": 0.726, + "args": { + "External id": 23212,"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": 2338707, "tid": 2338707, + "ts": 6197195743734.696, "dur": 0.640, + "args": { + "External id": 23213,"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": 2338707, "tid": 2338707, + "ts": 6197195743737.134, "dur": 0.608, + "args": { + "External id": 23214,"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": 2338707, "tid": 2338707, + "ts": 6197195743739.151, "dur": 5.518, + "args": { + "External id": 23215,"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": 2338707, "tid": 2338707, + "ts": 6197195743746.607, "dur": 0.718, + "args": { + "External id": 23216,"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": 2338707, "tid": 2338707, + "ts": 6197195743748.855, "dur": 0.332, + "args": { + "External id": 23217,"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": 2338707, "tid": 2338707, + "ts": 6197195743772.453, "dur": 71.499, + "args": { + "External id": 23218,"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": 2338707, "tid": 2338707, + "ts": 6197195743886.266, "dur": 150.293, + "args": { + "External id": 23219,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2338707, + "ts": 6197195743900.129, "dur": 6.644, + "args": { + "External id": 23220,"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": 2338707, "tid": 2338707, + "ts": 6197195743913.357, "dur": 12.854, + "args": { + "External id": 23221,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2338707, + "ts": 6197195743918.943, "dur": 6.759, + "args": { + "External id": 23222,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2338707, + "ts": 6197195743923.481, "dur": 0.649, + "args": { + "External id": 23223,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197195743935.058, "dur": 37.057, + "args": { + "External id": 23224,"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": 2338707, "tid": 2338707, + "ts": 6197195743937.583, "dur": 2.695, + "args": { + "External id": 23225,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197195743942.432, "dur": 0.384, + "args": { + "External id": 23226,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2338707, + "ts": 6197195743944.537, "dur": 0.370, + "args": { + "External id": 23227,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2338707, + "ts": 6197195743949.370, "dur": 2.839, + "args": { + "External id": 23228,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2338707, + "ts": 6197195743953.815, "dur": 0.370, + "args": { + "External id": 23229,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2338707, + "ts": 6197195743956.157, "dur": 0.347, + "args": { + "External id": 23230,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2338707, + "ts": 6197195743960.134, "dur": 0.255, + "args": { + "External id": 23231,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2338707, + "ts": 6197195743962.395, "dur": 0.383, + "args": { + "External id": 23232,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2338707, + "ts": 6197195743964.340, "dur": 2.590, + "args": { + "External id": 23233,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2338707, + "ts": 6197195743988.357, "dur": 38.634, + "args": { + "External id": 23234,"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": 2338707, "tid": 2338707, + "ts": 6197195744146.065, "dur": 440.543, + "args": { + "External id": 23235,"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": 2338707, "tid": 2338707, + "ts": 6197195744185.043, "dur": 395.251, + "args": { + "External id": 23236,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2338707, + "ts": 6197195744198.925, "dur": 374.345, + "args": { + "External id": 23237,"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": 2338707, "tid": 2338707, + "ts": 6197195744612.885, "dur": 2.856, + "args": { + "External id": 23238,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.6)", "pid": 2338707, "tid": 2338707, + "ts": 6197195744751.668, "dur": 31599.053, + "args": { + "External id": 23239,"Record function id": 0, "Ev Idx": 12555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6197195744877.963, "dur": 8.391, + "args": { + "External id": 23240,"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": 2338707, "tid": 2338707, + "ts": 6197195744890.201, "dur": 1.235, + "args": { + "External id": 23241,"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": 2338707, "tid": 2338707, + "ts": 6197195744893.364, "dur": 4.090, + "args": { + "External id": 23242,"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": 2338707, "tid": 2338707, + "ts": 6197195744899.482, "dur": 0.735, + "args": { + "External id": 23243,"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": 2338707, "tid": 2338707, + "ts": 6197195744901.758, "dur": 1.070, + "args": { + "External id": 23244,"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": 2338707, "tid": 2338707, + "ts": 6197195744904.251, "dur": 1.314, + "args": { + "External id": 23245,"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": 2338707, "tid": 2338707, + "ts": 6197195744909.786, "dur": 0.882, + "args": { + "External id": 23246,"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": 2338707, "tid": 2338707, + "ts": 6197195744912.432, "dur": 2.251, + "args": { + "External id": 23247,"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": 2338707, "tid": 2338707, + "ts": 6197195744916.463, "dur": 1.264, + "args": { + "External id": 23248,"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": 2338707, "tid": 2338707, + "ts": 6197195744919.504, "dur": 0.735, + "args": { + "External id": 23249,"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": 2338707, "tid": 2338707, + "ts": 6197195744945.305, "dur": 31350.926, + "args": { + "External id": 23250,"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": 2338707, "tid": 2338707, + "ts": 6197195744964.348, "dur": 31321.755, + "args": { + "External id": 23251,"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": 2338707, "tid": 2338707, + "ts": 6197195744994.065, "dur": 19.382, + "args": { + "External id": 23252,"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": 2338707, "tid": 2338707, + "ts": 6197195745017.645, "dur": 31227.228, + "args": { + "External id": 23253,"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": 2338707, "tid": 2338707, + "ts": 6197195745020.876, "dur": 31223.276, + "args": { + "External id": 23254,"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": 2338707, "tid": 2338707, + "ts": 6197195745028.065, "dur": 8.201, + "args": { + "External id": 23255,"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": 2338707, "tid": 2338707, + "ts": 6197195745038.850, "dur": 31201.454, + "args": { + "External id": 23256,"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": 2338707, "tid": 2338707, + "ts": 6197195776516.231, "dur": 37.492, + "args": { + "External id": 23257,"Sequence number": 479779, "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": 2338707, "tid": 2338707, "ts": 6197195776516.231, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6197195776537.165, "dur": 10.418, + "args": { + "External id": 23258,"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": 2338707, "tid": 2338707, + "ts": 6197195776541.517, "dur": 5.734, + "args": { + "External id": 23259,"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": 2338707, "tid": 2338707, + "ts": 6197195776634.399, "dur": 102.100, + "args": { + "External id": 23260,"Record function id": 0, "Ev Idx": 12576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6197195776739.784, "dur": 1380.372, + "args": { + "External id": 23261,"Record function id": 0, "Ev Idx": 12577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197195776791.022, "dur": 1309.147, + "args": { + "External id": 23262,"Sequence number": 479780, "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": 2338707, "tid": 2338707, "ts": 6197195776791.022, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6197195776876.555, "dur": 60.230, + "args": { + "External id": 23263,"kernel_hash": "cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/du/cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs.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": 2338707, "tid": 2338707, + "ts": 6197195776953.012, "dur": 161.292, + "args": { + "External id": 23264,"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": 2338707, "tid": 2338707, + "ts": 6197195777133.284, "dur": 48.871, + "args": { + "External id": 23265,"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": 2338707, "tid": 2338707, + "ts": 6197195777192.592, "dur": 34.881, + "args": { + "External id": 23266,"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": 2338707, "tid": 2338707, + "ts": 6197195777261.258, "dur": 30.841, + "args": { + "External id": 23267,"kernel_hash": "cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5", "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/jw/cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5.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": 2338707, "tid": 2338707, + "ts": 6197195777316.319, "dur": 21.081, + "args": { + "External id": 23268,"kernel_hash": "cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi", "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/xw/cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi.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": 2338707, "tid": 2338707, + "ts": 6197195777366.537, "dur": 157.187, + "args": { + "External id": 23269,"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": 2338707, "tid": 2338707, + "ts": 6197195777428.372, "dur": 14.213, + "args": { + "External id": 23270,"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": 2338707, "tid": 2338707, + "ts": 6197195777434.955, "dur": 6.550, + "args": { + "External id": 23271,"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": 2338707, "tid": 2338707, + "ts": 6197195777446.067, "dur": 4.512, + "args": { + "External id": 23272,"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": 2338707, "tid": 2338707, + "ts": 6197195777452.245, "dur": 1.175, + "args": { + "External id": 23273,"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": 2338707, "tid": 2338707, + "ts": 6197195777456.686, "dur": 5.999, + "args": { + "External id": 23274,"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": 2338707, "tid": 2338707, + "ts": 6197195777536.901, "dur": 59.793, + "args": { + "External id": 23275,"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": 2338707, "tid": 2338707, + "ts": 6197195777634.927, "dur": 35.307, + "args": { + "External id": 23276,"kernel_hash": "cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/dm/cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43.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": 2338707, "tid": 2338707, + "ts": 6197195777681.625, "dur": 68.013, + "args": { + "External id": 23277,"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": 2338707, "tid": 2338707, + "ts": 6197195777763.968, "dur": 44.257, + "args": { + "External id": 23278,"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": 2338707, "tid": 2338707, + "ts": 6197195777837.637, "dur": 33.977, + "args": { + "External id": 23279,"kernel_hash": "cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/b7/cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu.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": 2338707, "tid": 2338707, + "ts": 6197195777881.106, "dur": 42.876, + "args": { + "External id": 23280,"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": 2338707, "tid": 2338707, + "ts": 6197195777948.346, "dur": 22.199, + "args": { + "External id": 23281,"kernel_hash": "cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/gi/cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb.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": 2338707, "tid": 2338707, + "ts": 6197195778203.454, "dur": 98.341, + "args": { + "External id": 23282,"Record function id": 0, "Ev Idx": 12598 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6197195778396.195, "dur": 62.230, + "args": { + "External id": 23283,"Record function id": 0, "Ev Idx": 12599 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.7)", "pid": 2338707, "tid": 2338707, + "ts": 6197195778469.873, "dur": 32216.469, + "args": { + "External id": 23284,"Record function id": 0, "Ev Idx": 12600 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.7)", "pid": 2338707, "tid": 2338707, + "ts": 6197195778479.392, "dur": 1141.961, + "args": { + "External id": 23285,"Record function id": 0, "Ev Idx": 12601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6197195778584.483, "dur": 11.981, + "args": { + "External id": 23286,"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": 2338707, "tid": 2338707, + "ts": 6197195778612.425, "dur": 45.442, + "args": { + "External id": 23287,"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": 2338707, "tid": 2338707, + "ts": 6197195778619.512, "dur": 2.540, + "args": { + "External id": 23288,"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": 2338707, "tid": 2338707, + "ts": 6197195778627.300, "dur": 0.439, + "args": { + "External id": 23289,"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": 2338707, "tid": 2338707, + "ts": 6197195778629.617, "dur": 0.747, + "args": { + "External id": 23290,"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": 2338707, "tid": 2338707, + "ts": 6197195778631.982, "dur": 0.476, + "args": { + "External id": 23291,"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": 2338707, "tid": 2338707, + "ts": 6197195778635.980, "dur": 0.522, + "args": { + "External id": 23292,"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": 2338707, "tid": 2338707, + "ts": 6197195778638.121, "dur": 0.665, + "args": { + "External id": 23293,"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": 2338707, "tid": 2338707, + "ts": 6197195778640.661, "dur": 5.354, + "args": { + "External id": 23294,"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": 2338707, "tid": 2338707, + "ts": 6197195778647.371, "dur": 0.655, + "args": { + "External id": 23295,"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": 2338707, "tid": 2338707, + "ts": 6197195778649.568, "dur": 0.443, + "args": { + "External id": 23296,"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": 2338707, "tid": 2338707, + "ts": 6197195778672.468, "dur": 86.218, + "args": { + "External id": 23297,"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": 2338707, "tid": 2338707, + "ts": 6197195778802.953, "dur": 154.120, + "args": { + "External id": 23298,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2338707, + "ts": 6197195778817.366, "dur": 5.927, + "args": { + "External id": 23299,"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": 2338707, "tid": 2338707, + "ts": 6197195778829.633, "dur": 14.355, + "args": { + "External id": 23300,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2338707, + "ts": 6197195778835.588, "dur": 7.861, + "args": { + "External id": 23301,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2338707, + "ts": 6197195778840.447, "dur": 1.126, + "args": { + "External id": 23302,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197195778852.290, "dur": 34.799, + "args": { + "External id": 23303,"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": 2338707, "tid": 2338707, + "ts": 6197195778854.984, "dur": 2.970, + "args": { + "External id": 23304,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197195778859.864, "dur": 0.380, + "args": { + "External id": 23305,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2338707, + "ts": 6197195778862.183, "dur": 0.497, + "args": { + "External id": 23306,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2338707, + "ts": 6197195778866.560, "dur": 2.388, + "args": { + "External id": 23307,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2338707, + "ts": 6197195778870.139, "dur": 0.417, + "args": { + "External id": 23308,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2338707, + "ts": 6197195778871.753, "dur": 0.394, + "args": { + "External id": 23309,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2338707, + "ts": 6197195778876.209, "dur": 0.361, + "args": { + "External id": 23310,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2338707, + "ts": 6197195778877.642, "dur": 0.410, + "args": { + "External id": 23311,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2338707, + "ts": 6197195778879.639, "dur": 2.938, + "args": { + "External id": 23312,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2338707, + "ts": 6197195778905.793, "dur": 41.558, + "args": { + "External id": 23313,"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": 2338707, "tid": 2338707, + "ts": 6197195779023.872, "dur": 478.834, + "args": { + "External id": 23314,"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": 2338707, "tid": 2338707, + "ts": 6197195779101.315, "dur": 394.555, + "args": { + "External id": 23315,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2338707, + "ts": 6197195779116.505, "dur": 372.812, + "args": { + "External id": 23316,"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": 2338707, "tid": 2338707, + "ts": 6197195779532.926, "dur": 3.078, + "args": { + "External id": 23317,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.7)", "pid": 2338707, "tid": 2338707, + "ts": 6197195779647.779, "dur": 30807.054, + "args": { + "External id": 23318,"Record function id": 0, "Ev Idx": 12634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6197195779805.889, "dur": 9.135, + "args": { + "External id": 23319,"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": 2338707, "tid": 2338707, + "ts": 6197195779819.934, "dur": 1.339, + "args": { + "External id": 23320,"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": 2338707, "tid": 2338707, + "ts": 6197195779823.581, "dur": 3.588, + "args": { + "External id": 23321,"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": 2338707, "tid": 2338707, + "ts": 6197195779831.712, "dur": 1.199, + "args": { + "External id": 23322,"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": 2338707, "tid": 2338707, + "ts": 6197195779834.752, "dur": 1.297, + "args": { + "External id": 23323,"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": 2338707, "tid": 2338707, + "ts": 6197195779837.758, "dur": 0.974, + "args": { + "External id": 23324,"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": 2338707, "tid": 2338707, + "ts": 6197195779840.645, "dur": 1.072, + "args": { + "External id": 23325,"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": 2338707, "tid": 2338707, + "ts": 6197195779845.406, "dur": 2.260, + "args": { + "External id": 23326,"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": 2338707, "tid": 2338707, + "ts": 6197195779849.629, "dur": 1.070, + "args": { + "External id": 23327,"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": 2338707, "tid": 2338707, + "ts": 6197195779852.259, "dur": 0.807, + "args": { + "External id": 23328,"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": 2338707, "tid": 2338707, + "ts": 6197195779878.463, "dur": 30525.760, + "args": { + "External id": 23329,"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": 2338707, "tid": 2338707, + "ts": 6197195779897.261, "dur": 30497.248, + "args": { + "External id": 23330,"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": 2338707, "tid": 2338707, + "ts": 6197195779918.592, "dur": 20.602, + "args": { + "External id": 23331,"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": 2338707, "tid": 2338707, + "ts": 6197195779943.589, "dur": 30409.221, + "args": { + "External id": 23332,"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": 2338707, "tid": 2338707, + "ts": 6197195779946.738, "dur": 30405.421, + "args": { + "External id": 23333,"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": 2338707, "tid": 2338707, + "ts": 6197195779953.937, "dur": 7.569, + "args": { + "External id": 23334,"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": 2338707, "tid": 2338707, + "ts": 6197195779963.537, "dur": 30385.286, + "args": { + "External id": 23335,"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": 2338707, "tid": 2338707, + "ts": 6197195810618.185, "dur": 39.566, + "args": { + "External id": 23336,"Sequence number": 479781, "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": 2338707, "tid": 2338707, "ts": 6197195810618.185, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6197195810642.089, "dur": 9.465, + "args": { + "External id": 23337,"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": 2338707, "tid": 2338707, + "ts": 6197195810646.101, "dur": 5.263, + "args": { + "External id": 23338,"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": 2338707, "tid": 2338707, + "ts": 6197195810753.509, "dur": 90.613, + "args": { + "External id": 23339,"Record function id": 0, "Ev Idx": 12655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6197195810846.124, "dur": 1381.684, + "args": { + "External id": 23340,"Record function id": 0, "Ev Idx": 12656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197195810897.232, "dur": 1314.388, + "args": { + "External id": 23341,"Sequence number": 479782, "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": 2338707, "tid": 2338707, "ts": 6197195810897.232, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6197195810980.699, "dur": 61.221, + "args": { + "External id": 23342,"kernel_hash": "cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/du/cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs.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": 2338707, "tid": 2338707, + "ts": 6197195811095.747, "dur": 119.764, + "args": { + "External id": 23343,"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": 2338707, "tid": 2338707, + "ts": 6197195811232.296, "dur": 42.848, + "args": { + "External id": 23344,"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": 2338707, "tid": 2338707, + "ts": 6197195811285.995, "dur": 33.272, + "args": { + "External id": 23345,"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": 2338707, "tid": 2338707, + "ts": 6197195811349.156, "dur": 32.227, + "args": { + "External id": 23346,"kernel_hash": "cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5", "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/jw/cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5.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": 2338707, "tid": 2338707, + "ts": 6197195811406.844, "dur": 20.992, + "args": { + "External id": 23347,"kernel_hash": "cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi", "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/xw/cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi.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": 2338707, "tid": 2338707, + "ts": 6197195811456.217, "dur": 169.294, + "args": { + "External id": 23348,"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": 2338707, "tid": 2338707, + "ts": 6197195811515.015, "dur": 15.102, + "args": { + "External id": 23349,"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": 2338707, "tid": 2338707, + "ts": 6197195811522.074, "dur": 6.918, + "args": { + "External id": 23350,"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": 2338707, "tid": 2338707, + "ts": 6197195811533.157, "dur": 4.983, + "args": { + "External id": 23351,"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": 2338707, "tid": 2338707, + "ts": 6197195811547.144, "dur": 1.946, + "args": { + "External id": 23352,"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": 2338707, "tid": 2338707, + "ts": 6197195811554.113, "dur": 7.380, + "args": { + "External id": 23353,"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": 2338707, "tid": 2338707, + "ts": 6197195811638.989, "dur": 57.941, + "args": { + "External id": 23354,"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": 2338707, "tid": 2338707, + "ts": 6197195811757.653, "dur": 35.665, + "args": { + "External id": 23355,"kernel_hash": "cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/dm/cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43.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": 2338707, "tid": 2338707, + "ts": 6197195811805.256, "dur": 55.534, + "args": { + "External id": 23356,"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": 2338707, "tid": 2338707, + "ts": 6197195811868.748, "dur": 40.746, + "args": { + "External id": 23357,"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": 2338707, "tid": 2338707, + "ts": 6197195811934.335, "dur": 36.131, + "args": { + "External id": 23358,"kernel_hash": "cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/b7/cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu.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": 2338707, "tid": 2338707, + "ts": 6197195811977.799, "dur": 42.290, + "args": { + "External id": 23359,"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": 2338707, "tid": 2338707, + "ts": 6197195812042.977, "dur": 77.820, + "args": { + "External id": 23360,"kernel_hash": "cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/gi/cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb.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": 2338707, "tid": 2338707, + "ts": 6197195812308.781, "dur": 100.884, + "args": { + "External id": 23361,"Record function id": 0, "Ev Idx": 12677 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6197195812499.700, "dur": 58.642, + "args": { + "External id": 23362,"Record function id": 0, "Ev Idx": 12678 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.8)", "pid": 2338707, "tid": 2338707, + "ts": 6197195812569.664, "dur": 33908.397, + "args": { + "External id": 23363,"Record function id": 0, "Ev Idx": 12679 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.8)", "pid": 2338707, "tid": 2338707, + "ts": 6197195812580.524, "dur": 1202.393, + "args": { + "External id": 23364,"Record function id": 0, "Ev Idx": 12680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6197195812684.740, "dur": 10.039, + "args": { + "External id": 23365,"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": 2338707, "tid": 2338707, + "ts": 6197195812730.390, "dur": 43.459, + "args": { + "External id": 23366,"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": 2338707, "tid": 2338707, + "ts": 6197195812737.276, "dur": 3.234, + "args": { + "External id": 23367,"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": 2338707, "tid": 2338707, + "ts": 6197195812746.053, "dur": 0.510, + "args": { + "External id": 23368,"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": 2338707, "tid": 2338707, + "ts": 6197195812747.842, "dur": 0.461, + "args": { + "External id": 23369,"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": 2338707, "tid": 2338707, + "ts": 6197195812750.033, "dur": 0.668, + "args": { + "External id": 23370,"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": 2338707, "tid": 2338707, + "ts": 6197195812754.571, "dur": 0.619, + "args": { + "External id": 23371,"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": 2338707, "tid": 2338707, + "ts": 6197195812756.427, "dur": 0.630, + "args": { + "External id": 23372,"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": 2338707, "tid": 2338707, + "ts": 6197195812757.984, "dur": 5.162, + "args": { + "External id": 23373,"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": 2338707, "tid": 2338707, + "ts": 6197195812764.437, "dur": 0.340, + "args": { + "External id": 23374,"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": 2338707, "tid": 2338707, + "ts": 6197195812766.092, "dur": 0.523, + "args": { + "External id": 23375,"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": 2338707, "tid": 2338707, + "ts": 6197195812788.789, "dur": 68.814, + "args": { + "External id": 23376,"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": 2338707, "tid": 2338707, + "ts": 6197195812898.360, "dur": 141.870, + "args": { + "External id": 23377,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2338707, + "ts": 6197195812912.522, "dur": 6.273, + "args": { + "External id": 23378,"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": 2338707, "tid": 2338707, + "ts": 6197195812925.526, "dur": 14.240, + "args": { + "External id": 23379,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2338707, + "ts": 6197195812933.560, "dur": 5.659, + "args": { + "External id": 23380,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2338707, + "ts": 6197195812937.199, "dur": 0.624, + "args": { + "External id": 23381,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197195812947.533, "dur": 29.143, + "args": { + "External id": 23382,"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": 2338707, "tid": 2338707, + "ts": 6197195812949.807, "dur": 2.910, + "args": { + "External id": 23383,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197195812954.369, "dur": 0.316, + "args": { + "External id": 23384,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2338707, + "ts": 6197195812955.562, "dur": 0.396, + "args": { + "External id": 23385,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2338707, + "ts": 6197195812959.890, "dur": 2.719, + "args": { + "External id": 23386,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2338707, + "ts": 6197195812963.543, "dur": 0.256, + "args": { + "External id": 23387,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2338707, + "ts": 6197195812964.796, "dur": 0.492, + "args": { + "External id": 23388,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2338707, + "ts": 6197195812966.425, "dur": 0.581, + "args": { + "External id": 23389,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2338707, + "ts": 6197195812968.315, "dur": 0.458, + "args": { + "External id": 23390,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2338707, + "ts": 6197195812969.951, "dur": 2.057, + "args": { + "External id": 23391,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2338707, + "ts": 6197195812989.468, "dur": 41.143, + "args": { + "External id": 23392,"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": 2338707, "tid": 2338707, + "ts": 6197195813154.974, "dur": 487.730, + "args": { + "External id": 23393,"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": 2338707, "tid": 2338707, + "ts": 6197195813191.762, "dur": 444.185, + "args": { + "External id": 23394,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2338707, + "ts": 6197195813205.201, "dur": 423.483, + "args": { + "External id": 23395,"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": 2338707, "tid": 2338707, + "ts": 6197195813670.046, "dur": 2.812, + "args": { + "External id": 23396,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.8)", "pid": 2338707, "tid": 2338707, + "ts": 6197195813811.293, "dur": 32427.666, + "args": { + "External id": 23397,"Record function id": 0, "Ev Idx": 12713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6197195813941.595, "dur": 8.574, + "args": { + "External id": 23398,"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": 2338707, "tid": 2338707, + "ts": 6197195813954.555, "dur": 1.243, + "args": { + "External id": 23399,"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": 2338707, "tid": 2338707, + "ts": 6197195813958.096, "dur": 4.214, + "args": { + "External id": 23400,"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": 2338707, "tid": 2338707, + "ts": 6197195813964.296, "dur": 0.981, + "args": { + "External id": 23401,"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": 2338707, "tid": 2338707, + "ts": 6197195813967.273, "dur": 1.077, + "args": { + "External id": 23402,"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": 2338707, "tid": 2338707, + "ts": 6197195813969.877, "dur": 1.343, + "args": { + "External id": 23403,"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": 2338707, "tid": 2338707, + "ts": 6197195813975.778, "dur": 1.055, + "args": { + "External id": 23404,"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": 2338707, "tid": 2338707, + "ts": 6197195813978.453, "dur": 2.377, + "args": { + "External id": 23405,"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": 2338707, "tid": 2338707, + "ts": 6197195813982.386, "dur": 5.568, + "args": { + "External id": 23406,"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": 2338707, "tid": 2338707, + "ts": 6197195813989.650, "dur": 0.716, + "args": { + "External id": 23407,"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": 2338707, "tid": 2338707, + "ts": 6197195814027.021, "dur": 32154.673, + "args": { + "External id": 23408,"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": 2338707, "tid": 2338707, + "ts": 6197195814046.469, "dur": 32125.023, + "args": { + "External id": 23409,"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": 2338707, "tid": 2338707, + "ts": 6197195814108.265, "dur": 21.233, + "args": { + "External id": 23410,"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": 2338707, "tid": 2338707, + "ts": 6197195814134.295, "dur": 31993.122, + "args": { + "External id": 23411,"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": 2338707, "tid": 2338707, + "ts": 6197195814137.264, "dur": 31989.360, + "args": { + "External id": 23412,"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": 2338707, "tid": 2338707, + "ts": 6197195814144.330, "dur": 7.332, + "args": { + "External id": 23413,"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": 2338707, "tid": 2338707, + "ts": 6197195814153.811, "dur": 31968.874, + "args": { + "External id": 23414,"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": 2338707, "tid": 2338707, + "ts": 6197195846408.318, "dur": 39.583, + "args": { + "External id": 23415,"Sequence number": 479783, "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": 2338707, "tid": 2338707, "ts": 6197195846408.318, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6197195846431.341, "dur": 10.296, + "args": { + "External id": 23416,"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": 2338707, "tid": 2338707, + "ts": 6197195846435.815, "dur": 5.512, + "args": { + "External id": 23417,"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": 2338707, "tid": 2338707, + "ts": 6197195846528.172, "dur": 89.707, + "args": { + "External id": 23418,"Record function id": 0, "Ev Idx": 12734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6197195846619.500, "dur": 1356.371, + "args": { + "External id": 23419,"Record function id": 0, "Ev Idx": 12735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197195846668.270, "dur": 1291.361, + "args": { + "External id": 23420,"Sequence number": 479784, "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": 2338707, "tid": 2338707, "ts": 6197195846668.270, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6197195846766.751, "dur": 60.277, + "args": { + "External id": 23421,"kernel_hash": "cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/du/cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs.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": 2338707, "tid": 2338707, + "ts": 6197195846843.551, "dur": 121.137, + "args": { + "External id": 23422,"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": 2338707, "tid": 2338707, + "ts": 6197195846980.642, "dur": 43.013, + "args": { + "External id": 23423,"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": 2338707, "tid": 2338707, + "ts": 6197195847033.782, "dur": 81.029, + "args": { + "External id": 23424,"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": 2338707, "tid": 2338707, + "ts": 6197195847155.924, "dur": 32.688, + "args": { + "External id": 23425,"kernel_hash": "cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5", "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/jw/cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5.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": 2338707, "tid": 2338707, + "ts": 6197195847212.733, "dur": 18.356, + "args": { + "External id": 23426,"kernel_hash": "cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi", "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/xw/cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi.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": 2338707, "tid": 2338707, + "ts": 6197195847258.300, "dur": 160.559, + "args": { + "External id": 23427,"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": 2338707, "tid": 2338707, + "ts": 6197195847323.520, "dur": 14.308, + "args": { + "External id": 23428,"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": 2338707, "tid": 2338707, + "ts": 6197195847330.209, "dur": 6.715, + "args": { + "External id": 23429,"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": 2338707, "tid": 2338707, + "ts": 6197195847340.717, "dur": 4.856, + "args": { + "External id": 23430,"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": 2338707, "tid": 2338707, + "ts": 6197195847347.099, "dur": 1.282, + "args": { + "External id": 23431,"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": 2338707, "tid": 2338707, + "ts": 6197195847351.279, "dur": 5.963, + "args": { + "External id": 23432,"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": 2338707, "tid": 2338707, + "ts": 6197195847431.922, "dur": 64.008, + "args": { + "External id": 23433,"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": 2338707, "tid": 2338707, + "ts": 6197195847534.711, "dur": 36.511, + "args": { + "External id": 23434,"kernel_hash": "cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/dm/cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43.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": 2338707, "tid": 2338707, + "ts": 6197195847583.123, "dur": 50.225, + "args": { + "External id": 23435,"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": 2338707, "tid": 2338707, + "ts": 6197195847644.076, "dur": 41.548, + "args": { + "External id": 23436,"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": 2338707, "tid": 2338707, + "ts": 6197195847732.425, "dur": 34.817, + "args": { + "External id": 23437,"kernel_hash": "cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/b7/cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu.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": 2338707, "tid": 2338707, + "ts": 6197195847777.505, "dur": 48.563, + "args": { + "External id": 23438,"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": 2338707, "tid": 2338707, + "ts": 6197195847847.536, "dur": 22.988, + "args": { + "External id": 23439,"kernel_hash": "cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/gi/cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb.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": 2338707, "tid": 2338707, + "ts": 6197195848093.568, "dur": 104.110, + "args": { + "External id": 23440,"Record function id": 0, "Ev Idx": 12756 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6197195848289.455, "dur": 57.007, + "args": { + "External id": 23441,"Record function id": 0, "Ev Idx": 12757 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.9)", "pid": 2338707, "tid": 2338707, + "ts": 6197195848357.911, "dur": 31024.172, + "args": { + "External id": 23442,"Record function id": 0, "Ev Idx": 12758 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.9)", "pid": 2338707, "tid": 2338707, + "ts": 6197195848367.093, "dur": 1144.191, + "args": { + "External id": 23443,"Record function id": 0, "Ev Idx": 12759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6197195848467.994, "dur": 11.936, + "args": { + "External id": 23444,"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": 2338707, "tid": 2338707, + "ts": 6197195848495.951, "dur": 40.404, + "args": { + "External id": 23445,"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": 2338707, "tid": 2338707, + "ts": 6197195848502.830, "dur": 2.947, + "args": { + "External id": 23446,"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": 2338707, "tid": 2338707, + "ts": 6197195848510.733, "dur": 0.525, + "args": { + "External id": 23447,"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": 2338707, "tid": 2338707, + "ts": 6197195848512.247, "dur": 0.550, + "args": { + "External id": 23448,"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": 2338707, "tid": 2338707, + "ts": 6197195848514.030, "dur": 0.416, + "args": { + "External id": 23449,"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": 2338707, "tid": 2338707, + "ts": 6197195848517.783, "dur": 0.791, + "args": { + "External id": 23450,"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": 2338707, "tid": 2338707, + "ts": 6197195848519.597, "dur": 0.508, + "args": { + "External id": 23451,"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": 2338707, "tid": 2338707, + "ts": 6197195848521.442, "dur": 4.970, + "args": { + "External id": 23452,"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": 2338707, "tid": 2338707, + "ts": 6197195848527.523, "dur": 0.494, + "args": { + "External id": 23453,"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": 2338707, "tid": 2338707, + "ts": 6197195848529.068, "dur": 0.501, + "args": { + "External id": 23454,"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": 2338707, "tid": 2338707, + "ts": 6197195848550.210, "dur": 65.663, + "args": { + "External id": 23455,"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": 2338707, "tid": 2338707, + "ts": 6197195848654.065, "dur": 177.365, + "args": { + "External id": 23456,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2338707, + "ts": 6197195848666.884, "dur": 4.701, + "args": { + "External id": 23457,"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": 2338707, "tid": 2338707, + "ts": 6197195848678.093, "dur": 15.274, + "args": { + "External id": 23458,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2338707, + "ts": 6197195848686.760, "dur": 6.068, + "args": { + "External id": 23459,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2338707, + "ts": 6197195848690.855, "dur": 0.581, + "args": { + "External id": 23460,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197195848718.403, "dur": 35.652, + "args": { + "External id": 23461,"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": 2338707, "tid": 2338707, + "ts": 6197195848720.837, "dur": 3.167, + "args": { + "External id": 23462,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197195848730.331, "dur": 0.373, + "args": { + "External id": 23463,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2338707, + "ts": 6197195848732.170, "dur": 0.393, + "args": { + "External id": 23464,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2338707, + "ts": 6197195848736.271, "dur": 2.667, + "args": { + "External id": 23465,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2338707, + "ts": 6197195848740.064, "dur": 0.341, + "args": { + "External id": 23466,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2338707, + "ts": 6197195848741.398, "dur": 0.892, + "args": { + "External id": 23467,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2338707, + "ts": 6197195848743.526, "dur": 0.601, + "args": { + "External id": 23468,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2338707, + "ts": 6197195848745.054, "dur": 0.527, + "args": { + "External id": 23469,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2338707, + "ts": 6197195848748.953, "dur": 0.546, + "args": { + "External id": 23470,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2338707, + "ts": 6197195848779.324, "dur": 42.055, + "args": { + "External id": 23471,"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": 2338707, "tid": 2338707, + "ts": 6197195848901.710, "dur": 485.612, + "args": { + "External id": 23472,"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": 2338707, "tid": 2338707, + "ts": 6197195848941.449, "dur": 438.901, + "args": { + "External id": 23473,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2338707, + "ts": 6197195848955.248, "dur": 417.496, + "args": { + "External id": 23474,"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": 2338707, "tid": 2338707, + "ts": 6197195849418.668, "dur": 3.134, + "args": { + "External id": 23475,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.9)", "pid": 2338707, "tid": 2338707, + "ts": 6197195849536.557, "dur": 29614.222, + "args": { + "External id": 23476,"Record function id": 0, "Ev Idx": 12792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6197195849660.043, "dur": 8.061, + "args": { + "External id": 23477,"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": 2338707, "tid": 2338707, + "ts": 6197195849672.224, "dur": 1.229, + "args": { + "External id": 23478,"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": 2338707, "tid": 2338707, + "ts": 6197195849675.314, "dur": 4.138, + "args": { + "External id": 23479,"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": 2338707, "tid": 2338707, + "ts": 6197195849681.947, "dur": 1.107, + "args": { + "External id": 23480,"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": 2338707, "tid": 2338707, + "ts": 6197195849684.711, "dur": 0.982, + "args": { + "External id": 23481,"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": 2338707, "tid": 2338707, + "ts": 6197195849687.357, "dur": 1.276, + "args": { + "External id": 23482,"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": 2338707, "tid": 2338707, + "ts": 6197195849693.306, "dur": 1.013, + "args": { + "External id": 23483,"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": 2338707, "tid": 2338707, + "ts": 6197195849696.193, "dur": 2.610, + "args": { + "External id": 23484,"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": 2338707, "tid": 2338707, + "ts": 6197195849726.099, "dur": 1.708, + "args": { + "External id": 23485,"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": 2338707, "tid": 2338707, + "ts": 6197195849729.920, "dur": 0.857, + "args": { + "External id": 23486,"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": 2338707, "tid": 2338707, + "ts": 6197195849755.817, "dur": 29343.493, + "args": { + "External id": 23487,"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": 2338707, "tid": 2338707, + "ts": 6197195849775.312, "dur": 29314.052, + "args": { + "External id": 23488,"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": 2338707, "tid": 2338707, + "ts": 6197195849798.136, "dur": 20.161, + "args": { + "External id": 23489,"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": 2338707, "tid": 2338707, + "ts": 6197195849822.997, "dur": 29193.639, + "args": { + "External id": 23490,"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": 2338707, "tid": 2338707, + "ts": 6197195849826.517, "dur": 29189.541, + "args": { + "External id": 23491,"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": 2338707, "tid": 2338707, + "ts": 6197195849833.902, "dur": 6.444, + "args": { + "External id": 23492,"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": 2338707, "tid": 2338707, + "ts": 6197195849842.323, "dur": 29169.848, + "args": { + "External id": 23493,"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": 2338707, "tid": 2338707, + "ts": 6197195879315.791, "dur": 36.420, + "args": { + "External id": 23494,"Sequence number": 479785, "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": 2338707, "tid": 2338707, "ts": 6197195879315.791, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6197195879336.076, "dur": 10.107, + "args": { + "External id": 23495,"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": 2338707, "tid": 2338707, + "ts": 6197195879340.686, "dur": 5.201, + "args": { + "External id": 23496,"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": 2338707, "tid": 2338707, + "ts": 6197195879431.348, "dur": 88.107, + "args": { + "External id": 23497,"Record function id": 0, "Ev Idx": 12813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6197195879520.972, "dur": 1366.290, + "args": { + "External id": 23498,"Record function id": 0, "Ev Idx": 12814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197195879568.739, "dur": 1302.111, + "args": { + "External id": 23499,"Sequence number": 479786, "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": 2338707, "tid": 2338707, "ts": 6197195879568.739, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6197195879644.781, "dur": 79.041, + "args": { + "External id": 23500,"kernel_hash": "cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/du/cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs.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": 2338707, "tid": 2338707, + "ts": 6197195879743.187, "dur": 122.383, + "args": { + "External id": 23501,"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": 2338707, "tid": 2338707, + "ts": 6197195879880.412, "dur": 48.056, + "args": { + "External id": 23502,"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": 2338707, "tid": 2338707, + "ts": 6197195879939.139, "dur": 34.635, + "args": { + "External id": 23503,"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": 2338707, "tid": 2338707, + "ts": 6197195880006.086, "dur": 34.537, + "args": { + "External id": 23504,"kernel_hash": "cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5", "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/jw/cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5.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": 2338707, "tid": 2338707, + "ts": 6197195880104.248, "dur": 26.420, + "args": { + "External id": 23505,"kernel_hash": "cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi", "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/xw/cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi.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": 2338707, "tid": 2338707, + "ts": 6197195880159.554, "dur": 161.268, + "args": { + "External id": 23506,"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": 2338707, "tid": 2338707, + "ts": 6197195880222.483, "dur": 14.552, + "args": { + "External id": 23507,"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": 2338707, "tid": 2338707, + "ts": 6197195880228.647, "dur": 7.424, + "args": { + "External id": 23508,"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": 2338707, "tid": 2338707, + "ts": 6197195880240.196, "dur": 4.552, + "args": { + "External id": 23509,"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": 2338707, "tid": 2338707, + "ts": 6197195880246.521, "dur": 1.552, + "args": { + "External id": 23510,"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": 2338707, "tid": 2338707, + "ts": 6197195880251.053, "dur": 6.871, + "args": { + "External id": 23511,"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": 2338707, "tid": 2338707, + "ts": 6197195880334.757, "dur": 67.793, + "args": { + "External id": 23512,"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": 2338707, "tid": 2338707, + "ts": 6197195880440.707, "dur": 36.606, + "args": { + "External id": 23513,"kernel_hash": "cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/dm/cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43.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": 2338707, "tid": 2338707, + "ts": 6197195880495.790, "dur": 53.485, + "args": { + "External id": 23514,"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": 2338707, "tid": 2338707, + "ts": 6197195880559.633, "dur": 41.550, + "args": { + "External id": 23515,"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": 2338707, "tid": 2338707, + "ts": 6197195880630.029, "dur": 35.284, + "args": { + "External id": 23516,"kernel_hash": "cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/b7/cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu.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": 2338707, "tid": 2338707, + "ts": 6197195880675.265, "dur": 62.206, + "args": { + "External id": 23517,"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": 2338707, "tid": 2338707, + "ts": 6197195880762.758, "dur": 24.392, + "args": { + "External id": 23518,"kernel_hash": "cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/gi/cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb.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": 2338707, "tid": 2338707, + "ts": 6197195880964.415, "dur": 139.723, + "args": { + "External id": 23519,"Record function id": 0, "Ev Idx": 12835 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6197195881199.903, "dur": 61.837, + "args": { + "External id": 23520,"Record function id": 0, "Ev Idx": 12836 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.10)", "pid": 2338707, "tid": 2338707, + "ts": 6197195881272.740, "dur": 34072.556, + "args": { + "External id": 23521,"Record function id": 0, "Ev Idx": 12837 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.10)", "pid": 2338707, "tid": 2338707, + "ts": 6197195881283.592, "dur": 1199.024, + "args": { + "External id": 23522,"Record function id": 0, "Ev Idx": 12838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6197195881386.076, "dur": 11.102, + "args": { + "External id": 23523,"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": 2338707, "tid": 2338707, + "ts": 6197195881414.047, "dur": 45.501, + "args": { + "External id": 23524,"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": 2338707, "tid": 2338707, + "ts": 6197195881421.232, "dur": 7.018, + "args": { + "External id": 23525,"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": 2338707, "tid": 2338707, + "ts": 6197195881433.095, "dur": 0.726, + "args": { + "External id": 23526,"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": 2338707, "tid": 2338707, + "ts": 6197195881434.812, "dur": 0.598, + "args": { + "External id": 23527,"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": 2338707, "tid": 2338707, + "ts": 6197195881436.701, "dur": 0.663, + "args": { + "External id": 23528,"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": 2338707, "tid": 2338707, + "ts": 6197195881441.013, "dur": 0.426, + "args": { + "External id": 23529,"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": 2338707, "tid": 2338707, + "ts": 6197195881442.688, "dur": 0.673, + "args": { + "External id": 23530,"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": 2338707, "tid": 2338707, + "ts": 6197195881444.337, "dur": 5.296, + "args": { + "External id": 23531,"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": 2338707, "tid": 2338707, + "ts": 6197195881451.072, "dur": 0.398, + "args": { + "External id": 23532,"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": 2338707, "tid": 2338707, + "ts": 6197195881452.495, "dur": 0.328, + "args": { + "External id": 23533,"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": 2338707, "tid": 2338707, + "ts": 6197195881473.768, "dur": 67.553, + "args": { + "External id": 23534,"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": 2338707, "tid": 2338707, + "ts": 6197195881583.389, "dur": 166.131, + "args": { + "External id": 23535,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2338707, + "ts": 6197195881596.122, "dur": 4.949, + "args": { + "External id": 23536,"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": 2338707, "tid": 2338707, + "ts": 6197195881607.883, "dur": 18.211, + "args": { + "External id": 23537,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2338707, + "ts": 6197195881616.049, "dur": 9.525, + "args": { + "External id": 23538,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2338707, + "ts": 6197195881619.702, "dur": 4.310, + "args": { + "External id": 23539,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197195881634.075, "dur": 32.323, + "args": { + "External id": 23540,"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": 2338707, "tid": 2338707, + "ts": 6197195881636.203, "dur": 3.051, + "args": { + "External id": 23541,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197195881640.750, "dur": 0.396, + "args": { + "External id": 23542,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2338707, + "ts": 6197195881642.201, "dur": 0.741, + "args": { + "External id": 23543,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2338707, + "ts": 6197195881646.440, "dur": 2.630, + "args": { + "External id": 23544,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2338707, + "ts": 6197195881650.354, "dur": 0.437, + "args": { + "External id": 23545,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2338707, + "ts": 6197195881652.173, "dur": 0.562, + "args": { + "External id": 23546,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2338707, + "ts": 6197195881656.218, "dur": 0.432, + "args": { + "External id": 23547,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2338707, + "ts": 6197195881657.872, "dur": 0.343, + "args": { + "External id": 23548,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2338707, + "ts": 6197195881659.314, "dur": 2.639, + "args": { + "External id": 23549,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2338707, + "ts": 6197195881679.888, "dur": 58.024, + "args": { + "External id": 23550,"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": 2338707, "tid": 2338707, + "ts": 6197195881816.593, "dur": 539.240, + "args": { + "External id": 23551,"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": 2338707, "tid": 2338707, + "ts": 6197195881853.537, "dur": 495.319, + "args": { + "External id": 23552,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2338707, + "ts": 6197195881894.817, "dur": 443.688, + "args": { + "External id": 23553,"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": 2338707, "tid": 2338707, + "ts": 6197195882387.582, "dur": 3.434, + "args": { + "External id": 23554,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.10)", "pid": 2338707, "tid": 2338707, + "ts": 6197195882509.925, "dur": 32593.123, + "args": { + "External id": 23555,"Record function id": 0, "Ev Idx": 12871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6197195882639.034, "dur": 8.023, + "args": { + "External id": 23556,"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": 2338707, "tid": 2338707, + "ts": 6197195882651.351, "dur": 0.918, + "args": { + "External id": 23557,"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": 2338707, "tid": 2338707, + "ts": 6197195882654.228, "dur": 3.829, + "args": { + "External id": 23558,"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": 2338707, "tid": 2338707, + "ts": 6197195882660.127, "dur": 1.140, + "args": { + "External id": 23559,"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": 2338707, "tid": 2338707, + "ts": 6197195882662.794, "dur": 1.226, + "args": { + "External id": 23560,"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": 2338707, "tid": 2338707, + "ts": 6197195882665.721, "dur": 1.020, + "args": { + "External id": 23561,"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": 2338707, "tid": 2338707, + "ts": 6197195882670.665, "dur": 1.060, + "args": { + "External id": 23562,"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": 2338707, "tid": 2338707, + "ts": 6197195882673.407, "dur": 2.284, + "args": { + "External id": 23563,"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": 2338707, "tid": 2338707, + "ts": 6197195882677.221, "dur": 0.687, + "args": { + "External id": 23564,"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": 2338707, "tid": 2338707, + "ts": 6197195882679.852, "dur": 0.650, + "args": { + "External id": 23565,"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": 2338707, "tid": 2338707, + "ts": 6197195882724.212, "dur": 32294.113, + "args": { + "External id": 23566,"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": 2338707, "tid": 2338707, + "ts": 6197195882744.682, "dur": 32264.082, + "args": { + "External id": 23567,"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": 2338707, "tid": 2338707, + "ts": 6197195882765.470, "dur": 20.736, + "args": { + "External id": 23568,"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": 2338707, "tid": 2338707, + "ts": 6197195882790.615, "dur": 32174.650, + "args": { + "External id": 23569,"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": 2338707, "tid": 2338707, + "ts": 6197195882793.980, "dur": 32170.703, + "args": { + "External id": 23570,"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": 2338707, "tid": 2338707, + "ts": 6197195882801.189, "dur": 6.495, + "args": { + "External id": 23571,"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": 2338707, "tid": 2338707, + "ts": 6197195882809.908, "dur": 32150.864, + "args": { + "External id": 23572,"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": 2338707, "tid": 2338707, + "ts": 6197195915273.496, "dur": 41.362, + "args": { + "External id": 23573,"Sequence number": 479787, "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": 2338707, "tid": 2338707, "ts": 6197195915273.496, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6197195915298.360, "dur": 10.542, + "args": { + "External id": 23574,"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": 2338707, "tid": 2338707, + "ts": 6197195915302.710, "dur": 5.822, + "args": { + "External id": 23575,"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": 2338707, "tid": 2338707, + "ts": 6197195915399.232, "dur": 89.154, + "args": { + "External id": 23576,"Record function id": 0, "Ev Idx": 12892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6197195915490.268, "dur": 1373.025, + "args": { + "External id": 23577,"Record function id": 0, "Ev Idx": 12893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197195915538.240, "dur": 1308.713, + "args": { + "External id": 23578,"Sequence number": 479788, "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": 2338707, "tid": 2338707, "ts": 6197195915538.240, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6197195915622.050, "dur": 62.161, + "args": { + "External id": 23579,"kernel_hash": "cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/du/cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs.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": 2338707, "tid": 2338707, + "ts": 6197195915716.980, "dur": 119.968, + "args": { + "External id": 23580,"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": 2338707, "tid": 2338707, + "ts": 6197195915854.693, "dur": 46.342, + "args": { + "External id": 23581,"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": 2338707, "tid": 2338707, + "ts": 6197195915911.548, "dur": 35.458, + "args": { + "External id": 23582,"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": 2338707, "tid": 2338707, + "ts": 6197195915979.235, "dur": 37.556, + "args": { + "External id": 23583,"kernel_hash": "cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5", "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/jw/cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5.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": 2338707, "tid": 2338707, + "ts": 6197195916039.707, "dur": 65.361, + "args": { + "External id": 23584,"kernel_hash": "cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi", "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/xw/cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi.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": 2338707, "tid": 2338707, + "ts": 6197195916137.828, "dur": 159.653, + "args": { + "External id": 23585,"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": 2338707, "tid": 2338707, + "ts": 6197195916200.496, "dur": 15.056, + "args": { + "External id": 23586,"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": 2338707, "tid": 2338707, + "ts": 6197195916206.833, "dur": 7.620, + "args": { + "External id": 23587,"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": 2338707, "tid": 2338707, + "ts": 6197195916218.677, "dur": 5.029, + "args": { + "External id": 23588,"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": 2338707, "tid": 2338707, + "ts": 6197195916225.171, "dur": 1.151, + "args": { + "External id": 23589,"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": 2338707, "tid": 2338707, + "ts": 6197195916229.601, "dur": 5.459, + "args": { + "External id": 23590,"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": 2338707, "tid": 2338707, + "ts": 6197195916310.951, "dur": 66.988, + "args": { + "External id": 23591,"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": 2338707, "tid": 2338707, + "ts": 6197195916417.357, "dur": 40.682, + "args": { + "External id": 23592,"kernel_hash": "cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/dm/cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43.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": 2338707, "tid": 2338707, + "ts": 6197195916469.390, "dur": 51.962, + "args": { + "External id": 23593,"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": 2338707, "tid": 2338707, + "ts": 6197195916532.241, "dur": 43.448, + "args": { + "External id": 23594,"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": 2338707, "tid": 2338707, + "ts": 6197195916603.204, "dur": 34.202, + "args": { + "External id": 23595,"kernel_hash": "cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/b7/cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu.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": 2338707, "tid": 2338707, + "ts": 6197195916646.896, "dur": 43.230, + "args": { + "External id": 23596,"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": 2338707, "tid": 2338707, + "ts": 6197195916730.612, "dur": 28.039, + "args": { + "External id": 23597,"kernel_hash": "cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/gi/cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb.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": 2338707, "tid": 2338707, + "ts": 6197195916941.771, "dur": 98.378, + "args": { + "External id": 23598,"Record function id": 0, "Ev Idx": 12914 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6197195917181.668, "dur": 61.012, + "args": { + "External id": 23599,"Record function id": 0, "Ev Idx": 12915 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.11)", "pid": 2338707, "tid": 2338707, + "ts": 6197195917254.263, "dur": 31608.133, + "args": { + "External id": 23600,"Record function id": 0, "Ev Idx": 12916 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.11)", "pid": 2338707, "tid": 2338707, + "ts": 6197195917264.269, "dur": 1048.809, + "args": { + "External id": 23601,"Record function id": 0, "Ev Idx": 12917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6197195917367.909, "dur": 12.458, + "args": { + "External id": 23602,"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": 2338707, "tid": 2338707, + "ts": 6197195917396.331, "dur": 40.656, + "args": { + "External id": 23603,"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": 2338707, "tid": 2338707, + "ts": 6197195917403.029, "dur": 2.681, + "args": { + "External id": 23604,"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": 2338707, "tid": 2338707, + "ts": 6197195917410.402, "dur": 0.400, + "args": { + "External id": 23605,"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": 2338707, "tid": 2338707, + "ts": 6197195917412.229, "dur": 0.565, + "args": { + "External id": 23606,"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": 2338707, "tid": 2338707, + "ts": 6197195917413.945, "dur": 0.658, + "args": { + "External id": 23607,"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": 2338707, "tid": 2338707, + "ts": 6197195917418.094, "dur": 0.579, + "args": { + "External id": 23608,"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": 2338707, "tid": 2338707, + "ts": 6197195917419.892, "dur": 0.685, + "args": { + "External id": 23609,"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": 2338707, "tid": 2338707, + "ts": 6197195917421.743, "dur": 4.811, + "args": { + "External id": 23610,"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": 2338707, "tid": 2338707, + "ts": 6197195917427.542, "dur": 0.359, + "args": { + "External id": 23611,"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": 2338707, "tid": 2338707, + "ts": 6197195917429.160, "dur": 0.356, + "args": { + "External id": 23612,"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": 2338707, "tid": 2338707, + "ts": 6197195917454.959, "dur": 63.957, + "args": { + "External id": 23613,"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": 2338707, "tid": 2338707, + "ts": 6197195917557.893, "dur": 159.726, + "args": { + "External id": 23614,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2338707, + "ts": 6197195917570.593, "dur": 6.476, + "args": { + "External id": 23615,"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": 2338707, "tid": 2338707, + "ts": 6197195917583.133, "dur": 15.472, + "args": { + "External id": 23616,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2338707, + "ts": 6197195917591.790, "dur": 6.282, + "args": { + "External id": 23617,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2338707, + "ts": 6197195917595.602, "dur": 0.718, + "args": { + "External id": 23618,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197195917606.679, "dur": 29.981, + "args": { + "External id": 23619,"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": 2338707, "tid": 2338707, + "ts": 6197195917609.050, "dur": 0.568, + "args": { + "External id": 23620,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197195917611.203, "dur": 2.908, + "args": { + "External id": 23621,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2338707, + "ts": 6197195917615.199, "dur": 0.553, + "args": { + "External id": 23622,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2338707, + "ts": 6197195917616.990, "dur": 3.012, + "args": { + "External id": 23623,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2338707, + "ts": 6197195917623.200, "dur": 0.390, + "args": { + "External id": 23624,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2338707, + "ts": 6197195917624.709, "dur": 0.501, + "args": { + "External id": 23625,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2338707, + "ts": 6197195917626.392, "dur": 0.356, + "args": { + "External id": 23626,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2338707, + "ts": 6197195917630.604, "dur": 0.378, + "args": { + "External id": 23627,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2338707, + "ts": 6197195917631.903, "dur": 0.410, + "args": { + "External id": 23628,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2338707, + "ts": 6197195917651.036, "dur": 40.123, + "args": { + "External id": 23629,"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": 2338707, "tid": 2338707, + "ts": 6197195917789.527, "dur": 400.603, + "args": { + "External id": 23630,"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": 2338707, "tid": 2338707, + "ts": 6197195917827.102, "dur": 356.351, + "args": { + "External id": 23631,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2338707, + "ts": 6197195917839.550, "dur": 336.396, + "args": { + "External id": 23632,"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": 2338707, "tid": 2338707, + "ts": 6197195918220.293, "dur": 2.941, + "args": { + "External id": 23633,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.11)", "pid": 2338707, "tid": 2338707, + "ts": 6197195918337.824, "dur": 30272.741, + "args": { + "External id": 23634,"Record function id": 0, "Ev Idx": 12950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6197195918461.483, "dur": 7.624, + "args": { + "External id": 23635,"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": 2338707, "tid": 2338707, + "ts": 6197195918473.400, "dur": 1.222, + "args": { + "External id": 23636,"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": 2338707, "tid": 2338707, + "ts": 6197195918476.701, "dur": 4.175, + "args": { + "External id": 23637,"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": 2338707, "tid": 2338707, + "ts": 6197195918483.056, "dur": 1.025, + "args": { + "External id": 23638,"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": 2338707, "tid": 2338707, + "ts": 6197195918486.066, "dur": 1.079, + "args": { + "External id": 23639,"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": 2338707, "tid": 2338707, + "ts": 6197195918488.672, "dur": 1.220, + "args": { + "External id": 23640,"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": 2338707, "tid": 2338707, + "ts": 6197195918494.032, "dur": 0.842, + "args": { + "External id": 23641,"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": 2338707, "tid": 2338707, + "ts": 6197195918496.688, "dur": 2.772, + "args": { + "External id": 23642,"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": 2338707, "tid": 2338707, + "ts": 6197195918501.208, "dur": 0.767, + "args": { + "External id": 23643,"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": 2338707, "tid": 2338707, + "ts": 6197195918503.647, "dur": 1.139, + "args": { + "External id": 23644,"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": 2338707, "tid": 2338707, + "ts": 6197195918528.655, "dur": 30032.473, + "args": { + "External id": 23645,"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": 2338707, "tid": 2338707, + "ts": 6197195918546.288, "dur": 30005.256, + "args": { + "External id": 23646,"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": 2338707, "tid": 2338707, + "ts": 6197195918566.347, "dur": 24.908, + "args": { + "External id": 23647,"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": 2338707, "tid": 2338707, + "ts": 6197195918595.584, "dur": 29913.896, + "args": { + "External id": 23648,"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": 2338707, "tid": 2338707, + "ts": 6197195918598.950, "dur": 29909.922, + "args": { + "External id": 23649,"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": 2338707, "tid": 2338707, + "ts": 6197195918606.069, "dur": 6.590, + "args": { + "External id": 23650,"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": 2338707, "tid": 2338707, + "ts": 6197195918614.828, "dur": 29890.164, + "args": { + "External id": 23651,"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": 2338707, "tid": 2338707, + "ts": 6197195948789.725, "dur": 42.303, + "args": { + "External id": 23652,"Sequence number": 479789, "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": 2338707, "tid": 2338707, "ts": 6197195948789.725, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6197195948814.976, "dur": 10.982, + "args": { + "External id": 23653,"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": 2338707, "tid": 2338707, + "ts": 6197195948819.490, "dur": 6.027, + "args": { + "External id": 23654,"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": 2338707, "tid": 2338707, + "ts": 6197195948912.597, "dur": 90.411, + "args": { + "External id": 23655,"Record function id": 0, "Ev Idx": 12971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6197195949004.681, "dur": 1386.913, + "args": { + "External id": 23656,"Record function id": 0, "Ev Idx": 12972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197195949052.832, "dur": 1321.741, + "args": { + "External id": 23657,"Sequence number": 479790, "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": 2338707, "tid": 2338707, "ts": 6197195949052.832, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6197195949171.195, "dur": 61.800, + "args": { + "External id": 23658,"kernel_hash": "cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/du/cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs.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": 2338707, "tid": 2338707, + "ts": 6197195949249.616, "dur": 121.701, + "args": { + "External id": 23659,"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": 2338707, "tid": 2338707, + "ts": 6197195949387.133, "dur": 43.969, + "args": { + "External id": 23660,"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": 2338707, "tid": 2338707, + "ts": 6197195949440.888, "dur": 35.240, + "args": { + "External id": 23661,"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": 2338707, "tid": 2338707, + "ts": 6197195949506.289, "dur": 31.942, + "args": { + "External id": 23662,"kernel_hash": "cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5", "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/jw/cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5.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": 2338707, "tid": 2338707, + "ts": 6197195949561.032, "dur": 22.903, + "args": { + "External id": 23663,"kernel_hash": "cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi", "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/xw/cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi.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": 2338707, "tid": 2338707, + "ts": 6197195949610.347, "dur": 180.043, + "args": { + "External id": 23664,"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": 2338707, "tid": 2338707, + "ts": 6197195949672.856, "dur": 13.447, + "args": { + "External id": 23665,"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": 2338707, "tid": 2338707, + "ts": 6197195949678.965, "dur": 6.405, + "args": { + "External id": 23666,"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": 2338707, "tid": 2338707, + "ts": 6197195949689.469, "dur": 4.634, + "args": { + "External id": 23667,"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": 2338707, "tid": 2338707, + "ts": 6197195949695.617, "dur": 1.535, + "args": { + "External id": 23668,"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": 2338707, "tid": 2338707, + "ts": 6197195949718.489, "dur": 7.386, + "args": { + "External id": 23669,"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": 2338707, "tid": 2338707, + "ts": 6197195949804.590, "dur": 68.246, + "args": { + "External id": 23670,"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": 2338707, "tid": 2338707, + "ts": 6197195949911.684, "dur": 41.349, + "args": { + "External id": 23671,"kernel_hash": "cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/dm/cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43.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": 2338707, "tid": 2338707, + "ts": 6197195949966.575, "dur": 56.979, + "args": { + "External id": 23672,"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": 2338707, "tid": 2338707, + "ts": 6197195950033.263, "dur": 87.213, + "args": { + "External id": 23673,"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": 2338707, "tid": 2338707, + "ts": 6197195950151.530, "dur": 35.858, + "args": { + "External id": 23674,"kernel_hash": "cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/b7/cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu.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": 2338707, "tid": 2338707, + "ts": 6197195950197.654, "dur": 46.084, + "args": { + "External id": 23675,"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": 2338707, "tid": 2338707, + "ts": 6197195950265.947, "dur": 21.779, + "args": { + "External id": 23676,"kernel_hash": "cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/gi/cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb.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": 2338707, "tid": 2338707, + "ts": 6197195950472.018, "dur": 98.941, + "args": { + "External id": 23677,"Record function id": 0, "Ev Idx": 12993 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6197195950661.837, "dur": 79.945, + "args": { + "External id": 23678,"Record function id": 0, "Ev Idx": 12994 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.12)", "pid": 2338707, "tid": 2338707, + "ts": 6197195950755.382, "dur": 31777.375, + "args": { + "External id": 23679,"Record function id": 0, "Ev Idx": 12995 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.12)", "pid": 2338707, "tid": 2338707, + "ts": 6197195950767.389, "dur": 1134.643, + "args": { + "External id": 23680,"Record function id": 0, "Ev Idx": 12996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6197195950872.916, "dur": 11.522, + "args": { + "External id": 23681,"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": 2338707, "tid": 2338707, + "ts": 6197195950904.087, "dur": 40.743, + "args": { + "External id": 23682,"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": 2338707, "tid": 2338707, + "ts": 6197195950911.129, "dur": 2.717, + "args": { + "External id": 23683,"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": 2338707, "tid": 2338707, + "ts": 6197195950918.134, "dur": 0.657, + "args": { + "External id": 23684,"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": 2338707, "tid": 2338707, + "ts": 6197195950920.080, "dur": 0.405, + "args": { + "External id": 23685,"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": 2338707, "tid": 2338707, + "ts": 6197195950921.755, "dur": 2.399, + "args": { + "External id": 23686,"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": 2338707, "tid": 2338707, + "ts": 6197195950925.315, "dur": 0.643, + "args": { + "External id": 23687,"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": 2338707, "tid": 2338707, + "ts": 6197195950927.197, "dur": 0.366, + "args": { + "External id": 23688,"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": 2338707, "tid": 2338707, + "ts": 6197195950931.630, "dur": 2.769, + "args": { + "External id": 23689,"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": 2338707, "tid": 2338707, + "ts": 6197195950935.399, "dur": 0.379, + "args": { + "External id": 23690,"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": 2338707, "tid": 2338707, + "ts": 6197195950937.008, "dur": 0.395, + "args": { + "External id": 23691,"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": 2338707, "tid": 2338707, + "ts": 6197195950959.231, "dur": 67.616, + "args": { + "External id": 23692,"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": 2338707, "tid": 2338707, + "ts": 6197195951111.574, "dur": 152.258, + "args": { + "External id": 23693,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2338707, + "ts": 6197195951126.364, "dur": 7.241, + "args": { + "External id": 23694,"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": 2338707, "tid": 2338707, + "ts": 6197195951140.821, "dur": 16.816, + "args": { + "External id": 23695,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2338707, + "ts": 6197195951149.000, "dur": 8.059, + "args": { + "External id": 23696,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2338707, + "ts": 6197195951153.011, "dur": 1.813, + "args": { + "External id": 23697,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197195951166.073, "dur": 29.449, + "args": { + "External id": 23698,"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": 2338707, "tid": 2338707, + "ts": 6197195951168.292, "dur": 0.430, + "args": { + "External id": 23699,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197195951169.818, "dur": 0.857, + "args": { + "External id": 23700,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2338707, + "ts": 6197195951172.319, "dur": 0.430, + "args": { + "External id": 23701,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2338707, + "ts": 6197195951175.864, "dur": 3.131, + "args": { + "External id": 23702,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2338707, + "ts": 6197195951180.044, "dur": 0.674, + "args": { + "External id": 23703,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2338707, + "ts": 6197195951181.730, "dur": 2.262, + "args": { + "External id": 23704,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2338707, + "ts": 6197195951185.229, "dur": 0.562, + "args": { + "External id": 23705,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2338707, + "ts": 6197195951186.651, "dur": 0.487, + "args": { + "External id": 23706,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2338707, + "ts": 6197195951190.201, "dur": 0.306, + "args": { + "External id": 23707,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2338707, + "ts": 6197195951209.744, "dur": 44.147, + "args": { + "External id": 23708,"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": 2338707, "tid": 2338707, + "ts": 6197195951334.787, "dur": 447.793, + "args": { + "External id": 23709,"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": 2338707, "tid": 2338707, + "ts": 6197195951374.515, "dur": 401.500, + "args": { + "External id": 23710,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2338707, + "ts": 6197195951387.057, "dur": 381.485, + "args": { + "External id": 23711,"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": 2338707, "tid": 2338707, + "ts": 6197195951811.780, "dur": 3.068, + "args": { + "External id": 23712,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.12)", "pid": 2338707, "tid": 2338707, + "ts": 6197195951926.960, "dur": 30379.305, + "args": { + "External id": 23713,"Record function id": 0, "Ev Idx": 13029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6197195952046.203, "dur": 50.242, + "args": { + "External id": 23714,"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": 2338707, "tid": 2338707, + "ts": 6197195952104.409, "dur": 1.643, + "args": { + "External id": 23715,"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": 2338707, "tid": 2338707, + "ts": 6197195952108.237, "dur": 3.619, + "args": { + "External id": 23716,"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": 2338707, "tid": 2338707, + "ts": 6197195952114.019, "dur": 1.011, + "args": { + "External id": 23717,"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": 2338707, "tid": 2338707, + "ts": 6197195952116.587, "dur": 1.055, + "args": { + "External id": 23718,"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": 2338707, "tid": 2338707, + "ts": 6197195952119.236, "dur": 1.005, + "args": { + "External id": 23719,"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": 2338707, "tid": 2338707, + "ts": 6197195952124.385, "dur": 0.911, + "args": { + "External id": 23720,"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": 2338707, "tid": 2338707, + "ts": 6197195952127.219, "dur": 1.971, + "args": { + "External id": 23721,"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": 2338707, "tid": 2338707, + "ts": 6197195952130.941, "dur": 1.081, + "args": { + "External id": 23722,"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": 2338707, "tid": 2338707, + "ts": 6197195952133.727, "dur": 0.567, + "args": { + "External id": 23723,"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": 2338707, "tid": 2338707, + "ts": 6197195952159.740, "dur": 30096.983, + "args": { + "External id": 23724,"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": 2338707, "tid": 2338707, + "ts": 6197195952178.246, "dur": 30068.845, + "args": { + "External id": 23725,"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": 2338707, "tid": 2338707, + "ts": 6197195952200.490, "dur": 21.211, + "args": { + "External id": 23726,"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": 2338707, "tid": 2338707, + "ts": 6197195952226.461, "dur": 29979.018, + "args": { + "External id": 23727,"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": 2338707, "tid": 2338707, + "ts": 6197195952230.196, "dur": 29974.579, + "args": { + "External id": 23728,"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": 2338707, "tid": 2338707, + "ts": 6197195952237.297, "dur": 6.955, + "args": { + "External id": 23729,"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": 2338707, "tid": 2338707, + "ts": 6197195952246.343, "dur": 29954.715, + "args": { + "External id": 23730,"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": 2338707, "tid": 2338707, + "ts": 6197195982469.314, "dur": 34.803, + "args": { + "External id": 23731,"Sequence number": 479791, "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": 2338707, "tid": 2338707, "ts": 6197195982469.314, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6197195982488.933, "dur": 9.407, + "args": { + "External id": 23732,"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": 2338707, "tid": 2338707, + "ts": 6197195982492.912, "dur": 5.138, + "args": { + "External id": 23733,"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": 2338707, "tid": 2338707, + "ts": 6197195982583.138, "dur": 87.838, + "args": { + "External id": 23734,"Record function id": 0, "Ev Idx": 13050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6197195982672.745, "dur": 1323.969, + "args": { + "External id": 23735,"Record function id": 0, "Ev Idx": 13051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197195982739.481, "dur": 1241.087, + "args": { + "External id": 23736,"Sequence number": 479792, "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": 2338707, "tid": 2338707, "ts": 6197195982739.481, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6197195982818.880, "dur": 61.887, + "args": { + "External id": 23737,"kernel_hash": "cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/du/cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs.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": 2338707, "tid": 2338707, + "ts": 6197195982897.155, "dur": 121.844, + "args": { + "External id": 23738,"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": 2338707, "tid": 2338707, + "ts": 6197195983034.066, "dur": 88.478, + "args": { + "External id": 23739,"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": 2338707, "tid": 2338707, + "ts": 6197195983137.718, "dur": 38.983, + "args": { + "External id": 23740,"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": 2338707, "tid": 2338707, + "ts": 6197195983210.039, "dur": 33.059, + "args": { + "External id": 23741,"kernel_hash": "cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5", "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/jw/cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5.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": 2338707, "tid": 2338707, + "ts": 6197195983265.709, "dur": 21.183, + "args": { + "External id": 23742,"kernel_hash": "cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi", "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/xw/cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi.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": 2338707, "tid": 2338707, + "ts": 6197195983314.078, "dur": 157.616, + "args": { + "External id": 23743,"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": 2338707, "tid": 2338707, + "ts": 6197195983376.262, "dur": 14.103, + "args": { + "External id": 23744,"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": 2338707, "tid": 2338707, + "ts": 6197195983382.560, "dur": 6.871, + "args": { + "External id": 23745,"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": 2338707, "tid": 2338707, + "ts": 6197195983393.706, "dur": 4.890, + "args": { + "External id": 23746,"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": 2338707, "tid": 2338707, + "ts": 6197195983400.144, "dur": 1.273, + "args": { + "External id": 23747,"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": 2338707, "tid": 2338707, + "ts": 6197195983405.134, "dur": 6.327, + "args": { + "External id": 23748,"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": 2338707, "tid": 2338707, + "ts": 6197195983484.513, "dur": 57.789, + "args": { + "External id": 23749,"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": 2338707, "tid": 2338707, + "ts": 6197195983580.712, "dur": 31.427, + "args": { + "External id": 23750,"kernel_hash": "cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/dm/cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43.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": 2338707, "tid": 2338707, + "ts": 6197195983622.687, "dur": 47.473, + "args": { + "External id": 23751,"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": 2338707, "tid": 2338707, + "ts": 6197195983681.188, "dur": 58.219, + "args": { + "External id": 23752,"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": 2338707, "tid": 2338707, + "ts": 6197195983776.247, "dur": 34.472, + "args": { + "External id": 23753,"kernel_hash": "cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/b7/cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu.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": 2338707, "tid": 2338707, + "ts": 6197195983820.422, "dur": 43.054, + "args": { + "External id": 23754,"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": 2338707, "tid": 2338707, + "ts": 6197195983882.461, "dur": 20.373, + "args": { + "External id": 23755,"kernel_hash": "cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/gi/cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb.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": 2338707, "tid": 2338707, + "ts": 6197195984114.867, "dur": 96.994, + "args": { + "External id": 23756,"Record function id": 0, "Ev Idx": 13072 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6197195984305.303, "dur": 60.120, + "args": { + "External id": 23757,"Record function id": 0, "Ev Idx": 13073 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.13)", "pid": 2338707, "tid": 2338707, + "ts": 6197195984377.029, "dur": 33811.480, + "args": { + "External id": 23758,"Record function id": 0, "Ev Idx": 13074 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.13)", "pid": 2338707, "tid": 2338707, + "ts": 6197195984387.970, "dur": 1096.921, + "args": { + "External id": 23759,"Record function id": 0, "Ev Idx": 13075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6197195984484.171, "dur": 11.245, + "args": { + "External id": 23760,"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": 2338707, "tid": 2338707, + "ts": 6197195984510.797, "dur": 41.574, + "args": { + "External id": 23761,"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": 2338707, "tid": 2338707, + "ts": 6197195984517.537, "dur": 2.782, + "args": { + "External id": 23762,"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": 2338707, "tid": 2338707, + "ts": 6197195984524.724, "dur": 0.399, + "args": { + "External id": 23763,"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": 2338707, "tid": 2338707, + "ts": 6197195984526.391, "dur": 0.580, + "args": { + "External id": 23764,"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": 2338707, "tid": 2338707, + "ts": 6197195984528.059, "dur": 0.605, + "args": { + "External id": 23765,"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": 2338707, "tid": 2338707, + "ts": 6197195984532.250, "dur": 0.460, + "args": { + "External id": 23766,"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": 2338707, "tid": 2338707, + "ts": 6197195984533.640, "dur": 0.539, + "args": { + "External id": 23767,"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": 2338707, "tid": 2338707, + "ts": 6197195984535.764, "dur": 5.598, + "args": { + "External id": 23768,"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": 2338707, "tid": 2338707, + "ts": 6197195984543.005, "dur": 0.464, + "args": { + "External id": 23769,"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": 2338707, "tid": 2338707, + "ts": 6197195984544.998, "dur": 0.474, + "args": { + "External id": 23770,"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": 2338707, "tid": 2338707, + "ts": 6197195984569.482, "dur": 68.656, + "args": { + "External id": 23771,"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": 2338707, "tid": 2338707, + "ts": 6197195984678.703, "dur": 168.562, + "args": { + "External id": 23772,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2338707, + "ts": 6197195984691.630, "dur": 4.687, + "args": { + "External id": 23773,"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": 2338707, "tid": 2338707, + "ts": 6197195984720.535, "dur": 13.685, + "args": { + "External id": 23774,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2338707, + "ts": 6197195984725.997, "dur": 7.728, + "args": { + "External id": 23775,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2338707, + "ts": 6197195984730.574, "dur": 0.891, + "args": { + "External id": 23776,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197195984743.339, "dur": 35.184, + "args": { + "External id": 23777,"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": 2338707, "tid": 2338707, + "ts": 6197195984746.092, "dur": 2.761, + "args": { + "External id": 23778,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197195984750.771, "dur": 0.384, + "args": { + "External id": 23779,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2338707, + "ts": 6197195984752.537, "dur": 0.443, + "args": { + "External id": 23780,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2338707, + "ts": 6197195984757.000, "dur": 3.057, + "args": { + "External id": 23781,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2338707, + "ts": 6197195984762.008, "dur": 0.469, + "args": { + "External id": 23782,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2338707, + "ts": 6197195984764.211, "dur": 0.432, + "args": { + "External id": 23783,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2338707, + "ts": 6197195984768.172, "dur": 0.340, + "args": { + "External id": 23784,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2338707, + "ts": 6197195984769.801, "dur": 0.342, + "args": { + "External id": 23785,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2338707, + "ts": 6197195984771.585, "dur": 2.632, + "args": { + "External id": 23786,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2338707, + "ts": 6197195984794.626, "dur": 42.687, + "args": { + "External id": 23787,"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": 2338707, "tid": 2338707, + "ts": 6197195984911.396, "dur": 455.664, + "args": { + "External id": 23788,"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": 2338707, "tid": 2338707, + "ts": 6197195984947.060, "dur": 413.043, + "args": { + "External id": 23789,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2338707, + "ts": 6197195984962.679, "dur": 389.426, + "args": { + "External id": 23790,"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": 2338707, "tid": 2338707, + "ts": 6197195985397.605, "dur": 3.079, + "args": { + "External id": 23791,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.13)", "pid": 2338707, "tid": 2338707, + "ts": 6197195985510.124, "dur": 32419.481, + "args": { + "External id": 23792,"Record function id": 0, "Ev Idx": 13108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6197195985634.097, "dur": 7.718, + "args": { + "External id": 23793,"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": 2338707, "tid": 2338707, + "ts": 6197195985645.799, "dur": 1.402, + "args": { + "External id": 23794,"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": 2338707, "tid": 2338707, + "ts": 6197195985649.321, "dur": 4.139, + "args": { + "External id": 23795,"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": 2338707, "tid": 2338707, + "ts": 6197195985655.252, "dur": 1.029, + "args": { + "External id": 23796,"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": 2338707, "tid": 2338707, + "ts": 6197195985657.763, "dur": 1.020, + "args": { + "External id": 23797,"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": 2338707, "tid": 2338707, + "ts": 6197195985660.329, "dur": 0.829, + "args": { + "External id": 23798,"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": 2338707, "tid": 2338707, + "ts": 6197195985665.676, "dur": 0.866, + "args": { + "External id": 23799,"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": 2338707, "tid": 2338707, + "ts": 6197195985668.243, "dur": 2.415, + "args": { + "External id": 23800,"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": 2338707, "tid": 2338707, + "ts": 6197195985672.080, "dur": 0.975, + "args": { + "External id": 23801,"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": 2338707, "tid": 2338707, + "ts": 6197195985674.717, "dur": 0.960, + "args": { + "External id": 23802,"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": 2338707, "tid": 2338707, + "ts": 6197195985698.648, "dur": 32180.376, + "args": { + "External id": 23803,"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": 2338707, "tid": 2338707, + "ts": 6197195985737.911, "dur": 32131.496, + "args": { + "External id": 23804,"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": 2338707, "tid": 2338707, + "ts": 6197195985758.729, "dur": 20.374, + "args": { + "External id": 23805,"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": 2338707, "tid": 2338707, + "ts": 6197195985783.371, "dur": 32046.087, + "args": { + "External id": 23806,"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": 2338707, "tid": 2338707, + "ts": 6197195985786.820, "dur": 32041.968, + "args": { + "External id": 23807,"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": 2338707, "tid": 2338707, + "ts": 6197195985793.438, "dur": 6.800, + "args": { + "External id": 23808,"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": 2338707, "tid": 2338707, + "ts": 6197195985802.365, "dur": 32022.739, + "args": { + "External id": 23809,"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": 2338707, "tid": 2338707, + "ts": 6197196018121.069, "dur": 35.451, + "args": { + "External id": 23810,"Sequence number": 479793, "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": 2338707, "tid": 2338707, "ts": 6197196018121.069, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6197196018140.621, "dur": 9.911, + "args": { + "External id": 23811,"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": 2338707, "tid": 2338707, + "ts": 6197196018144.659, "dur": 5.449, + "args": { + "External id": 23812,"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": 2338707, "tid": 2338707, + "ts": 6197196018239.091, "dur": 87.362, + "args": { + "External id": 23813,"Record function id": 0, "Ev Idx": 13129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6197196018328.008, "dur": 1289.890, + "args": { + "External id": 23814,"Record function id": 0, "Ev Idx": 13130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197196018375.108, "dur": 1226.991, + "args": { + "External id": 23815,"Sequence number": 479794, "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": 2338707, "tid": 2338707, "ts": 6197196018375.108, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6197196018454.049, "dur": 59.048, + "args": { + "External id": 23816,"kernel_hash": "cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/du/cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs.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": 2338707, "tid": 2338707, + "ts": 6197196018528.632, "dur": 123.830, + "args": { + "External id": 23817,"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": 2338707, "tid": 2338707, + "ts": 6197196018665.409, "dur": 59.735, + "args": { + "External id": 23818,"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": 2338707, "tid": 2338707, + "ts": 6197196018739.029, "dur": 36.927, + "args": { + "External id": 23819,"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": 2338707, "tid": 2338707, + "ts": 6197196018807.347, "dur": 32.029, + "args": { + "External id": 23820,"kernel_hash": "cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5", "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/jw/cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5.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": 2338707, "tid": 2338707, + "ts": 6197196018864.035, "dur": 19.494, + "args": { + "External id": 23821,"kernel_hash": "cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi", "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/xw/cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi.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": 2338707, "tid": 2338707, + "ts": 6197196018910.005, "dur": 192.625, + "args": { + "External id": 23822,"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": 2338707, "tid": 2338707, + "ts": 6197196018969.493, "dur": 13.399, + "args": { + "External id": 23823,"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": 2338707, "tid": 2338707, + "ts": 6197196018975.878, "dur": 6.012, + "args": { + "External id": 23824,"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": 2338707, "tid": 2338707, + "ts": 6197196018986.036, "dur": 4.921, + "args": { + "External id": 23825,"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": 2338707, "tid": 2338707, + "ts": 6197196018992.665, "dur": 1.243, + "args": { + "External id": 23826,"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": 2338707, "tid": 2338707, + "ts": 6197196018996.871, "dur": 6.868, + "args": { + "External id": 23827,"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": 2338707, "tid": 2338707, + "ts": 6197196019118.375, "dur": 68.525, + "args": { + "External id": 23828,"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": 2338707, "tid": 2338707, + "ts": 6197196019226.205, "dur": 35.227, + "args": { + "External id": 23829,"kernel_hash": "cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/dm/cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43.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": 2338707, "tid": 2338707, + "ts": 6197196019274.170, "dur": 48.255, + "args": { + "External id": 23830,"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": 2338707, "tid": 2338707, + "ts": 6197196019333.335, "dur": 39.866, + "args": { + "External id": 23831,"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": 2338707, "tid": 2338707, + "ts": 6197196019400.436, "dur": 30.939, + "args": { + "External id": 23832,"kernel_hash": "cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/b7/cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu.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": 2338707, "tid": 2338707, + "ts": 6197196019440.304, "dur": 41.231, + "args": { + "External id": 23833,"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": 2338707, "tid": 2338707, + "ts": 6197196019502.300, "dur": 20.714, + "args": { + "External id": 23834,"kernel_hash": "cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/gi/cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb.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": 2338707, "tid": 2338707, + "ts": 6197196019696.307, "dur": 114.889, + "args": { + "External id": 23835,"Record function id": 0, "Ev Idx": 13151 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6197196019901.688, "dur": 57.385, + "args": { + "External id": 23836,"Record function id": 0, "Ev Idx": 13152 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.14)", "pid": 2338707, "tid": 2338707, + "ts": 6197196019970.978, "dur": 32616.536, + "args": { + "External id": 23837,"Record function id": 0, "Ev Idx": 13153 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.14)", "pid": 2338707, "tid": 2338707, + "ts": 6197196019979.416, "dur": 1180.898, + "args": { + "External id": 23838,"Record function id": 0, "Ev Idx": 13154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6197196020119.470, "dur": 12.190, + "args": { + "External id": 23839,"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": 2338707, "tid": 2338707, + "ts": 6197196020148.867, "dur": 50.291, + "args": { + "External id": 23840,"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": 2338707, "tid": 2338707, + "ts": 6197196020159.988, "dur": 2.958, + "args": { + "External id": 23841,"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": 2338707, "tid": 2338707, + "ts": 6197196020167.702, "dur": 0.559, + "args": { + "External id": 23842,"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": 2338707, "tid": 2338707, + "ts": 6197196020169.493, "dur": 0.423, + "args": { + "External id": 23843,"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": 2338707, "tid": 2338707, + "ts": 6197196020171.277, "dur": 2.466, + "args": { + "External id": 23844,"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": 2338707, "tid": 2338707, + "ts": 6197196020175.407, "dur": 0.474, + "args": { + "External id": 23845,"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": 2338707, "tid": 2338707, + "ts": 6197196020179.939, "dur": 0.339, + "args": { + "External id": 23846,"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": 2338707, "tid": 2338707, + "ts": 6197196020183.162, "dur": 2.843, + "args": { + "External id": 23847,"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": 2338707, "tid": 2338707, + "ts": 6197196020187.194, "dur": 0.364, + "args": { + "External id": 23848,"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": 2338707, "tid": 2338707, + "ts": 6197196020189.105, "dur": 3.139, + "args": { + "External id": 23849,"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": 2338707, "tid": 2338707, + "ts": 6197196020213.725, "dur": 69.947, + "args": { + "External id": 23850,"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": 2338707, "tid": 2338707, + "ts": 6197196020323.600, "dur": 139.270, + "args": { + "External id": 23851,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2338707, + "ts": 6197196020339.569, "dur": 4.703, + "args": { + "External id": 23852,"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": 2338707, "tid": 2338707, + "ts": 6197196020353.079, "dur": 12.628, + "args": { + "External id": 23853,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2338707, + "ts": 6197196020358.385, "dur": 6.852, + "args": { + "External id": 23854,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2338707, + "ts": 6197196020362.751, "dur": 0.776, + "args": { + "External id": 23855,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197196020373.338, "dur": 30.112, + "args": { + "External id": 23856,"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": 2338707, "tid": 2338707, + "ts": 6197196020375.242, "dur": 0.560, + "args": { + "External id": 23857,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197196020377.775, "dur": 0.620, + "args": { + "External id": 23858,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2338707, + "ts": 6197196020379.543, "dur": 2.418, + "args": { + "External id": 23859,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2338707, + "ts": 6197196020383.589, "dur": 2.940, + "args": { + "External id": 23860,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2338707, + "ts": 6197196020387.578, "dur": 0.347, + "args": { + "External id": 23861,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2338707, + "ts": 6197196020392.037, "dur": 0.385, + "args": { + "External id": 23862,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2338707, + "ts": 6197196020393.592, "dur": 0.466, + "args": { + "External id": 23863,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2338707, + "ts": 6197196020395.504, "dur": 0.474, + "args": { + "External id": 23864,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2338707, + "ts": 6197196020398.804, "dur": 0.495, + "args": { + "External id": 23865,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2338707, + "ts": 6197196020417.241, "dur": 36.024, + "args": { + "External id": 23866,"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": 2338707, "tid": 2338707, + "ts": 6197196020524.976, "dur": 471.951, + "args": { + "External id": 23867,"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": 2338707, "tid": 2338707, + "ts": 6197196020560.473, "dur": 429.728, + "args": { + "External id": 23868,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2338707, + "ts": 6197196020576.948, "dur": 406.049, + "args": { + "External id": 23869,"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": 2338707, "tid": 2338707, + "ts": 6197196021027.415, "dur": 2.800, + "args": { + "External id": 23870,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.14)", "pid": 2338707, "tid": 2338707, + "ts": 6197196021187.943, "dur": 31169.350, + "args": { + "External id": 23871,"Record function id": 0, "Ev Idx": 13187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6197196021312.249, "dur": 7.875, + "args": { + "External id": 23872,"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": 2338707, "tid": 2338707, + "ts": 6197196021324.067, "dur": 1.515, + "args": { + "External id": 23873,"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": 2338707, "tid": 2338707, + "ts": 6197196021327.482, "dur": 4.028, + "args": { + "External id": 23874,"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": 2338707, "tid": 2338707, + "ts": 6197196021333.918, "dur": 0.685, + "args": { + "External id": 23875,"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": 2338707, "tid": 2338707, + "ts": 6197196021336.242, "dur": 1.222, + "args": { + "External id": 23876,"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": 2338707, "tid": 2338707, + "ts": 6197196021339.033, "dur": 1.235, + "args": { + "External id": 23877,"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": 2338707, "tid": 2338707, + "ts": 6197196021344.353, "dur": 0.873, + "args": { + "External id": 23878,"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": 2338707, "tid": 2338707, + "ts": 6197196021347.370, "dur": 2.357, + "args": { + "External id": 23879,"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": 2338707, "tid": 2338707, + "ts": 6197196021351.213, "dur": 1.015, + "args": { + "External id": 23880,"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": 2338707, "tid": 2338707, + "ts": 6197196021353.930, "dur": 1.050, + "args": { + "External id": 23881,"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": 2338707, "tid": 2338707, + "ts": 6197196021378.188, "dur": 30925.861, + "args": { + "External id": 23882,"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": 2338707, "tid": 2338707, + "ts": 6197196021396.115, "dur": 30897.949, + "args": { + "External id": 23883,"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": 2338707, "tid": 2338707, + "ts": 6197196021415.878, "dur": 18.339, + "args": { + "External id": 23884,"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": 2338707, "tid": 2338707, + "ts": 6197196021438.478, "dur": 30809.465, + "args": { + "External id": 23885,"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": 2338707, "tid": 2338707, + "ts": 6197196021441.398, "dur": 30805.570, + "args": { + "External id": 23886,"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": 2338707, "tid": 2338707, + "ts": 6197196021448.377, "dur": 7.076, + "args": { + "External id": 23887,"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": 2338707, "tid": 2338707, + "ts": 6197196021457.488, "dur": 30785.434, + "args": { + "External id": 23888,"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": 2338707, "tid": 2338707, + "ts": 6197196052521.641, "dur": 37.505, + "args": { + "External id": 23889,"Sequence number": 479795, "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": 2338707, "tid": 2338707, "ts": 6197196052521.641, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6197196052543.584, "dur": 9.908, + "args": { + "External id": 23890,"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": 2338707, "tid": 2338707, + "ts": 6197196052548.305, "dur": 4.951, + "args": { + "External id": 23891,"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": 2338707, "tid": 2338707, + "ts": 6197196052633.574, "dur": 102.168, + "args": { + "External id": 23892,"Record function id": 0, "Ev Idx": 13208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6197196052738.925, "dur": 1377.115, + "args": { + "External id": 23893,"Record function id": 0, "Ev Idx": 13209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197196052786.825, "dur": 1310.855, + "args": { + "External id": 23894,"Sequence number": 479796, "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": 2338707, "tid": 2338707, "ts": 6197196052786.825, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6197196052868.952, "dur": 62.309, + "args": { + "External id": 23895,"kernel_hash": "cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/du/cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs.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": 2338707, "tid": 2338707, + "ts": 6197196052946.400, "dur": 156.768, + "args": { + "External id": 23896,"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": 2338707, "tid": 2338707, + "ts": 6197196053122.256, "dur": 51.639, + "args": { + "External id": 23897,"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": 2338707, "tid": 2338707, + "ts": 6197196053186.388, "dur": 34.003, + "args": { + "External id": 23898,"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": 2338707, "tid": 2338707, + "ts": 6197196053252.877, "dur": 36.785, + "args": { + "External id": 23899,"kernel_hash": "cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5", "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/jw/cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5.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": 2338707, "tid": 2338707, + "ts": 6197196053313.069, "dur": 21.713, + "args": { + "External id": 23900,"kernel_hash": "cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi", "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/xw/cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi.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": 2338707, "tid": 2338707, + "ts": 6197196053363.725, "dur": 166.320, + "args": { + "External id": 23901,"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": 2338707, "tid": 2338707, + "ts": 6197196053432.037, "dur": 14.107, + "args": { + "External id": 23902,"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": 2338707, "tid": 2338707, + "ts": 6197196053438.251, "dur": 6.846, + "args": { + "External id": 23903,"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": 2338707, "tid": 2338707, + "ts": 6197196053449.165, "dur": 4.876, + "args": { + "External id": 23904,"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": 2338707, "tid": 2338707, + "ts": 6197196053455.721, "dur": 1.211, + "args": { + "External id": 23905,"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": 2338707, "tid": 2338707, + "ts": 6197196053461.923, "dur": 6.501, + "args": { + "External id": 23906,"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": 2338707, "tid": 2338707, + "ts": 6197196053542.827, "dur": 63.495, + "args": { + "External id": 23907,"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": 2338707, "tid": 2338707, + "ts": 6197196053642.114, "dur": 37.624, + "args": { + "External id": 23908,"kernel_hash": "cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/dm/cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43.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": 2338707, "tid": 2338707, + "ts": 6197196053692.350, "dur": 71.329, + "args": { + "External id": 23909,"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": 2338707, "tid": 2338707, + "ts": 6197196053775.472, "dur": 46.055, + "args": { + "External id": 23910,"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": 2338707, "tid": 2338707, + "ts": 6197196053848.755, "dur": 36.483, + "args": { + "External id": 23911,"kernel_hash": "cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/b7/cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu.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": 2338707, "tid": 2338707, + "ts": 6197196053892.261, "dur": 41.832, + "args": { + "External id": 23912,"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": 2338707, "tid": 2338707, + "ts": 6197196053956.850, "dur": 20.439, + "args": { + "External id": 23913,"kernel_hash": "cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/gi/cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb.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": 2338707, "tid": 2338707, + "ts": 6197196054197.911, "dur": 96.517, + "args": { + "External id": 23914,"Record function id": 0, "Ev Idx": 13230 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6197196054381.016, "dur": 56.136, + "args": { + "External id": 23915,"Record function id": 0, "Ev Idx": 13231 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.15)", "pid": 2338707, "tid": 2338707, + "ts": 6197196054448.410, "dur": 31754.148, + "args": { + "External id": 23916,"Record function id": 0, "Ev Idx": 13232 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.15)", "pid": 2338707, "tid": 2338707, + "ts": 6197196054458.139, "dur": 1120.267, + "args": { + "External id": 23917,"Record function id": 0, "Ev Idx": 13233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6197196054560.716, "dur": 11.553, + "args": { + "External id": 23918,"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": 2338707, "tid": 2338707, + "ts": 6197196054588.515, "dur": 45.617, + "args": { + "External id": 23919,"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": 2338707, "tid": 2338707, + "ts": 6197196054595.662, "dur": 2.991, + "args": { + "External id": 23920,"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": 2338707, "tid": 2338707, + "ts": 6197196054604.013, "dur": 0.713, + "args": { + "External id": 23921,"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": 2338707, "tid": 2338707, + "ts": 6197196054606.703, "dur": 0.639, + "args": { + "External id": 23922,"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": 2338707, "tid": 2338707, + "ts": 6197196054608.790, "dur": 0.563, + "args": { + "External id": 23923,"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": 2338707, "tid": 2338707, + "ts": 6197196054613.216, "dur": 0.553, + "args": { + "External id": 23924,"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": 2338707, "tid": 2338707, + "ts": 6197196054615.370, "dur": 0.515, + "args": { + "External id": 23925,"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": 2338707, "tid": 2338707, + "ts": 6197196054617.722, "dur": 5.097, + "args": { + "External id": 23926,"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": 2338707, "tid": 2338707, + "ts": 6197196054624.297, "dur": 0.869, + "args": { + "External id": 23927,"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": 2338707, "tid": 2338707, + "ts": 6197196054626.796, "dur": 0.623, + "args": { + "External id": 23928,"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": 2338707, "tid": 2338707, + "ts": 6197196054647.990, "dur": 84.874, + "args": { + "External id": 23929,"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": 2338707, "tid": 2338707, + "ts": 6197196054777.981, "dur": 155.481, + "args": { + "External id": 23930,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2338707, + "ts": 6197196054791.929, "dur": 5.862, + "args": { + "External id": 23931,"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": 2338707, "tid": 2338707, + "ts": 6197196054803.930, "dur": 12.839, + "args": { + "External id": 23932,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2338707, + "ts": 6197196054809.477, "dur": 6.783, + "args": { + "External id": 23933,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2338707, + "ts": 6197196054813.550, "dur": 0.796, + "args": { + "External id": 23934,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197196054824.932, "dur": 34.119, + "args": { + "External id": 23935,"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": 2338707, "tid": 2338707, + "ts": 6197196054827.458, "dur": 2.989, + "args": { + "External id": 23936,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197196054832.262, "dur": 0.721, + "args": { + "External id": 23937,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2338707, + "ts": 6197196054834.503, "dur": 0.553, + "args": { + "External id": 23938,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2338707, + "ts": 6197196054839.086, "dur": 2.946, + "args": { + "External id": 23939,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2338707, + "ts": 6197196054843.424, "dur": 0.407, + "args": { + "External id": 23940,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2338707, + "ts": 6197196054845.187, "dur": 0.331, + "args": { + "External id": 23941,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2338707, + "ts": 6197196054848.560, "dur": 0.424, + "args": { + "External id": 23942,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2338707, + "ts": 6197196054850.815, "dur": 0.417, + "args": { + "External id": 23943,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2338707, + "ts": 6197196054852.321, "dur": 2.499, + "args": { + "External id": 23944,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2338707, + "ts": 6197196054881.676, "dur": 42.473, + "args": { + "External id": 23945,"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": 2338707, "tid": 2338707, + "ts": 6197196055000.232, "dur": 460.472, + "args": { + "External id": 23946,"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": 2338707, "tid": 2338707, + "ts": 6197196055035.926, "dur": 418.277, + "args": { + "External id": 23947,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2338707, + "ts": 6197196055050.020, "dur": 396.602, + "args": { + "External id": 23948,"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": 2338707, "tid": 2338707, + "ts": 6197196055490.027, "dur": 2.938, + "args": { + "External id": 23949,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.15)", "pid": 2338707, "tid": 2338707, + "ts": 6197196055602.487, "dur": 30328.941, + "args": { + "External id": 23950,"Record function id": 0, "Ev Idx": 13266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6197196055743.947, "dur": 7.706, + "args": { + "External id": 23951,"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": 2338707, "tid": 2338707, + "ts": 6197196055756.267, "dur": 1.045, + "args": { + "External id": 23952,"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": 2338707, "tid": 2338707, + "ts": 6197196055759.173, "dur": 3.811, + "args": { + "External id": 23953,"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": 2338707, "tid": 2338707, + "ts": 6197196055765.122, "dur": 0.974, + "args": { + "External id": 23954,"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": 2338707, "tid": 2338707, + "ts": 6197196055767.841, "dur": 0.942, + "args": { + "External id": 23955,"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": 2338707, "tid": 2338707, + "ts": 6197196055773.053, "dur": 0.862, + "args": { + "External id": 23956,"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": 2338707, "tid": 2338707, + "ts": 6197196055775.776, "dur": 0.753, + "args": { + "External id": 23957,"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": 2338707, "tid": 2338707, + "ts": 6197196055778.442, "dur": 2.502, + "args": { + "External id": 23958,"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": 2338707, "tid": 2338707, + "ts": 6197196055782.667, "dur": 0.780, + "args": { + "External id": 23959,"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": 2338707, "tid": 2338707, + "ts": 6197196055787.276, "dur": 0.905, + "args": { + "External id": 23960,"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": 2338707, "tid": 2338707, + "ts": 6197196055809.922, "dur": 30070.329, + "args": { + "External id": 23961,"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": 2338707, "tid": 2338707, + "ts": 6197196055828.921, "dur": 30041.440, + "args": { + "External id": 23962,"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": 2338707, "tid": 2338707, + "ts": 6197196055849.037, "dur": 19.824, + "args": { + "External id": 23963,"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": 2338707, "tid": 2338707, + "ts": 6197196055873.124, "dur": 29956.845, + "args": { + "External id": 23964,"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": 2338707, "tid": 2338707, + "ts": 6197196055876.441, "dur": 29952.839, + "args": { + "External id": 23965,"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": 2338707, "tid": 2338707, + "ts": 6197196055883.026, "dur": 6.298, + "args": { + "External id": 23966,"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": 2338707, "tid": 2338707, + "ts": 6197196055891.404, "dur": 29934.322, + "args": { + "External id": 23967,"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": 2338707, "tid": 2338707, + "ts": 6197196086129.194, "dur": 39.781, + "args": { + "External id": 23968,"Sequence number": 479797, "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": 2338707, "tid": 2338707, "ts": 6197196086129.194, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6197196086152.672, "dur": 10.318, + "args": { + "External id": 23969,"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": 2338707, "tid": 2338707, + "ts": 6197196086156.753, "dur": 5.800, + "args": { + "External id": 23970,"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": 2338707, "tid": 2338707, + "ts": 6197196086249.846, "dur": 88.205, + "args": { + "External id": 23971,"Record function id": 0, "Ev Idx": 13287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6197196086339.588, "dur": 1303.280, + "args": { + "External id": 23972,"Record function id": 0, "Ev Idx": 13288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197196086386.231, "dur": 1239.606, + "args": { + "External id": 23973,"Sequence number": 479798, "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": 2338707, "tid": 2338707, "ts": 6197196086386.231, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6197196086464.181, "dur": 58.778, + "args": { + "External id": 23974,"kernel_hash": "cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/du/cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs.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": 2338707, "tid": 2338707, + "ts": 6197196086538.628, "dur": 121.331, + "args": { + "External id": 23975,"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": 2338707, "tid": 2338707, + "ts": 6197196086675.302, "dur": 63.428, + "args": { + "External id": 23976,"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": 2338707, "tid": 2338707, + "ts": 6197196086754.701, "dur": 37.904, + "args": { + "External id": 23977,"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": 2338707, "tid": 2338707, + "ts": 6197196086823.943, "dur": 33.011, + "args": { + "External id": 23978,"kernel_hash": "cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5", "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/jw/cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5.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": 2338707, "tid": 2338707, + "ts": 6197196086879.338, "dur": 20.981, + "args": { + "External id": 23979,"kernel_hash": "cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi", "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/xw/cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi.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": 2338707, "tid": 2338707, + "ts": 6197196086926.702, "dur": 197.006, + "args": { + "External id": 23980,"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": 2338707, "tid": 2338707, + "ts": 6197196086988.533, "dur": 13.361, + "args": { + "External id": 23981,"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": 2338707, "tid": 2338707, + "ts": 6197196086994.489, "dur": 6.469, + "args": { + "External id": 23982,"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": 2338707, "tid": 2338707, + "ts": 6197196087004.944, "dur": 4.690, + "args": { + "External id": 23983,"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": 2338707, "tid": 2338707, + "ts": 6197196087011.026, "dur": 1.364, + "args": { + "External id": 23984,"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": 2338707, "tid": 2338707, + "ts": 6197196087015.244, "dur": 6.216, + "args": { + "External id": 23985,"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": 2338707, "tid": 2338707, + "ts": 6197196087138.739, "dur": 67.331, + "args": { + "External id": 23986,"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": 2338707, "tid": 2338707, + "ts": 6197196087245.224, "dur": 36.347, + "args": { + "External id": 23987,"kernel_hash": "cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/dm/cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43.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": 2338707, "tid": 2338707, + "ts": 6197196087294.933, "dur": 49.409, + "args": { + "External id": 23988,"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": 2338707, "tid": 2338707, + "ts": 6197196087355.026, "dur": 39.994, + "args": { + "External id": 23989,"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": 2338707, "tid": 2338707, + "ts": 6197196087423.732, "dur": 30.262, + "args": { + "External id": 23990,"kernel_hash": "cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/b7/cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu.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": 2338707, "tid": 2338707, + "ts": 6197196087463.199, "dur": 39.968, + "args": { + "External id": 23991,"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": 2338707, "tid": 2338707, + "ts": 6197196087524.540, "dur": 21.242, + "args": { + "External id": 23992,"kernel_hash": "cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/gi/cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb.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": 2338707, "tid": 2338707, + "ts": 6197196087742.208, "dur": 99.630, + "args": { + "External id": 23993,"Record function id": 0, "Ev Idx": 13309 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6197196087930.055, "dur": 54.191, + "args": { + "External id": 23994,"Record function id": 0, "Ev Idx": 13310 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.16)", "pid": 2338707, "tid": 2338707, + "ts": 6197196087995.707, "dur": 31903.162, + "args": { + "External id": 23995,"Record function id": 0, "Ev Idx": 13311 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.16)", "pid": 2338707, "tid": 2338707, + "ts": 6197196088005.850, "dur": 1130.885, + "args": { + "External id": 23996,"Record function id": 0, "Ev Idx": 13312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6197196088146.989, "dur": 10.881, + "args": { + "External id": 23997,"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": 2338707, "tid": 2338707, + "ts": 6197196088174.615, "dur": 45.971, + "args": { + "External id": 23998,"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": 2338707, "tid": 2338707, + "ts": 6197196088181.839, "dur": 3.315, + "args": { + "External id": 23999,"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": 2338707, "tid": 2338707, + "ts": 6197196088189.611, "dur": 0.687, + "args": { + "External id": 24000,"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": 2338707, "tid": 2338707, + "ts": 6197196088192.296, "dur": 0.886, + "args": { + "External id": 24001,"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": 2338707, "tid": 2338707, + "ts": 6197196088194.671, "dur": 0.604, + "args": { + "External id": 24002,"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": 2338707, "tid": 2338707, + "ts": 6197196088199.462, "dur": 0.447, + "args": { + "External id": 24003,"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": 2338707, "tid": 2338707, + "ts": 6197196088201.415, "dur": 0.671, + "args": { + "External id": 24004,"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": 2338707, "tid": 2338707, + "ts": 6197196088203.841, "dur": 5.247, + "args": { + "External id": 24005,"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": 2338707, "tid": 2338707, + "ts": 6197196088210.933, "dur": 0.585, + "args": { + "External id": 24006,"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": 2338707, "tid": 2338707, + "ts": 6197196088213.043, "dur": 0.612, + "args": { + "External id": 24007,"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": 2338707, "tid": 2338707, + "ts": 6197196088237.799, "dur": 64.570, + "args": { + "External id": 24008,"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": 2338707, "tid": 2338707, + "ts": 6197196088342.408, "dur": 137.239, + "args": { + "External id": 24009,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2338707, + "ts": 6197196088356.265, "dur": 5.382, + "args": { + "External id": 24010,"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": 2338707, "tid": 2338707, + "ts": 6197196088370.377, "dur": 12.244, + "args": { + "External id": 24011,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2338707, + "ts": 6197196088375.890, "dur": 6.089, + "args": { + "External id": 24012,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2338707, + "ts": 6197196088379.844, "dur": 0.560, + "args": { + "External id": 24013,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197196088390.368, "dur": 32.563, + "args": { + "External id": 24014,"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": 2338707, "tid": 2338707, + "ts": 6197196088392.652, "dur": 0.575, + "args": { + "External id": 24015,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197196088394.971, "dur": 2.403, + "args": { + "External id": 24016,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2338707, + "ts": 6197196088399.104, "dur": 0.729, + "args": { + "External id": 24017,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2338707, + "ts": 6197196088400.920, "dur": 3.397, + "args": { + "External id": 24018,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2338707, + "ts": 6197196088408.659, "dur": 0.327, + "args": { + "External id": 24019,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2338707, + "ts": 6197196088410.072, "dur": 0.445, + "args": { + "External id": 24020,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2338707, + "ts": 6197196088412.646, "dur": 0.267, + "args": { + "External id": 24021,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2338707, + "ts": 6197196088416.117, "dur": 0.393, + "args": { + "External id": 24022,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2338707, + "ts": 6197196088417.964, "dur": 0.395, + "args": { + "External id": 24023,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2338707, + "ts": 6197196088434.783, "dur": 35.417, + "args": { + "External id": 24024,"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": 2338707, "tid": 2338707, + "ts": 6197196088542.618, "dur": 430.012, + "args": { + "External id": 24025,"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": 2338707, "tid": 2338707, + "ts": 6197196088578.244, "dur": 388.262, + "args": { + "External id": 24026,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2338707, + "ts": 6197196088589.864, "dur": 369.368, + "args": { + "External id": 24027,"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": 2338707, "tid": 2338707, + "ts": 6197196089003.581, "dur": 2.820, + "args": { + "External id": 24028,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.16)", "pid": 2338707, "tid": 2338707, + "ts": 6197196089166.311, "dur": 30490.455, + "args": { + "External id": 24029,"Record function id": 0, "Ev Idx": 13345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6197196089291.511, "dur": 8.044, + "args": { + "External id": 24030,"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": 2338707, "tid": 2338707, + "ts": 6197196089303.550, "dur": 1.372, + "args": { + "External id": 24031,"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": 2338707, "tid": 2338707, + "ts": 6197196089306.895, "dur": 4.082, + "args": { + "External id": 24032,"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": 2338707, "tid": 2338707, + "ts": 6197196089312.847, "dur": 0.841, + "args": { + "External id": 24033,"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": 2338707, "tid": 2338707, + "ts": 6197196089315.345, "dur": 0.942, + "args": { + "External id": 24034,"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": 2338707, "tid": 2338707, + "ts": 6197196089317.661, "dur": 0.925, + "args": { + "External id": 24035,"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": 2338707, "tid": 2338707, + "ts": 6197196089322.555, "dur": 0.919, + "args": { + "External id": 24036,"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": 2338707, "tid": 2338707, + "ts": 6197196089325.308, "dur": 2.399, + "args": { + "External id": 24037,"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": 2338707, "tid": 2338707, + "ts": 6197196089329.424, "dur": 0.999, + "args": { + "External id": 24038,"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": 2338707, "tid": 2338707, + "ts": 6197196089332.252, "dur": 0.810, + "args": { + "External id": 24039,"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": 2338707, "tid": 2338707, + "ts": 6197196089356.937, "dur": 30251.750, + "args": { + "External id": 24040,"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": 2338707, "tid": 2338707, + "ts": 6197196089375.795, "dur": 30223.025, + "args": { + "External id": 24041,"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": 2338707, "tid": 2338707, + "ts": 6197196089394.458, "dur": 20.200, + "args": { + "External id": 24042,"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": 2338707, "tid": 2338707, + "ts": 6197196089419.078, "dur": 30139.804, + "args": { + "External id": 24043,"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": 2338707, "tid": 2338707, + "ts": 6197196089421.834, "dur": 30136.392, + "args": { + "External id": 24044,"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": 2338707, "tid": 2338707, + "ts": 6197196089430.283, "dur": 6.418, + "args": { + "External id": 24045,"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": 2338707, "tid": 2338707, + "ts": 6197196089438.665, "dur": 30115.900, + "args": { + "External id": 24046,"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": 2338707, "tid": 2338707, + "ts": 6197196119830.632, "dur": 36.876, + "args": { + "External id": 24047,"Sequence number": 479799, "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": 2338707, "tid": 2338707, "ts": 6197196119830.632, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6197196119852.066, "dur": 10.046, + "args": { + "External id": 24048,"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": 2338707, "tid": 2338707, + "ts": 6197196119855.991, "dur": 5.690, + "args": { + "External id": 24049,"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": 2338707, "tid": 2338707, + "ts": 6197196119948.944, "dur": 87.784, + "args": { + "External id": 24050,"Record function id": 0, "Ev Idx": 13366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6197196120038.460, "dur": 1384.699, + "args": { + "External id": 24051,"Record function id": 0, "Ev Idx": 13367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197196120122.224, "dur": 1283.924, + "args": { + "External id": 24052,"Sequence number": 479800, "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": 2338707, "tid": 2338707, "ts": 6197196120122.224, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6197196120201.310, "dur": 60.862, + "args": { + "External id": 24053,"kernel_hash": "cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/du/cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs.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": 2338707, "tid": 2338707, + "ts": 6197196120278.064, "dur": 122.843, + "args": { + "External id": 24054,"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": 2338707, "tid": 2338707, + "ts": 6197196120413.581, "dur": 44.104, + "args": { + "External id": 24055,"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": 2338707, "tid": 2338707, + "ts": 6197196120469.458, "dur": 33.444, + "args": { + "External id": 24056,"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": 2338707, "tid": 2338707, + "ts": 6197196120537.767, "dur": 35.722, + "args": { + "External id": 24057,"kernel_hash": "cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5", "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/jw/cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5.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": 2338707, "tid": 2338707, + "ts": 6197196120594.317, "dur": 20.295, + "args": { + "External id": 24058,"kernel_hash": "cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi", "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/xw/cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi.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": 2338707, "tid": 2338707, + "ts": 6197196120640.624, "dur": 174.858, + "args": { + "External id": 24059,"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": 2338707, "tid": 2338707, + "ts": 6197196120719.360, "dur": 14.644, + "args": { + "External id": 24060,"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": 2338707, "tid": 2338707, + "ts": 6197196120725.589, "dur": 7.355, + "args": { + "External id": 24061,"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": 2338707, "tid": 2338707, + "ts": 6197196120737.346, "dur": 4.846, + "args": { + "External id": 24062,"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": 2338707, "tid": 2338707, + "ts": 6197196120743.877, "dur": 1.222, + "args": { + "External id": 24063,"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": 2338707, "tid": 2338707, + "ts": 6197196120747.746, "dur": 7.796, + "args": { + "External id": 24064,"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": 2338707, "tid": 2338707, + "ts": 6197196120856.950, "dur": 66.484, + "args": { + "External id": 24065,"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": 2338707, "tid": 2338707, + "ts": 6197196120967.404, "dur": 35.839, + "args": { + "External id": 24066,"kernel_hash": "cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/dm/cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43.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": 2338707, "tid": 2338707, + "ts": 6197196121014.857, "dur": 88.562, + "args": { + "External id": 24067,"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": 2338707, "tid": 2338707, + "ts": 6197196121120.354, "dur": 46.573, + "args": { + "External id": 24068,"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": 2338707, "tid": 2338707, + "ts": 6197196121195.863, "dur": 32.887, + "args": { + "External id": 24069,"kernel_hash": "cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/b7/cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu.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": 2338707, "tid": 2338707, + "ts": 6197196121236.179, "dur": 42.547, + "args": { + "External id": 24070,"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": 2338707, "tid": 2338707, + "ts": 6197196121305.795, "dur": 20.424, + "args": { + "External id": 24071,"kernel_hash": "cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/gi/cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb.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": 2338707, "tid": 2338707, + "ts": 6197196121503.195, "dur": 97.999, + "args": { + "External id": 24072,"Record function id": 0, "Ev Idx": 13388 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6197196121688.746, "dur": 78.292, + "args": { + "External id": 24073,"Record function id": 0, "Ev Idx": 13389 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.17)", "pid": 2338707, "tid": 2338707, + "ts": 6197196121779.533, "dur": 33737.207, + "args": { + "External id": 24074,"Record function id": 0, "Ev Idx": 13390 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.17)", "pid": 2338707, "tid": 2338707, + "ts": 6197196121790.003, "dur": 1096.897, + "args": { + "External id": 24075,"Record function id": 0, "Ev Idx": 13391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6197196121892.248, "dur": 11.190, + "args": { + "External id": 24076,"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": 2338707, "tid": 2338707, + "ts": 6197196121919.395, "dur": 44.866, + "args": { + "External id": 24077,"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": 2338707, "tid": 2338707, + "ts": 6197196121926.671, "dur": 2.950, + "args": { + "External id": 24078,"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": 2338707, "tid": 2338707, + "ts": 6197196121935.265, "dur": 0.660, + "args": { + "External id": 24079,"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": 2338707, "tid": 2338707, + "ts": 6197196121937.605, "dur": 0.883, + "args": { + "External id": 24080,"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": 2338707, "tid": 2338707, + "ts": 6197196121939.967, "dur": 0.544, + "args": { + "External id": 24081,"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": 2338707, "tid": 2338707, + "ts": 6197196121944.911, "dur": 0.384, + "args": { + "External id": 24082,"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": 2338707, "tid": 2338707, + "ts": 6197196121946.457, "dur": 0.370, + "args": { + "External id": 24083,"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": 2338707, "tid": 2338707, + "ts": 6197196121948.990, "dur": 5.003, + "args": { + "External id": 24084,"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": 2338707, "tid": 2338707, + "ts": 6197196121955.109, "dur": 0.384, + "args": { + "External id": 24085,"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": 2338707, "tid": 2338707, + "ts": 6197196121957.189, "dur": 0.291, + "args": { + "External id": 24086,"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": 2338707, "tid": 2338707, + "ts": 6197196121977.877, "dur": 63.547, + "args": { + "External id": 24087,"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": 2338707, "tid": 2338707, + "ts": 6197196122125.955, "dur": 152.841, + "args": { + "External id": 24088,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2338707, + "ts": 6197196122141.481, "dur": 6.620, + "args": { + "External id": 24089,"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": 2338707, "tid": 2338707, + "ts": 6197196122154.565, "dur": 13.894, + "args": { + "External id": 24090,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2338707, + "ts": 6197196122160.253, "dur": 7.724, + "args": { + "External id": 24091,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2338707, + "ts": 6197196122165.071, "dur": 0.800, + "args": { + "External id": 24092,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197196122176.493, "dur": 33.682, + "args": { + "External id": 24093,"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": 2338707, "tid": 2338707, + "ts": 6197196122179.305, "dur": 2.678, + "args": { + "External id": 24094,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197196122183.610, "dur": 0.384, + "args": { + "External id": 24095,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2338707, + "ts": 6197196122185.615, "dur": 0.589, + "args": { + "External id": 24096,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2338707, + "ts": 6197196122190.208, "dur": 2.463, + "args": { + "External id": 24097,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2338707, + "ts": 6197196122194.173, "dur": 0.432, + "args": { + "External id": 24098,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2338707, + "ts": 6197196122196.060, "dur": 0.581, + "args": { + "External id": 24099,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2338707, + "ts": 6197196122199.752, "dur": 0.469, + "args": { + "External id": 24100,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2338707, + "ts": 6197196122201.669, "dur": 0.635, + "args": { + "External id": 24101,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2338707, + "ts": 6197196122203.663, "dur": 2.510, + "args": { + "External id": 24102,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2338707, + "ts": 6197196122225.665, "dur": 43.700, + "args": { + "External id": 24103,"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": 2338707, "tid": 2338707, + "ts": 6197196122342.837, "dur": 432.054, + "args": { + "External id": 24104,"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": 2338707, "tid": 2338707, + "ts": 6197196122379.707, "dur": 387.944, + "args": { + "External id": 24105,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2338707, + "ts": 6197196122391.519, "dur": 368.266, + "args": { + "External id": 24106,"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": 2338707, "tid": 2338707, + "ts": 6197196122803.539, "dur": 2.954, + "args": { + "External id": 24107,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.17)", "pid": 2338707, "tid": 2338707, + "ts": 6197196122911.858, "dur": 32371.107, + "args": { + "External id": 24108,"Record function id": 0, "Ev Idx": 13424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6197196123031.030, "dur": 8.003, + "args": { + "External id": 24109,"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": 2338707, "tid": 2338707, + "ts": 6197196123042.547, "dur": 1.205, + "args": { + "External id": 24110,"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": 2338707, "tid": 2338707, + "ts": 6197196123045.691, "dur": 3.707, + "args": { + "External id": 24111,"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": 2338707, "tid": 2338707, + "ts": 6197196123051.368, "dur": 0.857, + "args": { + "External id": 24112,"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": 2338707, "tid": 2338707, + "ts": 6197196123053.775, "dur": 1.159, + "args": { + "External id": 24113,"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": 2338707, "tid": 2338707, + "ts": 6197196123096.528, "dur": 1.550, + "args": { + "External id": 24114,"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": 2338707, "tid": 2338707, + "ts": 6197196123104.022, "dur": 1.026, + "args": { + "External id": 24115,"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": 2338707, "tid": 2338707, + "ts": 6197196123106.886, "dur": 2.428, + "args": { + "External id": 24116,"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": 2338707, "tid": 2338707, + "ts": 6197196123111.173, "dur": 1.237, + "args": { + "External id": 24117,"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": 2338707, "tid": 2338707, + "ts": 6197196123114.234, "dur": 0.878, + "args": { + "External id": 24118,"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": 2338707, "tid": 2338707, + "ts": 6197196123139.497, "dur": 32092.638, + "args": { + "External id": 24119,"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": 2338707, "tid": 2338707, + "ts": 6197196123157.327, "dur": 32064.724, + "args": { + "External id": 24120,"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": 2338707, "tid": 2338707, + "ts": 6197196123178.338, "dur": 20.053, + "args": { + "External id": 24121,"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": 2338707, "tid": 2338707, + "ts": 6197196123202.736, "dur": 31978.369, + "args": { + "External id": 24122,"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": 2338707, "tid": 2338707, + "ts": 6197196123205.906, "dur": 31974.536, + "args": { + "External id": 24123,"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": 2338707, "tid": 2338707, + "ts": 6197196123212.408, "dur": 6.804, + "args": { + "External id": 24124,"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": 2338707, "tid": 2338707, + "ts": 6197196123221.369, "dur": 31955.248, + "args": { + "External id": 24125,"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": 2338707, "tid": 2338707, + "ts": 6197196155449.684, "dur": 37.803, + "args": { + "External id": 24126,"Sequence number": 479801, "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": 2338707, "tid": 2338707, "ts": 6197196155449.684, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6197196155472.193, "dur": 9.756, + "args": { + "External id": 24127,"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": 2338707, "tid": 2338707, + "ts": 6197196155476.677, "dur": 5.029, + "args": { + "External id": 24128,"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": 2338707, "tid": 2338707, + "ts": 6197196155566.367, "dur": 89.074, + "args": { + "External id": 24129,"Record function id": 0, "Ev Idx": 13445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6197196155657.093, "dur": 1349.276, + "args": { + "External id": 24130,"Record function id": 0, "Ev Idx": 13446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197196155725.062, "dur": 1266.061, + "args": { + "External id": 24131,"Sequence number": 479802, "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": 2338707, "tid": 2338707, "ts": 6197196155725.062, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6197196155806.737, "dur": 67.129, + "args": { + "External id": 24132,"kernel_hash": "cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/du/cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs.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": 2338707, "tid": 2338707, + "ts": 6197196155889.704, "dur": 122.107, + "args": { + "External id": 24133,"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": 2338707, "tid": 2338707, + "ts": 6197196156026.179, "dur": 86.134, + "args": { + "External id": 24134,"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": 2338707, "tid": 2338707, + "ts": 6197196156128.878, "dur": 39.687, + "args": { + "External id": 24135,"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": 2338707, "tid": 2338707, + "ts": 6197196156201.505, "dur": 34.935, + "args": { + "External id": 24136,"kernel_hash": "cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5", "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/jw/cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5.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": 2338707, "tid": 2338707, + "ts": 6197196156259.976, "dur": 23.186, + "args": { + "External id": 24137,"kernel_hash": "cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi", "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/xw/cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi.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": 2338707, "tid": 2338707, + "ts": 6197196156311.780, "dur": 156.116, + "args": { + "External id": 24138,"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": 2338707, "tid": 2338707, + "ts": 6197196156370.997, "dur": 14.195, + "args": { + "External id": 24139,"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": 2338707, "tid": 2338707, + "ts": 6197196156377.574, "dur": 6.450, + "args": { + "External id": 24140,"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": 2338707, "tid": 2338707, + "ts": 6197196156388.416, "dur": 5.179, + "args": { + "External id": 24141,"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": 2338707, "tid": 2338707, + "ts": 6197196156395.263, "dur": 1.566, + "args": { + "External id": 24142,"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": 2338707, "tid": 2338707, + "ts": 6197196156399.536, "dur": 6.287, + "args": { + "External id": 24143,"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": 2338707, "tid": 2338707, + "ts": 6197196156481.009, "dur": 59.050, + "args": { + "External id": 24144,"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": 2338707, "tid": 2338707, + "ts": 6197196156577.011, "dur": 34.956, + "args": { + "External id": 24145,"kernel_hash": "cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/dm/cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43.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": 2338707, "tid": 2338707, + "ts": 6197196156625.302, "dur": 50.293, + "args": { + "External id": 24146,"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": 2338707, "tid": 2338707, + "ts": 6197196156685.125, "dur": 58.830, + "args": { + "External id": 24147,"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": 2338707, "tid": 2338707, + "ts": 6197196156775.595, "dur": 35.461, + "args": { + "External id": 24148,"kernel_hash": "cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/b7/cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu.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": 2338707, "tid": 2338707, + "ts": 6197196156821.232, "dur": 43.650, + "args": { + "External id": 24149,"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": 2338707, "tid": 2338707, + "ts": 6197196156888.282, "dur": 23.017, + "args": { + "External id": 24150,"kernel_hash": "cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/gi/cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb.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": 2338707, "tid": 2338707, + "ts": 6197196157125.651, "dur": 95.244, + "args": { + "External id": 24151,"Record function id": 0, "Ev Idx": 13467 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6197196157310.424, "dur": 58.991, + "args": { + "External id": 24152,"Record function id": 0, "Ev Idx": 13468 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.18)", "pid": 2338707, "tid": 2338707, + "ts": 6197196157380.087, "dur": 32088.074, + "args": { + "External id": 24153,"Record function id": 0, "Ev Idx": 13469 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.18)", "pid": 2338707, "tid": 2338707, + "ts": 6197196157390.206, "dur": 1100.252, + "args": { + "External id": 24154,"Record function id": 0, "Ev Idx": 13470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6197196157493.445, "dur": 11.112, + "args": { + "External id": 24155,"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": 2338707, "tid": 2338707, + "ts": 6197196157519.966, "dur": 45.251, + "args": { + "External id": 24156,"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": 2338707, "tid": 2338707, + "ts": 6197196157527.309, "dur": 3.070, + "args": { + "External id": 24157,"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": 2338707, "tid": 2338707, + "ts": 6197196157535.152, "dur": 0.749, + "args": { + "External id": 24158,"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": 2338707, "tid": 2338707, + "ts": 6197196157537.712, "dur": 0.804, + "args": { + "External id": 24159,"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": 2338707, "tid": 2338707, + "ts": 6197196157539.942, "dur": 0.984, + "args": { + "External id": 24160,"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": 2338707, "tid": 2338707, + "ts": 6197196157544.626, "dur": 0.712, + "args": { + "External id": 24161,"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": 2338707, "tid": 2338707, + "ts": 6197196157546.396, "dur": 0.816, + "args": { + "External id": 24162,"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": 2338707, "tid": 2338707, + "ts": 6197196157548.784, "dur": 4.593, + "args": { + "External id": 24163,"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": 2338707, "tid": 2338707, + "ts": 6197196157555.239, "dur": 0.737, + "args": { + "External id": 24164,"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": 2338707, "tid": 2338707, + "ts": 6197196157557.666, "dur": 0.624, + "args": { + "External id": 24165,"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": 2338707, "tid": 2338707, + "ts": 6197196157578.861, "dur": 62.996, + "args": { + "External id": 24166,"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": 2338707, "tid": 2338707, + "ts": 6197196157679.493, "dur": 169.701, + "args": { + "External id": 24167,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2338707, + "ts": 6197196157696.086, "dur": 23.829, + "args": { + "External id": 24168,"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": 2338707, "tid": 2338707, + "ts": 6197196157728.238, "dur": 13.840, + "args": { + "External id": 24169,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2338707, + "ts": 6197196157733.932, "dur": 7.460, + "args": { + "External id": 24170,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2338707, + "ts": 6197196157738.520, "dur": 0.766, + "args": { + "External id": 24171,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197196157750.527, "dur": 34.274, + "args": { + "External id": 24172,"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": 2338707, "tid": 2338707, + "ts": 6197196157753.314, "dur": 0.725, + "args": { + "External id": 24173,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197196157756.508, "dur": 3.103, + "args": { + "External id": 24174,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2338707, + "ts": 6197196157761.177, "dur": 0.571, + "args": { + "External id": 24175,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2338707, + "ts": 6197196157763.609, "dur": 2.984, + "args": { + "External id": 24176,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2338707, + "ts": 6197196157770.327, "dur": 0.413, + "args": { + "External id": 24177,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2338707, + "ts": 6197196157772.399, "dur": 0.578, + "args": { + "External id": 24178,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2338707, + "ts": 6197196157774.215, "dur": 0.301, + "args": { + "External id": 24179,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2338707, + "ts": 6197196157778.149, "dur": 0.275, + "args": { + "External id": 24180,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2338707, + "ts": 6197196157779.472, "dur": 0.383, + "args": { + "External id": 24181,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2338707, + "ts": 6197196157799.117, "dur": 41.111, + "args": { + "External id": 24182,"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": 2338707, "tid": 2338707, + "ts": 6197196157911.613, "dur": 456.093, + "args": { + "External id": 24183,"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": 2338707, "tid": 2338707, + "ts": 6197196157946.757, "dur": 414.317, + "args": { + "External id": 24184,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2338707, + "ts": 6197196157959.088, "dur": 391.326, + "args": { + "External id": 24185,"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": 2338707, "tid": 2338707, + "ts": 6197196158401.003, "dur": 2.939, + "args": { + "External id": 24186,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.18)", "pid": 2338707, "tid": 2338707, + "ts": 6197196158517.380, "dur": 30723.627, + "args": { + "External id": 24187,"Record function id": 0, "Ev Idx": 13503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6197196158643.978, "dur": 7.475, + "args": { + "External id": 24188,"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": 2338707, "tid": 2338707, + "ts": 6197196158658.325, "dur": 1.381, + "args": { + "External id": 24189,"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": 2338707, "tid": 2338707, + "ts": 6197196158661.741, "dur": 3.727, + "args": { + "External id": 24190,"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": 2338707, "tid": 2338707, + "ts": 6197196158667.445, "dur": 1.149, + "args": { + "External id": 24191,"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": 2338707, "tid": 2338707, + "ts": 6197196158670.152, "dur": 1.318, + "args": { + "External id": 24192,"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": 2338707, "tid": 2338707, + "ts": 6197196158672.813, "dur": 1.088, + "args": { + "External id": 24193,"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": 2338707, "tid": 2338707, + "ts": 6197196158675.939, "dur": 1.412, + "args": { + "External id": 24194,"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": 2338707, "tid": 2338707, + "ts": 6197196158679.165, "dur": 2.488, + "args": { + "External id": 24195,"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": 2338707, "tid": 2338707, + "ts": 6197196158683.394, "dur": 1.187, + "args": { + "External id": 24196,"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": 2338707, "tid": 2338707, + "ts": 6197196158688.672, "dur": 1.007, + "args": { + "External id": 24197,"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": 2338707, "tid": 2338707, + "ts": 6197196158733.137, "dur": 30457.909, + "args": { + "External id": 24198,"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": 2338707, "tid": 2338707, + "ts": 6197196158754.289, "dur": 30427.607, + "args": { + "External id": 24199,"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": 2338707, "tid": 2338707, + "ts": 6197196158773.338, "dur": 20.762, + "args": { + "External id": 24200,"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": 2338707, "tid": 2338707, + "ts": 6197196158798.394, "dur": 30338.589, + "args": { + "External id": 24201,"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": 2338707, "tid": 2338707, + "ts": 6197196158801.285, "dur": 30335.026, + "args": { + "External id": 24202,"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": 2338707, "tid": 2338707, + "ts": 6197196158809.255, "dur": 6.846, + "args": { + "External id": 24203,"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": 2338707, "tid": 2338707, + "ts": 6197196158818.245, "dur": 30314.944, + "args": { + "External id": 24204,"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": 2338707, "tid": 2338707, + "ts": 6197196189403.141, "dur": 36.399, + "args": { + "External id": 24205,"Sequence number": 479803, "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": 2338707, "tid": 2338707, "ts": 6197196189403.141, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6197196189424.826, "dur": 9.305, + "args": { + "External id": 24206,"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": 2338707, "tid": 2338707, + "ts": 6197196189428.889, "dur": 4.960, + "args": { + "External id": 24207,"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": 2338707, "tid": 2338707, + "ts": 6197196189517.429, "dur": 93.605, + "args": { + "External id": 24208,"Record function id": 0, "Ev Idx": 13524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6197196189612.406, "dur": 1333.246, + "args": { + "External id": 24209,"Record function id": 0, "Ev Idx": 13525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197196189659.158, "dur": 1270.618, + "args": { + "External id": 24210,"Sequence number": 479804, "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": 2338707, "tid": 2338707, "ts": 6197196189659.158, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6197196189759.963, "dur": 61.769, + "args": { + "External id": 24211,"kernel_hash": "cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/du/cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs.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": 2338707, "tid": 2338707, + "ts": 6197196189837.105, "dur": 123.292, + "args": { + "External id": 24212,"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": 2338707, "tid": 2338707, + "ts": 6197196189974.749, "dur": 43.758, + "args": { + "External id": 24213,"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": 2338707, "tid": 2338707, + "ts": 6197196190026.101, "dur": 73.367, + "args": { + "External id": 24214,"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": 2338707, "tid": 2338707, + "ts": 6197196190138.169, "dur": 36.701, + "args": { + "External id": 24215,"kernel_hash": "cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5", "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/jw/cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5.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": 2338707, "tid": 2338707, + "ts": 6197196190198.308, "dur": 22.315, + "args": { + "External id": 24216,"kernel_hash": "cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi", "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/xw/cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi.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": 2338707, "tid": 2338707, + "ts": 6197196190246.658, "dur": 158.419, + "args": { + "External id": 24217,"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": 2338707, "tid": 2338707, + "ts": 6197196190308.831, "dur": 13.264, + "args": { + "External id": 24218,"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": 2338707, "tid": 2338707, + "ts": 6197196190314.905, "dur": 6.224, + "args": { + "External id": 24219,"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": 2338707, "tid": 2338707, + "ts": 6197196190325.265, "dur": 5.309, + "args": { + "External id": 24220,"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": 2338707, "tid": 2338707, + "ts": 6197196190331.993, "dur": 2.817, + "args": { + "External id": 24221,"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": 2338707, "tid": 2338707, + "ts": 6197196190337.737, "dur": 6.364, + "args": { + "External id": 24222,"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": 2338707, "tid": 2338707, + "ts": 6197196190417.301, "dur": 64.949, + "args": { + "External id": 24223,"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": 2338707, "tid": 2338707, + "ts": 6197196190518.173, "dur": 36.117, + "args": { + "External id": 24224,"kernel_hash": "cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/dm/cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43.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": 2338707, "tid": 2338707, + "ts": 6197196190565.142, "dur": 50.147, + "args": { + "External id": 24225,"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": 2338707, "tid": 2338707, + "ts": 6197196190625.452, "dur": 40.492, + "args": { + "External id": 24226,"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": 2338707, "tid": 2338707, + "ts": 6197196190693.669, "dur": 50.824, + "args": { + "External id": 24227,"kernel_hash": "cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/b7/cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu.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": 2338707, "tid": 2338707, + "ts": 6197196190754.090, "dur": 47.408, + "args": { + "External id": 24228,"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": 2338707, "tid": 2338707, + "ts": 6197196190827.190, "dur": 25.405, + "args": { + "External id": 24229,"kernel_hash": "cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/gi/cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb.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": 2338707, "tid": 2338707, + "ts": 6197196191022.475, "dur": 138.435, + "args": { + "External id": 24230,"Record function id": 0, "Ev Idx": 13546 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6197196191256.341, "dur": 60.060, + "args": { + "External id": 24231,"Record function id": 0, "Ev Idx": 13547 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.19)", "pid": 2338707, "tid": 2338707, + "ts": 6197196191327.713, "dur": 33762.599, + "args": { + "External id": 24232,"Record function id": 0, "Ev Idx": 13548 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.19)", "pid": 2338707, "tid": 2338707, + "ts": 6197196191340.212, "dur": 1143.756, + "args": { + "External id": 24233,"Record function id": 0, "Ev Idx": 13549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6197196191439.245, "dur": 10.828, + "args": { + "External id": 24234,"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": 2338707, "tid": 2338707, + "ts": 6197196191466.780, "dur": 42.590, + "args": { + "External id": 24235,"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": 2338707, "tid": 2338707, + "ts": 6197196191474.261, "dur": 2.760, + "args": { + "External id": 24236,"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": 2338707, "tid": 2338707, + "ts": 6197196191481.014, "dur": 0.515, + "args": { + "External id": 24237,"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": 2338707, "tid": 2338707, + "ts": 6197196191483.182, "dur": 0.464, + "args": { + "External id": 24238,"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": 2338707, "tid": 2338707, + "ts": 6197196191484.956, "dur": 1.015, + "args": { + "External id": 24239,"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": 2338707, "tid": 2338707, + "ts": 6197196191489.723, "dur": 0.567, + "args": { + "External id": 24240,"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": 2338707, "tid": 2338707, + "ts": 6197196191491.336, "dur": 0.479, + "args": { + "External id": 24241,"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": 2338707, "tid": 2338707, + "ts": 6197196191493.212, "dur": 5.430, + "args": { + "External id": 24242,"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": 2338707, "tid": 2338707, + "ts": 6197196191500.204, "dur": 0.559, + "args": { + "External id": 24243,"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": 2338707, "tid": 2338707, + "ts": 6197196191502.028, "dur": 0.506, + "args": { + "External id": 24244,"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": 2338707, "tid": 2338707, + "ts": 6197196191523.523, "dur": 69.166, + "args": { + "External id": 24245,"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": 2338707, "tid": 2338707, + "ts": 6197196191630.559, "dur": 162.524, + "args": { + "External id": 24246,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2338707, + "ts": 6197196191643.469, "dur": 4.474, + "args": { + "External id": 24247,"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": 2338707, "tid": 2338707, + "ts": 6197196191653.682, "dur": 11.851, + "args": { + "External id": 24248,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2338707, + "ts": 6197196191658.843, "dur": 6.193, + "args": { + "External id": 24249,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2338707, + "ts": 6197196191663.007, "dur": 0.589, + "args": { + "External id": 24250,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197196191673.017, "dur": 51.393, + "args": { + "External id": 24251,"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": 2338707, "tid": 2338707, + "ts": 6197196191675.297, "dur": 1.898, + "args": { + "External id": 24252,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197196191678.866, "dur": 0.472, + "args": { + "External id": 24253,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2338707, + "ts": 6197196191680.626, "dur": 0.391, + "args": { + "External id": 24254,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2338707, + "ts": 6197196191684.647, "dur": 2.796, + "args": { + "External id": 24255,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2338707, + "ts": 6197196191689.289, "dur": 0.514, + "args": { + "External id": 24256,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2338707, + "ts": 6197196191691.781, "dur": 0.329, + "args": { + "External id": 24257,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2338707, + "ts": 6197196191695.189, "dur": 0.427, + "args": { + "External id": 24258,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2338707, + "ts": 6197196191697.417, "dur": 0.625, + "args": { + "External id": 24259,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2338707, + "ts": 6197196191716.105, "dur": 2.632, + "args": { + "External id": 24260,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2338707, + "ts": 6197196191742.305, "dur": 41.273, + "args": { + "External id": 24261,"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": 2338707, "tid": 2338707, + "ts": 6197196191856.198, "dur": 506.113, + "args": { + "External id": 24262,"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": 2338707, "tid": 2338707, + "ts": 6197196191891.454, "dur": 463.307, + "args": { + "External id": 24263,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2338707, + "ts": 6197196191904.153, "dur": 442.311, + "args": { + "External id": 24264,"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": 2338707, "tid": 2338707, + "ts": 6197196192393.201, "dur": 2.954, + "args": { + "External id": 24265,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.19)", "pid": 2338707, "tid": 2338707, + "ts": 6197196192509.688, "dur": 32322.214, + "args": { + "External id": 24266,"Record function id": 0, "Ev Idx": 13582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6197196192632.489, "dur": 7.606, + "args": { + "External id": 24267,"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": 2338707, "tid": 2338707, + "ts": 6197196192651.206, "dur": 1.096, + "args": { + "External id": 24268,"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": 2338707, "tid": 2338707, + "ts": 6197196192654.442, "dur": 4.160, + "args": { + "External id": 24269,"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": 2338707, "tid": 2338707, + "ts": 6197196192662.246, "dur": 0.923, + "args": { + "External id": 24270,"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": 2338707, "tid": 2338707, + "ts": 6197196192664.756, "dur": 0.926, + "args": { + "External id": 24271,"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": 2338707, "tid": 2338707, + "ts": 6197196192667.402, "dur": 0.940, + "args": { + "External id": 24272,"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": 2338707, "tid": 2338707, + "ts": 6197196192670.122, "dur": 1.120, + "args": { + "External id": 24273,"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": 2338707, "tid": 2338707, + "ts": 6197196192675.562, "dur": 2.230, + "args": { + "External id": 24274,"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": 2338707, "tid": 2338707, + "ts": 6197196192679.704, "dur": 0.832, + "args": { + "External id": 24275,"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": 2338707, "tid": 2338707, + "ts": 6197196192682.115, "dur": 0.723, + "args": { + "External id": 24276,"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": 2338707, "tid": 2338707, + "ts": 6197196192724.047, "dur": 32057.865, + "args": { + "External id": 24277,"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": 2338707, "tid": 2338707, + "ts": 6197196192744.045, "dur": 32028.110, + "args": { + "External id": 24278,"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": 2338707, "tid": 2338707, + "ts": 6197196192762.805, "dur": 21.539, + "args": { + "External id": 24279,"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": 2338707, "tid": 2338707, + "ts": 6197196192791.446, "dur": 31938.118, + "args": { + "External id": 24280,"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": 2338707, "tid": 2338707, + "ts": 6197196192794.423, "dur": 31934.302, + "args": { + "External id": 24281,"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": 2338707, "tid": 2338707, + "ts": 6197196192800.929, "dur": 7.160, + "args": { + "External id": 24282,"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": 2338707, "tid": 2338707, + "ts": 6197196192810.347, "dur": 31914.590, + "args": { + "External id": 24283,"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": 2338707, "tid": 2338707, + "ts": 6197196224992.665, "dur": 37.521, + "args": { + "External id": 24284,"Sequence number": 479805, "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": 2338707, "tid": 2338707, "ts": 6197196224992.665, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6197196225015.177, "dur": 9.385, + "args": { + "External id": 24285,"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": 2338707, "tid": 2338707, + "ts": 6197196225019.157, "dur": 5.185, + "args": { + "External id": 24286,"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": 2338707, "tid": 2338707, + "ts": 6197196225140.325, "dur": 87.562, + "args": { + "External id": 24287,"Record function id": 0, "Ev Idx": 13603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6197196225229.431, "dur": 1342.802, + "args": { + "External id": 24288,"Record function id": 0, "Ev Idx": 13604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197196225275.525, "dur": 1280.349, + "args": { + "External id": 24289,"Sequence number": 479806, "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": 2338707, "tid": 2338707, "ts": 6197196225275.525, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6197196225363.941, "dur": 62.914, + "args": { + "External id": 24290,"kernel_hash": "cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/du/cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs.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": 2338707, "tid": 2338707, + "ts": 6197196225441.810, "dur": 121.547, + "args": { + "External id": 24291,"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": 2338707, "tid": 2338707, + "ts": 6197196225577.860, "dur": 43.900, + "args": { + "External id": 24292,"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": 2338707, "tid": 2338707, + "ts": 6197196225631.862, "dur": 34.518, + "args": { + "External id": 24293,"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": 2338707, "tid": 2338707, + "ts": 6197196225696.272, "dur": 54.643, + "args": { + "External id": 24294,"kernel_hash": "cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5", "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/jw/cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5.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": 2338707, "tid": 2338707, + "ts": 6197196225780.660, "dur": 21.195, + "args": { + "External id": 24295,"kernel_hash": "cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi", "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/xw/cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi.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": 2338707, "tid": 2338707, + "ts": 6197196225829.959, "dur": 151.453, + "args": { + "External id": 24296,"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": 2338707, "tid": 2338707, + "ts": 6197196225890.272, "dur": 13.075, + "args": { + "External id": 24297,"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": 2338707, "tid": 2338707, + "ts": 6197196225896.394, "dur": 5.987, + "args": { + "External id": 24298,"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": 2338707, "tid": 2338707, + "ts": 6197196225906.539, "dur": 4.496, + "args": { + "External id": 24299,"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": 2338707, "tid": 2338707, + "ts": 6197196225912.461, "dur": 1.304, + "args": { + "External id": 24300,"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": 2338707, "tid": 2338707, + "ts": 6197196225916.608, "dur": 6.118, + "args": { + "External id": 24301,"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": 2338707, "tid": 2338707, + "ts": 6197196225995.199, "dur": 120.192, + "args": { + "External id": 24302,"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": 2338707, "tid": 2338707, + "ts": 6197196226164.544, "dur": 39.332, + "args": { + "External id": 24303,"kernel_hash": "cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/dm/cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43.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": 2338707, "tid": 2338707, + "ts": 6197196226216.040, "dur": 56.508, + "args": { + "External id": 24304,"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": 2338707, "tid": 2338707, + "ts": 6197196226284.884, "dur": 39.247, + "args": { + "External id": 24305,"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": 2338707, "tid": 2338707, + "ts": 6197196226349.563, "dur": 33.824, + "args": { + "External id": 24306,"kernel_hash": "cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/b7/cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu.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": 2338707, "tid": 2338707, + "ts": 6197196226392.309, "dur": 40.475, + "args": { + "External id": 24307,"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": 2338707, "tid": 2338707, + "ts": 6197196226456.382, "dur": 20.039, + "args": { + "External id": 24308,"kernel_hash": "cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/gi/cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb.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": 2338707, "tid": 2338707, + "ts": 6197196226649.536, "dur": 118.464, + "args": { + "External id": 24309,"Record function id": 0, "Ev Idx": 13625 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6197196226860.904, "dur": 57.188, + "args": { + "External id": 24310,"Record function id": 0, "Ev Idx": 13626 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.20)", "pid": 2338707, "tid": 2338707, + "ts": 6197196226928.585, "dur": 30928.615, + "args": { + "External id": 24311,"Record function id": 0, "Ev Idx": 13627 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.20)", "pid": 2338707, "tid": 2338707, + "ts": 6197196226938.967, "dur": 1099.754, + "args": { + "External id": 24312,"Record function id": 0, "Ev Idx": 13628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6197196227040.728, "dur": 9.926, + "args": { + "External id": 24313,"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": 2338707, "tid": 2338707, + "ts": 6197196227107.078, "dur": 42.017, + "args": { + "External id": 24314,"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": 2338707, "tid": 2338707, + "ts": 6197196227113.822, "dur": 2.899, + "args": { + "External id": 24315,"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": 2338707, "tid": 2338707, + "ts": 6197196227121.384, "dur": 0.506, + "args": { + "External id": 24316,"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": 2338707, "tid": 2338707, + "ts": 6197196227123.468, "dur": 0.486, + "args": { + "External id": 24317,"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": 2338707, "tid": 2338707, + "ts": 6197196227125.637, "dur": 0.679, + "args": { + "External id": 24318,"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": 2338707, "tid": 2338707, + "ts": 6197196227130.423, "dur": 0.459, + "args": { + "External id": 24319,"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": 2338707, "tid": 2338707, + "ts": 6197196227132.241, "dur": 0.508, + "args": { + "External id": 24320,"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": 2338707, "tid": 2338707, + "ts": 6197196227134.375, "dur": 3.941, + "args": { + "External id": 24321,"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": 2338707, "tid": 2338707, + "ts": 6197196227139.751, "dur": 0.287, + "args": { + "External id": 24322,"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": 2338707, "tid": 2338707, + "ts": 6197196227141.678, "dur": 0.317, + "args": { + "External id": 24323,"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": 2338707, "tid": 2338707, + "ts": 6197196227163.817, "dur": 65.632, + "args": { + "External id": 24324,"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": 2338707, "tid": 2338707, + "ts": 6197196227270.337, "dur": 144.473, + "args": { + "External id": 24325,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2338707, + "ts": 6197196227284.721, "dur": 5.752, + "args": { + "External id": 24326,"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": 2338707, "tid": 2338707, + "ts": 6197196227296.496, "dur": 12.616, + "args": { + "External id": 24327,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2338707, + "ts": 6197196227302.136, "dur": 6.471, + "args": { + "External id": 24328,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2338707, + "ts": 6197196227306.460, "dur": 0.624, + "args": { + "External id": 24329,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197196227316.725, "dur": 35.756, + "args": { + "External id": 24330,"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": 2338707, "tid": 2338707, + "ts": 6197196227318.511, "dur": 2.461, + "args": { + "External id": 24331,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197196227322.756, "dur": 0.520, + "args": { + "External id": 24332,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2338707, + "ts": 6197196227327.442, "dur": 0.735, + "args": { + "External id": 24333,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2338707, + "ts": 6197196227331.411, "dur": 3.297, + "args": { + "External id": 24334,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2338707, + "ts": 6197196227336.120, "dur": 0.457, + "args": { + "External id": 24335,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2338707, + "ts": 6197196227338.612, "dur": 2.614, + "args": { + "External id": 24336,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2338707, + "ts": 6197196227342.443, "dur": 0.349, + "args": { + "External id": 24337,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2338707, + "ts": 6197196227344.451, "dur": 0.599, + "args": { + "External id": 24338,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2338707, + "ts": 6197196227348.147, "dur": 0.291, + "args": { + "External id": 24339,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2338707, + "ts": 6197196227366.165, "dur": 39.093, + "args": { + "External id": 24340,"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": 2338707, "tid": 2338707, + "ts": 6197196227478.982, "dur": 441.993, + "args": { + "External id": 24341,"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": 2338707, "tid": 2338707, + "ts": 6197196227514.647, "dur": 399.646, + "args": { + "External id": 24342,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2338707, + "ts": 6197196227527.491, "dur": 378.640, + "args": { + "External id": 24343,"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": 2338707, "tid": 2338707, + "ts": 6197196227953.777, "dur": 2.788, + "args": { + "External id": 24344,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.20)", "pid": 2338707, "tid": 2338707, + "ts": 6197196228104.339, "dur": 29502.584, + "args": { + "External id": 24345,"Record function id": 0, "Ev Idx": 13661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6197196228228.447, "dur": 7.691, + "args": { + "External id": 24346,"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": 2338707, "tid": 2338707, + "ts": 6197196228240.135, "dur": 1.580, + "args": { + "External id": 24347,"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": 2338707, "tid": 2338707, + "ts": 6197196228243.708, "dur": 3.796, + "args": { + "External id": 24348,"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": 2338707, "tid": 2338707, + "ts": 6197196228249.802, "dur": 1.049, + "args": { + "External id": 24349,"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": 2338707, "tid": 2338707, + "ts": 6197196228252.459, "dur": 0.913, + "args": { + "External id": 24350,"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": 2338707, "tid": 2338707, + "ts": 6197196228254.973, "dur": 1.054, + "args": { + "External id": 24351,"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": 2338707, "tid": 2338707, + "ts": 6197196228257.668, "dur": 0.842, + "args": { + "External id": 24352,"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": 2338707, "tid": 2338707, + "ts": 6197196228260.595, "dur": 2.235, + "args": { + "External id": 24353,"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": 2338707, "tid": 2338707, + "ts": 6197196228264.557, "dur": 0.963, + "args": { + "External id": 24354,"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": 2338707, "tid": 2338707, + "ts": 6197196228269.645, "dur": 1.003, + "args": { + "External id": 24355,"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": 2338707, "tid": 2338707, + "ts": 6197196228292.035, "dur": 29263.300, + "args": { + "External id": 24356,"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": 2338707, "tid": 2338707, + "ts": 6197196228310.238, "dur": 29236.106, + "args": { + "External id": 24357,"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": 2338707, "tid": 2338707, + "ts": 6197196228329.727, "dur": 20.430, + "args": { + "External id": 24358,"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": 2338707, "tid": 2338707, + "ts": 6197196228354.498, "dur": 29150.416, + "args": { + "External id": 24359,"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": 2338707, "tid": 2338707, + "ts": 6197196228357.575, "dur": 29146.509, + "args": { + "External id": 24360,"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": 2338707, "tid": 2338707, + "ts": 6197196228364.372, "dur": 6.144, + "args": { + "External id": 24361,"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": 2338707, "tid": 2338707, + "ts": 6197196228372.668, "dur": 29127.622, + "args": { + "External id": 24362,"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": 2338707, "tid": 2338707, + "ts": 6197196257784.507, "dur": 41.879, + "args": { + "External id": 24363,"Sequence number": 479807, "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": 2338707, "tid": 2338707, "ts": 6197196257784.507, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6197196257810.322, "dur": 10.350, + "args": { + "External id": 24364,"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": 2338707, "tid": 2338707, + "ts": 6197196257814.496, "dur": 5.830, + "args": { + "External id": 24365,"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": 2338707, "tid": 2338707, + "ts": 6197196257906.602, "dur": 87.048, + "args": { + "External id": 24366,"Record function id": 0, "Ev Idx": 13682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6197196257995.421, "dur": 1349.883, + "args": { + "External id": 24367,"Record function id": 0, "Ev Idx": 13683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197196258040.047, "dur": 1289.149, + "args": { + "External id": 24368,"Sequence number": 479808, "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": 2338707, "tid": 2338707, "ts": 6197196258040.047, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6197196258159.156, "dur": 62.628, + "args": { + "External id": 24369,"kernel_hash": "cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/du/cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs.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": 2338707, "tid": 2338707, + "ts": 6197196258236.835, "dur": 122.317, + "args": { + "External id": 24370,"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": 2338707, "tid": 2338707, + "ts": 6197196258375.168, "dur": 46.432, + "args": { + "External id": 24371,"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": 2338707, "tid": 2338707, + "ts": 6197196258429.982, "dur": 33.988, + "args": { + "External id": 24372,"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": 2338707, "tid": 2338707, + "ts": 6197196258501.230, "dur": 31.194, + "args": { + "External id": 24373,"kernel_hash": "cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5", "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/jw/cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5.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": 2338707, "tid": 2338707, + "ts": 6197196258553.834, "dur": 20.371, + "args": { + "External id": 24374,"kernel_hash": "cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi", "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/xw/cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi.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": 2338707, "tid": 2338707, + "ts": 6197196258600.443, "dur": 178.263, + "args": { + "External id": 24375,"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": 2338707, "tid": 2338707, + "ts": 6197196258661.736, "dur": 13.269, + "args": { + "External id": 24376,"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": 2338707, "tid": 2338707, + "ts": 6197196258667.988, "dur": 6.090, + "args": { + "External id": 24377,"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": 2338707, "tid": 2338707, + "ts": 6197196258678.052, "dur": 4.947, + "args": { + "External id": 24378,"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": 2338707, "tid": 2338707, + "ts": 6197196258684.812, "dur": 1.382, + "args": { + "External id": 24379,"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": 2338707, "tid": 2338707, + "ts": 6197196258690.359, "dur": 6.529, + "args": { + "External id": 24380,"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": 2338707, "tid": 2338707, + "ts": 6197196258793.279, "dur": 65.783, + "args": { + "External id": 24381,"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": 2338707, "tid": 2338707, + "ts": 6197196258895.384, "dur": 39.071, + "args": { + "External id": 24382,"kernel_hash": "cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/dm/cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43.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": 2338707, "tid": 2338707, + "ts": 6197196258946.862, "dur": 50.138, + "args": { + "External id": 24383,"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": 2338707, "tid": 2338707, + "ts": 6197196259006.110, "dur": 41.068, + "args": { + "External id": 24384,"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": 2338707, "tid": 2338707, + "ts": 6197196259112.535, "dur": 38.788, + "args": { + "External id": 24385,"kernel_hash": "cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/b7/cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu.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": 2338707, "tid": 2338707, + "ts": 6197196259159.343, "dur": 47.988, + "args": { + "External id": 24386,"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": 2338707, "tid": 2338707, + "ts": 6197196259231.389, "dur": 21.572, + "args": { + "External id": 24387,"kernel_hash": "cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/gi/cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb.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": 2338707, "tid": 2338707, + "ts": 6197196259423.866, "dur": 92.899, + "args": { + "External id": 24388,"Record function id": 0, "Ev Idx": 13704 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6197196259606.932, "dur": 56.313, + "args": { + "External id": 24389,"Record function id": 0, "Ev Idx": 13705 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.21)", "pid": 2338707, "tid": 2338707, + "ts": 6197196259673.800, "dur": 32747.926, + "args": { + "External id": 24390,"Record function id": 0, "Ev Idx": 13706 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.21)", "pid": 2338707, "tid": 2338707, + "ts": 6197196259683.612, "dur": 1125.667, + "args": { + "External id": 24391,"Record function id": 0, "Ev Idx": 13707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6197196259804.893, "dur": 11.286, + "args": { + "External id": 24392,"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": 2338707, "tid": 2338707, + "ts": 6197196259832.925, "dur": 41.455, + "args": { + "External id": 24393,"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": 2338707, "tid": 2338707, + "ts": 6197196259839.865, "dur": 2.781, + "args": { + "External id": 24394,"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": 2338707, "tid": 2338707, + "ts": 6197196259847.015, "dur": 0.431, + "args": { + "External id": 24395,"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": 2338707, "tid": 2338707, + "ts": 6197196259849.198, "dur": 0.477, + "args": { + "External id": 24396,"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": 2338707, "tid": 2338707, + "ts": 6197196259850.998, "dur": 0.676, + "args": { + "External id": 24397,"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": 2338707, "tid": 2338707, + "ts": 6197196259855.420, "dur": 0.620, + "args": { + "External id": 24398,"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": 2338707, "tid": 2338707, + "ts": 6197196259857.345, "dur": 0.690, + "args": { + "External id": 24399,"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": 2338707, "tid": 2338707, + "ts": 6197196259859.860, "dur": 4.045, + "args": { + "External id": 24400,"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": 2338707, "tid": 2338707, + "ts": 6197196259865.311, "dur": 0.360, + "args": { + "External id": 24401,"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": 2338707, "tid": 2338707, + "ts": 6197196259867.260, "dur": 0.259, + "args": { + "External id": 24402,"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": 2338707, "tid": 2338707, + "ts": 6197196259888.071, "dur": 65.141, + "args": { + "External id": 24403,"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": 2338707, "tid": 2338707, + "ts": 6197196259991.983, "dur": 187.635, + "args": { + "External id": 24404,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2338707, + "ts": 6197196260005.140, "dur": 4.279, + "args": { + "External id": 24405,"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": 2338707, "tid": 2338707, + "ts": 6197196260015.130, "dur": 11.850, + "args": { + "External id": 24406,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2338707, + "ts": 6197196260020.277, "dur": 6.196, + "args": { + "External id": 24407,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2338707, + "ts": 6197196260024.474, "dur": 0.518, + "args": { + "External id": 24408,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197196260034.338, "dur": 74.127, + "args": { + "External id": 24409,"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": 2338707, "tid": 2338707, + "ts": 6197196260036.529, "dur": 2.451, + "args": { + "External id": 24410,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197196260040.702, "dur": 0.582, + "args": { + "External id": 24411,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2338707, + "ts": 6197196260042.601, "dur": 0.633, + "args": { + "External id": 24412,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2338707, + "ts": 6197196260046.404, "dur": 2.586, + "args": { + "External id": 24413,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2338707, + "ts": 6197196260050.074, "dur": 0.435, + "args": { + "External id": 24414,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2338707, + "ts": 6197196260091.992, "dur": 0.783, + "args": { + "External id": 24415,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2338707, + "ts": 6197196260096.590, "dur": 0.488, + "args": { + "External id": 24416,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2338707, + "ts": 6197196260098.733, "dur": 0.440, + "args": { + "External id": 24417,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2338707, + "ts": 6197196260100.868, "dur": 2.425, + "args": { + "External id": 24418,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2338707, + "ts": 6197196260125.863, "dur": 44.475, + "args": { + "External id": 24419,"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": 2338707, "tid": 2338707, + "ts": 6197196260254.900, "dur": 413.620, + "args": { + "External id": 24420,"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": 2338707, "tid": 2338707, + "ts": 6197196260293.470, "dur": 369.242, + "args": { + "External id": 24421,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2338707, + "ts": 6197196260305.966, "dur": 350.025, + "args": { + "External id": 24422,"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": 2338707, "tid": 2338707, + "ts": 6197196260697.816, "dur": 23.243, + "args": { + "External id": 24423,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.21)", "pid": 2338707, "tid": 2338707, + "ts": 6197196260835.712, "dur": 31356.102, + "args": { + "External id": 24424,"Record function id": 0, "Ev Idx": 13740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6197196260960.431, "dur": 7.541, + "args": { + "External id": 24425,"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": 2338707, "tid": 2338707, + "ts": 6197196260972.003, "dur": 1.380, + "args": { + "External id": 24426,"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": 2338707, "tid": 2338707, + "ts": 6197196260975.339, "dur": 3.581, + "args": { + "External id": 24427,"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": 2338707, "tid": 2338707, + "ts": 6197196260980.804, "dur": 0.902, + "args": { + "External id": 24428,"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": 2338707, "tid": 2338707, + "ts": 6197196260983.305, "dur": 1.000, + "args": { + "External id": 24429,"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": 2338707, "tid": 2338707, + "ts": 6197196260985.671, "dur": 1.133, + "args": { + "External id": 24430,"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": 2338707, "tid": 2338707, + "ts": 6197196260988.301, "dur": 0.913, + "args": { + "External id": 24431,"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": 2338707, "tid": 2338707, + "ts": 6197196260991.165, "dur": 2.106, + "args": { + "External id": 24432,"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": 2338707, "tid": 2338707, + "ts": 6197196260994.841, "dur": 1.119, + "args": { + "External id": 24433,"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": 2338707, "tid": 2338707, + "ts": 6197196261000.189, "dur": 0.888, + "args": { + "External id": 24434,"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": 2338707, "tid": 2338707, + "ts": 6197196261022.721, "dur": 31119.167, + "args": { + "External id": 24435,"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": 2338707, "tid": 2338707, + "ts": 6197196261040.185, "dur": 31091.892, + "args": { + "External id": 24436,"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": 2338707, "tid": 2338707, + "ts": 6197196261099.457, "dur": 21.613, + "args": { + "External id": 24437,"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": 2338707, "tid": 2338707, + "ts": 6197196261125.683, "dur": 30959.729, + "args": { + "External id": 24438,"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": 2338707, "tid": 2338707, + "ts": 6197196261128.769, "dur": 30956.047, + "args": { + "External id": 24439,"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": 2338707, "tid": 2338707, + "ts": 6197196261135.674, "dur": 7.546, + "args": { + "External id": 24440,"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": 2338707, "tid": 2338707, + "ts": 6197196261145.279, "dur": 30935.628, + "args": { + "External id": 24441,"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": 2338707, "tid": 2338707, + "ts": 6197196292357.380, "dur": 34.877, + "args": { + "External id": 24442,"Sequence number": 479809, "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": 2338707, "tid": 2338707, "ts": 6197196292357.380, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6197196292377.486, "dur": 9.364, + "args": { + "External id": 24443,"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": 2338707, "tid": 2338707, + "ts": 6197196292381.724, "dur": 4.949, + "args": { + "External id": 24444,"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": 2338707, "tid": 2338707, + "ts": 6197196292470.501, "dur": 84.576, + "args": { + "External id": 24445,"Record function id": 0, "Ev Idx": 13761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6197196292556.673, "dur": 1329.109, + "args": { + "External id": 24446,"Record function id": 0, "Ev Idx": 13762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197196292605.257, "dur": 1264.681, + "args": { + "External id": 24447,"Sequence number": 479810, "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": 2338707, "tid": 2338707, "ts": 6197196292605.257, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6197196292689.644, "dur": 74.516, + "args": { + "External id": 24448,"kernel_hash": "cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/du/cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs.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": 2338707, "tid": 2338707, + "ts": 6197196292782.780, "dur": 119.915, + "args": { + "External id": 24449,"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": 2338707, "tid": 2338707, + "ts": 6197196292917.331, "dur": 43.364, + "args": { + "External id": 24450,"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": 2338707, "tid": 2338707, + "ts": 6197196292970.563, "dur": 34.843, + "args": { + "External id": 24451,"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": 2338707, "tid": 2338707, + "ts": 6197196293036.690, "dur": 73.805, + "args": { + "External id": 24452,"kernel_hash": "cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5", "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/jw/cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5.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": 2338707, "tid": 2338707, + "ts": 6197196293141.558, "dur": 24.291, + "args": { + "External id": 24453,"kernel_hash": "cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi", "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/xw/cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi.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": 2338707, "tid": 2338707, + "ts": 6197196293193.282, "dur": 154.650, + "args": { + "External id": 24454,"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": 2338707, "tid": 2338707, + "ts": 6197196293254.150, "dur": 13.380, + "args": { + "External id": 24455,"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": 2338707, "tid": 2338707, + "ts": 6197196293260.463, "dur": 6.072, + "args": { + "External id": 24456,"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": 2338707, "tid": 2338707, + "ts": 6197196293270.520, "dur": 4.606, + "args": { + "External id": 24457,"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": 2338707, "tid": 2338707, + "ts": 6197196293276.625, "dur": 1.267, + "args": { + "External id": 24458,"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": 2338707, "tid": 2338707, + "ts": 6197196293280.848, "dur": 6.657, + "args": { + "External id": 24459,"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": 2338707, "tid": 2338707, + "ts": 6197196293360.750, "dur": 65.511, + "args": { + "External id": 24460,"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": 2338707, "tid": 2338707, + "ts": 6197196293463.358, "dur": 36.843, + "args": { + "External id": 24461,"kernel_hash": "cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/dm/cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43.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": 2338707, "tid": 2338707, + "ts": 6197196293511.278, "dur": 51.778, + "args": { + "External id": 24462,"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": 2338707, "tid": 2338707, + "ts": 6197196293574.670, "dur": 40.244, + "args": { + "External id": 24463,"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": 2338707, "tid": 2338707, + "ts": 6197196293640.234, "dur": 31.940, + "args": { + "External id": 24464,"kernel_hash": "cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/b7/cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu.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": 2338707, "tid": 2338707, + "ts": 6197196293680.735, "dur": 60.425, + "args": { + "External id": 24465,"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": 2338707, "tid": 2338707, + "ts": 6197196293769.045, "dur": 22.778, + "args": { + "External id": 24466,"kernel_hash": "cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/gi/cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb.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": 2338707, "tid": 2338707, + "ts": 6197196293964.741, "dur": 146.969, + "args": { + "External id": 24467,"Record function id": 0, "Ev Idx": 13783 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6197196294207.256, "dur": 58.199, + "args": { + "External id": 24468,"Record function id": 0, "Ev Idx": 13784 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.22)", "pid": 2338707, "tid": 2338707, + "ts": 6197196294276.191, "dur": 31182.568, + "args": { + "External id": 24469,"Record function id": 0, "Ev Idx": 13785 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.22)", "pid": 2338707, "tid": 2338707, + "ts": 6197196294286.867, "dur": 1086.958, + "args": { + "External id": 24470,"Record function id": 0, "Ev Idx": 13786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6197196294384.684, "dur": 10.821, + "args": { + "External id": 24471,"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": 2338707, "tid": 2338707, + "ts": 6197196294410.837, "dur": 41.844, + "args": { + "External id": 24472,"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": 2338707, "tid": 2338707, + "ts": 6197196294418.091, "dur": 2.687, + "args": { + "External id": 24473,"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": 2338707, "tid": 2338707, + "ts": 6197196294425.272, "dur": 0.593, + "args": { + "External id": 24474,"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": 2338707, "tid": 2338707, + "ts": 6197196294427.558, "dur": 0.498, + "args": { + "External id": 24475,"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": 2338707, "tid": 2338707, + "ts": 6197196294429.386, "dur": 0.332, + "args": { + "External id": 24476,"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": 2338707, "tid": 2338707, + "ts": 6197196294432.961, "dur": 0.396, + "args": { + "External id": 24477,"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": 2338707, "tid": 2338707, + "ts": 6197196294434.541, "dur": 0.900, + "args": { + "External id": 24478,"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": 2338707, "tid": 2338707, + "ts": 6197196294437.237, "dur": 4.628, + "args": { + "External id": 24479,"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": 2338707, "tid": 2338707, + "ts": 6197196294443.377, "dur": 0.406, + "args": { + "External id": 24480,"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": 2338707, "tid": 2338707, + "ts": 6197196294445.452, "dur": 0.453, + "args": { + "External id": 24481,"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": 2338707, "tid": 2338707, + "ts": 6197196294466.027, "dur": 66.083, + "args": { + "External id": 24482,"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": 2338707, "tid": 2338707, + "ts": 6197196294569.901, "dur": 163.512, + "args": { + "External id": 24483,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2338707, + "ts": 6197196294582.988, "dur": 4.558, + "args": { + "External id": 24484,"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": 2338707, "tid": 2338707, + "ts": 6197196294593.753, "dur": 12.103, + "args": { + "External id": 24485,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2338707, + "ts": 6197196294599.249, "dur": 6.095, + "args": { + "External id": 24486,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2338707, + "ts": 6197196294603.123, "dur": 0.881, + "args": { + "External id": 24487,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197196294613.837, "dur": 38.804, + "args": { + "External id": 24488,"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": 2338707, "tid": 2338707, + "ts": 6197196294616.109, "dur": 1.968, + "args": { + "External id": 24489,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197196294619.838, "dur": 0.555, + "args": { + "External id": 24490,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2338707, + "ts": 6197196294622.562, "dur": 0.845, + "args": { + "External id": 24491,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2338707, + "ts": 6197196294627.128, "dur": 2.991, + "args": { + "External id": 24492,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2338707, + "ts": 6197196294632.145, "dur": 0.642, + "args": { + "External id": 24493,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2338707, + "ts": 6197196294634.493, "dur": 0.733, + "args": { + "External id": 24494,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2338707, + "ts": 6197196294638.517, "dur": 0.509, + "args": { + "External id": 24495,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2338707, + "ts": 6197196294640.426, "dur": 0.807, + "args": { + "External id": 24496,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2338707, + "ts": 6197196294645.537, "dur": 2.345, + "args": { + "External id": 24497,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2338707, + "ts": 6197196294664.570, "dur": 57.321, + "args": { + "External id": 24498,"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": 2338707, "tid": 2338707, + "ts": 6197196294799.607, "dur": 451.948, + "args": { + "External id": 24499,"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": 2338707, "tid": 2338707, + "ts": 6197196294836.850, "dur": 407.941, + "args": { + "External id": 24500,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2338707, + "ts": 6197196294849.726, "dur": 388.197, + "args": { + "External id": 24501,"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": 2338707, "tid": 2338707, + "ts": 6197196295283.287, "dur": 3.073, + "args": { + "External id": 24502,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.22)", "pid": 2338707, "tid": 2338707, + "ts": 6197196295399.123, "dur": 29827.959, + "args": { + "External id": 24503,"Record function id": 0, "Ev Idx": 13819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6197196295520.058, "dur": 8.188, + "args": { + "External id": 24504,"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": 2338707, "tid": 2338707, + "ts": 6197196295532.084, "dur": 1.225, + "args": { + "External id": 24505,"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": 2338707, "tid": 2338707, + "ts": 6197196295535.580, "dur": 4.464, + "args": { + "External id": 24506,"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": 2338707, "tid": 2338707, + "ts": 6197196295541.911, "dur": 1.274, + "args": { + "External id": 24507,"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": 2338707, "tid": 2338707, + "ts": 6197196295544.928, "dur": 0.796, + "args": { + "External id": 24508,"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": 2338707, "tid": 2338707, + "ts": 6197196295547.169, "dur": 1.188, + "args": { + "External id": 24509,"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": 2338707, "tid": 2338707, + "ts": 6197196295550.462, "dur": 1.183, + "args": { + "External id": 24510,"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": 2338707, "tid": 2338707, + "ts": 6197196295553.712, "dur": 2.513, + "args": { + "External id": 24511,"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": 2338707, "tid": 2338707, + "ts": 6197196295557.845, "dur": 1.076, + "args": { + "External id": 24512,"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": 2338707, "tid": 2338707, + "ts": 6197196295562.748, "dur": 0.938, + "args": { + "External id": 24513,"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": 2338707, "tid": 2338707, + "ts": 6197196295584.442, "dur": 29593.205, + "args": { + "External id": 24514,"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": 2338707, "tid": 2338707, + "ts": 6197196295606.106, "dur": 29562.138, + "args": { + "External id": 24515,"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": 2338707, "tid": 2338707, + "ts": 6197196295623.338, "dur": 18.649, + "args": { + "External id": 24516,"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": 2338707, "tid": 2338707, + "ts": 6197196295646.088, "dur": 29481.615, + "args": { + "External id": 24517,"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": 2338707, "tid": 2338707, + "ts": 6197196295649.246, "dur": 29477.744, + "args": { + "External id": 24518,"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": 2338707, "tid": 2338707, + "ts": 6197196295656.691, "dur": 5.965, + "args": { + "External id": 24519,"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": 2338707, "tid": 2338707, + "ts": 6197196295664.758, "dur": 29458.656, + "args": { + "External id": 24520,"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": 2338707, "tid": 2338707, + "ts": 6197196325389.945, "dur": 39.556, + "args": { + "External id": 24521,"Sequence number": 479811, "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": 2338707, "tid": 2338707, "ts": 6197196325389.945, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6197196325411.494, "dur": 12.352, + "args": { + "External id": 24522,"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": 2338707, "tid": 2338707, + "ts": 6197196325418.276, "dur": 5.349, + "args": { + "External id": 24523,"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": 2338707, "tid": 2338707, + "ts": 6197196325507.552, "dur": 86.641, + "args": { + "External id": 24524,"Record function id": 0, "Ev Idx": 13840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6197196325596.236, "dur": 1374.898, + "args": { + "External id": 24525,"Record function id": 0, "Ev Idx": 13841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197196325640.281, "dur": 1314.598, + "args": { + "External id": 24526,"Sequence number": 479812, "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": 2338707, "tid": 2338707, "ts": 6197196325640.281, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6197196325740.550, "dur": 60.575, + "args": { + "External id": 24527,"kernel_hash": "cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/du/cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs.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": 2338707, "tid": 2338707, + "ts": 6197196325818.928, "dur": 120.240, + "args": { + "External id": 24528,"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": 2338707, "tid": 2338707, + "ts": 6197196325953.528, "dur": 43.760, + "args": { + "External id": 24529,"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": 2338707, "tid": 2338707, + "ts": 6197196326007.766, "dur": 33.371, + "args": { + "External id": 24530,"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": 2338707, "tid": 2338707, + "ts": 6197196326132.287, "dur": 39.917, + "args": { + "External id": 24531,"kernel_hash": "cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5", "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/jw/cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5.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": 2338707, "tid": 2338707, + "ts": 6197196326200.080, "dur": 22.470, + "args": { + "External id": 24532,"kernel_hash": "cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi", "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/xw/cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi.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": 2338707, "tid": 2338707, + "ts": 6197196326251.323, "dur": 157.226, + "args": { + "External id": 24533,"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": 2338707, "tid": 2338707, + "ts": 6197196326312.180, "dur": 14.250, + "args": { + "External id": 24534,"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": 2338707, "tid": 2338707, + "ts": 6197196326318.679, "dur": 6.890, + "args": { + "External id": 24535,"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": 2338707, "tid": 2338707, + "ts": 6197196326330.384, "dur": 5.261, + "args": { + "External id": 24536,"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": 2338707, "tid": 2338707, + "ts": 6197196326337.342, "dur": 1.127, + "args": { + "External id": 24537,"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": 2338707, "tid": 2338707, + "ts": 6197196326341.601, "dur": 6.817, + "args": { + "External id": 24538,"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": 2338707, "tid": 2338707, + "ts": 6197196326421.332, "dur": 69.744, + "args": { + "External id": 24539,"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": 2338707, "tid": 2338707, + "ts": 6197196326527.054, "dur": 35.741, + "args": { + "External id": 24540,"kernel_hash": "cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/dm/cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43.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": 2338707, "tid": 2338707, + "ts": 6197196326574.077, "dur": 50.226, + "args": { + "External id": 24541,"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": 2338707, "tid": 2338707, + "ts": 6197196326637.390, "dur": 40.906, + "args": { + "External id": 24542,"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": 2338707, "tid": 2338707, + "ts": 6197196326721.863, "dur": 47.117, + "args": { + "External id": 24543,"kernel_hash": "cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/b7/cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu.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": 2338707, "tid": 2338707, + "ts": 6197196326778.908, "dur": 47.483, + "args": { + "External id": 24544,"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": 2338707, "tid": 2338707, + "ts": 6197196326850.040, "dur": 23.613, + "args": { + "External id": 24545,"kernel_hash": "cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/gi/cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb.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": 2338707, "tid": 2338707, + "ts": 6197196327050.199, "dur": 140.143, + "args": { + "External id": 24546,"Record function id": 0, "Ev Idx": 13862 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6197196327284.556, "dur": 55.595, + "args": { + "External id": 24547,"Record function id": 0, "Ev Idx": 13863 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.23)", "pid": 2338707, "tid": 2338707, + "ts": 6197196327351.600, "dur": 32203.937, + "args": { + "External id": 24548,"Record function id": 0, "Ev Idx": 13864 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.23)", "pid": 2338707, "tid": 2338707, + "ts": 6197196327362.019, "dur": 1146.886, + "args": { + "External id": 24549,"Record function id": 0, "Ev Idx": 13865 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6197196327466.889, "dur": 10.772, + "args": { + "External id": 24550,"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": 2338707, "tid": 2338707, + "ts": 6197196327497.840, "dur": 43.784, + "args": { + "External id": 24551,"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": 2338707, "tid": 2338707, + "ts": 6197196327505.495, "dur": 2.990, + "args": { + "External id": 24552,"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": 2338707, "tid": 2338707, + "ts": 6197196327513.400, "dur": 0.615, + "args": { + "External id": 24553,"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": 2338707, "tid": 2338707, + "ts": 6197196327515.695, "dur": 0.388, + "args": { + "External id": 24554,"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": 2338707, "tid": 2338707, + "ts": 6197196327517.955, "dur": 0.591, + "args": { + "External id": 24555,"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": 2338707, "tid": 2338707, + "ts": 6197196327522.374, "dur": 0.491, + "args": { + "External id": 24556,"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": 2338707, "tid": 2338707, + "ts": 6197196327523.981, "dur": 0.762, + "args": { + "External id": 24557,"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": 2338707, "tid": 2338707, + "ts": 6197196327526.584, "dur": 4.171, + "args": { + "External id": 24558,"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": 2338707, "tid": 2338707, + "ts": 6197196327532.330, "dur": 0.355, + "args": { + "External id": 24559,"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": 2338707, "tid": 2338707, + "ts": 6197196327534.186, "dur": 0.307, + "args": { + "External id": 24560,"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": 2338707, "tid": 2338707, + "ts": 6197196327555.836, "dur": 65.608, + "args": { + "External id": 24561,"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": 2338707, "tid": 2338707, + "ts": 6197196327660.864, "dur": 202.950, + "args": { + "External id": 24562,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2338707, + "ts": 6197196327673.991, "dur": 4.525, + "args": { + "External id": 24563,"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": 2338707, "tid": 2338707, + "ts": 6197196327685.080, "dur": 12.710, + "args": { + "External id": 24564,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2338707, + "ts": 6197196327691.108, "dur": 6.186, + "args": { + "External id": 24565,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2338707, + "ts": 6197196327695.175, "dur": 0.690, + "args": { + "External id": 24566,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197196327726.533, "dur": 36.043, + "args": { + "External id": 24567,"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": 2338707, "tid": 2338707, + "ts": 6197196327729.114, "dur": 3.201, + "args": { + "External id": 24568,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197196327734.535, "dur": 0.575, + "args": { + "External id": 24569,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2338707, + "ts": 6197196327736.856, "dur": 0.495, + "args": { + "External id": 24570,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2338707, + "ts": 6197196327741.430, "dur": 2.890, + "args": { + "External id": 24571,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2338707, + "ts": 6197196327746.273, "dur": 0.547, + "args": { + "External id": 24572,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2338707, + "ts": 6197196327748.808, "dur": 0.407, + "args": { + "External id": 24573,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2338707, + "ts": 6197196327751.971, "dur": 0.828, + "args": { + "External id": 24574,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2338707, + "ts": 6197196327754.575, "dur": 0.600, + "args": { + "External id": 24575,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2338707, + "ts": 6197196327756.438, "dur": 1.640, + "args": { + "External id": 24576,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2338707, + "ts": 6197196327810.029, "dur": 43.980, + "args": { + "External id": 24577,"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": 2338707, "tid": 2338707, + "ts": 6197196327929.901, "dur": 461.328, + "args": { + "External id": 24578,"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": 2338707, "tid": 2338707, + "ts": 6197196327966.294, "dur": 418.364, + "args": { + "External id": 24579,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2338707, + "ts": 6197196327980.429, "dur": 396.758, + "args": { + "External id": 24580,"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": 2338707, "tid": 2338707, + "ts": 6197196328423.719, "dur": 2.713, + "args": { + "External id": 24581,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.23)", "pid": 2338707, "tid": 2338707, + "ts": 6197196328533.504, "dur": 30794.557, + "args": { + "External id": 24582,"Record function id": 0, "Ev Idx": 13898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6197196328656.475, "dur": 7.461, + "args": { + "External id": 24583,"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": 2338707, "tid": 2338707, + "ts": 6197196328668.208, "dur": 1.388, + "args": { + "External id": 24584,"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": 2338707, "tid": 2338707, + "ts": 6197196328671.782, "dur": 4.243, + "args": { + "External id": 24585,"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": 2338707, "tid": 2338707, + "ts": 6197196328677.997, "dur": 1.271, + "args": { + "External id": 24586,"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": 2338707, "tid": 2338707, + "ts": 6197196328680.916, "dur": 0.885, + "args": { + "External id": 24587,"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": 2338707, "tid": 2338707, + "ts": 6197196328683.421, "dur": 1.044, + "args": { + "External id": 24588,"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": 2338707, "tid": 2338707, + "ts": 6197196328686.268, "dur": 1.056, + "args": { + "External id": 24589,"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": 2338707, "tid": 2338707, + "ts": 6197196328689.401, "dur": 2.398, + "args": { + "External id": 24590,"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": 2338707, "tid": 2338707, + "ts": 6197196328693.356, "dur": 0.883, + "args": { + "External id": 24591,"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": 2338707, "tid": 2338707, + "ts": 6197196328698.304, "dur": 17.910, + "args": { + "External id": 24592,"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": 2338707, "tid": 2338707, + "ts": 6197196328740.757, "dur": 30537.457, + "args": { + "External id": 24593,"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": 2338707, "tid": 2338707, + "ts": 6197196328760.391, "dur": 30507.969, + "args": { + "External id": 24594,"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": 2338707, "tid": 2338707, + "ts": 6197196328779.414, "dur": 20.464, + "args": { + "External id": 24595,"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": 2338707, "tid": 2338707, + "ts": 6197196328804.298, "dur": 30420.663, + "args": { + "External id": 24596,"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": 2338707, "tid": 2338707, + "ts": 6197196328807.622, "dur": 30416.658, + "args": { + "External id": 24597,"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": 2338707, "tid": 2338707, + "ts": 6197196328815.577, "dur": 7.215, + "args": { + "External id": 24598,"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": 2338707, "tid": 2338707, + "ts": 6197196328824.742, "dur": 30396.011, + "args": { + "External id": 24599,"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": 2338707, "tid": 2338707, + "ts": 6197196359488.673, "dur": 40.004, + "args": { + "External id": 24600,"Sequence number": 479813, "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": 2338707, "tid": 2338707, "ts": 6197196359488.673, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6197196359513.836, "dur": 9.314, + "args": { + "External id": 24601,"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": 2338707, "tid": 2338707, + "ts": 6197196359517.877, "dur": 5.034, + "args": { + "External id": 24602,"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": 2338707, "tid": 2338707, + "ts": 6197196359603.290, "dur": 89.686, + "args": { + "External id": 24603,"Record function id": 0, "Ev Idx": 13919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6197196359694.686, "dur": 1341.508, + "args": { + "External id": 24604,"Record function id": 0, "Ev Idx": 13920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197196359759.408, "dur": 1261.159, + "args": { + "External id": 24605,"Sequence number": 479814, "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": 2338707, "tid": 2338707, "ts": 6197196359759.408, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6197196359842.546, "dur": 59.250, + "args": { + "External id": 24606,"kernel_hash": "cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/du/cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs.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": 2338707, "tid": 2338707, + "ts": 6197196359917.092, "dur": 123.038, + "args": { + "External id": 24607,"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": 2338707, "tid": 2338707, + "ts": 6197196360093.856, "dur": 53.638, + "args": { + "External id": 24608,"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": 2338707, "tid": 2338707, + "ts": 6197196360160.905, "dur": 35.532, + "args": { + "External id": 24609,"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": 2338707, "tid": 2338707, + "ts": 6197196360231.233, "dur": 34.191, + "args": { + "External id": 24610,"kernel_hash": "cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5", "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/jw/cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5.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": 2338707, "tid": 2338707, + "ts": 6197196360288.711, "dur": 23.048, + "args": { + "External id": 24611,"kernel_hash": "cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi", "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/xw/cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi.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": 2338707, "tid": 2338707, + "ts": 6197196360339.621, "dur": 159.394, + "args": { + "External id": 24612,"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": 2338707, "tid": 2338707, + "ts": 6197196360405.402, "dur": 13.494, + "args": { + "External id": 24613,"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": 2338707, "tid": 2338707, + "ts": 6197196360411.785, "dur": 6.072, + "args": { + "External id": 24614,"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": 2338707, "tid": 2338707, + "ts": 6197196360422.327, "dur": 4.701, + "args": { + "External id": 24615,"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": 2338707, "tid": 2338707, + "ts": 6197196360428.880, "dur": 1.224, + "args": { + "External id": 24616,"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": 2338707, "tid": 2338707, + "ts": 6197196360432.977, "dur": 6.135, + "args": { + "External id": 24617,"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": 2338707, "tid": 2338707, + "ts": 6197196360512.285, "dur": 59.875, + "args": { + "External id": 24618,"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": 2338707, "tid": 2338707, + "ts": 6197196360607.501, "dur": 35.506, + "args": { + "External id": 24619,"kernel_hash": "cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/dm/cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43.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": 2338707, "tid": 2338707, + "ts": 6197196360655.332, "dur": 68.202, + "args": { + "External id": 24620,"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": 2338707, "tid": 2338707, + "ts": 6197196360739.904, "dur": 44.265, + "args": { + "External id": 24621,"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": 2338707, "tid": 2338707, + "ts": 6197196360812.330, "dur": 34.048, + "args": { + "External id": 24622,"kernel_hash": "cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/b7/cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu.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": 2338707, "tid": 2338707, + "ts": 6197196360855.667, "dur": 40.751, + "args": { + "External id": 24623,"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": 2338707, "tid": 2338707, + "ts": 6197196360919.292, "dur": 21.298, + "args": { + "External id": 24624,"kernel_hash": "cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/gi/cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb.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": 2338707, "tid": 2338707, + "ts": 6197196361154.065, "dur": 96.923, + "args": { + "External id": 24625,"Record function id": 0, "Ev Idx": 13941 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6197196361344.080, "dur": 55.673, + "args": { + "External id": 24626,"Record function id": 0, "Ev Idx": 13942 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.24)", "pid": 2338707, "tid": 2338707, + "ts": 6197196361409.716, "dur": 33569.142, + "args": { + "External id": 24627,"Record function id": 0, "Ev Idx": 13943 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.24)", "pid": 2338707, "tid": 2338707, + "ts": 6197196361420.286, "dur": 1150.940, + "args": { + "External id": 24628,"Record function id": 0, "Ev Idx": 13944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6197196361519.305, "dur": 10.042, + "args": { + "External id": 24629,"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": 2338707, "tid": 2338707, + "ts": 6197196361544.835, "dur": 42.792, + "args": { + "External id": 24630,"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": 2338707, "tid": 2338707, + "ts": 6197196361552.440, "dur": 2.720, + "args": { + "External id": 24631,"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": 2338707, "tid": 2338707, + "ts": 6197196361559.476, "dur": 0.512, + "args": { + "External id": 24632,"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": 2338707, "tid": 2338707, + "ts": 6197196361561.588, "dur": 0.585, + "args": { + "External id": 24633,"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": 2338707, "tid": 2338707, + "ts": 6197196361563.447, "dur": 0.723, + "args": { + "External id": 24634,"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": 2338707, "tid": 2338707, + "ts": 6197196361568.191, "dur": 0.758, + "args": { + "External id": 24635,"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": 2338707, "tid": 2338707, + "ts": 6197196361570.501, "dur": 0.656, + "args": { + "External id": 24636,"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": 2338707, "tid": 2338707, + "ts": 6197196361572.487, "dur": 3.535, + "args": { + "External id": 24637,"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": 2338707, "tid": 2338707, + "ts": 6197196361577.873, "dur": 0.653, + "args": { + "External id": 24638,"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": 2338707, "tid": 2338707, + "ts": 6197196361580.364, "dur": 0.375, + "args": { + "External id": 24639,"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": 2338707, "tid": 2338707, + "ts": 6197196361601.594, "dur": 65.146, + "args": { + "External id": 24640,"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": 2338707, "tid": 2338707, + "ts": 6197196361723.504, "dur": 146.763, + "args": { + "External id": 24641,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2338707, + "ts": 6197196361737.610, "dur": 6.131, + "args": { + "External id": 24642,"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": 2338707, "tid": 2338707, + "ts": 6197196361750.308, "dur": 13.738, + "args": { + "External id": 24643,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2338707, + "ts": 6197196361756.244, "dur": 7.332, + "args": { + "External id": 24644,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2338707, + "ts": 6197196361760.893, "dur": 0.802, + "args": { + "External id": 24645,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197196361772.628, "dur": 33.063, + "args": { + "External id": 24646,"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": 2338707, "tid": 2338707, + "ts": 6197196361775.635, "dur": 2.485, + "args": { + "External id": 24647,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197196361779.770, "dur": 0.773, + "args": { + "External id": 24648,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2338707, + "ts": 6197196361781.942, "dur": 0.373, + "args": { + "External id": 24649,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2338707, + "ts": 6197196361785.562, "dur": 2.969, + "args": { + "External id": 24650,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2338707, + "ts": 6197196361790.065, "dur": 0.297, + "args": { + "External id": 24651,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2338707, + "ts": 6197196361792.115, "dur": 0.492, + "args": { + "External id": 24652,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2338707, + "ts": 6197196361795.402, "dur": 0.813, + "args": { + "External id": 24653,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2338707, + "ts": 6197196361797.845, "dur": 0.363, + "args": { + "External id": 24654,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2338707, + "ts": 6197196361799.504, "dur": 1.809, + "args": { + "External id": 24655,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2338707, + "ts": 6197196361821.131, "dur": 39.810, + "args": { + "External id": 24656,"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": 2338707, "tid": 2338707, + "ts": 6197196361934.992, "dur": 511.820, + "args": { + "External id": 24657,"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": 2338707, "tid": 2338707, + "ts": 6197196361975.347, "dur": 464.477, + "args": { + "External id": 24658,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2338707, + "ts": 6197196361987.930, "dur": 443.674, + "args": { + "External id": 24659,"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": 2338707, "tid": 2338707, + "ts": 6197196362479.615, "dur": 2.973, + "args": { + "External id": 24660,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.24)", "pid": 2338707, "tid": 2338707, + "ts": 6197196362595.626, "dur": 32159.420, + "args": { + "External id": 24661,"Record function id": 0, "Ev Idx": 13977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6197196362737.986, "dur": 8.634, + "args": { + "External id": 24662,"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": 2338707, "tid": 2338707, + "ts": 6197196362756.721, "dur": 1.232, + "args": { + "External id": 24663,"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": 2338707, "tid": 2338707, + "ts": 6197196362759.841, "dur": 3.893, + "args": { + "External id": 24664,"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": 2338707, "tid": 2338707, + "ts": 6197196362768.203, "dur": 0.878, + "args": { + "External id": 24665,"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": 2338707, "tid": 2338707, + "ts": 6197196362770.667, "dur": 1.199, + "args": { + "External id": 24666,"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": 2338707, "tid": 2338707, + "ts": 6197196362773.331, "dur": 0.770, + "args": { + "External id": 24667,"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": 2338707, "tid": 2338707, + "ts": 6197196362775.789, "dur": 0.979, + "args": { + "External id": 24668,"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": 2338707, "tid": 2338707, + "ts": 6197196362781.014, "dur": 2.441, + "args": { + "External id": 24669,"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": 2338707, "tid": 2338707, + "ts": 6197196362785.222, "dur": 0.776, + "args": { + "External id": 24670,"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": 2338707, "tid": 2338707, + "ts": 6197196362787.954, "dur": 0.804, + "args": { + "External id": 24671,"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": 2338707, "tid": 2338707, + "ts": 6197196362811.891, "dur": 31882.118, + "args": { + "External id": 24672,"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": 2338707, "tid": 2338707, + "ts": 6197196362830.635, "dur": 31854.353, + "args": { + "External id": 24673,"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": 2338707, "tid": 2338707, + "ts": 6197196362847.823, "dur": 18.751, + "args": { + "External id": 24674,"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": 2338707, "tid": 2338707, + "ts": 6197196362873.481, "dur": 31771.090, + "args": { + "External id": 24675,"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": 2338707, "tid": 2338707, + "ts": 6197196362877.060, "dur": 31766.843, + "args": { + "External id": 24676,"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": 2338707, "tid": 2338707, + "ts": 6197196362884.948, "dur": 7.394, + "args": { + "External id": 24677,"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": 2338707, "tid": 2338707, + "ts": 6197196362894.461, "dur": 31746.065, + "args": { + "External id": 24678,"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": 2338707, "tid": 2338707, + "ts": 6197196394915.600, "dur": 35.544, + "args": { + "External id": 24679,"Sequence number": 479815, "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": 2338707, "tid": 2338707, "ts": 6197196394915.600, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6197196394935.181, "dur": 10.328, + "args": { + "External id": 24680,"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": 2338707, "tid": 2338707, + "ts": 6197196394939.808, "dur": 5.413, + "args": { + "External id": 24681,"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": 2338707, "tid": 2338707, + "ts": 6197196395025.271, "dur": 116.629, + "args": { + "External id": 24682,"Record function id": 0, "Ev Idx": 13998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6197196395145.302, "dur": 1315.268, + "args": { + "External id": 24683,"Record function id": 0, "Ev Idx": 13999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197196395193.467, "dur": 1251.304, + "args": { + "External id": 24684,"Sequence number": 479816, "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": 2338707, "tid": 2338707, "ts": 6197196395193.467, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6197196395278.221, "dur": 61.703, + "args": { + "External id": 24685,"kernel_hash": "cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/du/cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs.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": 2338707, "tid": 2338707, + "ts": 6197196395355.355, "dur": 122.058, + "args": { + "External id": 24686,"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": 2338707, "tid": 2338707, + "ts": 6197196395491.436, "dur": 41.579, + "args": { + "External id": 24687,"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": 2338707, "tid": 2338707, + "ts": 6197196395543.517, "dur": 32.903, + "args": { + "External id": 24688,"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": 2338707, "tid": 2338707, + "ts": 6197196395606.104, "dur": 33.971, + "args": { + "External id": 24689,"kernel_hash": "cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5", "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/jw/cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5.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": 2338707, "tid": 2338707, + "ts": 6197196395664.487, "dur": 26.548, + "args": { + "External id": 24690,"kernel_hash": "cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi", "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/xw/cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi.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": 2338707, "tid": 2338707, + "ts": 6197196395738.110, "dur": 152.823, + "args": { + "External id": 24691,"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": 2338707, "tid": 2338707, + "ts": 6197196395796.098, "dur": 14.317, + "args": { + "External id": 24692,"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": 2338707, "tid": 2338707, + "ts": 6197196395801.935, "dur": 7.130, + "args": { + "External id": 24693,"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": 2338707, "tid": 2338707, + "ts": 6197196395813.715, "dur": 4.669, + "args": { + "External id": 24694,"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": 2338707, "tid": 2338707, + "ts": 6197196395820.768, "dur": 1.051, + "args": { + "External id": 24695,"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": 2338707, "tid": 2338707, + "ts": 6197196395824.612, "dur": 6.047, + "args": { + "External id": 24696,"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": 2338707, "tid": 2338707, + "ts": 6197196395904.031, "dur": 61.468, + "args": { + "External id": 24697,"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": 2338707, "tid": 2338707, + "ts": 6197196396003.323, "dur": 34.555, + "args": { + "External id": 24698,"kernel_hash": "cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/dm/cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43.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": 2338707, "tid": 2338707, + "ts": 6197196396050.857, "dur": 94.403, + "args": { + "External id": 24699,"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": 2338707, "tid": 2338707, + "ts": 6197196396161.457, "dur": 39.880, + "args": { + "External id": 24700,"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": 2338707, "tid": 2338707, + "ts": 6197196396234.175, "dur": 35.200, + "args": { + "External id": 24701,"kernel_hash": "cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/b7/cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu.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": 2338707, "tid": 2338707, + "ts": 6197196396278.645, "dur": 42.162, + "args": { + "External id": 24702,"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": 2338707, "tid": 2338707, + "ts": 6197196396343.984, "dur": 23.286, + "args": { + "External id": 24703,"kernel_hash": "cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/gi/cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb.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": 2338707, "tid": 2338707, + "ts": 6197196396538.820, "dur": 90.891, + "args": { + "External id": 24704,"Record function id": 0, "Ev Idx": 14020 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6197196396740.686, "dur": 58.175, + "args": { + "External id": 24705,"Record function id": 0, "Ev Idx": 14021 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.25)", "pid": 2338707, "tid": 2338707, + "ts": 6197196396809.651, "dur": 31630.159, + "args": { + "External id": 24706,"Record function id": 0, "Ev Idx": 14022 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.25)", "pid": 2338707, "tid": 2338707, + "ts": 6197196396819.752, "dur": 1112.119, + "args": { + "External id": 24707,"Record function id": 0, "Ev Idx": 14023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6197196396921.195, "dur": 10.995, + "args": { + "External id": 24708,"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": 2338707, "tid": 2338707, + "ts": 6197196396947.436, "dur": 42.185, + "args": { + "External id": 24709,"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": 2338707, "tid": 2338707, + "ts": 6197196396954.425, "dur": 3.042, + "args": { + "External id": 24710,"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": 2338707, "tid": 2338707, + "ts": 6197196396961.937, "dur": 0.472, + "args": { + "External id": 24711,"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": 2338707, "tid": 2338707, + "ts": 6197196396964.256, "dur": 0.463, + "args": { + "External id": 24712,"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": 2338707, "tid": 2338707, + "ts": 6197196396965.837, "dur": 0.801, + "args": { + "External id": 24713,"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": 2338707, "tid": 2338707, + "ts": 6197196396970.230, "dur": 0.739, + "args": { + "External id": 24714,"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": 2338707, "tid": 2338707, + "ts": 6197196396972.374, "dur": 0.678, + "args": { + "External id": 24715,"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": 2338707, "tid": 2338707, + "ts": 6197196396974.481, "dur": 4.185, + "args": { + "External id": 24716,"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": 2338707, "tid": 2338707, + "ts": 6197196396980.156, "dur": 0.469, + "args": { + "External id": 24717,"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": 2338707, "tid": 2338707, + "ts": 6197196396982.214, "dur": 0.665, + "args": { + "External id": 24718,"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": 2338707, "tid": 2338707, + "ts": 6197196397003.756, "dur": 106.444, + "args": { + "External id": 24719,"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": 2338707, "tid": 2338707, + "ts": 6197196397154.880, "dur": 148.321, + "args": { + "External id": 24720,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2338707, + "ts": 6197196397168.893, "dur": 5.443, + "args": { + "External id": 24721,"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": 2338707, "tid": 2338707, + "ts": 6197196397181.090, "dur": 13.996, + "args": { + "External id": 24722,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2338707, + "ts": 6197196397186.993, "dur": 7.607, + "args": { + "External id": 24723,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2338707, + "ts": 6197196397191.987, "dur": 0.816, + "args": { + "External id": 24724,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197196397203.600, "dur": 33.036, + "args": { + "External id": 24725,"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": 2338707, "tid": 2338707, + "ts": 6197196397205.732, "dur": 2.300, + "args": { + "External id": 24726,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197196397210.051, "dur": 0.509, + "args": { + "External id": 24727,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2338707, + "ts": 6197196397212.156, "dur": 0.484, + "args": { + "External id": 24728,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2338707, + "ts": 6197196397216.583, "dur": 2.729, + "args": { + "External id": 24729,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2338707, + "ts": 6197196397220.616, "dur": 0.391, + "args": { + "External id": 24730,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2338707, + "ts": 6197196397222.331, "dur": 0.395, + "args": { + "External id": 24731,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2338707, + "ts": 6197196397226.353, "dur": 0.499, + "args": { + "External id": 24732,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2338707, + "ts": 6197196397228.230, "dur": 0.458, + "args": { + "External id": 24733,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2338707, + "ts": 6197196397230.083, "dur": 2.194, + "args": { + "External id": 24734,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2338707, + "ts": 6197196397252.383, "dur": 41.537, + "args": { + "External id": 24735,"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": 2338707, "tid": 2338707, + "ts": 6197196397368.848, "dur": 439.093, + "args": { + "External id": 24736,"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": 2338707, "tid": 2338707, + "ts": 6197196397405.544, "dur": 396.059, + "args": { + "External id": 24737,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2338707, + "ts": 6197196397418.208, "dur": 376.166, + "args": { + "External id": 24738,"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": 2338707, "tid": 2338707, + "ts": 6197196397838.257, "dur": 6.813, + "args": { + "External id": 24739,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.25)", "pid": 2338707, "tid": 2338707, + "ts": 6197196397956.877, "dur": 30254.716, + "args": { + "External id": 24740,"Record function id": 0, "Ev Idx": 14056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6197196398119.970, "dur": 8.208, + "args": { + "External id": 24741,"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": 2338707, "tid": 2338707, + "ts": 6197196398133.253, "dur": 1.046, + "args": { + "External id": 24742,"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": 2338707, "tid": 2338707, + "ts": 6197196398136.345, "dur": 4.118, + "args": { + "External id": 24743,"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": 2338707, "tid": 2338707, + "ts": 6197196398142.412, "dur": 0.815, + "args": { + "External id": 24744,"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": 2338707, "tid": 2338707, + "ts": 6197196398144.761, "dur": 1.207, + "args": { + "External id": 24745,"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": 2338707, "tid": 2338707, + "ts": 6197196398147.377, "dur": 1.184, + "args": { + "External id": 24746,"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": 2338707, "tid": 2338707, + "ts": 6197196398152.500, "dur": 1.276, + "args": { + "External id": 24747,"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": 2338707, "tid": 2338707, + "ts": 6197196398155.986, "dur": 2.140, + "args": { + "External id": 24748,"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": 2338707, "tid": 2338707, + "ts": 6197196398159.656, "dur": 0.876, + "args": { + "External id": 24749,"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": 2338707, "tid": 2338707, + "ts": 6197196398162.117, "dur": 0.940, + "args": { + "External id": 24750,"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": 2338707, "tid": 2338707, + "ts": 6197196398187.756, "dur": 29973.088, + "args": { + "External id": 24751,"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": 2338707, "tid": 2338707, + "ts": 6197196398206.606, "dur": 29945.134, + "args": { + "External id": 24752,"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": 2338707, "tid": 2338707, + "ts": 6197196398226.951, "dur": 20.135, + "args": { + "External id": 24753,"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": 2338707, "tid": 2338707, + "ts": 6197196398251.343, "dur": 29858.143, + "args": { + "External id": 24754,"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": 2338707, "tid": 2338707, + "ts": 6197196398254.328, "dur": 29854.599, + "args": { + "External id": 24755,"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": 2338707, "tid": 2338707, + "ts": 6197196398260.863, "dur": 6.132, + "args": { + "External id": 24756,"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": 2338707, "tid": 2338707, + "ts": 6197196398269.025, "dur": 29835.781, + "args": { + "External id": 24757,"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": 2338707, "tid": 2338707, + "ts": 6197196428377.034, "dur": 34.737, + "args": { + "External id": 24758,"Sequence number": 479817, "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": 2338707, "tid": 2338707, "ts": 6197196428377.034, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6197196428396.423, "dur": 9.688, + "args": { + "External id": 24759,"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": 2338707, "tid": 2338707, + "ts": 6197196428400.474, "dur": 5.349, + "args": { + "External id": 24760,"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": 2338707, "tid": 2338707, + "ts": 6197196428486.742, "dur": 84.750, + "args": { + "External id": 24761,"Record function id": 0, "Ev Idx": 14077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6197196428573.110, "dur": 1321.769, + "args": { + "External id": 24762,"Record function id": 0, "Ev Idx": 14078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197196428620.102, "dur": 1258.630, + "args": { + "External id": 24763,"Sequence number": 479818, "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": 2338707, "tid": 2338707, "ts": 6197196428620.102, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6197196428695.552, "dur": 79.395, + "args": { + "External id": 24764,"kernel_hash": "cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/du/cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs.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": 2338707, "tid": 2338707, + "ts": 6197196428793.323, "dur": 121.974, + "args": { + "External id": 24765,"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": 2338707, "tid": 2338707, + "ts": 6197196428928.506, "dur": 42.427, + "args": { + "External id": 24766,"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": 2338707, "tid": 2338707, + "ts": 6197196428981.764, "dur": 33.953, + "args": { + "External id": 24767,"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": 2338707, "tid": 2338707, + "ts": 6197196429047.744, "dur": 74.639, + "args": { + "External id": 24768,"kernel_hash": "cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5", "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/jw/cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5.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": 2338707, "tid": 2338707, + "ts": 6197196429153.592, "dur": 22.796, + "args": { + "External id": 24769,"kernel_hash": "cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi", "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/xw/cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi.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": 2338707, "tid": 2338707, + "ts": 6197196429202.201, "dur": 157.193, + "args": { + "External id": 24770,"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": 2338707, "tid": 2338707, + "ts": 6197196429263.546, "dur": 14.319, + "args": { + "External id": 24771,"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": 2338707, "tid": 2338707, + "ts": 6197196429270.295, "dur": 6.479, + "args": { + "External id": 24772,"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": 2338707, "tid": 2338707, + "ts": 6197196429280.962, "dur": 4.792, + "args": { + "External id": 24773,"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": 2338707, "tid": 2338707, + "ts": 6197196429287.149, "dur": 1.331, + "args": { + "External id": 24774,"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": 2338707, "tid": 2338707, + "ts": 6197196429291.534, "dur": 6.234, + "args": { + "External id": 24775,"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": 2338707, "tid": 2338707, + "ts": 6197196429372.188, "dur": 65.099, + "args": { + "External id": 24776,"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": 2338707, "tid": 2338707, + "ts": 6197196429472.569, "dur": 36.438, + "args": { + "External id": 24777,"kernel_hash": "cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/dm/cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43.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": 2338707, "tid": 2338707, + "ts": 6197196429520.185, "dur": 50.435, + "args": { + "External id": 24778,"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": 2338707, "tid": 2338707, + "ts": 6197196429582.793, "dur": 39.902, + "args": { + "External id": 24779,"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": 2338707, "tid": 2338707, + "ts": 6197196429650.458, "dur": 31.369, + "args": { + "External id": 24780,"kernel_hash": "cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/b7/cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu.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": 2338707, "tid": 2338707, + "ts": 6197196429690.446, "dur": 59.474, + "args": { + "External id": 24781,"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": 2338707, "tid": 2338707, + "ts": 6197196429775.813, "dur": 22.276, + "args": { + "External id": 24782,"kernel_hash": "cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/gi/cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb.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": 2338707, "tid": 2338707, + "ts": 6197196429971.048, "dur": 40.188, + "args": { + "External id": 24783,"Record function id": 0, "Ev Idx": 14099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197196430220.345, "dur": 342.545, + "args": { + "External id": 24784,"Sequence number": 479819, "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": 2338707, "tid": 2338707, "ts": 6197196430220.345, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6197196430258.797, "dur": 10.631, + "args": { + "External id": 24785,"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": 2338707, "tid": 2338707, + "ts": 6197196430261.598, "dur": 7.297, + "args": { + "External id": 24786,"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": 2338707, "tid": 2338707, + "ts": 6197196430282.312, "dur": 16.086, + "args": { + "External id": 24787,"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": 2338707, "tid": 2338707, + "ts": 6197196430286.406, "dur": 11.366, + "args": { + "External id": 24788,"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": 2338707, "tid": 2338707, + "ts": 6197196430310.297, "dur": 5.478, + "args": { + "External id": 24789,"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": 2338707, "tid": 2338707, + "ts": 6197196430539.114, "dur": 7.239, + "args": { + "External id": 24790,"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": 2338707, "tid": 2338707, + "ts": 6197196430542.672, "dur": 3.298, + "args": { + "External id": 24791,"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": 2338707, "tid": 2338707, + "ts": 6197196430596.700, "dur": 191.199, + "args": { + "External id": 24792,"Sequence number": 479820, "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": 2338707, "tid": 2338707, + "ts": 6197196430599.775, "dur": 17.591, + "args": { + "External id": 24793,"Sequence number": 479820, "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": 2338707, "tid": 2338707, "ts": 6197196430599.775, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6197196430605.947, "dur": 9.142, + "args": { + "External id": 24794,"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": 2338707, "tid": 2338707, + "ts": 6197196430611.864, "dur": 2.850, + "args": { + "External id": 24795,"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": 2338707, "tid": 2338707, + "ts": 6197196430620.189, "dur": 167.171, + "args": { + "External id": 24796,"Sequence number": 479821, "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": 2338707, "tid": 2338707, + "ts": 6197196430623.545, "dur": 5.376, + "args": { + "External id": 24797,"Sequence number": 479821, "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": 2338707, "tid": 2338707, + "ts": 6197196430624.420, "dur": 4.348, + "args": { + "External id": 24798,"Sequence number": 479821, "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": 2338707, "tid": 2338707, "ts": 6197196430624.420, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6197196430630.907, "dur": 136.141, + "args": { + "External id": 24799,"Sequence number": 479822, "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": 2338707, "tid": 2338707, "ts": 6197196430630.907, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6197196430775.387, "dur": 10.623, + "args": { + "External id": 24800,"Sequence number": 479823, "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": 2338707, "tid": 2338707, "ts": 6197196430775.387, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338707, "tid": 2338707, + "ts": 6197196430801.710, "dur": 89.696, + "args": { + "External id": 24801,"Sequence number": 479824, "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": 2338707, "tid": 2338707, + "ts": 6197196430803.141, "dur": 11.421, + "args": { + "External id": 24802,"Sequence number": 479824, "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": 2338707, "tid": 2338707, "ts": 6197196430803.141, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6197196430805.784, "dur": 7.109, + "args": { + "External id": 24803,"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": 2338707, "tid": 2338707, + "ts": 6197196430810.821, "dur": 1.714, + "args": { + "External id": 24804,"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": 2338707, "tid": 2338707, + "ts": 6197196430815.370, "dur": 75.698, + "args": { + "External id": 24805,"Sequence number": 479825, "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": 2338707, "tid": 2338707, + "ts": 6197196430816.744, "dur": 5.897, + "args": { + "External id": 24806,"Sequence number": 479825, "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": 2338707, "tid": 2338707, + "ts": 6197196430817.841, "dur": 4.624, + "args": { + "External id": 24807,"Sequence number": 479825, "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": 2338707, "tid": 2338707, "ts": 6197196430817.841, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6197196430823.319, "dur": 59.867, + "args": { + "External id": 24808,"Sequence number": 479826, "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": 2338707, "tid": 2338707, "ts": 6197196430823.319, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6197196430885.782, "dur": 4.890, + "args": { + "External id": 24809,"Sequence number": 479827, "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": 2338707, "tid": 2338707, "ts": 6197196430885.782, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338707, "tid": 2338707, + "ts": 6197196430901.125, "dur": 72.726, + "args": { + "External id": 24810,"Sequence number": 479828, "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": 2338707, "tid": 2338707, + "ts": 6197196430902.131, "dur": 6.595, + "args": { + "External id": 24811,"Sequence number": 479828, "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": 2338707, "tid": 2338707, "ts": 6197196430902.131, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6197196430904.358, "dur": 3.004, + "args": { + "External id": 24812,"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": 2338707, "tid": 2338707, + "ts": 6197196430906.572, "dur": 0.628, + "args": { + "External id": 24813,"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": 2338707, "tid": 2338707, + "ts": 6197196430911.942, "dur": 61.668, + "args": { + "External id": 24814,"Sequence number": 479829, "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": 2338707, "tid": 2338707, + "ts": 6197196430913.637, "dur": 5.432, + "args": { + "External id": 24815,"Sequence number": 479829, "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": 2338707, "tid": 2338707, + "ts": 6197196430914.507, "dur": 4.404, + "args": { + "External id": 24816,"Sequence number": 479829, "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": 2338707, "tid": 2338707, "ts": 6197196430914.507, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6197196430919.734, "dur": 44.581, + "args": { + "External id": 24817,"Sequence number": 479830, "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": 2338707, "tid": 2338707, "ts": 6197196430919.734, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6197196430966.597, "dur": 6.606, + "args": { + "External id": 24818,"Sequence number": 479831, "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": 2338707, "tid": 2338707, "ts": 6197196430966.597, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6197196431001.081, "dur": 4.528, + "args": { + "External id": 24819,"Sequence number": 479832, "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": 2338707, "tid": 2338707, + "ts": 6197196431002.149, "dur": 3.263, + "args": { + "External id": 24820,"Sequence number": 479832, "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": 2338707, "tid": 2338707, "ts": 6197196431002.149, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6197196431014.216, "dur": 4.663, + "args": { + "External id": 24821,"Sequence number": 479833, "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": 2338707, "tid": 2338707, + "ts": 6197196431016.027, "dur": 2.686, + "args": { + "External id": 24822,"Sequence number": 479833, "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": 2338707, "tid": 2338707, "ts": 6197196431016.027, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6197196431026.202, "dur": 5.068, + "args": { + "External id": 24823,"Sequence number": 479834, "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": 2338707, "tid": 2338707, + "ts": 6197196431027.310, "dur": 3.786, + "args": { + "External id": 24824,"Sequence number": 479834, "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": 2338707, "tid": 2338707, "ts": 6197196431027.310, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197196431118.364, "dur": 231.740, + "args": { + "External id": 24825,"Sequence number": 479835, "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": 2338707, "tid": 2338707, "ts": 6197196431118.364, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338707, "tid": 2338707, + "ts": 6197196431150.732, "dur": 12.839, + "args": { + "External id": 24826,"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": 2338707, "tid": 2338707, + "ts": 6197196431154.770, "dur": 8.133, + "args": { + "External id": 24827,"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": 2338707, "tid": 2338707, + "ts": 6197196431365.812, "dur": 135.412, + "args": { + "External id": 24828,"Sequence number": 479836, "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": 2338707, "tid": 2338707, "ts": 6197196431365.812, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338707, "tid": 2338707, + "ts": 6197196431383.198, "dur": 8.662, + "args": { + "External id": 24829,"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": 2338707, "tid": 2338707, + "ts": 6197196431386.498, "dur": 4.903, + "args": { + "External id": 24830,"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": 2338707, "tid": 2338707, + "ts": 6197196431536.292, "dur": 252.101, + "args": { + "External id": 24831,"Sequence number": 479837, "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": 2338707, "tid": 2338707, "ts": 6197196431536.292, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338707, "tid": 2338707, + "ts": 6197196431574.244, "dur": 176.886, + "args": { + "External id": 24832,"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": 2338707, "tid": 2338707, + "ts": 6197196431633.619, "dur": 9.035, + "args": { + "External id": 24833,"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": 2338707, "tid": 2338707, + "ts": 6197196431636.896, "dur": 5.259, + "args": { + "External id": 24834,"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": 2338707, "tid": 2338707, + "ts": 6197196431648.441, "dur": 5.089, + "args": { + "External id": 24835,"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": 2338707, "tid": 2338707, + "ts": 6197196431657.248, "dur": 0.960, + "args": { + "External id": 24836,"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": 2338707, "tid": 2338707, + "ts": 6197196431663.659, "dur": 4.732, + "args": { + "External id": 24837,"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": 2338707, "tid": 2338707, + "ts": 6197196431769.872, "dur": 6.503, + "args": { + "External id": 24838,"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": 2338707, "tid": 2338707, + "ts": 6197196431795.867, "dur": 7.324, + "args": { + "External id": 24839,"Sequence number": 479838, "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": 2338707, "tid": 2338707, + "ts": 6197196431797.447, "dur": 5.559, + "args": { + "External id": 24840,"Sequence number": 479838, "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": 2338707, "tid": 2338707, "ts": 6197196431797.447, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338707, "tid": 2338707, + "ts": 6197196431818.514, "dur": 141.627, + "args": { + "External id": 24841,"Sequence number": 479839, "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": 2338707, "tid": 2338707, + "ts": 6197196431820.280, "dur": 12.610, + "args": { + "External id": 24842,"Sequence number": 479839, "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": 2338707, "tid": 2338707, "ts": 6197196431820.280, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6197196431823.550, "dur": 7.970, + "args": { + "External id": 24843,"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": 2338707, "tid": 2338707, + "ts": 6197196431829.307, "dur": 1.883, + "args": { + "External id": 24844,"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": 2338707, "tid": 2338707, + "ts": 6197196431834.467, "dur": 125.269, + "args": { + "External id": 24845,"Sequence number": 479840, "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": 2338707, "tid": 2338707, + "ts": 6197196431836.540, "dur": 4.013, + "args": { + "External id": 24846,"Sequence number": 479840, "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": 2338707, "tid": 2338707, + "ts": 6197196431837.565, "dur": 2.782, + "args": { + "External id": 24847,"Sequence number": 479840, "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": 2338707, "tid": 2338707, "ts": 6197196431837.565, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6197196431844.023, "dur": 106.723, + "args": { + "External id": 24848,"Sequence number": 479841, "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": 2338707, "tid": 2338707, "ts": 6197196431844.023, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6197196431954.622, "dur": 4.227, + "args": { + "External id": 24849,"Sequence number": 479842, "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": 2338707, "tid": 2338707, "ts": 6197196431954.622, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197196432005.280, "dur": 320.798, + "args": { + "External id": 24850,"Sequence number": 479843, "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": 2338707, "tid": 2338707, "ts": 6197196432005.280, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6197196432026.577, "dur": 5.736, + "args": { + "External id": 24851,"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": 2338707, "tid": 2338707, + "ts": 6197196432030.543, "dur": 1.618, + "args": { + "External id": 24852,"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": 2338707, "tid": 2338707, + "ts": 6197196432039.653, "dur": 5.578, + "args": { + "External id": 24853,"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": 2338707, "tid": 2338707, + "ts": 6197196432040.626, "dur": 4.453, + "args": { + "External id": 24854,"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": 2338707, "tid": 2338707, + "ts": 6197196432041.643, "dur": 3.320, + "args": { + "External id": 24855,"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": 2338707, "tid": 2338707, + "ts": 6197196432054.730, "dur": 51.036, + "args": { + "External id": 24856,"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": 2338707, "tid": 2338707, + "ts": 6197196432098.046, "dur": 7.045, + "args": { + "External id": 24857,"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": 2338707, "tid": 2338707, + "ts": 6197196432116.814, "dur": 3.547, + "args": { + "External id": 24858,"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": 2338707, "tid": 2338707, + "ts": 6197196432127.506, "dur": 4.005, + "args": { + "External id": 24859,"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": 2338707, "tid": 2338707, + "ts": 6197196432297.388, "dur": 5.667, + "args": { + "External id": 24860,"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": 2338707, "tid": 2338707, + "ts": 6197196432298.979, "dur": 3.625, + "args": { + "External id": 24861,"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": 2338707, "tid": 2338707, + "ts": 6197196432306.106, "dur": 2.395, + "args": { + "External id": 24862,"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": 2338707, "tid": 2338707, + "ts": 6197196432307.331, "dur": 1.046, + "args": { + "External id": 24863,"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": 2338707, "tid": 2338707, + "ts": 6197196432351.592, "dur": 126.097, + "args": { + "External id": 24864,"Sequence number": 479844, "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": 2338707, "tid": 2338707, + "ts": 6197196432352.957, "dur": 11.908, + "args": { + "External id": 24865,"Sequence number": 479844, "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": 2338707, "tid": 2338707, "ts": 6197196432352.957, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6197196432358.142, "dur": 5.355, + "args": { + "External id": 24866,"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": 2338707, "tid": 2338707, + "ts": 6197196432361.075, "dur": 2.124, + "args": { + "External id": 24867,"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": 2338707, "tid": 2338707, + "ts": 6197196432366.133, "dur": 111.231, + "args": { + "External id": 24868,"Sequence number": 479845, "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": 2338707, "tid": 2338707, + "ts": 6197196432368.197, "dur": 6.092, + "args": { + "External id": 24869,"Sequence number": 479845, "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": 2338707, "tid": 2338707, + "ts": 6197196432371.186, "dur": 2.973, + "args": { + "External id": 24870,"Sequence number": 479845, "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": 2338707, "tid": 2338707, "ts": 6197196432371.186, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6197196432375.285, "dur": 88.972, + "args": { + "External id": 24871,"Sequence number": 479846, "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": 2338707, "tid": 2338707, "ts": 6197196432375.285, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6197196432466.757, "dur": 9.959, + "args": { + "External id": 24872,"Sequence number": 479847, "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": 2338707, "tid": 2338707, "ts": 6197196432466.757, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338707, "tid": 2338707, + "ts": 6197196432489.126, "dur": 81.020, + "args": { + "External id": 24873,"Sequence number": 479848, "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": 2338707, "tid": 2338707, + "ts": 6197196432489.826, "dur": 10.032, + "args": { + "External id": 24874,"Sequence number": 479848, "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": 2338707, "tid": 2338707, "ts": 6197196432489.826, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6197196432494.435, "dur": 3.602, + "args": { + "External id": 24875,"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": 2338707, "tid": 2338707, + "ts": 6197196432496.622, "dur": 1.257, + "args": { + "External id": 24876,"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": 2338707, "tid": 2338707, + "ts": 6197196432500.566, "dur": 69.294, + "args": { + "External id": 24877,"Sequence number": 479849, "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": 2338707, "tid": 2338707, + "ts": 6197196432501.967, "dur": 7.008, + "args": { + "External id": 24878,"Sequence number": 479849, "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": 2338707, "tid": 2338707, + "ts": 6197196432503.113, "dur": 5.686, + "args": { + "External id": 24879,"Sequence number": 479849, "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": 2338707, "tid": 2338707, "ts": 6197196432503.113, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6197196432509.637, "dur": 55.489, + "args": { + "External id": 24880,"Sequence number": 479850, "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": 2338707, "tid": 2338707, "ts": 6197196432509.637, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6197196432567.363, "dur": 2.038, + "args": { + "External id": 24881,"Sequence number": 479851, "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": 2338707, "tid": 2338707, "ts": 6197196432567.363, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197196432598.707, "dur": 218.866, + "args": { + "External id": 24882,"Sequence number": 479852, "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": 2338707, "tid": 2338707, "ts": 6197196432598.707, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6197196432654.014, "dur": 4.880, + "args": { + "External id": 24883,"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": 2338707, "tid": 2338707, + "ts": 6197196432696.012, "dur": 103.751, + "args": { + "External id": 24884,"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": 2338707, "tid": 2338707, + "ts": 6197196432696.899, "dur": 27.447, + "args": { + "External id": 24885,"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": 2338707, "tid": 2338707, + "ts": 6197196432698.292, "dur": 24.356, + "args": { + "External id": 24886,"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": 2338707, "tid": 2338707, + "ts": 6197196432720.740, "dur": 1.409, + "args": { + "External id": 24887,"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": 2338707, "tid": 2338707, + "ts": 6197196432725.813, "dur": 73.534, + "args": { + "External id": 24888,"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": 2338707, "tid": 2338707, + "ts": 6197196432727.395, "dur": 5.852, + "args": { + "External id": 24889,"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": 2338707, "tid": 2338707, + "ts": 6197196432731.446, "dur": 1.696, + "args": { + "External id": 24890,"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": 2338707, "tid": 2338707, + "ts": 6197196432734.122, "dur": 60.144, + "args": { + "External id": 24891,"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": 2338707, "tid": 2338707, + "ts": 6197196432797.157, "dur": 1.171, + "args": { + "External id": 24892,"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": 2338707, "tid": 2338707, + "ts": 6197196432830.779, "dur": 29.942, + "args": { + "External id": 24893,"Sequence number": 479853, "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": 2338707, "tid": 2338707, "ts": 6197196432830.779, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197196432905.552, "dur": 267.868, + "args": { + "External id": 24894,"Sequence number": 479854, "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": 2338707, "tid": 2338707, "ts": 6197196432905.552, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6197196432927.118, "dur": 4.049, + "args": { + "External id": 24895,"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": 2338707, "tid": 2338707, + "ts": 6197196432928.478, "dur": 2.402, + "args": { + "External id": 24896,"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": 2338707, "tid": 2338707, + "ts": 6197196432941.342, "dur": 11.355, + "args": { + "External id": 24897,"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": 2338707, "tid": 2338707, + "ts": 6197196432947.167, "dur": 5.111, + "args": { + "External id": 24898,"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": 2338707, "tid": 2338707, + "ts": 6197196432959.447, "dur": 4.315, + "args": { + "External id": 24899,"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": 2338707, "tid": 2338707, + "ts": 6197196433152.259, "dur": 5.173, + "args": { + "External id": 24900,"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": 2338707, "tid": 2338707, + "ts": 6197196433153.787, "dur": 3.294, + "args": { + "External id": 24901,"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": 2338707, "tid": 2338707, + "ts": 6197196433195.724, "dur": 116.089, + "args": { + "External id": 24902,"Sequence number": 479855, "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": 2338707, "tid": 2338707, + "ts": 6197196433197.130, "dur": 12.726, + "args": { + "External id": 24903,"Sequence number": 479855, "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": 2338707, "tid": 2338707, "ts": 6197196433197.130, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6197196433200.353, "dur": 7.968, + "args": { + "External id": 24904,"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": 2338707, "tid": 2338707, + "ts": 6197196433205.828, "dur": 2.066, + "args": { + "External id": 24905,"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": 2338707, "tid": 2338707, + "ts": 6197196433210.965, "dur": 100.484, + "args": { + "External id": 24906,"Sequence number": 479856, "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": 2338707, "tid": 2338707, + "ts": 6197196433212.707, "dur": 8.551, + "args": { + "External id": 24907,"Sequence number": 479856, "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": 2338707, "tid": 2338707, + "ts": 6197196433213.674, "dur": 7.307, + "args": { + "External id": 24908,"Sequence number": 479856, "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": 2338707, "tid": 2338707, "ts": 6197196433213.674, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6197196433224.618, "dur": 78.212, + "args": { + "External id": 24909,"Sequence number": 479857, "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": 2338707, "tid": 2338707, "ts": 6197196433224.618, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6197196433305.287, "dur": 5.362, + "args": { + "External id": 24910,"Sequence number": 479858, "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": 2338707, "tid": 2338707, "ts": 6197196433305.287, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338707, "tid": 2338707, + "ts": 6197196433322.667, "dur": 81.165, + "args": { + "External id": 24911,"Sequence number": 479859, "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": 2338707, "tid": 2338707, + "ts": 6197196433323.315, "dur": 11.342, + "args": { + "External id": 24912,"Sequence number": 479859, "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": 2338707, "tid": 2338707, "ts": 6197196433323.315, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6197196433328.107, "dur": 5.431, + "args": { + "External id": 24913,"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": 2338707, "tid": 2338707, + "ts": 6197196433332.572, "dur": 0.764, + "args": { + "External id": 24914,"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": 2338707, "tid": 2338707, + "ts": 6197196433335.479, "dur": 68.082, + "args": { + "External id": 24915,"Sequence number": 479860, "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": 2338707, "tid": 2338707, + "ts": 6197196433337.006, "dur": 4.298, + "args": { + "External id": 24916,"Sequence number": 479860, "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": 2338707, "tid": 2338707, + "ts": 6197196433338.393, "dur": 2.722, + "args": { + "External id": 24917,"Sequence number": 479860, "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": 2338707, "tid": 2338707, "ts": 6197196433338.393, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6197196433341.935, "dur": 51.956, + "args": { + "External id": 24918,"Sequence number": 479861, "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": 2338707, "tid": 2338707, "ts": 6197196433341.935, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6197196433395.782, "dur": 6.895, + "args": { + "External id": 24919,"Sequence number": 479862, "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": 2338707, "tid": 2338707, "ts": 6197196433395.782, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338707, "tid": 2338707, + "ts": 6197196433412.716, "dur": 66.416, + "args": { + "External id": 24920,"Sequence number": 479863, "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": 2338707, "tid": 2338707, + "ts": 6197196433413.398, "dur": 7.620, + "args": { + "External id": 24921,"Sequence number": 479863, "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": 2338707, "tid": 2338707, "ts": 6197196433413.398, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6197196433416.080, "dur": 3.245, + "args": { + "External id": 24922,"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": 2338707, "tid": 2338707, + "ts": 6197196433418.196, "dur": 0.975, + "args": { + "External id": 24923,"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": 2338707, "tid": 2338707, + "ts": 6197196433422.133, "dur": 56.723, + "args": { + "External id": 24924,"Sequence number": 479864, "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": 2338707, "tid": 2338707, + "ts": 6197196433425.759, "dur": 6.569, + "args": { + "External id": 24925,"Sequence number": 479864, "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": 2338707, "tid": 2338707, + "ts": 6197196433426.787, "dur": 5.405, + "args": { + "External id": 24926,"Sequence number": 479864, "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": 2338707, "tid": 2338707, "ts": 6197196433426.787, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6197196433433.083, "dur": 41.020, + "args": { + "External id": 24927,"Sequence number": 479865, "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": 2338707, "tid": 2338707, "ts": 6197196433433.083, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6197196433476.545, "dur": 1.915, + "args": { + "External id": 24928,"Sequence number": 479866, "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": 2338707, "tid": 2338707, "ts": 6197196433476.545, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6197196433500.648, "dur": 4.362, + "args": { + "External id": 24929,"Sequence number": 479867, "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": 2338707, "tid": 2338707, + "ts": 6197196433501.903, "dur": 2.965, + "args": { + "External id": 24930,"Sequence number": 479867, "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": 2338707, "tid": 2338707, "ts": 6197196433501.903, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6197196433512.714, "dur": 5.235, + "args": { + "External id": 24931,"Sequence number": 479868, "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": 2338707, "tid": 2338707, + "ts": 6197196433514.177, "dur": 3.581, + "args": { + "External id": 24932,"Sequence number": 479868, "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": 2338707, "tid": 2338707, "ts": 6197196433514.177, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6197196433522.735, "dur": 6.402, + "args": { + "External id": 24933,"Sequence number": 479869, "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": 2338707, "tid": 2338707, + "ts": 6197196433527.072, "dur": 1.915, + "args": { + "External id": 24934,"Sequence number": 479869, "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": 2338707, "tid": 2338707, "ts": 6197196433527.072, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197196433564.732, "dur": 198.706, + "args": { + "External id": 24935,"Sequence number": 479870, "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": 2338707, "tid": 2338707, "ts": 6197196433564.732, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338707, "tid": 2338707, + "ts": 6197196433587.718, "dur": 9.639, + "args": { + "External id": 24936,"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": 2338707, "tid": 2338707, + "ts": 6197196433590.975, "dur": 5.982, + "args": { + "External id": 24937,"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": 2338707, "tid": 2338707, + "ts": 6197196433780.069, "dur": 128.430, + "args": { + "External id": 24938,"Sequence number": 479871, "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": 2338707, "tid": 2338707, "ts": 6197196433780.069, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338707, "tid": 2338707, + "ts": 6197196433797.098, "dur": 9.749, + "args": { + "External id": 24939,"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": 2338707, "tid": 2338707, + "ts": 6197196433800.297, "dur": 6.121, + "args": { + "External id": 24940,"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": 2338707, "tid": 2338707, + "ts": 6197196433945.106, "dur": 264.637, + "args": { + "External id": 24941,"Sequence number": 479872, "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": 2338707, "tid": 2338707, "ts": 6197196433945.106, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338707, "tid": 2338707, + "ts": 6197196433984.219, "dur": 194.024, + "args": { + "External id": 24942,"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": 2338707, "tid": 2338707, + "ts": 6197196434041.889, "dur": 9.974, + "args": { + "External id": 24943,"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": 2338707, "tid": 2338707, + "ts": 6197196434044.573, "dur": 6.705, + "args": { + "External id": 24944,"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": 2338707, "tid": 2338707, + "ts": 6197196434054.940, "dur": 44.466, + "args": { + "External id": 24945,"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": 2338707, "tid": 2338707, + "ts": 6197196434102.623, "dur": 1.175, + "args": { + "External id": 24946,"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": 2338707, "tid": 2338707, + "ts": 6197196434106.693, "dur": 4.640, + "args": { + "External id": 24947,"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": 2338707, "tid": 2338707, + "ts": 6197196434191.299, "dur": 6.355, + "args": { + "External id": 24948,"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": 2338707, "tid": 2338707, + "ts": 6197196434216.669, "dur": 7.664, + "args": { + "External id": 24949,"Sequence number": 479873, "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": 2338707, "tid": 2338707, + "ts": 6197196434218.716, "dur": 5.421, + "args": { + "External id": 24950,"Sequence number": 479873, "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": 2338707, "tid": 2338707, "ts": 6197196434218.716, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338707, "tid": 2338707, + "ts": 6197196434239.700, "dur": 142.581, + "args": { + "External id": 24951,"Sequence number": 479874, "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": 2338707, "tid": 2338707, + "ts": 6197196434240.944, "dur": 12.630, + "args": { + "External id": 24952,"Sequence number": 479874, "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": 2338707, "tid": 2338707, "ts": 6197196434240.944, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6197196434246.401, "dur": 5.769, + "args": { + "External id": 24953,"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": 2338707, "tid": 2338707, + "ts": 6197196434249.557, "dur": 2.297, + "args": { + "External id": 24954,"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": 2338707, "tid": 2338707, + "ts": 6197196434255.266, "dur": 126.667, + "args": { + "External id": 24955,"Sequence number": 479875, "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": 2338707, "tid": 2338707, + "ts": 6197196434258.443, "dur": 5.967, + "args": { + "External id": 24956,"Sequence number": 479875, "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": 2338707, "tid": 2338707, + "ts": 6197196434261.821, "dur": 2.372, + "args": { + "External id": 24957,"Sequence number": 479875, "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": 2338707, "tid": 2338707, "ts": 6197196434261.821, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6197196434265.343, "dur": 105.238, + "args": { + "External id": 24958,"Sequence number": 479876, "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": 2338707, "tid": 2338707, "ts": 6197196434265.343, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6197196434374.439, "dur": 6.514, + "args": { + "External id": 24959,"Sequence number": 479877, "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": 2338707, "tid": 2338707, "ts": 6197196434374.439, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197196434429.188, "dur": 265.268, + "args": { + "External id": 24960,"Sequence number": 479878, "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": 2338707, "tid": 2338707, "ts": 6197196434429.188, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6197196434455.908, "dur": 5.433, + "args": { + "External id": 24961,"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": 2338707, "tid": 2338707, + "ts": 6197196434457.266, "dur": 3.862, + "args": { + "External id": 24962,"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": 2338707, "tid": 2338707, + "ts": 6197196434465.970, "dur": 3.805, + "args": { + "External id": 24963,"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": 2338707, "tid": 2338707, + "ts": 6197196434467.493, "dur": 2.155, + "args": { + "External id": 24964,"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": 2338707, "tid": 2338707, + "ts": 6197196434468.419, "dur": 1.118, + "args": { + "External id": 24965,"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": 2338707, "tid": 2338707, + "ts": 6197196434479.738, "dur": 10.447, + "args": { + "External id": 24966,"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": 2338707, "tid": 2338707, + "ts": 6197196434484.416, "dur": 5.344, + "args": { + "External id": 24967,"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": 2338707, "tid": 2338707, + "ts": 6197196434497.496, "dur": 3.587, + "args": { + "External id": 24968,"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": 2338707, "tid": 2338707, + "ts": 6197196434505.143, "dur": 5.079, + "args": { + "External id": 24969,"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": 2338707, "tid": 2338707, + "ts": 6197196434668.624, "dur": 4.468, + "args": { + "External id": 24970,"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": 2338707, "tid": 2338707, + "ts": 6197196434670.027, "dur": 2.721, + "args": { + "External id": 24971,"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": 2338707, "tid": 2338707, + "ts": 6197196434676.090, "dur": 2.685, + "args": { + "External id": 24972,"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": 2338707, "tid": 2338707, + "ts": 6197196434677.348, "dur": 1.318, + "args": { + "External id": 24973,"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": 2338707, "tid": 2338707, + "ts": 6197196434736.216, "dur": 129.019, + "args": { + "External id": 24974,"Sequence number": 479879, "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": 2338707, "tid": 2338707, + "ts": 6197196434737.753, "dur": 11.814, + "args": { + "External id": 24975,"Sequence number": 479879, "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": 2338707, "tid": 2338707, "ts": 6197196434737.753, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6197196434741.964, "dur": 5.519, + "args": { + "External id": 24976,"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": 2338707, "tid": 2338707, + "ts": 6197196434744.917, "dur": 2.098, + "args": { + "External id": 24977,"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": 2338707, "tid": 2338707, + "ts": 6197196434750.775, "dur": 114.140, + "args": { + "External id": 24978,"Sequence number": 479880, "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": 2338707, "tid": 2338707, + "ts": 6197196434755.103, "dur": 7.366, + "args": { + "External id": 24979,"Sequence number": 479880, "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": 2338707, "tid": 2338707, + "ts": 6197196434755.884, "dur": 6.382, + "args": { + "External id": 24980,"Sequence number": 479880, "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": 2338707, "tid": 2338707, "ts": 6197196434755.884, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6197196434763.480, "dur": 94.915, + "args": { + "External id": 24981,"Sequence number": 479881, "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": 2338707, "tid": 2338707, "ts": 6197196434763.480, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6197196434861.275, "dur": 2.779, + "args": { + "External id": 24982,"Sequence number": 479882, "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": 2338707, "tid": 2338707, "ts": 6197196434861.275, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338707, "tid": 2338707, + "ts": 6197196434876.619, "dur": 94.603, + "args": { + "External id": 24983,"Sequence number": 479883, "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": 2338707, "tid": 2338707, + "ts": 6197196434880.090, "dur": 15.489, + "args": { + "External id": 24984,"Sequence number": 479883, "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": 2338707, "tid": 2338707, "ts": 6197196434880.090, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6197196434890.715, "dur": 3.376, + "args": { + "External id": 24985,"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": 2338707, "tid": 2338707, + "ts": 6197196434893.157, "dur": 0.782, + "args": { + "External id": 24986,"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": 2338707, "tid": 2338707, + "ts": 6197196434896.675, "dur": 74.224, + "args": { + "External id": 24987,"Sequence number": 479884, "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": 2338707, "tid": 2338707, + "ts": 6197196434897.858, "dur": 10.124, + "args": { + "External id": 24988,"Sequence number": 479884, "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": 2338707, "tid": 2338707, + "ts": 6197196434901.647, "dur": 6.156, + "args": { + "External id": 24989,"Sequence number": 479884, "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": 2338707, "tid": 2338707, "ts": 6197196434901.647, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6197196434908.604, "dur": 53.367, + "args": { + "External id": 24990,"Sequence number": 479885, "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": 2338707, "tid": 2338707, "ts": 6197196434908.604, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6197196434964.356, "dur": 6.110, + "args": { + "External id": 24991,"Sequence number": 479886, "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": 2338707, "tid": 2338707, "ts": 6197196434964.356, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197196434998.491, "dur": 244.749, + "args": { + "External id": 24992,"Sequence number": 479887, "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": 2338707, "tid": 2338707, "ts": 6197196434998.491, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6197196435045.658, "dur": 5.282, + "args": { + "External id": 24993,"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": 2338707, "tid": 2338707, + "ts": 6197196435136.933, "dur": 88.067, + "args": { + "External id": 24994,"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": 2338707, "tid": 2338707, + "ts": 6197196435137.964, "dur": 8.195, + "args": { + "External id": 24995,"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": 2338707, "tid": 2338707, + "ts": 6197196435140.024, "dur": 4.728, + "args": { + "External id": 24996,"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": 2338707, "tid": 2338707, + "ts": 6197196435142.950, "dur": 1.399, + "args": { + "External id": 24997,"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": 2338707, "tid": 2338707, + "ts": 6197196435147.212, "dur": 77.365, + "args": { + "External id": 24998,"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": 2338707, "tid": 2338707, + "ts": 6197196435152.197, "dur": 2.900, + "args": { + "External id": 24999,"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": 2338707, "tid": 2338707, + "ts": 6197196435153.195, "dur": 1.802, + "args": { + "External id": 25000,"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": 2338707, "tid": 2338707, + "ts": 6197196435156.055, "dur": 63.329, + "args": { + "External id": 25001,"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": 2338707, "tid": 2338707, + "ts": 6197196435222.239, "dur": 1.407, + "args": { + "External id": 25002,"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": 2338707, "tid": 2338707, + "ts": 6197196435253.944, "dur": 31.682, + "args": { + "External id": 25003,"Sequence number": 479888, "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": 2338707, "tid": 2338707, "ts": 6197196435253.944, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197196435332.626, "dur": 229.748, + "args": { + "External id": 25004,"Sequence number": 479889, "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": 2338707, "tid": 2338707, "ts": 6197196435332.626, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6197196435356.256, "dur": 5.963, + "args": { + "External id": 25005,"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": 2338707, "tid": 2338707, + "ts": 6197196435360.413, "dur": 1.670, + "args": { + "External id": 25006,"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": 2338707, "tid": 2338707, + "ts": 6197196435372.345, "dur": 8.242, + "args": { + "External id": 25007,"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": 2338707, "tid": 2338707, + "ts": 6197196435375.371, "dur": 4.791, + "args": { + "External id": 25008,"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": 2338707, "tid": 2338707, + "ts": 6197196435388.103, "dur": 6.754, + "args": { + "External id": 25009,"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": 2338707, "tid": 2338707, + "ts": 6197196435544.708, "dur": 4.359, + "args": { + "External id": 25010,"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": 2338707, "tid": 2338707, + "ts": 6197196435546.420, "dur": 2.442, + "args": { + "External id": 25011,"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": 2338707, "tid": 2338707, + "ts": 6197196435584.136, "dur": 103.277, + "args": { + "External id": 25012,"Sequence number": 479890, "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": 2338707, "tid": 2338707, + "ts": 6197196435585.460, "dur": 10.495, + "args": { + "External id": 25013,"Sequence number": 479890, "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": 2338707, "tid": 2338707, "ts": 6197196435585.460, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6197196435590.239, "dur": 4.128, + "args": { + "External id": 25014,"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": 2338707, "tid": 2338707, + "ts": 6197196435592.610, "dur": 1.578, + "args": { + "External id": 25015,"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": 2338707, "tid": 2338707, + "ts": 6197196435596.845, "dur": 90.215, + "args": { + "External id": 25016,"Sequence number": 479891, "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": 2338707, "tid": 2338707, + "ts": 6197196435598.364, "dur": 6.676, + "args": { + "External id": 25017,"Sequence number": 479891, "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": 2338707, "tid": 2338707, + "ts": 6197196435601.421, "dur": 3.450, + "args": { + "External id": 25018,"Sequence number": 479891, "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": 2338707, "tid": 2338707, "ts": 6197196435601.421, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6197196435606.054, "dur": 74.397, + "args": { + "External id": 25019,"Sequence number": 479892, "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": 2338707, "tid": 2338707, "ts": 6197196435606.054, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6197196435683.060, "dur": 3.274, + "args": { + "External id": 25020,"Sequence number": 479893, "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": 2338707, "tid": 2338707, "ts": 6197196435683.060, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338707, "tid": 2338707, + "ts": 6197196435697.283, "dur": 105.345, + "args": { + "External id": 25021,"Sequence number": 479894, "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": 2338707, "tid": 2338707, + "ts": 6197196435697.995, "dur": 29.168, + "args": { + "External id": 25022,"Sequence number": 479894, "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": 2338707, "tid": 2338707, "ts": 6197196435697.995, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6197196435721.029, "dur": 4.140, + "args": { + "External id": 25023,"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": 2338707, "tid": 2338707, + "ts": 6197196435723.569, "dur": 1.262, + "args": { + "External id": 25024,"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": 2338707, "tid": 2338707, + "ts": 6197196435727.977, "dur": 74.336, + "args": { + "External id": 25025,"Sequence number": 479895, "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": 2338707, "tid": 2338707, + "ts": 6197196435729.613, "dur": 6.528, + "args": { + "External id": 25026,"Sequence number": 479895, "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": 2338707, "tid": 2338707, + "ts": 6197196435730.755, "dur": 5.247, + "args": { + "External id": 25027,"Sequence number": 479895, "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": 2338707, "tid": 2338707, "ts": 6197196435730.755, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6197196435736.916, "dur": 60.275, + "args": { + "External id": 25028,"Sequence number": 479896, "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": 2338707, "tid": 2338707, "ts": 6197196435736.916, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6197196435799.662, "dur": 2.087, + "args": { + "External id": 25029,"Sequence number": 479897, "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": 2338707, "tid": 2338707, "ts": 6197196435799.662, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338707, "tid": 2338707, + "ts": 6197196435813.907, "dur": 72.289, + "args": { + "External id": 25030,"Sequence number": 479898, "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": 2338707, "tid": 2338707, + "ts": 6197196435815.103, "dur": 9.931, + "args": { + "External id": 25031,"Sequence number": 479898, "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": 2338707, "tid": 2338707, "ts": 6197196435815.103, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6197196435817.313, "dur": 6.409, + "args": { + "External id": 25032,"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": 2338707, "tid": 2338707, + "ts": 6197196435821.196, "dur": 2.295, + "args": { + "External id": 25033,"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": 2338707, "tid": 2338707, + "ts": 6197196435825.892, "dur": 59.915, + "args": { + "External id": 25034,"Sequence number": 479899, "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": 2338707, "tid": 2338707, + "ts": 6197196435827.265, "dur": 4.997, + "args": { + "External id": 25035,"Sequence number": 479899, "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": 2338707, "tid": 2338707, + "ts": 6197196435828.376, "dur": 3.733, + "args": { + "External id": 25036,"Sequence number": 479899, "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": 2338707, "tid": 2338707, "ts": 6197196435828.376, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6197196435832.994, "dur": 43.706, + "args": { + "External id": 25037,"Sequence number": 479900, "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": 2338707, "tid": 2338707, "ts": 6197196435832.994, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6197196435878.643, "dur": 6.730, + "args": { + "External id": 25038,"Sequence number": 479901, "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": 2338707, "tid": 2338707, "ts": 6197196435878.643, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6197196435905.824, "dur": 4.773, + "args": { + "External id": 25039,"Sequence number": 479902, "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": 2338707, "tid": 2338707, + "ts": 6197196435907.202, "dur": 3.195, + "args": { + "External id": 25040,"Sequence number": 479902, "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": 2338707, "tid": 2338707, "ts": 6197196435907.202, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6197196435918.903, "dur": 5.763, + "args": { + "External id": 25041,"Sequence number": 479903, "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": 2338707, "tid": 2338707, + "ts": 6197196435920.394, "dur": 4.131, + "args": { + "External id": 25042,"Sequence number": 479903, "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": 2338707, "tid": 2338707, "ts": 6197196435920.394, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6197196435929.354, "dur": 6.169, + "args": { + "External id": 25043,"Sequence number": 479904, "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": 2338707, "tid": 2338707, + "ts": 6197196435930.889, "dur": 4.501, + "args": { + "External id": 25044,"Sequence number": 479904, "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": 2338707, "tid": 2338707, "ts": 6197196435930.889, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197196435969.327, "dur": 225.958, + "args": { + "External id": 25045,"Sequence number": 479905, "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": 2338707, "tid": 2338707, "ts": 6197196435969.327, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338707, "tid": 2338707, + "ts": 6197196435991.042, "dur": 11.932, + "args": { + "External id": 25046,"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": 2338707, "tid": 2338707, + "ts": 6197196435994.470, "dur": 8.020, + "args": { + "External id": 25047,"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": 2338707, "tid": 2338707, + "ts": 6197196436214.311, "dur": 133.736, + "args": { + "External id": 25048,"Sequence number": 479906, "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": 2338707, "tid": 2338707, "ts": 6197196436214.311, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338707, "tid": 2338707, + "ts": 6197196436231.296, "dur": 10.674, + "args": { + "External id": 25049,"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": 2338707, "tid": 2338707, + "ts": 6197196436234.727, "dur": 6.738, + "args": { + "External id": 25050,"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": 2338707, "tid": 2338707, + "ts": 6197196436379.788, "dur": 203.446, + "args": { + "External id": 25051,"Sequence number": 479907, "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": 2338707, "tid": 2338707, "ts": 6197196436379.788, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338707, "tid": 2338707, + "ts": 6197196436412.233, "dur": 142.136, + "args": { + "External id": 25052,"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": 2338707, "tid": 2338707, + "ts": 6197196436463.681, "dur": 8.241, + "args": { + "External id": 25053,"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": 2338707, "tid": 2338707, + "ts": 6197196436466.671, "dur": 4.475, + "args": { + "External id": 25054,"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": 2338707, "tid": 2338707, + "ts": 6197196436474.748, "dur": 6.854, + "args": { + "External id": 25055,"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": 2338707, "tid": 2338707, + "ts": 6197196436483.192, "dur": 1.173, + "args": { + "External id": 25056,"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": 2338707, "tid": 2338707, + "ts": 6197196436487.660, "dur": 4.154, + "args": { + "External id": 25057,"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": 2338707, "tid": 2338707, + "ts": 6197196436567.194, "dur": 5.882, + "args": { + "External id": 25058,"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": 2338707, "tid": 2338707, + "ts": 6197196436589.435, "dur": 7.327, + "args": { + "External id": 25059,"Sequence number": 479908, "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": 2338707, "tid": 2338707, + "ts": 6197196436591.724, "dur": 4.838, + "args": { + "External id": 25060,"Sequence number": 479908, "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": 2338707, "tid": 2338707, "ts": 6197196436591.724, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338707, "tid": 2338707, + "ts": 6197196436614.264, "dur": 172.931, + "args": { + "External id": 25061,"Sequence number": 479909, "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": 2338707, "tid": 2338707, + "ts": 6197196436615.816, "dur": 12.478, + "args": { + "External id": 25062,"Sequence number": 479909, "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": 2338707, "tid": 2338707, "ts": 6197196436615.816, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6197196436621.925, "dur": 5.007, + "args": { + "External id": 25063,"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": 2338707, "tid": 2338707, + "ts": 6197196436624.725, "dur": 1.925, + "args": { + "External id": 25064,"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": 2338707, "tid": 2338707, + "ts": 6197196436630.102, "dur": 156.790, + "args": { + "External id": 25065,"Sequence number": 479910, "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": 2338707, "tid": 2338707, + "ts": 6197196436634.471, "dur": 6.256, + "args": { + "External id": 25066,"Sequence number": 479910, "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": 2338707, "tid": 2338707, + "ts": 6197196436635.787, "dur": 4.807, + "args": { + "External id": 25067,"Sequence number": 479910, "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": 2338707, "tid": 2338707, "ts": 6197196436635.787, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6197196436642.029, "dur": 132.425, + "args": { + "External id": 25068,"Sequence number": 479911, "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": 2338707, "tid": 2338707, "ts": 6197196436642.029, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6197196436778.973, "dur": 6.993, + "args": { + "External id": 25069,"Sequence number": 479912, "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": 2338707, "tid": 2338707, "ts": 6197196436778.973, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197196436830.657, "dur": 321.546, + "args": { + "External id": 25070,"Sequence number": 479913, "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": 2338707, "tid": 2338707, "ts": 6197196436830.657, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6197196436855.777, "dur": 3.164, + "args": { + "External id": 25071,"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": 2338707, "tid": 2338707, + "ts": 6197196436856.842, "dur": 1.867, + "args": { + "External id": 25072,"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": 2338707, "tid": 2338707, + "ts": 6197196436864.502, "dur": 6.468, + "args": { + "External id": 25073,"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": 2338707, "tid": 2338707, + "ts": 6197196436865.690, "dur": 5.139, + "args": { + "External id": 25074,"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": 2338707, "tid": 2338707, + "ts": 6197196436869.301, "dur": 1.435, + "args": { + "External id": 25075,"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": 2338707, "tid": 2338707, + "ts": 6197196436880.398, "dur": 15.764, + "args": { + "External id": 25076,"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": 2338707, "tid": 2338707, + "ts": 6197196436887.291, "dur": 8.465, + "args": { + "External id": 25077,"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": 2338707, "tid": 2338707, + "ts": 6197196436903.529, "dur": 3.617, + "args": { + "External id": 25078,"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": 2338707, "tid": 2338707, + "ts": 6197196436910.942, "dur": 5.122, + "args": { + "External id": 25079,"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": 2338707, "tid": 2338707, + "ts": 6197196437123.397, "dur": 4.623, + "args": { + "External id": 25080,"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": 2338707, "tid": 2338707, + "ts": 6197196437124.472, "dur": 3.211, + "args": { + "External id": 25081,"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": 2338707, "tid": 2338707, + "ts": 6197196437133.525, "dur": 2.589, + "args": { + "External id": 25082,"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": 2338707, "tid": 2338707, + "ts": 6197196437134.929, "dur": 1.066, + "args": { + "External id": 25083,"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": 2338707, "tid": 2338707, + "ts": 6197196437175.656, "dur": 158.843, + "args": { + "External id": 25084,"Sequence number": 479914, "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": 2338707, "tid": 2338707, + "ts": 6197196437177.016, "dur": 12.431, + "args": { + "External id": 25085,"Sequence number": 479914, "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": 2338707, "tid": 2338707, "ts": 6197196437177.016, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6197196437180.235, "dur": 7.595, + "args": { + "External id": 25086,"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": 2338707, "tid": 2338707, + "ts": 6197196437182.830, "dur": 4.669, + "args": { + "External id": 25087,"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": 2338707, "tid": 2338707, + "ts": 6197196437193.831, "dur": 140.319, + "args": { + "External id": 25088,"Sequence number": 479915, "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": 2338707, "tid": 2338707, + "ts": 6197196437221.149, "dur": 4.323, + "args": { + "External id": 25089,"Sequence number": 479915, "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": 2338707, "tid": 2338707, + "ts": 6197196437222.415, "dur": 2.911, + "args": { + "External id": 25090,"Sequence number": 479915, "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": 2338707, "tid": 2338707, "ts": 6197196437222.415, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6197196437226.615, "dur": 98.958, + "args": { + "External id": 25091,"Sequence number": 479916, "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": 2338707, "tid": 2338707, "ts": 6197196437226.615, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6197196437328.348, "dur": 5.147, + "args": { + "External id": 25092,"Sequence number": 479917, "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": 2338707, "tid": 2338707, "ts": 6197196437328.348, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338707, "tid": 2338707, + "ts": 6197196437345.155, "dur": 84.320, + "args": { + "External id": 25093,"Sequence number": 479918, "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": 2338707, "tid": 2338707, + "ts": 6197196437345.726, "dur": 9.211, + "args": { + "External id": 25094,"Sequence number": 479918, "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": 2338707, "tid": 2338707, "ts": 6197196437345.726, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6197196437347.651, "dur": 5.947, + "args": { + "External id": 25095,"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": 2338707, "tid": 2338707, + "ts": 6197196437349.806, "dur": 3.628, + "args": { + "External id": 25096,"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": 2338707, "tid": 2338707, + "ts": 6197196437355.910, "dur": 73.157, + "args": { + "External id": 25097,"Sequence number": 479919, "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": 2338707, "tid": 2338707, + "ts": 6197196437359.200, "dur": 6.723, + "args": { + "External id": 25098,"Sequence number": 479919, "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": 2338707, "tid": 2338707, + "ts": 6197196437359.890, "dur": 5.860, + "args": { + "External id": 25099,"Sequence number": 479919, "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": 2338707, "tid": 2338707, "ts": 6197196437359.890, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6197196437366.526, "dur": 54.337, + "args": { + "External id": 25100,"Sequence number": 479920, "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": 2338707, "tid": 2338707, "ts": 6197196437366.526, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6197196437423.065, "dur": 5.613, + "args": { + "External id": 25101,"Sequence number": 479921, "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": 2338707, "tid": 2338707, "ts": 6197196437423.065, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197196437460.215, "dur": 177.325, + "args": { + "External id": 25102,"Sequence number": 479922, "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": 2338707, "tid": 2338707, "ts": 6197196437460.215, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6197196437507.243, "dur": 5.083, + "args": { + "External id": 25103,"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": 2338707, "tid": 2338707, + "ts": 6197196437550.301, "dur": 71.074, + "args": { + "External id": 25104,"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": 2338707, "tid": 2338707, + "ts": 6197196437551.452, "dur": 6.098, + "args": { + "External id": 25105,"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": 2338707, "tid": 2338707, + "ts": 6197196437552.915, "dur": 3.564, + "args": { + "External id": 25106,"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": 2338707, "tid": 2338707, + "ts": 6197196437554.802, "dur": 1.220, + "args": { + "External id": 25107,"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": 2338707, "tid": 2338707, + "ts": 6197196437561.098, "dur": 59.793, + "args": { + "External id": 25108,"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": 2338707, "tid": 2338707, + "ts": 6197196437562.611, "dur": 2.376, + "args": { + "External id": 25109,"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": 2338707, "tid": 2338707, + "ts": 6197196437563.529, "dur": 1.297, + "args": { + "External id": 25110,"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": 2338707, "tid": 2338707, + "ts": 6197196437565.563, "dur": 51.019, + "args": { + "External id": 25111,"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": 2338707, "tid": 2338707, + "ts": 6197196437618.844, "dur": 1.293, + "args": { + "External id": 25112,"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": 2338707, "tid": 2338707, + "ts": 6197196437646.784, "dur": 30.969, + "args": { + "External id": 25113,"Sequence number": 479923, "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": 2338707, "tid": 2338707, "ts": 6197196437646.784, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197196437742.545, "dur": 241.246, + "args": { + "External id": 25114,"Sequence number": 479924, "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": 2338707, "tid": 2338707, "ts": 6197196437742.545, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6197196437771.707, "dur": 4.525, + "args": { + "External id": 25115,"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": 2338707, "tid": 2338707, + "ts": 6197196437772.649, "dur": 3.278, + "args": { + "External id": 25116,"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": 2338707, "tid": 2338707, + "ts": 6197196437786.419, "dur": 10.391, + "args": { + "External id": 25117,"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": 2338707, "tid": 2338707, + "ts": 6197196437790.358, "dur": 5.852, + "args": { + "External id": 25118,"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": 2338707, "tid": 2338707, + "ts": 6197196437804.635, "dur": 4.325, + "args": { + "External id": 25119,"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": 2338707, "tid": 2338707, + "ts": 6197196437963.895, "dur": 3.263, + "args": { + "External id": 25120,"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": 2338707, "tid": 2338707, + "ts": 6197196437965.195, "dur": 1.786, + "args": { + "External id": 25121,"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": 2338707, "tid": 2338707, + "ts": 6197196438004.607, "dur": 162.329, + "args": { + "External id": 25122,"Sequence number": 479925, "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": 2338707, "tid": 2338707, + "ts": 6197196438005.401, "dur": 8.702, + "args": { + "External id": 25123,"Sequence number": 479925, "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": 2338707, "tid": 2338707, "ts": 6197196438005.401, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6197196438008.282, "dur": 4.197, + "args": { + "External id": 25124,"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": 2338707, "tid": 2338707, + "ts": 6197196438010.871, "dur": 1.408, + "args": { + "External id": 25125,"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": 2338707, "tid": 2338707, + "ts": 6197196438015.552, "dur": 151.096, + "args": { + "External id": 25126,"Sequence number": 479926, "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": 2338707, "tid": 2338707, + "ts": 6197196438019.790, "dur": 4.052, + "args": { + "External id": 25127,"Sequence number": 479926, "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": 2338707, "tid": 2338707, + "ts": 6197196438020.950, "dur": 2.720, + "args": { + "External id": 25128,"Sequence number": 479926, "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": 2338707, "tid": 2338707, "ts": 6197196438020.950, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6197196438027.621, "dur": 125.773, + "args": { + "External id": 25129,"Sequence number": 479927, "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": 2338707, "tid": 2338707, "ts": 6197196438027.621, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6197196438158.522, "dur": 6.784, + "args": { + "External id": 25130,"Sequence number": 479928, "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": 2338707, "tid": 2338707, "ts": 6197196438158.522, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338707, "tid": 2338707, + "ts": 6197196438179.871, "dur": 79.561, + "args": { + "External id": 25131,"Sequence number": 479929, "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": 2338707, "tid": 2338707, + "ts": 6197196438183.170, "dur": 7.416, + "args": { + "External id": 25132,"Sequence number": 479929, "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": 2338707, "tid": 2338707, "ts": 6197196438183.170, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6197196438185.692, "dur": 3.480, + "args": { + "External id": 25133,"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": 2338707, "tid": 2338707, + "ts": 6197196438187.864, "dur": 1.125, + "args": { + "External id": 25134,"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": 2338707, "tid": 2338707, + "ts": 6197196438191.473, "dur": 67.715, + "args": { + "External id": 25135,"Sequence number": 479930, "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": 2338707, "tid": 2338707, + "ts": 6197196438192.783, "dur": 6.651, + "args": { + "External id": 25136,"Sequence number": 479930, "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": 2338707, "tid": 2338707, + "ts": 6197196438195.938, "dur": 3.358, + "args": { + "External id": 25137,"Sequence number": 479930, "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": 2338707, "tid": 2338707, "ts": 6197196438195.938, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6197196438200.026, "dur": 53.740, + "args": { + "External id": 25138,"Sequence number": 479931, "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": 2338707, "tid": 2338707, "ts": 6197196438200.026, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6197196438256.017, "dur": 2.773, + "args": { + "External id": 25139,"Sequence number": 479932, "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": 2338707, "tid": 2338707, "ts": 6197196438256.017, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338707, "tid": 2338707, + "ts": 6197196438268.829, "dur": 69.147, + "args": { + "External id": 25140,"Sequence number": 479933, "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": 2338707, "tid": 2338707, + "ts": 6197196438269.571, "dur": 11.051, + "args": { + "External id": 25141,"Sequence number": 479933, "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": 2338707, "tid": 2338707, "ts": 6197196438269.571, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6197196438274.124, "dur": 5.122, + "args": { + "External id": 25142,"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": 2338707, "tid": 2338707, + "ts": 6197196438276.005, "dur": 3.045, + "args": { + "External id": 25143,"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": 2338707, "tid": 2338707, + "ts": 6197196438281.588, "dur": 56.097, + "args": { + "External id": 25144,"Sequence number": 479934, "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": 2338707, "tid": 2338707, + "ts": 6197196438282.742, "dur": 6.757, + "args": { + "External id": 25145,"Sequence number": 479934, "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": 2338707, "tid": 2338707, + "ts": 6197196438283.744, "dur": 5.620, + "args": { + "External id": 25146,"Sequence number": 479934, "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": 2338707, "tid": 2338707, "ts": 6197196438283.744, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6197196438289.985, "dur": 40.674, + "args": { + "External id": 25147,"Sequence number": 479935, "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": 2338707, "tid": 2338707, "ts": 6197196438289.985, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6197196438332.889, "dur": 4.416, + "args": { + "External id": 25148,"Sequence number": 479936, "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": 2338707, "tid": 2338707, "ts": 6197196438332.889, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6197196438358.369, "dur": 4.449, + "args": { + "External id": 25149,"Sequence number": 479937, "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": 2338707, "tid": 2338707, + "ts": 6197196438359.450, "dur": 3.228, + "args": { + "External id": 25150,"Sequence number": 479937, "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": 2338707, "tid": 2338707, "ts": 6197196438359.450, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6197196438373.806, "dur": 9.076, + "args": { + "External id": 25151,"Sequence number": 479938, "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": 2338707, "tid": 2338707, + "ts": 6197196438375.131, "dur": 7.624, + "args": { + "External id": 25152,"Sequence number": 479938, "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": 2338707, "tid": 2338707, "ts": 6197196438375.131, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6197196438387.890, "dur": 3.975, + "args": { + "External id": 25153,"Sequence number": 479939, "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": 2338707, "tid": 2338707, + "ts": 6197196438389.730, "dur": 2.022, + "args": { + "External id": 25154,"Sequence number": 479939, "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": 2338707, "tid": 2338707, "ts": 6197196438389.730, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197196438426.796, "dur": 193.574, + "args": { + "External id": 25155,"Sequence number": 479940, "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": 2338707, "tid": 2338707, "ts": 6197196438426.796, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338707, "tid": 2338707, + "ts": 6197196438450.769, "dur": 13.182, + "args": { + "External id": 25156,"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": 2338707, "tid": 2338707, + "ts": 6197196438454.091, "dur": 9.425, + "args": { + "External id": 25157,"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": 2338707, "tid": 2338707, + "ts": 6197196438634.672, "dur": 148.279, + "args": { + "External id": 25158,"Sequence number": 479941, "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": 2338707, "tid": 2338707, "ts": 6197196438634.672, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338707, "tid": 2338707, + "ts": 6197196438650.105, "dur": 8.402, + "args": { + "External id": 25159,"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": 2338707, "tid": 2338707, + "ts": 6197196438653.034, "dur": 5.046, + "args": { + "External id": 25160,"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": 2338707, "tid": 2338707, + "ts": 6197196438821.313, "dur": 200.329, + "args": { + "External id": 25161,"Sequence number": 479942, "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": 2338707, "tid": 2338707, "ts": 6197196438821.313, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338707, "tid": 2338707, + "ts": 6197196438853.118, "dur": 140.450, + "args": { + "External id": 25162,"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": 2338707, "tid": 2338707, + "ts": 6197196438905.741, "dur": 8.646, + "args": { + "External id": 25163,"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": 2338707, "tid": 2338707, + "ts": 6197196438908.653, "dur": 5.240, + "args": { + "External id": 25164,"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": 2338707, "tid": 2338707, + "ts": 6197196438917.351, "dur": 4.557, + "args": { + "External id": 25165,"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": 2338707, "tid": 2338707, + "ts": 6197196438923.506, "dur": 3.391, + "args": { + "External id": 25166,"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": 2338707, "tid": 2338707, + "ts": 6197196438930.618, "dur": 4.011, + "args": { + "External id": 25167,"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": 2338707, "tid": 2338707, + "ts": 6197196439005.947, "dur": 5.494, + "args": { + "External id": 25168,"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": 2338707, "tid": 2338707, + "ts": 6197196439027.821, "dur": 9.011, + "args": { + "External id": 25169,"Sequence number": 479943, "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": 2338707, "tid": 2338707, + "ts": 6197196439029.592, "dur": 7.065, + "args": { + "External id": 25170,"Sequence number": 479943, "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": 2338707, "tid": 2338707, "ts": 6197196439029.592, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338707, "tid": 2338707, + "ts": 6197196439097.002, "dur": 133.893, + "args": { + "External id": 25171,"Sequence number": 479944, "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": 2338707, "tid": 2338707, + "ts": 6197196439098.304, "dur": 11.053, + "args": { + "External id": 25172,"Sequence number": 479944, "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": 2338707, "tid": 2338707, "ts": 6197196439098.304, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6197196439101.877, "dur": 5.697, + "args": { + "External id": 25173,"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": 2338707, "tid": 2338707, + "ts": 6197196439104.952, "dur": 2.035, + "args": { + "External id": 25174,"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": 2338707, "tid": 2338707, + "ts": 6197196439110.811, "dur": 119.705, + "args": { + "External id": 25175,"Sequence number": 479945, "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": 2338707, "tid": 2338707, + "ts": 6197196439115.476, "dur": 4.275, + "args": { + "External id": 25176,"Sequence number": 479945, "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": 2338707, "tid": 2338707, + "ts": 6197196439116.491, "dur": 3.076, + "args": { + "External id": 25177,"Sequence number": 479945, "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": 2338707, "tid": 2338707, "ts": 6197196439116.491, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6197196439120.642, "dur": 100.169, + "args": { + "External id": 25178,"Sequence number": 479946, "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": 2338707, "tid": 2338707, "ts": 6197196439120.642, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6197196439223.685, "dur": 5.882, + "args": { + "External id": 25179,"Sequence number": 479947, "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": 2338707, "tid": 2338707, "ts": 6197196439223.685, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197196439279.588, "dur": 254.779, + "args": { + "External id": 25180,"Sequence number": 479948, "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": 2338707, "tid": 2338707, "ts": 6197196439279.588, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6197196439304.301, "dur": 2.644, + "args": { + "External id": 25181,"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": 2338707, "tid": 2338707, + "ts": 6197196439305.244, "dur": 1.531, + "args": { + "External id": 25182,"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": 2338707, "tid": 2338707, + "ts": 6197196439311.530, "dur": 5.658, + "args": { + "External id": 25183,"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": 2338707, "tid": 2338707, + "ts": 6197196439312.695, "dur": 4.353, + "args": { + "External id": 25184,"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": 2338707, "tid": 2338707, + "ts": 6197196439315.836, "dur": 1.099, + "args": { + "External id": 25185,"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": 2338707, "tid": 2338707, + "ts": 6197196439326.422, "dur": 9.820, + "args": { + "External id": 25186,"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": 2338707, "tid": 2338707, + "ts": 6197196439329.831, "dur": 6.079, + "args": { + "External id": 25187,"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": 2338707, "tid": 2338707, + "ts": 6197196439343.264, "dur": 5.908, + "args": { + "External id": 25188,"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": 2338707, "tid": 2338707, + "ts": 6197196439353.396, "dur": 4.143, + "args": { + "External id": 25189,"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": 2338707, "tid": 2338707, + "ts": 6197196439510.268, "dur": 3.615, + "args": { + "External id": 25190,"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": 2338707, "tid": 2338707, + "ts": 6197196439511.690, "dur": 1.967, + "args": { + "External id": 25191,"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": 2338707, "tid": 2338707, + "ts": 6197196439516.524, "dur": 2.892, + "args": { + "External id": 25192,"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": 2338707, "tid": 2338707, + "ts": 6197196439518.247, "dur": 1.050, + "args": { + "External id": 25193,"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": 2338707, "tid": 2338707, + "ts": 6197196439555.332, "dur": 107.887, + "args": { + "External id": 25194,"Sequence number": 479949, "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": 2338707, "tid": 2338707, + "ts": 6197196439556.276, "dur": 10.778, + "args": { + "External id": 25195,"Sequence number": 479949, "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": 2338707, "tid": 2338707, "ts": 6197196439556.276, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6197196439559.162, "dur": 6.544, + "args": { + "External id": 25196,"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": 2338707, "tid": 2338707, + "ts": 6197196439563.889, "dur": 1.550, + "args": { + "External id": 25197,"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": 2338707, "tid": 2338707, + "ts": 6197196439568.154, "dur": 94.717, + "args": { + "External id": 25198,"Sequence number": 479950, "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": 2338707, "tid": 2338707, + "ts": 6197196439569.904, "dur": 2.708, + "args": { + "External id": 25199,"Sequence number": 479950, "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": 2338707, "tid": 2338707, + "ts": 6197196439570.410, "dur": 2.074, + "args": { + "External id": 25200,"Sequence number": 479950, "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": 2338707, "tid": 2338707, "ts": 6197196439570.410, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6197196439573.643, "dur": 83.057, + "args": { + "External id": 25201,"Sequence number": 479951, "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": 2338707, "tid": 2338707, "ts": 6197196439573.643, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6197196439659.321, "dur": 2.962, + "args": { + "External id": 25202,"Sequence number": 479952, "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": 2338707, "tid": 2338707, "ts": 6197196439659.321, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338707, "tid": 2338707, + "ts": 6197196439672.887, "dur": 117.991, + "args": { + "External id": 25203,"Sequence number": 479953, "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": 2338707, "tid": 2338707, + "ts": 6197196439673.500, "dur": 11.256, + "args": { + "External id": 25204,"Sequence number": 479953, "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": 2338707, "tid": 2338707, "ts": 6197196439673.500, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6197196439678.247, "dur": 4.995, + "args": { + "External id": 25205,"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": 2338707, "tid": 2338707, + "ts": 6197196439680.086, "dur": 2.934, + "args": { + "External id": 25206,"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": 2338707, "tid": 2338707, + "ts": 6197196439688.171, "dur": 102.380, + "args": { + "External id": 25207,"Sequence number": 479954, "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": 2338707, "tid": 2338707, + "ts": 6197196439689.237, "dur": 4.852, + "args": { + "External id": 25208,"Sequence number": 479954, "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": 2338707, "tid": 2338707, + "ts": 6197196439690.396, "dur": 3.550, + "args": { + "External id": 25209,"Sequence number": 479954, "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": 2338707, "tid": 2338707, "ts": 6197196439690.396, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6197196439694.743, "dur": 81.717, + "args": { + "External id": 25210,"Sequence number": 479955, "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": 2338707, "tid": 2338707, "ts": 6197196439694.743, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6197196439780.197, "dur": 9.335, + "args": { + "External id": 25211,"Sequence number": 479956, "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": 2338707, "tid": 2338707, "ts": 6197196439780.197, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197196439817.913, "dur": 171.441, + "args": { + "External id": 25212,"Sequence number": 479957, "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": 2338707, "tid": 2338707, "ts": 6197196439817.913, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6197196439862.830, "dur": 5.909, + "args": { + "External id": 25213,"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": 2338707, "tid": 2338707, + "ts": 6197196439905.017, "dur": 68.463, + "args": { + "External id": 25214,"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": 2338707, "tid": 2338707, + "ts": 6197196439905.931, "dur": 9.252, + "args": { + "External id": 25215,"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": 2338707, "tid": 2338707, + "ts": 6197196439907.517, "dur": 6.062, + "args": { + "External id": 25216,"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": 2338707, "tid": 2338707, + "ts": 6197196439912.217, "dur": 1.126, + "args": { + "External id": 25217,"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": 2338707, "tid": 2338707, + "ts": 6197196439915.970, "dur": 57.128, + "args": { + "External id": 25218,"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": 2338707, "tid": 2338707, + "ts": 6197196439917.280, "dur": 2.386, + "args": { + "External id": 25219,"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": 2338707, "tid": 2338707, + "ts": 6197196439918.257, "dur": 1.309, + "args": { + "External id": 25220,"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": 2338707, "tid": 2338707, + "ts": 6197196439920.226, "dur": 49.005, + "args": { + "External id": 25221,"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": 2338707, "tid": 2338707, + "ts": 6197196439971.277, "dur": 1.169, + "args": { + "External id": 25222,"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": 2338707, "tid": 2338707, + "ts": 6197196439998.856, "dur": 28.781, + "args": { + "External id": 25223,"Sequence number": 479958, "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": 2338707, "tid": 2338707, "ts": 6197196439998.856, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::stack", "pid": 2338707, "tid": 2338707, + "ts": 6197196440051.238, "dur": 92.978, + "args": { + "External id": 25224,"Sequence number": 479959, "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": 2338707, "tid": 2338707, "ts": 6197196440051.238, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::cat", "pid": 2338707, "tid": 2338707, + "ts": 6197196440101.713, "dur": 36.285, + "args": { + "External id": 25225,"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": 2338707, "tid": 2338707, + "ts": 6197196440140.281, "dur": 1.406, + "args": { + "External id": 25226,"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": 2338707, "tid": 2338707, + "ts": 6197196440190.792, "dur": 54.378, + "args": { + "External id": 25227,"Record function id": 0, "Ev Idx": 14543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 2/0", "pid": 2338707, "tid": 2338707, + "ts": 6197196440246.444, "dur": 241.645, + "args": { + "External id": 25228,"Record function id": 0, "Ev Idx": 14544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197196440292.451, "dur": 185.390, + "args": { + "External id": 25229,"Sequence number": 479960, "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": 2338707, "tid": 2338707, "ts": 6197196440292.451, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6197196440386.049, "dur": 45.163, + "args": { + "External id": 25230,"kernel_hash": "cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/du/cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs.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": 2338707, "tid": 2338707, + "ts": 6197196440589.812, "dur": 42.873, + "args": { + "External id": 25231,"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": 2338707, "tid": 2338707, + "ts": 6197196440593.124, "dur": 5.375, + "args": { + "External id": 25232,"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": 2338707, "tid": 2338707, + "ts": 6197196440602.066, "dur": 30.213, + "args": { + "External id": 25233,"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": 2338707, "tid": 2338707, + "ts": 6197196440606.009, "dur": 25.668, + "args": { + "External id": 25234,"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": 2338707, "tid": 2338707, + "ts": 6197196440638.542, "dur": 17.346, + "args": { + "External id": 25235,"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": 2338707, "tid": 2338707, + "ts": 6197196440639.906, "dur": 2.311, + "args": { + "External id": 25236,"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": 2338707, "tid": 2338707, + "ts": 6197196440642.951, "dur": 12.653, + "args": { + "External id": 25237,"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": 2338707, "tid": 2338707, + "ts": 6197196440643.545, "dur": 11.747, + "args": { + "External id": 25238,"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": 2338707, "tid": 2338707, + "ts": 6197196440659.168, "dur": 21.435, + "args": { + "External id": 25239,"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": 2338707, "tid": 2338707, + "ts": 6197196440660.581, "dur": 4.476, + "args": { + "External id": 25240,"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": 2338707, "tid": 2338707, + "ts": 6197196440668.201, "dur": 12.011, + "args": { + "External id": 25241,"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": 2338707, "tid": 2338707, + "ts": 6197196440668.684, "dur": 11.138, + "args": { + "External id": 25242,"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": 2338707, "tid": 2338707, + "ts": 6197196440692.492, "dur": 0.816, + "args": { + "External id": 25243,"Sequence number": 479961, "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": 2338707, "tid": 2338707, + "ts": 6197196440720.764, "dur": 12.448, + "args": { + "External id": 25244,"Sequence number": 479961, "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": 2338707, "tid": 2338707, + "ts": 6197196440727.664, "dur": 2.835, + "args": { + "External id": 25245,"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": 2338707, "tid": 2338707, + "ts": 6197196440741.492, "dur": 8.245, + "args": { + "External id": 25246,"Sequence number": 479961, "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": 2338707, "tid": 2338707, + "ts": 6197196440746.700, "dur": 0.977, + "args": { + "External id": 25247,"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": 2338707, "tid": 2338707, + "ts": 6197196440751.106, "dur": 3.656, + "args": { + "External id": 25248,"Sequence number": 479961, "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": 2338707, "tid": 2338707, + "ts": 6197196440753.258, "dur": 0.564, + "args": { + "External id": 25249,"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": 2338707, "tid": 2338707, + "ts": 6197196440756.363, "dur": 3.434, + "args": { + "External id": 25250,"Sequence number": 479961, "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": 2338707, "tid": 2338707, + "ts": 6197196440758.552, "dur": 0.623, + "args": { + "External id": 25251,"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": 2338707, "tid": 2338707, + "ts": 6197196440763.335, "dur": 6.022, + "args": { + "External id": 25252,"Sequence number": 479961, "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": 2338707, "tid": 2338707, + "ts": 6197196440765.733, "dur": 2.960, + "args": { + "External id": 25253,"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": 2338707, "tid": 2338707, + "ts": 6197196440772.715, "dur": 3.255, + "args": { + "External id": 25254,"Sequence number": 479961, "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": 2338707, "tid": 2338707, + "ts": 6197196440774.576, "dur": 0.529, + "args": { + "External id": 25255,"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": 2338707, "tid": 2338707, + "ts": 6197196440777.149, "dur": 3.320, + "args": { + "External id": 25256,"Sequence number": 479961, "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": 2338707, "tid": 2338707, + "ts": 6197196440779.276, "dur": 0.602, + "args": { + "External id": 25257,"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": 2338707, "tid": 2338707, + "ts": 6197196440785.372, "dur": 6.179, + "args": { + "External id": 25258,"Sequence number": 479961, "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": 2338707, "tid": 2338707, + "ts": 6197196440790.057, "dur": 0.527, + "args": { + "External id": 25259,"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": 2338707, "tid": 2338707, + "ts": 6197196440796.584, "dur": 3.737, + "args": { + "External id": 25260,"Sequence number": 479961, "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": 2338707, "tid": 2338707, + "ts": 6197196440799.135, "dur": 0.523, + "args": { + "External id": 25261,"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": 2338707, "tid": 2338707, + "ts": 6197196440804.090, "dur": 7.907, + "args": { + "External id": 25262,"Sequence number": 479961, "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": 2338707, "tid": 2338707, + "ts": 6197196440809.930, "dur": 0.733, + "args": { + "External id": 25263,"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": 2338707, "tid": 2338707, + "ts": 6197196440813.346, "dur": 5.732, + "args": { + "External id": 25264,"Sequence number": 479961, "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": 2338707, "tid": 2338707, + "ts": 6197196440817.784, "dur": 0.644, + "args": { + "External id": 25265,"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": 2338707, "tid": 2338707, + "ts": 6197196440821.711, "dur": 6.734, + "args": { + "External id": 25266,"Sequence number": 479961, "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": 2338707, "tid": 2338707, "ts": 6197196440821.711, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2338707, + "ts": 6197196440826.006, "dur": 0.611, + "args": { + "External id": 25267,"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": 2338707, "tid": 2338707, + "ts": 6197196440829.692, "dur": 7.131, + "args": { + "External id": 25268,"Sequence number": 479962, "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": 2338707, "tid": 2338707, "ts": 6197196440829.692, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2338707, + "ts": 6197196440833.002, "dur": 2.866, + "args": { + "External id": 25269,"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": 2338707, "tid": 2338707, + "ts": 6197196440840.811, "dur": 6.474, + "args": { + "External id": 25270,"Sequence number": 479963, "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": 2338707, "tid": 2338707, "ts": 6197196440840.811, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2338707, + "ts": 6197196440845.686, "dur": 0.408, + "args": { + "External id": 25271,"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": 2338707, "tid": 2338707, + "ts": 6197196440848.357, "dur": 5.116, + "args": { + "External id": 25272,"Sequence number": 479964, "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": 2338707, "tid": 2338707, "ts": 6197196440848.357, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2338707, + "ts": 6197196440851.893, "dur": 0.599, + "args": { + "External id": 25273,"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": 2338707, "tid": 2338707, + "ts": 6197196440858.692, "dur": 46.443, + "args": { + "External id": 25274,"Sequence number": 479965, "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": 2338707, "tid": 2338707, + "ts": 6197196440860.814, "dur": 44.084, + "args": { + "External id": 25275,"Sequence number": 479965, "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": 2338707, "tid": 2338707, + "ts": 6197196440863.953, "dur": 8.273, + "args": { + "External id": 25276,"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": 2338707, "tid": 2338707, + "ts": 6197196440866.503, "dur": 5.180, + "args": { + "External id": 25277,"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": 2338707, "tid": 2338707, + "ts": 6197196440876.212, "dur": 28.056, + "args": { + "External id": 25278,"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": 2338707, "tid": 2338707, + "ts": 6197196440935.432, "dur": 7.744, + "args": { + "External id": 25279,"Sequence number": 479965, "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": 2338707, "tid": 2338707, "ts": 6197196440935.432, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6197196440945.917, "dur": 1.237, + "args": { + "External id": 25280,"Sequence number": 479966, "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": 2338707, "tid": 2338707, + "ts": 6197196440980.028, "dur": 134173.191, + "args": { + "External id": 25281,"Sequence number": 479966, "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": 2338707, "tid": 2338707, "ts": 6197196440980.028, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338707, "tid": 2338707, + "ts": 6197196441000.361, "dur": 34.361, + "args": { + "External id": 25282,"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": 2338707, "tid": 2338707, + "ts": 6197196441001.339, "dur": 33.104, + "args": { + "External id": 25283,"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": 2338707, "tid": 2338707, + "ts": 6197196441002.873, "dur": 9.899, + "args": { + "External id": 25284,"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": 2338707, "tid": 2338707, + "ts": 6197196441007.209, "dur": 5.054, + "args": { + "External id": 25285,"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": 2338707, "tid": 2338707, + "ts": 6197196441013.623, "dur": 20.209, + "args": { + "External id": 25286,"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": 2338707, "tid": 2338707, + "ts": 6197196441054.468, "dur": 72.098, + "args": { + "External id": 25287,"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": 2338707, "tid": 2338707, + "ts": 6197196441094.904, "dur": 9.343, + "args": { + "External id": 25288,"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": 2338707, "tid": 2338707, + "ts": 6197196441098.015, "dur": 5.653, + "args": { + "External id": 25289,"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": 2338707, "tid": 2338707, + "ts": 6197196441105.584, "dur": 20.728, + "args": { + "External id": 25290,"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": 2338707, "tid": 2338707, + "ts": 6197196441107.049, "dur": 18.749, + "args": { + "External id": 25291,"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": 2338707, "tid": 2338707, + "ts": 6197196441132.228, "dur": 25.924, + "args": { + "External id": 25292,"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": 2338707, "tid": 2338707, + "ts": 6197196441133.359, "dur": 7.834, + "args": { + "External id": 25293,"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": 2338707, "tid": 2338707, + "ts": 6197196441135.285, "dur": 5.579, + "args": { + "External id": 25294,"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": 2338707, "tid": 2338707, + "ts": 6197196441141.886, "dur": 16.033, + "args": { + "External id": 25295,"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": 2338707, "tid": 2338707, + "ts": 6197196441144.842, "dur": 12.715, + "args": { + "External id": 25296,"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": 2338707, "tid": 2338707, + "ts": 6197196441164.816, "dur": 22.284, + "args": { + "External id": 25297,"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": 2338707, "tid": 2338707, + "ts": 6197196441169.700, "dur": 3.823, + "args": { + "External id": 25298,"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": 2338707, "tid": 2338707, + "ts": 6197196441174.127, "dur": 12.636, + "args": { + "External id": 25299,"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": 2338707, "tid": 2338707, + "ts": 6197196441174.864, "dur": 11.474, + "args": { + "External id": 25300,"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": 2338707, "tid": 2338707, + "ts": 6197196441195.046, "dur": 29.921, + "args": { + "External id": 25301,"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": 2338707, "tid": 2338707, + "ts": 6197196441229.741, "dur": 74.443, + "args": { + "External id": 25302,"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": 2338707, "tid": 2338707, + "ts": 6197196441233.493, "dur": 70.230, + "args": { + "External id": 25303,"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": 2338707, "tid": 2338707, + "ts": 6197196441240.719, "dur": 1.579, + "args": { + "External id": 25304,"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": 2338707, "tid": 2338707, + "ts": 6197196441246.530, "dur": 35.383, + "args": { + "External id": 25305,"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": 2338707, "tid": 2338707, + "ts": 6197196441249.056, "dur": 32.634, + "args": { + "External id": 25306,"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": 2338707, "tid": 2338707, + "ts": 6197196441259.937, "dur": 3.153, + "args": { + "External id": 25307,"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": 2338707, "tid": 2338707, + "ts": 6197196441264.268, "dur": 16.989, + "args": { + "External id": 25308,"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": 2338707, "tid": 2338707, + "ts": 6197196441309.513, "dur": 126724.174, + "args": { + "External id": 25309,"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": 2338707, "tid": 2338707, + "ts": 6197196441311.860, "dur": 126719.936, + "args": { + "External id": 25310,"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": 2338707, "tid": 2338707, + "ts": 6197196568077.363, "dur": 11.588, + "args": { + "External id": 25311,"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": 2338707, "tid": 2338707, + "ts": 6197196568084.524, "dur": 1.786, + "args": { + "External id": 25312,"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": 2338707, "tid": 2338707, + "ts": 6197196568096.572, "dur": 151.239, + "args": { + "External id": 25313,"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": 2338707, "tid": 2338707, + "ts": 6197196568101.206, "dur": 7.731, + "args": { + "External id": 25314,"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": 2338707, "tid": 2338707, + "ts": 6197196568104.450, "dur": 3.354, + "args": { + "External id": 25315,"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": 2338707, "tid": 2338707, + "ts": 6197196568106.589, "dur": 0.907, + "args": { + "External id": 25316,"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": 2338707, "tid": 2338707, + "ts": 6197196568110.534, "dur": 136.136, + "args": { + "External id": 25317,"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": 2338707, "tid": 2338707, + "ts": 6197196568116.158, "dur": 129.380, + "args": { + "External id": 25318,"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": 2338707, "tid": 2338707, + "ts": 6197196568253.591, "dur": 6.036, + "args": { + "External id": 25319,"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": 2338707, "tid": 2338707, + "ts": 6197196568256.885, "dur": 0.905, + "args": { + "External id": 25320,"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": 2338707, "tid": 2338707, + "ts": 6197196568273.450, "dur": 4.374, + "args": { + "External id": 25321,"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": 2338707, "tid": 2338707, + "ts": 6197196568293.336, "dur": 10.437, + "args": { + "External id": 25322,"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": 2338707, "tid": 2338707, + "ts": 6197196568296.702, "dur": 6.695, + "args": { + "External id": 25323,"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": 2338707, "tid": 2338707, + "ts": 6197196568484.003, "dur": 308.571, + "args": { + "External id": 25324,"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": 2338707, "tid": 2338707, + "ts": 6197196568489.577, "dur": 2.664, + "args": { + "External id": 25325,"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": 2338707, "tid": 2338707, + "ts": 6197196568495.807, "dur": 295.874, + "args": { + "External id": 25326,"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": 2338707, "tid": 2338707, + "ts": 6197196568501.861, "dur": 1.032, + "args": { + "External id": 25327,"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": 2338707, "tid": 2338707, + "ts": 6197196568506.239, "dur": 35.333, + "args": { + "External id": 25328,"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": 2338707, "tid": 2338707, + "ts": 6197196568544.468, "dur": 6.615, + "args": { + "External id": 25329,"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": 2338707, "tid": 2338707, + "ts": 6197196568549.904, "dur": 0.737, + "args": { + "External id": 25330,"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": 2338707, "tid": 2338707, + "ts": 6197196568553.088, "dur": 31.653, + "args": { + "External id": 25331,"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": 2338707, "tid": 2338707, + "ts": 6197196568554.524, "dur": 1.728, + "args": { + "External id": 25332,"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": 2338707, "tid": 2338707, + "ts": 6197196568559.277, "dur": 25.142, + "args": { + "External id": 25333,"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": 2338707, "tid": 2338707, + "ts": 6197196568563.971, "dur": 3.866, + "args": { + "External id": 25334,"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": 2338707, "tid": 2338707, + "ts": 6197196568592.458, "dur": 28.069, + "args": { + "External id": 25335,"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": 2338707, "tid": 2338707, + "ts": 6197196568624.413, "dur": 24.598, + "args": { + "External id": 25336,"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": 2338707, "tid": 2338707, + "ts": 6197196568656.113, "dur": 19.733, + "args": { + "External id": 25337,"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": 2338707, "tid": 2338707, + "ts": 6197196568679.111, "dur": 18.053, + "args": { + "External id": 25338,"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": 2338707, "tid": 2338707, + "ts": 6197196568716.930, "dur": 31.811, + "args": { + "External id": 25339,"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": 2338707, "tid": 2338707, + "ts": 6197196568720.386, "dur": 2.760, + "args": { + "External id": 25340,"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": 2338707, "tid": 2338707, + "ts": 6197196568726.373, "dur": 0.830, + "args": { + "External id": 25341,"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": 2338707, "tid": 2338707, + "ts": 6197196568751.615, "dur": 18.136, + "args": { + "External id": 25342,"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": 2338707, "tid": 2338707, + "ts": 6197196568774.994, "dur": 15.020, + "args": { + "External id": 25343,"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": 2338707, "tid": 2338707, + "ts": 6197196568803.359, "dur": 2.866, + "args": { + "External id": 25344,"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": 2338707, "tid": 2338707, + "ts": 6197196568815.597, "dur": 5.063, + "args": { + "External id": 25345,"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": 2338707, "tid": 2338707, + "ts": 6197196568818.900, "dur": 0.434, + "args": { + "External id": 25346,"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": 2338707, "tid": 2338707, + "ts": 6197196568927.001, "dur": 96.589, + "args": { + "External id": 25347,"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": 2338707, "tid": 2338707, + "ts": 6197196569030.823, "dur": 9.223, + "args": { + "External id": 25348,"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": 2338707, "tid": 2338707, + "ts": 6197196569034.921, "dur": 3.370, + "args": { + "External id": 25349,"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": 2338707, "tid": 2338707, + "ts": 6197196569042.117, "dur": 73.967, + "args": { + "External id": 25350,"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": 2338707, "tid": 2338707, + "ts": 6197196569128.253, "dur": 9.133, + "args": { + "External id": 25351,"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": 2338707, "tid": 2338707, + "ts": 6197196569130.592, "dur": 5.687, + "args": { + "External id": 25352,"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": 2338707, "tid": 2338707, + "ts": 6197196569134.300, "dur": 1.702, + "args": { + "External id": 25353,"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": 2338707, "tid": 2338707, + "ts": 6197196569142.784, "dur": 70.325, + "args": { + "External id": 25354,"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": 2338707, "tid": 2338707, + "ts": 6197196569144.086, "dur": 68.301, + "args": { + "External id": 25355,"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": 2338707, "tid": 2338707, + "ts": 6197196569220.302, "dur": 23.944, + "args": { + "External id": 25356,"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": 2338707, "tid": 2338707, + "ts": 6197196569253.425, "dur": 8.083, + "args": { + "External id": 25357,"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": 2338707, "tid": 2338707, + "ts": 6197196569259.260, "dur": 0.824, + "args": { + "External id": 25358,"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": 2338707, "tid": 2338707, + "ts": 6197196569267.342, "dur": 59.068, + "args": { + "External id": 25359,"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": 2338707, "tid": 2338707, + "ts": 6197196569268.421, "dur": 5.342, + "args": { + "External id": 25360,"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": 2338707, "tid": 2338707, + "ts": 6197196569269.528, "dur": 3.389, + "args": { + "External id": 25361,"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": 2338707, "tid": 2338707, + "ts": 6197196569271.756, "dur": 0.954, + "args": { + "External id": 25362,"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": 2338707, "tid": 2338707, + "ts": 6197196569274.409, "dur": 51.443, + "args": { + "External id": 25363,"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": 2338707, "tid": 2338707, + "ts": 6197196569277.490, "dur": 47.704, + "args": { + "External id": 25364,"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": 2338707, "tid": 2338707, + "ts": 6197196569331.665, "dur": 4.838, + "args": { + "External id": 25365,"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": 2338707, "tid": 2338707, + "ts": 6197196569334.394, "dur": 0.536, + "args": { + "External id": 25366,"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": 2338707, "tid": 2338707, + "ts": 6197196569344.617, "dur": 2.322, + "args": { + "External id": 25367,"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": 2338707, "tid": 2338707, + "ts": 6197196569358.222, "dur": 11.074, + "args": { + "External id": 25368,"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": 2338707, "tid": 2338707, + "ts": 6197196569361.327, "dur": 7.575, + "args": { + "External id": 25369,"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": 2338707, "tid": 2338707, + "ts": 6197196569494.086, "dur": 240.616, + "args": { + "External id": 25370,"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": 2338707, "tid": 2338707, + "ts": 6197196569496.875, "dur": 2.210, + "args": { + "External id": 25371,"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": 2338707, "tid": 2338707, + "ts": 6197196569501.229, "dur": 232.617, + "args": { + "External id": 25372,"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": 2338707, "tid": 2338707, + "ts": 6197196569503.231, "dur": 0.468, + "args": { + "External id": 25373,"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": 2338707, "tid": 2338707, + "ts": 6197196569505.427, "dur": 29.258, + "args": { + "External id": 25374,"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": 2338707, "tid": 2338707, + "ts": 6197196569536.988, "dur": 6.642, + "args": { + "External id": 25375,"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": 2338707, "tid": 2338707, + "ts": 6197196569540.196, "dur": 3.155, + "args": { + "External id": 25376,"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": 2338707, "tid": 2338707, + "ts": 6197196569545.126, "dur": 30.383, + "args": { + "External id": 25377,"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": 2338707, "tid": 2338707, + "ts": 6197196569546.238, "dur": 1.597, + "args": { + "External id": 25378,"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": 2338707, "tid": 2338707, + "ts": 6197196569552.147, "dur": 22.882, + "args": { + "External id": 25379,"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": 2338707, "tid": 2338707, + "ts": 6197196569558.403, "dur": 2.855, + "args": { + "External id": 25380,"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": 2338707, "tid": 2338707, + "ts": 6197196569577.364, "dur": 24.870, + "args": { + "External id": 25381,"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": 2338707, "tid": 2338707, + "ts": 6197196569604.351, "dur": 15.292, + "args": { + "External id": 25382,"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": 2338707, "tid": 2338707, + "ts": 6197196569622.731, "dur": 14.770, + "args": { + "External id": 25383,"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": 2338707, "tid": 2338707, + "ts": 6197196569639.478, "dur": 14.572, + "args": { + "External id": 25384,"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": 2338707, "tid": 2338707, + "ts": 6197196569656.555, "dur": 23.857, + "args": { + "External id": 25385,"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": 2338707, "tid": 2338707, + "ts": 6197196569659.300, "dur": 2.665, + "args": { + "External id": 25386,"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": 2338707, "tid": 2338707, + "ts": 6197196569664.518, "dur": 0.692, + "args": { + "External id": 25387,"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": 2338707, "tid": 2338707, + "ts": 6197196569684.439, "dur": 13.413, + "args": { + "External id": 25388,"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": 2338707, "tid": 2338707, + "ts": 6197196569716.358, "dur": 15.136, + "args": { + "External id": 25389,"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": 2338707, "tid": 2338707, + "ts": 6197196569745.503, "dur": 3.292, + "args": { + "External id": 25390,"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": 2338707, "tid": 2338707, + "ts": 6197196569761.439, "dur": 6.005, + "args": { + "External id": 25391,"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": 2338707, "tid": 2338707, + "ts": 6197196569765.184, "dur": 0.954, + "args": { + "External id": 25392,"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": 2338707, "tid": 2338707, + "ts": 6197196569855.538, "dur": 73.090, + "args": { + "External id": 25393,"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": 2338707, "tid": 2338707, + "ts": 6197196569934.652, "dur": 6.440, + "args": { + "External id": 25394,"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": 2338707, "tid": 2338707, + "ts": 6197196569938.716, "dur": 1.092, + "args": { + "External id": 25395,"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": 2338707, "tid": 2338707, + "ts": 6197196569945.393, "dur": 28.642, + "args": { + "External id": 25396,"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": 2338707, "tid": 2338707, + "ts": 6197196569980.053, "dur": 7.339, + "args": { + "External id": 25397,"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": 2338707, "tid": 2338707, + "ts": 6197196569982.436, "dur": 4.076, + "args": { + "External id": 25398,"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": 2338707, "tid": 2338707, + "ts": 6197196569985.118, "dur": 1.195, + "args": { + "External id": 25399,"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": 2338707, "tid": 2338707, + "ts": 6197196569990.682, "dur": 52.646, + "args": { + "External id": 25400,"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": 2338707, "tid": 2338707, + "ts": 6197196569992.033, "dur": 50.372, + "args": { + "External id": 25401,"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": 2338707, "tid": 2338707, + "ts": 6197196570048.597, "dur": 59.865, + "args": { + "External id": 25402,"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": 2338707, "tid": 2338707, + "ts": 6197196570121.657, "dur": 5.997, + "args": { + "External id": 25403,"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": 2338707, "tid": 2338707, + "ts": 6197196570125.099, "dur": 1.050, + "args": { + "External id": 25404,"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": 2338707, "tid": 2338707, + "ts": 6197196570133.935, "dur": 88.193, + "args": { + "External id": 25405,"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": 2338707, "tid": 2338707, + "ts": 6197196570135.464, "dur": 6.760, + "args": { + "External id": 25406,"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": 2338707, "tid": 2338707, + "ts": 6197196570136.722, "dur": 4.746, + "args": { + "External id": 25407,"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": 2338707, "tid": 2338707, + "ts": 6197196570138.772, "dur": 2.448, + "args": { + "External id": 25408,"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": 2338707, "tid": 2338707, + "ts": 6197196570145.468, "dur": 76.072, + "args": { + "External id": 25409,"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": 2338707, "tid": 2338707, + "ts": 6197196570146.178, "dur": 74.599, + "args": { + "External id": 25410,"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": 2338707, "tid": 2338707, + "ts": 6197196570227.273, "dur": 6.470, + "args": { + "External id": 25411,"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": 2338707, "tid": 2338707, + "ts": 6197196570229.581, "dur": 2.762, + "args": { + "External id": 25412,"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": 2338707, "tid": 2338707, + "ts": 6197196570242.535, "dur": 2.415, + "args": { + "External id": 25413,"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": 2338707, "tid": 2338707, + "ts": 6197196570255.257, "dur": 9.885, + "args": { + "External id": 25414,"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": 2338707, "tid": 2338707, + "ts": 6197196570260.650, "dur": 4.145, + "args": { + "External id": 25415,"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": 2338707, "tid": 2338707, + "ts": 6197196570382.239, "dur": 210.227, + "args": { + "External id": 25416,"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": 2338707, "tid": 2338707, + "ts": 6197196570385.341, "dur": 2.581, + "args": { + "External id": 25417,"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": 2338707, "tid": 2338707, + "ts": 6197196570390.011, "dur": 201.919, + "args": { + "External id": 25418,"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": 2338707, "tid": 2338707, + "ts": 6197196570391.408, "dur": 0.454, + "args": { + "External id": 25419,"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": 2338707, "tid": 2338707, + "ts": 6197196570395.822, "dur": 25.384, + "args": { + "External id": 25420,"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": 2338707, "tid": 2338707, + "ts": 6197196570423.135, "dur": 4.007, + "args": { + "External id": 25421,"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": 2338707, "tid": 2338707, + "ts": 6197196570426.002, "dur": 0.919, + "args": { + "External id": 25422,"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": 2338707, "tid": 2338707, + "ts": 6197196570428.419, "dur": 30.009, + "args": { + "External id": 25423,"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": 2338707, "tid": 2338707, + "ts": 6197196570432.304, "dur": 3.678, + "args": { + "External id": 25424,"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": 2338707, "tid": 2338707, + "ts": 6197196570437.947, "dur": 20.116, + "args": { + "External id": 25425,"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": 2338707, "tid": 2338707, + "ts": 6197196570441.396, "dur": 3.518, + "args": { + "External id": 25426,"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": 2338707, "tid": 2338707, + "ts": 6197196570460.103, "dur": 25.386, + "args": { + "External id": 25427,"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": 2338707, "tid": 2338707, + "ts": 6197196570487.571, "dur": 15.112, + "args": { + "External id": 25428,"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": 2338707, "tid": 2338707, + "ts": 6197196570506.190, "dur": 15.337, + "args": { + "External id": 25429,"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": 2338707, "tid": 2338707, + "ts": 6197196570523.076, "dur": 13.101, + "args": { + "External id": 25430,"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": 2338707, "tid": 2338707, + "ts": 6197196570538.322, "dur": 25.305, + "args": { + "External id": 25431,"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": 2338707, "tid": 2338707, + "ts": 6197196570541.333, "dur": 1.733, + "args": { + "External id": 25432,"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": 2338707, "tid": 2338707, + "ts": 6197196570548.147, "dur": 0.725, + "args": { + "External id": 25433,"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": 2338707, "tid": 2338707, + "ts": 6197196570565.175, "dur": 12.796, + "args": { + "External id": 25434,"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": 2338707, "tid": 2338707, + "ts": 6197196570579.270, "dur": 11.497, + "args": { + "External id": 25435,"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": 2338707, "tid": 2338707, + "ts": 6197196570601.064, "dur": 2.270, + "args": { + "External id": 25436,"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": 2338707, "tid": 2338707, + "ts": 6197196570614.797, "dur": 4.577, + "args": { + "External id": 25437,"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": 2338707, "tid": 2338707, + "ts": 6197196570617.907, "dur": 0.447, + "args": { + "External id": 25438,"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": 2338707, "tid": 2338707, + "ts": 6197196570722.312, "dur": 75.946, + "args": { + "External id": 25439,"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": 2338707, "tid": 2338707, + "ts": 6197196570808.752, "dur": 7.766, + "args": { + "External id": 25440,"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": 2338707, "tid": 2338707, + "ts": 6197196570813.309, "dur": 1.227, + "args": { + "External id": 25441,"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": 2338707, "tid": 2338707, + "ts": 6197196570818.285, "dur": 30.333, + "args": { + "External id": 25442,"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": 2338707, "tid": 2338707, + "ts": 6197196570854.061, "dur": 6.764, + "args": { + "External id": 25443,"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": 2338707, "tid": 2338707, + "ts": 6197196570856.018, "dur": 3.826, + "args": { + "External id": 25444,"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": 2338707, "tid": 2338707, + "ts": 6197196570858.445, "dur": 1.147, + "args": { + "External id": 25445,"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": 2338707, "tid": 2338707, + "ts": 6197196570866.584, "dur": 53.253, + "args": { + "External id": 25446,"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": 2338707, "tid": 2338707, + "ts": 6197196570868.020, "dur": 50.980, + "args": { + "External id": 25447,"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": 2338707, "tid": 2338707, + "ts": 6197196570924.896, "dur": 17.463, + "args": { + "External id": 25448,"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": 2338707, "tid": 2338707, + "ts": 6197196570949.909, "dur": 4.469, + "args": { + "External id": 25449,"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": 2338707, "tid": 2338707, + "ts": 6197196570952.661, "dur": 0.685, + "args": { + "External id": 25450,"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": 2338707, "tid": 2338707, + "ts": 6197196570959.434, "dur": 57.169, + "args": { + "External id": 25451,"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": 2338707, "tid": 2338707, + "ts": 6197196570960.855, "dur": 8.758, + "args": { + "External id": 25452,"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": 2338707, "tid": 2338707, + "ts": 6197196570964.452, "dur": 4.383, + "args": { + "External id": 25453,"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": 2338707, "tid": 2338707, + "ts": 6197196570967.999, "dur": 0.664, + "args": { + "External id": 25454,"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": 2338707, "tid": 2338707, + "ts": 6197196570970.463, "dur": 45.650, + "args": { + "External id": 25455,"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": 2338707, "tid": 2338707, + "ts": 6197196570971.187, "dur": 44.052, + "args": { + "External id": 25456,"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": 2338707, "tid": 2338707, + "ts": 6197196571021.779, "dur": 5.278, + "args": { + "External id": 25457,"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": 2338707, "tid": 2338707, + "ts": 6197196571025.048, "dur": 0.645, + "args": { + "External id": 25458,"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": 2338707, "tid": 2338707, + "ts": 6197196571034.112, "dur": 1.850, + "args": { + "External id": 25459,"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": 2338707, "tid": 2338707, + "ts": 6197196571047.253, "dur": 6.700, + "args": { + "External id": 25460,"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": 2338707, "tid": 2338707, + "ts": 6197196571049.493, "dur": 4.181, + "args": { + "External id": 25461,"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": 2338707, "tid": 2338707, + "ts": 6197196571211.087, "dur": 211.118, + "args": { + "External id": 25462,"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": 2338707, "tid": 2338707, + "ts": 6197196571214.385, "dur": 5.849, + "args": { + "External id": 25463,"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": 2338707, "tid": 2338707, + "ts": 6197196571222.694, "dur": 198.907, + "args": { + "External id": 25464,"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": 2338707, "tid": 2338707, + "ts": 6197196571227.087, "dur": 0.511, + "args": { + "External id": 25465,"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": 2338707, "tid": 2338707, + "ts": 6197196571231.441, "dur": 26.006, + "args": { + "External id": 25466,"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": 2338707, "tid": 2338707, + "ts": 6197196571259.470, "dur": 3.948, + "args": { + "External id": 25467,"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": 2338707, "tid": 2338707, + "ts": 6197196571262.099, "dur": 1.024, + "args": { + "External id": 25468,"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": 2338707, "tid": 2338707, + "ts": 6197196571264.735, "dur": 26.097, + "args": { + "External id": 25469,"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": 2338707, "tid": 2338707, + "ts": 6197196571268.564, "dur": 1.144, + "args": { + "External id": 25470,"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": 2338707, "tid": 2338707, + "ts": 6197196571271.138, "dur": 19.285, + "args": { + "External id": 25471,"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": 2338707, "tid": 2338707, + "ts": 6197196571274.337, "dur": 3.104, + "args": { + "External id": 25472,"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": 2338707, "tid": 2338707, + "ts": 6197196571292.763, "dur": 24.193, + "args": { + "External id": 25473,"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": 2338707, "tid": 2338707, + "ts": 6197196571319.264, "dur": 14.554, + "args": { + "External id": 25474,"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": 2338707, "tid": 2338707, + "ts": 6197196571337.239, "dur": 14.611, + "args": { + "External id": 25475,"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": 2338707, "tid": 2338707, + "ts": 6197196571353.780, "dur": 13.260, + "args": { + "External id": 25476,"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": 2338707, "tid": 2338707, + "ts": 6197196571371.613, "dur": 22.210, + "args": { + "External id": 25477,"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": 2338707, "tid": 2338707, + "ts": 6197196571374.126, "dur": 1.742, + "args": { + "External id": 25478,"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": 2338707, "tid": 2338707, + "ts": 6197196571378.497, "dur": 0.691, + "args": { + "External id": 25479,"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": 2338707, "tid": 2338707, + "ts": 6197196571395.181, "dur": 12.674, + "args": { + "External id": 25480,"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": 2338707, "tid": 2338707, + "ts": 6197196571408.905, "dur": 11.554, + "args": { + "External id": 25481,"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": 2338707, "tid": 2338707, + "ts": 6197196571430.598, "dur": 2.818, + "args": { + "External id": 25482,"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": 2338707, "tid": 2338707, + "ts": 6197196571444.171, "dur": 4.817, + "args": { + "External id": 25483,"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": 2338707, "tid": 2338707, + "ts": 6197196571447.503, "dur": 0.501, + "args": { + "External id": 25484,"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": 2338707, "tid": 2338707, + "ts": 6197196571529.077, "dur": 71.866, + "args": { + "External id": 25485,"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": 2338707, "tid": 2338707, + "ts": 6197196571607.514, "dur": 8.393, + "args": { + "External id": 25486,"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": 2338707, "tid": 2338707, + "ts": 6197196571611.371, "dur": 3.038, + "args": { + "External id": 25487,"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": 2338707, "tid": 2338707, + "ts": 6197196571618.162, "dur": 29.517, + "args": { + "External id": 25488,"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": 2338707, "tid": 2338707, + "ts": 6197196571653.072, "dur": 9.358, + "args": { + "External id": 25489,"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": 2338707, "tid": 2338707, + "ts": 6197196571655.134, "dur": 6.108, + "args": { + "External id": 25490,"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": 2338707, "tid": 2338707, + "ts": 6197196571659.925, "dur": 0.958, + "args": { + "External id": 25491,"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": 2338707, "tid": 2338707, + "ts": 6197196571665.816, "dur": 69.507, + "args": { + "External id": 25492,"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": 2338707, "tid": 2338707, + "ts": 6197196571667.319, "dur": 66.880, + "args": { + "External id": 25493,"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": 2338707, "tid": 2338707, + "ts": 6197196571742.110, "dur": 20.826, + "args": { + "External id": 25494,"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": 2338707, "tid": 2338707, + "ts": 6197196571770.994, "dur": 5.294, + "args": { + "External id": 25495,"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": 2338707, "tid": 2338707, + "ts": 6197196571773.974, "dur": 1.072, + "args": { + "External id": 25496,"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": 2338707, "tid": 2338707, + "ts": 6197196571781.516, "dur": 64.127, + "args": { + "External id": 25497,"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": 2338707, "tid": 2338707, + "ts": 6197196571785.178, "dur": 4.527, + "args": { + "External id": 25498,"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": 2338707, "tid": 2338707, + "ts": 6197196571786.597, "dur": 2.373, + "args": { + "External id": 25499,"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": 2338707, "tid": 2338707, + "ts": 6197196571788.209, "dur": 0.601, + "args": { + "External id": 25500,"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": 2338707, "tid": 2338707, + "ts": 6197196571790.332, "dur": 54.943, + "args": { + "External id": 25501,"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": 2338707, "tid": 2338707, + "ts": 6197196571791.036, "dur": 53.434, + "args": { + "External id": 25502,"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": 2338707, "tid": 2338707, + "ts": 6197196571850.637, "dur": 4.471, + "args": { + "External id": 25503,"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": 2338707, "tid": 2338707, + "ts": 6197196571853.004, "dur": 0.644, + "args": { + "External id": 25504,"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": 2338707, "tid": 2338707, + "ts": 6197196571864.536, "dur": 1.942, + "args": { + "External id": 25505,"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": 2338707, "tid": 2338707, + "ts": 6197196571876.054, "dur": 10.397, + "args": { + "External id": 25506,"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": 2338707, "tid": 2338707, + "ts": 6197196571878.542, "dur": 7.490, + "args": { + "External id": 25507,"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": 2338707, "tid": 2338707, + "ts": 6197196571991.000, "dur": 268.938, + "args": { + "External id": 25508,"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": 2338707, "tid": 2338707, + "ts": 6197196571993.157, "dur": 4.958, + "args": { + "External id": 25509,"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": 2338707, "tid": 2338707, + "ts": 6197196571999.945, "dur": 258.988, + "args": { + "External id": 25510,"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": 2338707, "tid": 2338707, + "ts": 6197196572004.002, "dur": 0.372, + "args": { + "External id": 25511,"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": 2338707, "tid": 2338707, + "ts": 6197196572005.710, "dur": 25.113, + "args": { + "External id": 25512,"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": 2338707, "tid": 2338707, + "ts": 6197196572033.032, "dur": 5.791, + "args": { + "External id": 25513,"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": 2338707, "tid": 2338707, + "ts": 6197196572037.763, "dur": 0.822, + "args": { + "External id": 25514,"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": 2338707, "tid": 2338707, + "ts": 6197196572039.933, "dur": 66.480, + "args": { + "External id": 25515,"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": 2338707, "tid": 2338707, + "ts": 6197196572041.492, "dur": 1.292, + "args": { + "External id": 25516,"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": 2338707, "tid": 2338707, + "ts": 6197196572044.311, "dur": 61.382, + "args": { + "External id": 25517,"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": 2338707, "tid": 2338707, + "ts": 6197196572047.344, "dur": 3.494, + "args": { + "External id": 25518,"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": 2338707, "tid": 2338707, + "ts": 6197196572109.001, "dur": 26.645, + "args": { + "External id": 25519,"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": 2338707, "tid": 2338707, + "ts": 6197196572137.601, "dur": 18.037, + "args": { + "External id": 25520,"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": 2338707, "tid": 2338707, + "ts": 6197196572161.497, "dur": 15.797, + "args": { + "External id": 25521,"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": 2338707, "tid": 2338707, + "ts": 6197196572179.067, "dur": 15.989, + "args": { + "External id": 25522,"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": 2338707, "tid": 2338707, + "ts": 6197196572197.180, "dur": 27.037, + "args": { + "External id": 25523,"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": 2338707, "tid": 2338707, + "ts": 6197196572202.324, "dur": 1.919, + "args": { + "External id": 25524,"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": 2338707, "tid": 2338707, + "ts": 6197196572206.600, "dur": 0.793, + "args": { + "External id": 25525,"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": 2338707, "tid": 2338707, + "ts": 6197196572225.962, "dur": 15.142, + "args": { + "External id": 25526,"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": 2338707, "tid": 2338707, + "ts": 6197196572244.794, "dur": 12.679, + "args": { + "External id": 25527,"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": 2338707, "tid": 2338707, + "ts": 6197196572269.691, "dur": 2.597, + "args": { + "External id": 25528,"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": 2338707, "tid": 2338707, + "ts": 6197196572284.188, "dur": 4.829, + "args": { + "External id": 25529,"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": 2338707, "tid": 2338707, + "ts": 6197196572287.139, "dur": 0.895, + "args": { + "External id": 25530,"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": 2338707, "tid": 2338707, + "ts": 6197196572373.143, "dur": 69.565, + "args": { + "External id": 25531,"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": 2338707, "tid": 2338707, + "ts": 6197196572449.222, "dur": 5.516, + "args": { + "External id": 25532,"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": 2338707, "tid": 2338707, + "ts": 6197196572452.721, "dur": 0.726, + "args": { + "External id": 25533,"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": 2338707, "tid": 2338707, + "ts": 6197196572456.623, "dur": 27.177, + "args": { + "External id": 25534,"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": 2338707, "tid": 2338707, + "ts": 6197196572491.448, "dur": 6.616, + "args": { + "External id": 25535,"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": 2338707, "tid": 2338707, + "ts": 6197196572493.288, "dur": 3.599, + "args": { + "External id": 25536,"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": 2338707, "tid": 2338707, + "ts": 6197196572495.332, "dur": 1.397, + "args": { + "External id": 25537,"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": 2338707, "tid": 2338707, + "ts": 6197196572501.341, "dur": 49.733, + "args": { + "External id": 25538,"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": 2338707, "tid": 2338707, + "ts": 6197196572502.642, "dur": 47.826, + "args": { + "External id": 25539,"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": 2338707, "tid": 2338707, + "ts": 6197196572555.761, "dur": 17.245, + "args": { + "External id": 25540,"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": 2338707, "tid": 2338707, + "ts": 6197196572579.559, "dur": 6.918, + "args": { + "External id": 25541,"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": 2338707, "tid": 2338707, + "ts": 6197196572585.004, "dur": 0.497, + "args": { + "External id": 25542,"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": 2338707, "tid": 2338707, + "ts": 6197196572591.320, "dur": 56.674, + "args": { + "External id": 25543,"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": 2338707, "tid": 2338707, + "ts": 6197196572592.537, "dur": 6.289, + "args": { + "External id": 25544,"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": 2338707, "tid": 2338707, + "ts": 6197196572593.532, "dur": 4.596, + "args": { + "External id": 25545,"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": 2338707, "tid": 2338707, + "ts": 6197196572594.888, "dur": 3.083, + "args": { + "External id": 25546,"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": 2338707, "tid": 2338707, + "ts": 6197196572599.428, "dur": 48.174, + "args": { + "External id": 25547,"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": 2338707, "tid": 2338707, + "ts": 6197196572602.443, "dur": 44.285, + "args": { + "External id": 25548,"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": 2338707, "tid": 2338707, + "ts": 6197196572653.000, "dur": 3.817, + "args": { + "External id": 25549,"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": 2338707, "tid": 2338707, + "ts": 6197196572655.184, "dur": 0.430, + "args": { + "External id": 25550,"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": 2338707, "tid": 2338707, + "ts": 6197196572662.850, "dur": 1.661, + "args": { + "External id": 25551,"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": 2338707, "tid": 2338707, + "ts": 6197196572677.792, "dur": 12.255, + "args": { + "External id": 25552,"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": 2338707, "tid": 2338707, + "ts": 6197196572682.962, "dur": 6.698, + "args": { + "External id": 25553,"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": 2338707, "tid": 2338707, + "ts": 6197196572810.539, "dur": 228.530, + "args": { + "External id": 25554,"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": 2338707, "tid": 2338707, + "ts": 6197196572813.279, "dur": 3.205, + "args": { + "External id": 25555,"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": 2338707, "tid": 2338707, + "ts": 6197196572819.126, "dur": 219.192, + "args": { + "External id": 25556,"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": 2338707, "tid": 2338707, + "ts": 6197196572821.197, "dur": 0.430, + "args": { + "External id": 25557,"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": 2338707, "tid": 2338707, + "ts": 6197196572822.979, "dur": 29.018, + "args": { + "External id": 25558,"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": 2338707, "tid": 2338707, + "ts": 6197196572854.131, "dur": 3.885, + "args": { + "External id": 25559,"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": 2338707, "tid": 2338707, + "ts": 6197196572856.929, "dur": 0.815, + "args": { + "External id": 25560,"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": 2338707, "tid": 2338707, + "ts": 6197196572859.079, "dur": 29.811, + "args": { + "External id": 25561,"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": 2338707, "tid": 2338707, + "ts": 6197196572862.522, "dur": 1.559, + "args": { + "External id": 25562,"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": 2338707, "tid": 2338707, + "ts": 6197196572865.409, "dur": 23.107, + "args": { + "External id": 25563,"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": 2338707, "tid": 2338707, + "ts": 6197196572870.903, "dur": 2.829, + "args": { + "External id": 25564,"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": 2338707, "tid": 2338707, + "ts": 6197196572890.614, "dur": 29.987, + "args": { + "External id": 25565,"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": 2338707, "tid": 2338707, + "ts": 6197196572922.839, "dur": 15.370, + "args": { + "External id": 25566,"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": 2338707, "tid": 2338707, + "ts": 6197196572941.044, "dur": 17.748, + "args": { + "External id": 25567,"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": 2338707, "tid": 2338707, + "ts": 6197196572960.707, "dur": 15.278, + "args": { + "External id": 25568,"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": 2338707, "tid": 2338707, + "ts": 6197196572980.503, "dur": 26.414, + "args": { + "External id": 25569,"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": 2338707, "tid": 2338707, + "ts": 6197196572982.983, "dur": 1.839, + "args": { + "External id": 25570,"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": 2338707, "tid": 2338707, + "ts": 6197196572989.398, "dur": 0.542, + "args": { + "External id": 25571,"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": 2338707, "tid": 2338707, + "ts": 6197196573008.347, "dur": 14.899, + "args": { + "External id": 25572,"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": 2338707, "tid": 2338707, + "ts": 6197196573024.377, "dur": 12.696, + "args": { + "External id": 25573,"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": 2338707, "tid": 2338707, + "ts": 6197196573047.484, "dur": 2.577, + "args": { + "External id": 25574,"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": 2338707, "tid": 2338707, + "ts": 6197196573101.386, "dur": 6.165, + "args": { + "External id": 25575,"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": 2338707, "tid": 2338707, + "ts": 6197196573105.067, "dur": 0.925, + "args": { + "External id": 25576,"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": 2338707, "tid": 2338707, + "ts": 6197196573187.407, "dur": 70.759, + "args": { + "External id": 25577,"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": 2338707, "tid": 2338707, + "ts": 6197196573264.687, "dur": 10.641, + "args": { + "External id": 25578,"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": 2338707, "tid": 2338707, + "ts": 6197196573271.105, "dur": 2.794, + "args": { + "External id": 25579,"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": 2338707, "tid": 2338707, + "ts": 6197196573277.082, "dur": 28.503, + "args": { + "External id": 25580,"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": 2338707, "tid": 2338707, + "ts": 6197196573310.735, "dur": 5.850, + "args": { + "External id": 25581,"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": 2338707, "tid": 2338707, + "ts": 6197196573312.557, "dur": 3.179, + "args": { + "External id": 25582,"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": 2338707, "tid": 2338707, + "ts": 6197196573314.763, "dur": 0.758, + "args": { + "External id": 25583,"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": 2338707, "tid": 2338707, + "ts": 6197196573319.526, "dur": 47.233, + "args": { + "External id": 25584,"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": 2338707, "tid": 2338707, + "ts": 6197196573320.865, "dur": 45.074, + "args": { + "External id": 25585,"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": 2338707, "tid": 2338707, + "ts": 6197196573373.799, "dur": 17.087, + "args": { + "External id": 25586,"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": 2338707, "tid": 2338707, + "ts": 6197196573397.332, "dur": 4.762, + "args": { + "External id": 25587,"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": 2338707, "tid": 2338707, + "ts": 6197196573400.366, "dur": 0.689, + "args": { + "External id": 25588,"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": 2338707, "tid": 2338707, + "ts": 6197196573407.258, "dur": 56.823, + "args": { + "External id": 25589,"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": 2338707, "tid": 2338707, + "ts": 6197196573408.286, "dur": 6.338, + "args": { + "External id": 25590,"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": 2338707, "tid": 2338707, + "ts": 6197196573409.178, "dur": 4.735, + "args": { + "External id": 25591,"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": 2338707, "tid": 2338707, + "ts": 6197196573412.913, "dur": 0.859, + "args": { + "External id": 25592,"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": 2338707, "tid": 2338707, + "ts": 6197196573415.477, "dur": 48.054, + "args": { + "External id": 25593,"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": 2338707, "tid": 2338707, + "ts": 6197196573416.006, "dur": 46.873, + "args": { + "External id": 25594,"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": 2338707, "tid": 2338707, + "ts": 6197196573468.762, "dur": 6.748, + "args": { + "External id": 25595,"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": 2338707, "tid": 2338707, + "ts": 6197196573471.172, "dur": 3.017, + "args": { + "External id": 25596,"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": 2338707, "tid": 2338707, + "ts": 6197196573482.307, "dur": 1.776, + "args": { + "External id": 25597,"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": 2338707, "tid": 2338707, + "ts": 6197196573493.224, "dur": 9.186, + "args": { + "External id": 25598,"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": 2338707, "tid": 2338707, + "ts": 6197196573497.878, "dur": 4.228, + "args": { + "External id": 25599,"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": 2338707, "tid": 2338707, + "ts": 6197196573595.601, "dur": 257.727, + "args": { + "External id": 25600,"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": 2338707, "tid": 2338707, + "ts": 6197196573625.974, "dur": 4.080, + "args": { + "External id": 25601,"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": 2338707, "tid": 2338707, + "ts": 6197196573633.697, "dur": 218.877, + "args": { + "External id": 25602,"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": 2338707, "tid": 2338707, + "ts": 6197196573635.099, "dur": 0.366, + "args": { + "External id": 25603,"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": 2338707, "tid": 2338707, + "ts": 6197196573636.607, "dur": 23.874, + "args": { + "External id": 25604,"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": 2338707, "tid": 2338707, + "ts": 6197196573662.576, "dur": 5.513, + "args": { + "External id": 25605,"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": 2338707, "tid": 2338707, + "ts": 6197196573667.114, "dur": 0.697, + "args": { + "External id": 25606,"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": 2338707, "tid": 2338707, + "ts": 6197196573671.283, "dur": 22.094, + "args": { + "External id": 25607,"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": 2338707, "tid": 2338707, + "ts": 6197196573672.372, "dur": 1.064, + "args": { + "External id": 25608,"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": 2338707, "tid": 2338707, + "ts": 6197196573674.804, "dur": 18.217, + "args": { + "External id": 25609,"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": 2338707, "tid": 2338707, + "ts": 6197196573677.969, "dur": 2.823, + "args": { + "External id": 25610,"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": 2338707, "tid": 2338707, + "ts": 6197196573694.969, "dur": 45.492, + "args": { + "External id": 25611,"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": 2338707, "tid": 2338707, + "ts": 6197196573743.296, "dur": 15.355, + "args": { + "External id": 25612,"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": 2338707, "tid": 2338707, + "ts": 6197196573761.705, "dur": 14.793, + "args": { + "External id": 25613,"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": 2338707, "tid": 2338707, + "ts": 6197196573778.060, "dur": 13.805, + "args": { + "External id": 25614,"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": 2338707, "tid": 2338707, + "ts": 6197196573794.340, "dur": 27.066, + "args": { + "External id": 25615,"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": 2338707, "tid": 2338707, + "ts": 6197196573799.035, "dur": 1.860, + "args": { + "External id": 25616,"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": 2338707, "tid": 2338707, + "ts": 6197196573803.478, "dur": 2.969, + "args": { + "External id": 25617,"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": 2338707, "tid": 2338707, + "ts": 6197196573822.875, "dur": 15.512, + "args": { + "External id": 25618,"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": 2338707, "tid": 2338707, + "ts": 6197196573839.438, "dur": 11.902, + "args": { + "External id": 25619,"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": 2338707, "tid": 2338707, + "ts": 6197196573862.630, "dur": 2.373, + "args": { + "External id": 25620,"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": 2338707, "tid": 2338707, + "ts": 6197196573876.769, "dur": 4.626, + "args": { + "External id": 25621,"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": 2338707, "tid": 2338707, + "ts": 6197196573879.761, "dur": 0.504, + "args": { + "External id": 25622,"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": 2338707, "tid": 2338707, + "ts": 6197196573964.898, "dur": 72.202, + "args": { + "External id": 25623,"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": 2338707, "tid": 2338707, + "ts": 6197196574043.059, "dur": 5.502, + "args": { + "External id": 25624,"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": 2338707, "tid": 2338707, + "ts": 6197196574046.328, "dur": 0.978, + "args": { + "External id": 25625,"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": 2338707, "tid": 2338707, + "ts": 6197196574050.089, "dur": 68.027, + "args": { + "External id": 25626,"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": 2338707, "tid": 2338707, + "ts": 6197196574125.810, "dur": 10.175, + "args": { + "External id": 25627,"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": 2338707, "tid": 2338707, + "ts": 6197196574127.677, "dur": 7.274, + "args": { + "External id": 25628,"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": 2338707, "tid": 2338707, + "ts": 6197196574133.118, "dur": 1.607, + "args": { + "External id": 25629,"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": 2338707, "tid": 2338707, + "ts": 6197196574140.131, "dur": 58.033, + "args": { + "External id": 25630,"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": 2338707, "tid": 2338707, + "ts": 6197196574141.533, "dur": 55.788, + "args": { + "External id": 25631,"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": 2338707, "tid": 2338707, + "ts": 6197196574202.968, "dur": 19.727, + "args": { + "External id": 25632,"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": 2338707, "tid": 2338707, + "ts": 6197196574230.597, "dur": 4.240, + "args": { + "External id": 25633,"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": 2338707, "tid": 2338707, + "ts": 6197196574233.030, "dur": 0.760, + "args": { + "External id": 25634,"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": 2338707, "tid": 2338707, + "ts": 6197196574239.698, "dur": 54.777, + "args": { + "External id": 25635,"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": 2338707, "tid": 2338707, + "ts": 6197196574243.144, "dur": 4.396, + "args": { + "External id": 25636,"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": 2338707, "tid": 2338707, + "ts": 6197196574244.334, "dur": 2.517, + "args": { + "External id": 25637,"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": 2338707, "tid": 2338707, + "ts": 6197196574245.860, "dur": 0.851, + "args": { + "External id": 25638,"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": 2338707, "tid": 2338707, + "ts": 6197196574248.197, "dur": 45.714, + "args": { + "External id": 25639,"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": 2338707, "tid": 2338707, + "ts": 6197196574248.884, "dur": 44.299, + "args": { + "External id": 25640,"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": 2338707, "tid": 2338707, + "ts": 6197196574299.603, "dur": 3.986, + "args": { + "External id": 25641,"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": 2338707, "tid": 2338707, + "ts": 6197196574301.878, "dur": 0.494, + "args": { + "External id": 25642,"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": 2338707, "tid": 2338707, + "ts": 6197196574313.764, "dur": 1.883, + "args": { + "External id": 25643,"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": 2338707, "tid": 2338707, + "ts": 6197196574325.370, "dur": 7.600, + "args": { + "External id": 25644,"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": 2338707, "tid": 2338707, + "ts": 6197196574327.905, "dur": 4.753, + "args": { + "External id": 25645,"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": 2338707, "tid": 2338707, + "ts": 6197196574440.892, "dur": 216.755, + "args": { + "External id": 25646,"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": 2338707, "tid": 2338707, + "ts": 6197196574445.782, "dur": 4.616, + "args": { + "External id": 25647,"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": 2338707, "tid": 2338707, + "ts": 6197196574452.424, "dur": 204.566, + "args": { + "External id": 25648,"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": 2338707, "tid": 2338707, + "ts": 6197196574456.696, "dur": 0.497, + "args": { + "External id": 25649,"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": 2338707, "tid": 2338707, + "ts": 6197196574458.564, "dur": 26.293, + "args": { + "External id": 25650,"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": 2338707, "tid": 2338707, + "ts": 6197196574486.859, "dur": 6.413, + "args": { + "External id": 25651,"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": 2338707, "tid": 2338707, + "ts": 6197196574491.875, "dur": 1.150, + "args": { + "External id": 25652,"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": 2338707, "tid": 2338707, + "ts": 6197196574494.396, "dur": 25.534, + "args": { + "External id": 25653,"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": 2338707, "tid": 2338707, + "ts": 6197196574495.595, "dur": 1.228, + "args": { + "External id": 25654,"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": 2338707, "tid": 2338707, + "ts": 6197196574498.329, "dur": 21.258, + "args": { + "External id": 25655,"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": 2338707, "tid": 2338707, + "ts": 6197196574501.782, "dur": 2.982, + "args": { + "External id": 25656,"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": 2338707, "tid": 2338707, + "ts": 6197196574521.510, "dur": 24.441, + "args": { + "External id": 25657,"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": 2338707, "tid": 2338707, + "ts": 6197196574547.506, "dur": 18.155, + "args": { + "External id": 25658,"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": 2338707, "tid": 2338707, + "ts": 6197196574571.296, "dur": 17.634, + "args": { + "External id": 25659,"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": 2338707, "tid": 2338707, + "ts": 6197196574590.558, "dur": 14.648, + "args": { + "External id": 25660,"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": 2338707, "tid": 2338707, + "ts": 6197196574607.146, "dur": 21.402, + "args": { + "External id": 25661,"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": 2338707, "tid": 2338707, + "ts": 6197196574609.541, "dur": 1.809, + "args": { + "External id": 25662,"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": 2338707, "tid": 2338707, + "ts": 6197196574613.452, "dur": 0.451, + "args": { + "External id": 25663,"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": 2338707, "tid": 2338707, + "ts": 6197196574629.980, "dur": 13.173, + "args": { + "External id": 25664,"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": 2338707, "tid": 2338707, + "ts": 6197196574644.090, "dur": 11.770, + "args": { + "External id": 25665,"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": 2338707, "tid": 2338707, + "ts": 6197196574668.240, "dur": 1.761, + "args": { + "External id": 25666,"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": 2338707, "tid": 2338707, + "ts": 6197196574680.329, "dur": 4.145, + "args": { + "External id": 25667,"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": 2338707, "tid": 2338707, + "ts": 6197196574683.080, "dur": 0.393, + "args": { + "External id": 25668,"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": 2338707, "tid": 2338707, + "ts": 6197196574782.841, "dur": 65.576, + "args": { + "External id": 25669,"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": 2338707, "tid": 2338707, + "ts": 6197196574855.427, "dur": 6.138, + "args": { + "External id": 25670,"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": 2338707, "tid": 2338707, + "ts": 6197196574858.870, "dur": 1.116, + "args": { + "External id": 25671,"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": 2338707, "tid": 2338707, + "ts": 6197196574863.194, "dur": 28.760, + "args": { + "External id": 25672,"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": 2338707, "tid": 2338707, + "ts": 6197196574897.754, "dur": 8.770, + "args": { + "External id": 25673,"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": 2338707, "tid": 2338707, + "ts": 6197196574899.423, "dur": 6.199, + "args": { + "External id": 25674,"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": 2338707, "tid": 2338707, + "ts": 6197196574904.193, "dur": 1.220, + "args": { + "External id": 25675,"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": 2338707, "tid": 2338707, + "ts": 6197196574909.410, "dur": 47.758, + "args": { + "External id": 25676,"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": 2338707, "tid": 2338707, + "ts": 6197196574910.821, "dur": 45.480, + "args": { + "External id": 25677,"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": 2338707, "tid": 2338707, + "ts": 6197196574961.618, "dur": 17.110, + "args": { + "External id": 25678,"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": 2338707, "tid": 2338707, + "ts": 6197196574984.348, "dur": 28.558, + "args": { + "External id": 25679,"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": 2338707, "tid": 2338707, + "ts": 6197196574987.081, "dur": 25.293, + "args": { + "External id": 25680,"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": 2338707, "tid": 2338707, + "ts": 6197196574992.423, "dur": 2.458, + "args": { + "External id": 25681,"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": 2338707, "tid": 2338707, + "ts": 6197196575019.679, "dur": 32.339, + "args": { + "External id": 25682,"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": 2338707, "tid": 2338707, + "ts": 6197196575024.231, "dur": 27.470, + "args": { + "External id": 25683,"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": 2338707, "tid": 2338707, + "ts": 6197196575029.501, "dur": 4.421, + "args": { + "External id": 25684,"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": 2338707, "tid": 2338707, + "ts": 6197196575035.497, "dur": 15.566, + "args": { + "External id": 25685,"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": 2338707, "tid": 2338707, + "ts": 6197196575111.990, "dur": 7.431, + "args": { + "External id": 25686,"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": 2338707, "tid": 2338707, + "ts": 6197196575114.323, "dur": 4.501, + "args": { + "External id": 25687,"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": 2338707, "tid": 2338707, + "ts": 6197196575120.991, "dur": 4.653, + "args": { + "External id": 25688,"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": 2338707, "tid": 2338707, + "ts": 6197196575124.589, "dur": 0.658, + "args": { + "External id": 25689,"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": 2338707, "tid": 2338707, + "ts": 6197196575176.038, "dur": 31.955, + "args": { + "External id": 25690,"Sequence number": 479967, "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": 2338707, "tid": 2338707, "ts": 6197196575176.038, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338707, "tid": 2338707, + "ts": 6197196575216.209, "dur": 7.697, + "args": { + "External id": 25691,"Sequence number": 479968, "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": 2338707, "tid": 2338707, + "ts": 6197196575220.693, "dur": 1.416, + "args": { + "External id": 25692,"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": 2338707, "tid": 2338707, + "ts": 6197196575227.227, "dur": 7.460, + "args": { + "External id": 25693,"Sequence number": 479968, "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": 2338707, "tid": 2338707, + "ts": 6197196575232.550, "dur": 0.539, + "args": { + "External id": 25694,"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": 2338707, "tid": 2338707, + "ts": 6197196575236.150, "dur": 5.773, + "args": { + "External id": 25695,"Sequence number": 479968, "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": 2338707, "tid": 2338707, + "ts": 6197196575240.704, "dur": 0.465, + "args": { + "External id": 25696,"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": 2338707, "tid": 2338707, + "ts": 6197196575246.741, "dur": 7.549, + "args": { + "External id": 25697,"Sequence number": 479968, "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": 2338707, "tid": 2338707, "ts": 6197196575246.741, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2338707, + "ts": 6197196575251.812, "dur": 0.912, + "args": { + "External id": 25698,"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": 2338707, "tid": 2338707, + "ts": 6197196575255.485, "dur": 5.809, + "args": { + "External id": 25699,"Sequence number": 479969, "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": 2338707, "tid": 2338707, "ts": 6197196575255.485, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2338707, + "ts": 6197196575259.960, "dur": 0.418, + "args": { + "External id": 25700,"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": 2338707, "tid": 2338707, + "ts": 6197196575264.639, "dur": 6.228, + "args": { + "External id": 25701,"Sequence number": 479970, "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": 2338707, "tid": 2338707, "ts": 6197196575264.639, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2338707, + "ts": 6197196575268.710, "dur": 1.012, + "args": { + "External id": 25702,"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": 2338707, "tid": 2338707, + "ts": 6197196575272.511, "dur": 7.281, + "args": { + "External id": 25703,"Sequence number": 479971, "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": 2338707, "tid": 2338707, "ts": 6197196575272.511, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2338707, + "ts": 6197196575276.027, "dur": 2.824, + "args": { + "External id": 25704,"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": 2338707, "tid": 2338707, + "ts": 6197196575284.742, "dur": 39.821, + "args": { + "External id": 25705,"Sequence number": 479972, "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": 2338707, "tid": 2338707, + "ts": 6197196575286.778, "dur": 37.460, + "args": { + "External id": 25706,"Sequence number": 479972, "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": 2338707, "tid": 2338707, + "ts": 6197196575289.912, "dur": 10.521, + "args": { + "External id": 25707,"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": 2338707, "tid": 2338707, + "ts": 6197196575294.789, "dur": 4.977, + "args": { + "External id": 25708,"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": 2338707, "tid": 2338707, + "ts": 6197196575304.145, "dur": 19.485, + "args": { + "External id": 25709,"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": 2338707, "tid": 2338707, + "ts": 6197196575355.279, "dur": 5.257, + "args": { + "External id": 25710,"Sequence number": 479972, "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": 2338707, "tid": 2338707, "ts": 6197196575355.279, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6197196575363.829, "dur": 1.053, + "args": { + "External id": 25711,"Sequence number": 479973, "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": 2338707, "tid": 2338707, + "ts": 6197196575401.613, "dur": 46124.465, + "args": { + "External id": 25712,"Sequence number": 479973, "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": 2338707, "tid": 2338707, "ts": 6197196575401.613, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338707, "tid": 2338707, + "ts": 6197196575420.700, "dur": 31.970, + "args": { + "External id": 25713,"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": 2338707, "tid": 2338707, + "ts": 6197196575421.787, "dur": 30.637, + "args": { + "External id": 25714,"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": 2338707, "tid": 2338707, + "ts": 6197196575423.480, "dur": 7.848, + "args": { + "External id": 25715,"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": 2338707, "tid": 2338707, + "ts": 6197196575427.312, "dur": 3.620, + "args": { + "External id": 25716,"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": 2338707, "tid": 2338707, + "ts": 6197196575432.364, "dur": 19.532, + "args": { + "External id": 25717,"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": 2338707, "tid": 2338707, + "ts": 6197196575471.391, "dur": 31.440, + "args": { + "External id": 25718,"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": 2338707, "tid": 2338707, + "ts": 6197196575472.872, "dur": 6.318, + "args": { + "External id": 25719,"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": 2338707, "tid": 2338707, + "ts": 6197196575475.283, "dur": 3.564, + "args": { + "External id": 25720,"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": 2338707, "tid": 2338707, + "ts": 6197196575480.749, "dur": 21.802, + "args": { + "External id": 25721,"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": 2338707, "tid": 2338707, + "ts": 6197196575483.195, "dur": 18.656, + "args": { + "External id": 25722,"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": 2338707, "tid": 2338707, + "ts": 6197196575508.005, "dur": 24.172, + "args": { + "External id": 25723,"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": 2338707, "tid": 2338707, + "ts": 6197196575508.896, "dur": 5.478, + "args": { + "External id": 25724,"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": 2338707, "tid": 2338707, + "ts": 6197196575510.727, "dur": 3.393, + "args": { + "External id": 25725,"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": 2338707, "tid": 2338707, + "ts": 6197196575514.911, "dur": 17.003, + "args": { + "External id": 25726,"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": 2338707, "tid": 2338707, + "ts": 6197196575518.030, "dur": 13.497, + "args": { + "External id": 25727,"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": 2338707, "tid": 2338707, + "ts": 6197196575539.567, "dur": 19.638, + "args": { + "External id": 25728,"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": 2338707, "tid": 2338707, + "ts": 6197196575541.582, "dur": 3.094, + "args": { + "External id": 25729,"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": 2338707, "tid": 2338707, + "ts": 6197196575545.453, "dur": 13.441, + "args": { + "External id": 25730,"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": 2338707, "tid": 2338707, + "ts": 6197196575546.284, "dur": 12.283, + "args": { + "External id": 25731,"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": 2338707, "tid": 2338707, + "ts": 6197196575565.363, "dur": 26.343, + "args": { + "External id": 25732,"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": 2338707, "tid": 2338707, + "ts": 6197196575594.971, "dur": 59.709, + "args": { + "External id": 25733,"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": 2338707, "tid": 2338707, + "ts": 6197196575597.158, "dur": 57.034, + "args": { + "External id": 25734,"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": 2338707, "tid": 2338707, + "ts": 6197196575601.761, "dur": 3.090, + "args": { + "External id": 25735,"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": 2338707, "tid": 2338707, + "ts": 6197196575606.516, "dur": 29.396, + "args": { + "External id": 25736,"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": 2338707, "tid": 2338707, + "ts": 6197196575611.082, "dur": 24.605, + "args": { + "External id": 25737,"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": 2338707, "tid": 2338707, + "ts": 6197196575613.674, "dur": 3.742, + "args": { + "External id": 25738,"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": 2338707, "tid": 2338707, + "ts": 6197196575618.562, "dur": 16.775, + "args": { + "External id": 25739,"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": 2338707, "tid": 2338707, + "ts": 6197196575659.902, "dur": 39075.368, + "args": { + "External id": 25740,"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": 2338707, "tid": 2338707, + "ts": 6197196575661.729, "dur": 39072.250, + "args": { + "External id": 25741,"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": 2338707, "tid": 2338707, + "ts": 6197196614748.165, "dur": 8.115, + "args": { + "External id": 25742,"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": 2338707, "tid": 2338707, + "ts": 6197196614753.094, "dur": 1.039, + "args": { + "External id": 25743,"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": 2338707, "tid": 2338707, + "ts": 6197196614762.999, "dur": 125.286, + "args": { + "External id": 25744,"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": 2338707, "tid": 2338707, + "ts": 6197196614767.420, "dur": 6.215, + "args": { + "External id": 25745,"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": 2338707, "tid": 2338707, + "ts": 6197196614770.031, "dur": 2.623, + "args": { + "External id": 25746,"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": 2338707, "tid": 2338707, + "ts": 6197196614771.831, "dur": 0.559, + "args": { + "External id": 25747,"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": 2338707, "tid": 2338707, + "ts": 6197196614775.391, "dur": 112.126, + "args": { + "External id": 25748,"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": 2338707, "tid": 2338707, + "ts": 6197196614777.324, "dur": 108.848, + "args": { + "External id": 25749,"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": 2338707, "tid": 2338707, + "ts": 6197196614893.563, "dur": 5.427, + "args": { + "External id": 25750,"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": 2338707, "tid": 2338707, + "ts": 6197196614896.130, "dur": 0.898, + "args": { + "External id": 25751,"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": 2338707, "tid": 2338707, + "ts": 6197196614910.347, "dur": 2.838, + "args": { + "External id": 25752,"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": 2338707, "tid": 2338707, + "ts": 6197196614925.047, "dur": 7.819, + "args": { + "External id": 25753,"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": 2338707, "tid": 2338707, + "ts": 6197196614927.470, "dur": 5.014, + "args": { + "External id": 25754,"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": 2338707, "tid": 2338707, + "ts": 6197196615124.086, "dur": 255.309, + "args": { + "External id": 25755,"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": 2338707, "tid": 2338707, + "ts": 6197196615129.690, "dur": 3.338, + "args": { + "External id": 25756,"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": 2338707, "tid": 2338707, + "ts": 6197196615135.840, "dur": 242.895, + "args": { + "External id": 25757,"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": 2338707, "tid": 2338707, + "ts": 6197196615140.626, "dur": 0.636, + "args": { + "External id": 25758,"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": 2338707, "tid": 2338707, + "ts": 6197196615143.439, "dur": 35.932, + "args": { + "External id": 25759,"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": 2338707, "tid": 2338707, + "ts": 6197196615181.697, "dur": 6.468, + "args": { + "External id": 25760,"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": 2338707, "tid": 2338707, + "ts": 6197196615186.667, "dur": 1.073, + "args": { + "External id": 25761,"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": 2338707, "tid": 2338707, + "ts": 6197196615189.316, "dur": 28.017, + "args": { + "External id": 25762,"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": 2338707, "tid": 2338707, + "ts": 6197196615190.844, "dur": 1.405, + "args": { + "External id": 25763,"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": 2338707, "tid": 2338707, + "ts": 6197196615193.732, "dur": 23.286, + "args": { + "External id": 25764,"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": 2338707, "tid": 2338707, + "ts": 6197196615198.043, "dur": 3.287, + "args": { + "External id": 25765,"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": 2338707, "tid": 2338707, + "ts": 6197196615219.804, "dur": 28.995, + "args": { + "External id": 25766,"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": 2338707, "tid": 2338707, + "ts": 6197196615251.025, "dur": 18.711, + "args": { + "External id": 25767,"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": 2338707, "tid": 2338707, + "ts": 6197196615275.914, "dur": 18.086, + "args": { + "External id": 25768,"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": 2338707, "tid": 2338707, + "ts": 6197196615295.991, "dur": 17.299, + "args": { + "External id": 25769,"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": 2338707, "tid": 2338707, + "ts": 6197196615315.713, "dur": 26.325, + "args": { + "External id": 25770,"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": 2338707, "tid": 2338707, + "ts": 6197196615320.016, "dur": 1.618, + "args": { + "External id": 25771,"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": 2338707, "tid": 2338707, + "ts": 6197196615324.438, "dur": 0.702, + "args": { + "External id": 25772,"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": 2338707, "tid": 2338707, + "ts": 6197196615343.805, "dur": 16.016, + "args": { + "External id": 25773,"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": 2338707, "tid": 2338707, + "ts": 6197196615363.654, "dur": 13.815, + "args": { + "External id": 25774,"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": 2338707, "tid": 2338707, + "ts": 6197196615389.170, "dur": 2.915, + "args": { + "External id": 25775,"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": 2338707, "tid": 2338707, + "ts": 6197196615400.793, "dur": 5.117, + "args": { + "External id": 25776,"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": 2338707, "tid": 2338707, + "ts": 6197196615404.182, "dur": 0.662, + "args": { + "External id": 25777,"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": 2338707, "tid": 2338707, + "ts": 6197196615500.048, "dur": 84.667, + "args": { + "External id": 25778,"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": 2338707, "tid": 2338707, + "ts": 6197196615591.783, "dur": 6.672, + "args": { + "External id": 25779,"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": 2338707, "tid": 2338707, + "ts": 6197196615594.916, "dur": 0.873, + "args": { + "External id": 25780,"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": 2338707, "tid": 2338707, + "ts": 6197196615600.675, "dur": 31.615, + "args": { + "External id": 25781,"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": 2338707, "tid": 2338707, + "ts": 6197196615641.918, "dur": 7.795, + "args": { + "External id": 25782,"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": 2338707, "tid": 2338707, + "ts": 6197196615644.215, "dur": 4.616, + "args": { + "External id": 25783,"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": 2338707, "tid": 2338707, + "ts": 6197196615646.873, "dur": 1.634, + "args": { + "External id": 25784,"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": 2338707, "tid": 2338707, + "ts": 6197196615653.970, "dur": 77.125, + "args": { + "External id": 25785,"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": 2338707, "tid": 2338707, + "ts": 6197196615655.634, "dur": 74.340, + "args": { + "External id": 25786,"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": 2338707, "tid": 2338707, + "ts": 6197196615741.602, "dur": 22.481, + "args": { + "External id": 25787,"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": 2338707, "tid": 2338707, + "ts": 6197196615773.162, "dur": 8.373, + "args": { + "External id": 25788,"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": 2338707, "tid": 2338707, + "ts": 6197196615778.985, "dur": 0.926, + "args": { + "External id": 25789,"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": 2338707, "tid": 2338707, + "ts": 6197196615787.323, "dur": 60.970, + "args": { + "External id": 25790,"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": 2338707, "tid": 2338707, + "ts": 6197196615788.737, "dur": 4.664, + "args": { + "External id": 25791,"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": 2338707, "tid": 2338707, + "ts": 6197196615790.247, "dur": 2.452, + "args": { + "External id": 25792,"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": 2338707, "tid": 2338707, + "ts": 6197196615791.980, "dur": 0.575, + "args": { + "External id": 25793,"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": 2338707, "tid": 2338707, + "ts": 6197196615794.223, "dur": 53.594, + "args": { + "External id": 25794,"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": 2338707, "tid": 2338707, + "ts": 6197196615797.467, "dur": 49.576, + "args": { + "External id": 25795,"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": 2338707, "tid": 2338707, + "ts": 6197196615854.938, "dur": 4.685, + "args": { + "External id": 25796,"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": 2338707, "tid": 2338707, + "ts": 6197196615857.471, "dur": 0.480, + "args": { + "External id": 25797,"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": 2338707, "tid": 2338707, + "ts": 6197196615867.389, "dur": 1.946, + "args": { + "External id": 25798,"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": 2338707, "tid": 2338707, + "ts": 6197196615878.968, "dur": 9.295, + "args": { + "External id": 25799,"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": 2338707, "tid": 2338707, + "ts": 6197196615881.596, "dur": 6.323, + "args": { + "External id": 25800,"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": 2338707, "tid": 2338707, + "ts": 6197196616004.639, "dur": 274.243, + "args": { + "External id": 25801,"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": 2338707, "tid": 2338707, + "ts": 6197196616007.235, "dur": 2.290, + "args": { + "External id": 25802,"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": 2338707, "tid": 2338707, + "ts": 6197196616011.360, "dur": 266.760, + "args": { + "External id": 25803,"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": 2338707, "tid": 2338707, + "ts": 6197196616013.033, "dur": 0.561, + "args": { + "External id": 25804,"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": 2338707, "tid": 2338707, + "ts": 6197196616015.327, "dur": 29.415, + "args": { + "External id": 25805,"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": 2338707, "tid": 2338707, + "ts": 6197196616046.839, "dur": 4.421, + "args": { + "External id": 25806,"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": 2338707, "tid": 2338707, + "ts": 6197196616050.121, "dur": 0.870, + "args": { + "External id": 25807,"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": 2338707, "tid": 2338707, + "ts": 6197196616089.091, "dur": 38.522, + "args": { + "External id": 25808,"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": 2338707, "tid": 2338707, + "ts": 6197196616090.751, "dur": 5.185, + "args": { + "External id": 25809,"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": 2338707, "tid": 2338707, + "ts": 6197196616100.676, "dur": 26.544, + "args": { + "External id": 25810,"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": 2338707, "tid": 2338707, + "ts": 6197196616106.854, "dur": 3.004, + "args": { + "External id": 25811,"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": 2338707, "tid": 2338707, + "ts": 6197196616129.896, "dur": 26.894, + "args": { + "External id": 25812,"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": 2338707, "tid": 2338707, + "ts": 6197196616158.794, "dur": 16.924, + "args": { + "External id": 25813,"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": 2338707, "tid": 2338707, + "ts": 6197196616178.752, "dur": 17.127, + "args": { + "External id": 25814,"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": 2338707, "tid": 2338707, + "ts": 6197196616197.587, "dur": 15.264, + "args": { + "External id": 25815,"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": 2338707, "tid": 2338707, + "ts": 6197196616215.086, "dur": 25.829, + "args": { + "External id": 25816,"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": 2338707, "tid": 2338707, + "ts": 6197196616217.516, "dur": 2.377, + "args": { + "External id": 25817,"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": 2338707, "tid": 2338707, + "ts": 6197196616222.711, "dur": 0.859, + "args": { + "External id": 25818,"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": 2338707, "tid": 2338707, + "ts": 6197196616245.622, "dur": 15.272, + "args": { + "External id": 25819,"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": 2338707, "tid": 2338707, + "ts": 6197196616262.304, "dur": 14.385, + "args": { + "External id": 25820,"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": 2338707, "tid": 2338707, + "ts": 6197196616289.090, "dur": 3.158, + "args": { + "External id": 25821,"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": 2338707, "tid": 2338707, + "ts": 6197196616304.882, "dur": 4.847, + "args": { + "External id": 25822,"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": 2338707, "tid": 2338707, + "ts": 6197196616308.162, "dur": 0.519, + "args": { + "External id": 25823,"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": 2338707, "tid": 2338707, + "ts": 6197196616401.900, "dur": 74.770, + "args": { + "External id": 25824,"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": 2338707, "tid": 2338707, + "ts": 6197196616482.971, "dur": 8.757, + "args": { + "External id": 25825,"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": 2338707, "tid": 2338707, + "ts": 6197196616486.759, "dur": 3.446, + "args": { + "External id": 25826,"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": 2338707, "tid": 2338707, + "ts": 6197196616496.152, "dur": 32.374, + "args": { + "External id": 25827,"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": 2338707, "tid": 2338707, + "ts": 6197196616534.354, "dur": 6.879, + "args": { + "External id": 25828,"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": 2338707, "tid": 2338707, + "ts": 6197196616536.234, "dur": 4.031, + "args": { + "External id": 25829,"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": 2338707, "tid": 2338707, + "ts": 6197196616538.974, "dur": 1.081, + "args": { + "External id": 25830,"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": 2338707, "tid": 2338707, + "ts": 6197196616544.955, "dur": 50.322, + "args": { + "External id": 25831,"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": 2338707, "tid": 2338707, + "ts": 6197196616546.381, "dur": 48.018, + "args": { + "External id": 25832,"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": 2338707, "tid": 2338707, + "ts": 6197196616599.585, "dur": 18.462, + "args": { + "External id": 25833,"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": 2338707, "tid": 2338707, + "ts": 6197196616627.696, "dur": 4.178, + "args": { + "External id": 25834,"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": 2338707, "tid": 2338707, + "ts": 6197196616630.251, "dur": 0.522, + "args": { + "External id": 25835,"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": 2338707, "tid": 2338707, + "ts": 6197196616636.879, "dur": 55.302, + "args": { + "External id": 25836,"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": 2338707, "tid": 2338707, + "ts": 6197196616638.006, "dur": 3.765, + "args": { + "External id": 25837,"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": 2338707, "tid": 2338707, + "ts": 6197196616638.804, "dur": 2.342, + "args": { + "External id": 25838,"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": 2338707, "tid": 2338707, + "ts": 6197196616640.434, "dur": 0.551, + "args": { + "External id": 25839,"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": 2338707, "tid": 2338707, + "ts": 6197196616644.597, "dur": 47.094, + "args": { + "External id": 25840,"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": 2338707, "tid": 2338707, + "ts": 6197196616645.443, "dur": 45.611, + "args": { + "External id": 25841,"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": 2338707, "tid": 2338707, + "ts": 6197196616721.454, "dur": 7.221, + "args": { + "External id": 25842,"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": 2338707, "tid": 2338707, + "ts": 6197196616725.476, "dur": 0.814, + "args": { + "External id": 25843,"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": 2338707, "tid": 2338707, + "ts": 6197196616737.772, "dur": 2.054, + "args": { + "External id": 25844,"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": 2338707, "tid": 2338707, + "ts": 6197196616749.401, "dur": 14.586, + "args": { + "External id": 25845,"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": 2338707, "tid": 2338707, + "ts": 6197196616755.086, "dur": 8.440, + "args": { + "External id": 25846,"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": 2338707, "tid": 2338707, + "ts": 6197196616876.501, "dur": 295.996, + "args": { + "External id": 25847,"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": 2338707, "tid": 2338707, + "ts": 6197196616879.638, "dur": 1.700, + "args": { + "External id": 25848,"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": 2338707, "tid": 2338707, + "ts": 6197196616883.316, "dur": 288.499, + "args": { + "External id": 25849,"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": 2338707, "tid": 2338707, + "ts": 6197196616884.834, "dur": 0.363, + "args": { + "External id": 25850,"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": 2338707, "tid": 2338707, + "ts": 6197196616886.826, "dur": 30.740, + "args": { + "External id": 25851,"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": 2338707, "tid": 2338707, + "ts": 6197196616919.672, "dur": 4.137, + "args": { + "External id": 25852,"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": 2338707, "tid": 2338707, + "ts": 6197196616922.576, "dur": 0.924, + "args": { + "External id": 25853,"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": 2338707, "tid": 2338707, + "ts": 6197196616924.912, "dur": 33.381, + "args": { + "External id": 25854,"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": 2338707, "tid": 2338707, + "ts": 6197196616928.617, "dur": 1.471, + "args": { + "External id": 25855,"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": 2338707, "tid": 2338707, + "ts": 6197196616931.495, "dur": 26.311, + "args": { + "External id": 25856,"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": 2338707, "tid": 2338707, + "ts": 6197196616936.765, "dur": 3.548, + "args": { + "External id": 25857,"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": 2338707, "tid": 2338707, + "ts": 6197196616959.936, "dur": 42.100, + "args": { + "External id": 25858,"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": 2338707, "tid": 2338707, + "ts": 6197196617003.748, "dur": 21.930, + "args": { + "External id": 25859,"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": 2338707, "tid": 2338707, + "ts": 6197196617028.817, "dur": 18.862, + "args": { + "External id": 25860,"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": 2338707, "tid": 2338707, + "ts": 6197196617049.659, "dur": 56.676, + "args": { + "External id": 25861,"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": 2338707, "tid": 2338707, + "ts": 6197196617110.080, "dur": 29.444, + "args": { + "External id": 25862,"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": 2338707, "tid": 2338707, + "ts": 6197196617112.790, "dur": 2.341, + "args": { + "External id": 25863,"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": 2338707, "tid": 2338707, + "ts": 6197196617119.850, "dur": 0.883, + "args": { + "External id": 25864,"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": 2338707, "tid": 2338707, + "ts": 6197196617141.450, "dur": 15.515, + "args": { + "External id": 25865,"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": 2338707, "tid": 2338707, + "ts": 6197196617158.190, "dur": 12.316, + "args": { + "External id": 25866,"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": 2338707, "tid": 2338707, + "ts": 6197196617182.691, "dur": 2.590, + "args": { + "External id": 25867,"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": 2338707, "tid": 2338707, + "ts": 6197196617197.566, "dur": 4.762, + "args": { + "External id": 25868,"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": 2338707, "tid": 2338707, + "ts": 6197196617200.677, "dur": 0.700, + "args": { + "External id": 25869,"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": 2338707, "tid": 2338707, + "ts": 6197196617284.121, "dur": 70.745, + "args": { + "External id": 25870,"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": 2338707, "tid": 2338707, + "ts": 6197196617363.333, "dur": 5.680, + "args": { + "External id": 25871,"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": 2338707, "tid": 2338707, + "ts": 6197196617366.332, "dur": 1.081, + "args": { + "External id": 25872,"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": 2338707, "tid": 2338707, + "ts": 6197196617370.906, "dur": 30.466, + "args": { + "External id": 25873,"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": 2338707, "tid": 2338707, + "ts": 6197196617407.272, "dur": 6.261, + "args": { + "External id": 25874,"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": 2338707, "tid": 2338707, + "ts": 6197196617409.225, "dur": 3.483, + "args": { + "External id": 25875,"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": 2338707, "tid": 2338707, + "ts": 6197196617411.505, "dur": 0.960, + "args": { + "External id": 25876,"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": 2338707, "tid": 2338707, + "ts": 6197196617419.034, "dur": 48.985, + "args": { + "External id": 25877,"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": 2338707, "tid": 2338707, + "ts": 6197196617420.506, "dur": 46.820, + "args": { + "External id": 25878,"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": 2338707, "tid": 2338707, + "ts": 6197196617472.466, "dur": 15.390, + "args": { + "External id": 25879,"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": 2338707, "tid": 2338707, + "ts": 6197196617495.332, "dur": 4.329, + "args": { + "External id": 25880,"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": 2338707, "tid": 2338707, + "ts": 6197196617497.902, "dur": 0.727, + "args": { + "External id": 25881,"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": 2338707, "tid": 2338707, + "ts": 6197196617504.611, "dur": 54.740, + "args": { + "External id": 25882,"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": 2338707, "tid": 2338707, + "ts": 6197196617505.697, "dur": 8.378, + "args": { + "External id": 25883,"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": 2338707, "tid": 2338707, + "ts": 6197196617509.254, "dur": 4.014, + "args": { + "External id": 25884,"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": 2338707, "tid": 2338707, + "ts": 6197196617510.972, "dur": 2.085, + "args": { + "External id": 25885,"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": 2338707, "tid": 2338707, + "ts": 6197196617514.756, "dur": 44.174, + "args": { + "External id": 25886,"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": 2338707, "tid": 2338707, + "ts": 6197196617515.548, "dur": 42.712, + "args": { + "External id": 25887,"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": 2338707, "tid": 2338707, + "ts": 6197196617564.263, "dur": 4.561, + "args": { + "External id": 25888,"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": 2338707, "tid": 2338707, + "ts": 6197196617566.687, "dur": 0.666, + "args": { + "External id": 25889,"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": 2338707, "tid": 2338707, + "ts": 6197196617575.172, "dur": 1.739, + "args": { + "External id": 25890,"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": 2338707, "tid": 2338707, + "ts": 6197196617588.322, "dur": 8.895, + "args": { + "External id": 25891,"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": 2338707, "tid": 2338707, + "ts": 6197196617590.560, "dur": 6.339, + "args": { + "External id": 25892,"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": 2338707, "tid": 2338707, + "ts": 6197196617692.186, "dur": 223.155, + "args": { + "External id": 25893,"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": 2338707, "tid": 2338707, + "ts": 6197196617695.052, "dur": 2.065, + "args": { + "External id": 25894,"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": 2338707, "tid": 2338707, + "ts": 6197196617698.676, "dur": 216.077, + "args": { + "External id": 25895,"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": 2338707, "tid": 2338707, + "ts": 6197196617717.477, "dur": 0.462, + "args": { + "External id": 25896,"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": 2338707, "tid": 2338707, + "ts": 6197196617724.644, "dur": 26.946, + "args": { + "External id": 25897,"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": 2338707, "tid": 2338707, + "ts": 6197196617753.439, "dur": 3.706, + "args": { + "External id": 25898,"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": 2338707, "tid": 2338707, + "ts": 6197196617755.937, "dur": 0.833, + "args": { + "External id": 25899,"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": 2338707, "tid": 2338707, + "ts": 6197196617758.126, "dur": 24.926, + "args": { + "External id": 25900,"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": 2338707, "tid": 2338707, + "ts": 6197196617759.334, "dur": 3.305, + "args": { + "External id": 25901,"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": 2338707, "tid": 2338707, + "ts": 6197196617764.121, "dur": 18.580, + "args": { + "External id": 25902,"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": 2338707, "tid": 2338707, + "ts": 6197196617767.597, "dur": 3.021, + "args": { + "External id": 25903,"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": 2338707, "tid": 2338707, + "ts": 6197196617784.849, "dur": 25.286, + "args": { + "External id": 25904,"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": 2338707, "tid": 2338707, + "ts": 6197196617811.805, "dur": 14.356, + "args": { + "External id": 25905,"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": 2338707, "tid": 2338707, + "ts": 6197196617829.395, "dur": 15.082, + "args": { + "External id": 25906,"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": 2338707, "tid": 2338707, + "ts": 6197196617846.225, "dur": 12.666, + "args": { + "External id": 25907,"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": 2338707, "tid": 2338707, + "ts": 6197196617863.381, "dur": 21.774, + "args": { + "External id": 25908,"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": 2338707, "tid": 2338707, + "ts": 6197196617865.836, "dur": 1.735, + "args": { + "External id": 25909,"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": 2338707, "tid": 2338707, + "ts": 6197196617870.590, "dur": 0.558, + "args": { + "External id": 25910,"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": 2338707, "tid": 2338707, + "ts": 6197196617886.814, "dur": 13.323, + "args": { + "External id": 25911,"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": 2338707, "tid": 2338707, + "ts": 6197196617901.495, "dur": 12.085, + "args": { + "External id": 25912,"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": 2338707, "tid": 2338707, + "ts": 6197196617924.508, "dur": 2.576, + "args": { + "External id": 25913,"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": 2338707, "tid": 2338707, + "ts": 6197196617937.389, "dur": 4.197, + "args": { + "External id": 25914,"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": 2338707, "tid": 2338707, + "ts": 6197196617940.207, "dur": 0.416, + "args": { + "External id": 25915,"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": 2338707, "tid": 2338707, + "ts": 6197196618019.032, "dur": 106.021, + "args": { + "External id": 25916,"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": 2338707, "tid": 2338707, + "ts": 6197196618133.892, "dur": 7.326, + "args": { + "External id": 25917,"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": 2338707, "tid": 2338707, + "ts": 6197196618138.015, "dur": 1.205, + "args": { + "External id": 25918,"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": 2338707, "tid": 2338707, + "ts": 6197196618142.976, "dur": 29.260, + "args": { + "External id": 25919,"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": 2338707, "tid": 2338707, + "ts": 6197196618178.927, "dur": 8.949, + "args": { + "External id": 25920,"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": 2338707, "tid": 2338707, + "ts": 6197196618181.037, "dur": 6.034, + "args": { + "External id": 25921,"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": 2338707, "tid": 2338707, + "ts": 6197196618185.814, "dur": 1.038, + "args": { + "External id": 25922,"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": 2338707, "tid": 2338707, + "ts": 6197196618191.442, "dur": 52.605, + "args": { + "External id": 25923,"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": 2338707, "tid": 2338707, + "ts": 6197196618192.550, "dur": 50.792, + "args": { + "External id": 25924,"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": 2338707, "tid": 2338707, + "ts": 6197196618248.781, "dur": 17.233, + "args": { + "External id": 25925,"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": 2338707, "tid": 2338707, + "ts": 6197196618273.881, "dur": 3.502, + "args": { + "External id": 25926,"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": 2338707, "tid": 2338707, + "ts": 6197196618275.979, "dur": 0.383, + "args": { + "External id": 25927,"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": 2338707, "tid": 2338707, + "ts": 6197196618282.174, "dur": 54.299, + "args": { + "External id": 25928,"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": 2338707, "tid": 2338707, + "ts": 6197196618285.617, "dur": 5.635, + "args": { + "External id": 25929,"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": 2338707, "tid": 2338707, + "ts": 6197196618286.573, "dur": 3.911, + "args": { + "External id": 25930,"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": 2338707, "tid": 2338707, + "ts": 6197196618289.834, "dur": 0.453, + "args": { + "External id": 25931,"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": 2338707, "tid": 2338707, + "ts": 6197196618291.944, "dur": 44.101, + "args": { + "External id": 25932,"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": 2338707, "tid": 2338707, + "ts": 6197196618292.537, "dur": 42.841, + "args": { + "External id": 25933,"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": 2338707, "tid": 2338707, + "ts": 6197196618342.302, "dur": 3.903, + "args": { + "External id": 25934,"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": 2338707, "tid": 2338707, + "ts": 6197196618344.462, "dur": 0.383, + "args": { + "External id": 25935,"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": 2338707, "tid": 2338707, + "ts": 6197196618355.766, "dur": 1.641, + "args": { + "External id": 25936,"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": 2338707, "tid": 2338707, + "ts": 6197196618366.905, "dur": 10.013, + "args": { + "External id": 25937,"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": 2338707, "tid": 2338707, + "ts": 6197196618369.400, "dur": 7.186, + "args": { + "External id": 25938,"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": 2338707, "tid": 2338707, + "ts": 6197196618475.735, "dur": 204.236, + "args": { + "External id": 25939,"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": 2338707, "tid": 2338707, + "ts": 6197196618478.052, "dur": 2.043, + "args": { + "External id": 25940,"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": 2338707, "tid": 2338707, + "ts": 6197196618481.787, "dur": 197.649, + "args": { + "External id": 25941,"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": 2338707, "tid": 2338707, + "ts": 6197196618487.626, "dur": 0.372, + "args": { + "External id": 25942,"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": 2338707, "tid": 2338707, + "ts": 6197196618489.778, "dur": 23.827, + "args": { + "External id": 25943,"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": 2338707, "tid": 2338707, + "ts": 6197196618515.718, "dur": 4.221, + "args": { + "External id": 25944,"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": 2338707, "tid": 2338707, + "ts": 6197196618518.690, "dur": 1.040, + "args": { + "External id": 25945,"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": 2338707, "tid": 2338707, + "ts": 6197196618520.992, "dur": 25.993, + "args": { + "External id": 25946,"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": 2338707, "tid": 2338707, + "ts": 6197196618523.338, "dur": 1.105, + "args": { + "External id": 25947,"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": 2338707, "tid": 2338707, + "ts": 6197196618526.118, "dur": 20.480, + "args": { + "External id": 25948,"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": 2338707, "tid": 2338707, + "ts": 6197196618529.222, "dur": 4.137, + "args": { + "External id": 25949,"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": 2338707, "tid": 2338707, + "ts": 6197196618548.562, "dur": 25.668, + "args": { + "External id": 25950,"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": 2338707, "tid": 2338707, + "ts": 6197196618575.737, "dur": 16.514, + "args": { + "External id": 25951,"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": 2338707, "tid": 2338707, + "ts": 6197196618597.946, "dur": 14.233, + "args": { + "External id": 25952,"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": 2338707, "tid": 2338707, + "ts": 6197196618613.782, "dur": 13.264, + "args": { + "External id": 25953,"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": 2338707, "tid": 2338707, + "ts": 6197196618629.003, "dur": 20.883, + "args": { + "External id": 25954,"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": 2338707, "tid": 2338707, + "ts": 6197196618630.726, "dur": 1.907, + "args": { + "External id": 25955,"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": 2338707, "tid": 2338707, + "ts": 6197196618635.290, "dur": 0.648, + "args": { + "External id": 25956,"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": 2338707, "tid": 2338707, + "ts": 6197196618651.316, "dur": 12.597, + "args": { + "External id": 25957,"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": 2338707, "tid": 2338707, + "ts": 6197196618667.339, "dur": 10.958, + "args": { + "External id": 25958,"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": 2338707, "tid": 2338707, + "ts": 6197196618687.566, "dur": 1.687, + "args": { + "External id": 25959,"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": 2338707, "tid": 2338707, + "ts": 6197196618698.770, "dur": 23.207, + "args": { + "External id": 25960,"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": 2338707, "tid": 2338707, + "ts": 6197196618719.703, "dur": 0.803, + "args": { + "External id": 25961,"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": 2338707, "tid": 2338707, + "ts": 6197196618799.544, "dur": 63.813, + "args": { + "External id": 25962,"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": 2338707, "tid": 2338707, + "ts": 6197196618869.533, "dur": 7.909, + "args": { + "External id": 25963,"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": 2338707, "tid": 2338707, + "ts": 6197196618873.031, "dur": 3.049, + "args": { + "External id": 25964,"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": 2338707, "tid": 2338707, + "ts": 6197196618879.197, "dur": 28.480, + "args": { + "External id": 25965,"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": 2338707, "tid": 2338707, + "ts": 6197196618915.574, "dur": 5.733, + "args": { + "External id": 25966,"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": 2338707, "tid": 2338707, + "ts": 6197196618917.257, "dur": 3.250, + "args": { + "External id": 25967,"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": 2338707, "tid": 2338707, + "ts": 6197196618919.378, "dur": 0.958, + "args": { + "External id": 25968,"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": 2338707, "tid": 2338707, + "ts": 6197196618924.234, "dur": 46.217, + "args": { + "External id": 25969,"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": 2338707, "tid": 2338707, + "ts": 6197196618925.253, "dur": 44.269, + "args": { + "External id": 25970,"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": 2338707, "tid": 2338707, + "ts": 6197196618979.709, "dur": 16.554, + "args": { + "External id": 25971,"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": 2338707, "tid": 2338707, + "ts": 6197196619003.073, "dur": 6.669, + "args": { + "External id": 25972,"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": 2338707, "tid": 2338707, + "ts": 6197196619007.962, "dur": 0.559, + "args": { + "External id": 25973,"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": 2338707, "tid": 2338707, + "ts": 6197196619014.342, "dur": 96.517, + "args": { + "External id": 25974,"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": 2338707, "tid": 2338707, + "ts": 6197196619015.370, "dur": 6.791, + "args": { + "External id": 25975,"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": 2338707, "tid": 2338707, + "ts": 6197196619016.234, "dur": 5.059, + "args": { + "External id": 25976,"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": 2338707, "tid": 2338707, + "ts": 6197196619017.839, "dur": 3.294, + "args": { + "External id": 25977,"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": 2338707, "tid": 2338707, + "ts": 6197196619022.740, "dur": 87.488, + "args": { + "External id": 25978,"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": 2338707, "tid": 2338707, + "ts": 6197196619026.077, "dur": 82.707, + "args": { + "External id": 25979,"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": 2338707, "tid": 2338707, + "ts": 6197196619119.033, "dur": 5.681, + "args": { + "External id": 25980,"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": 2338707, "tid": 2338707, + "ts": 6197196619122.172, "dur": 0.923, + "args": { + "External id": 25981,"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": 2338707, "tid": 2338707, + "ts": 6197196619132.416, "dur": 1.867, + "args": { + "External id": 25982,"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": 2338707, "tid": 2338707, + "ts": 6197196619143.319, "dur": 9.143, + "args": { + "External id": 25983,"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": 2338707, "tid": 2338707, + "ts": 6197196619145.892, "dur": 6.186, + "args": { + "External id": 25984,"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": 2338707, "tid": 2338707, + "ts": 6197196619257.177, "dur": 207.333, + "args": { + "External id": 25985,"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": 2338707, "tid": 2338707, + "ts": 6197196619259.746, "dur": 2.316, + "args": { + "External id": 25986,"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": 2338707, "tid": 2338707, + "ts": 6197196619263.558, "dur": 200.435, + "args": { + "External id": 25987,"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": 2338707, "tid": 2338707, + "ts": 6197196619265.084, "dur": 0.373, + "args": { + "External id": 25988,"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": 2338707, "tid": 2338707, + "ts": 6197196619267.028, "dur": 27.730, + "args": { + "External id": 25989,"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": 2338707, "tid": 2338707, + "ts": 6197196619296.589, "dur": 3.467, + "args": { + "External id": 25990,"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": 2338707, "tid": 2338707, + "ts": 6197196619299.114, "dur": 0.762, + "args": { + "External id": 25991,"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": 2338707, "tid": 2338707, + "ts": 6197196619301.016, "dur": 28.024, + "args": { + "External id": 25992,"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": 2338707, "tid": 2338707, + "ts": 6197196619302.138, "dur": 1.709, + "args": { + "External id": 25993,"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": 2338707, "tid": 2338707, + "ts": 6197196619307.896, "dur": 20.822, + "args": { + "External id": 25994,"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": 2338707, "tid": 2338707, + "ts": 6197196619312.866, "dur": 2.835, + "args": { + "External id": 25995,"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": 2338707, "tid": 2338707, + "ts": 6197196619331.178, "dur": 27.446, + "args": { + "External id": 25996,"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": 2338707, "tid": 2338707, + "ts": 6197196619360.590, "dur": 14.050, + "args": { + "External id": 25997,"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": 2338707, "tid": 2338707, + "ts": 6197196619377.627, "dur": 16.499, + "args": { + "External id": 25998,"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": 2338707, "tid": 2338707, + "ts": 6197196619395.732, "dur": 13.374, + "args": { + "External id": 25999,"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": 2338707, "tid": 2338707, + "ts": 6197196619411.044, "dur": 21.609, + "args": { + "External id": 26000,"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": 2338707, "tid": 2338707, + "ts": 6197196619413.103, "dur": 2.222, + "args": { + "External id": 26001,"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": 2338707, "tid": 2338707, + "ts": 6197196619417.828, "dur": 0.782, + "args": { + "External id": 26002,"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": 2338707, "tid": 2338707, + "ts": 6197196619437.226, "dur": 12.382, + "args": { + "External id": 26003,"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": 2338707, "tid": 2338707, + "ts": 6197196619450.785, "dur": 11.968, + "args": { + "External id": 26004,"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": 2338707, "tid": 2338707, + "ts": 6197196619472.814, "dur": 1.884, + "args": { + "External id": 26005,"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": 2338707, "tid": 2338707, + "ts": 6197196619485.413, "dur": 4.566, + "args": { + "External id": 26006,"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": 2338707, "tid": 2338707, + "ts": 6197196619488.464, "dur": 0.605, + "args": { + "External id": 26007,"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": 2338707, "tid": 2338707, + "ts": 6197196619565.409, "dur": 66.300, + "args": { + "External id": 26008,"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": 2338707, "tid": 2338707, + "ts": 6197196619637.646, "dur": 5.956, + "args": { + "External id": 26009,"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": 2338707, "tid": 2338707, + "ts": 6197196619641.307, "dur": 0.866, + "args": { + "External id": 26010,"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": 2338707, "tid": 2338707, + "ts": 6197196619648.390, "dur": 27.772, + "args": { + "External id": 26011,"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": 2338707, "tid": 2338707, + "ts": 6197196619681.619, "dur": 6.409, + "args": { + "External id": 26012,"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": 2338707, "tid": 2338707, + "ts": 6197196619683.641, "dur": 3.479, + "args": { + "External id": 26013,"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": 2338707, "tid": 2338707, + "ts": 6197196619685.974, "dur": 0.935, + "args": { + "External id": 26014,"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": 2338707, "tid": 2338707, + "ts": 6197196619691.218, "dur": 69.601, + "args": { + "External id": 26015,"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": 2338707, "tid": 2338707, + "ts": 6197196619692.453, "dur": 67.026, + "args": { + "External id": 26016,"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": 2338707, "tid": 2338707, + "ts": 6197196619766.964, "dur": 18.433, + "args": { + "External id": 26017,"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": 2338707, "tid": 2338707, + "ts": 6197196619795.668, "dur": 5.210, + "args": { + "External id": 26018,"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": 2338707, "tid": 2338707, + "ts": 6197196619798.512, "dur": 0.869, + "args": { + "External id": 26019,"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": 2338707, "tid": 2338707, + "ts": 6197196619805.851, "dur": 56.243, + "args": { + "External id": 26020,"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": 2338707, "tid": 2338707, + "ts": 6197196619806.994, "dur": 5.758, + "args": { + "External id": 26021,"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": 2338707, "tid": 2338707, + "ts": 6197196619807.870, "dur": 4.227, + "args": { + "External id": 26022,"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": 2338707, "tid": 2338707, + "ts": 6197196619809.668, "dur": 2.200, + "args": { + "External id": 26023,"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": 2338707, "tid": 2338707, + "ts": 6197196619816.120, "dur": 45.376, + "args": { + "External id": 26024,"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": 2338707, "tid": 2338707, + "ts": 6197196619816.939, "dur": 43.827, + "args": { + "External id": 26025,"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": 2338707, "tid": 2338707, + "ts": 6197196619867.048, "dur": 4.143, + "args": { + "External id": 26026,"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": 2338707, "tid": 2338707, + "ts": 6197196619869.445, "dur": 0.514, + "args": { + "External id": 26027,"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": 2338707, "tid": 2338707, + "ts": 6197196619878.101, "dur": 1.534, + "args": { + "External id": 26028,"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": 2338707, "tid": 2338707, + "ts": 6197196619888.830, "dur": 15.376, + "args": { + "External id": 26029,"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": 2338707, "tid": 2338707, + "ts": 6197196619896.997, "dur": 6.880, + "args": { + "External id": 26030,"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": 2338707, "tid": 2338707, + "ts": 6197196620002.041, "dur": 262.321, + "args": { + "External id": 26031,"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": 2338707, "tid": 2338707, + "ts": 6197196620005.882, "dur": 1.835, + "args": { + "External id": 26032,"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": 2338707, "tid": 2338707, + "ts": 6197196620009.233, "dur": 254.496, + "args": { + "External id": 26033,"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": 2338707, "tid": 2338707, + "ts": 6197196620010.750, "dur": 0.401, + "args": { + "External id": 26034,"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": 2338707, "tid": 2338707, + "ts": 6197196620012.977, "dur": 23.830, + "args": { + "External id": 26035,"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": 2338707, "tid": 2338707, + "ts": 6197196620038.702, "dur": 5.037, + "args": { + "External id": 26036,"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": 2338707, "tid": 2338707, + "ts": 6197196620042.627, "dur": 0.896, + "args": { + "External id": 26037,"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": 2338707, "tid": 2338707, + "ts": 6197196620044.730, "dur": 67.609, + "args": { + "External id": 26038,"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": 2338707, "tid": 2338707, + "ts": 6197196620048.619, "dur": 1.418, + "args": { + "External id": 26039,"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": 2338707, "tid": 2338707, + "ts": 6197196620051.493, "dur": 60.414, + "args": { + "External id": 26040,"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": 2338707, "tid": 2338707, + "ts": 6197196620054.703, "dur": 41.359, + "args": { + "External id": 26041,"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": 2338707, "tid": 2338707, + "ts": 6197196620114.730, "dur": 25.039, + "args": { + "External id": 26042,"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": 2338707, "tid": 2338707, + "ts": 6197196620141.593, "dur": 17.441, + "args": { + "External id": 26043,"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": 2338707, "tid": 2338707, + "ts": 6197196620162.627, "dur": 16.436, + "args": { + "External id": 26044,"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": 2338707, "tid": 2338707, + "ts": 6197196620180.573, "dur": 15.881, + "args": { + "External id": 26045,"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": 2338707, "tid": 2338707, + "ts": 6197196620198.585, "dur": 32.734, + "args": { + "External id": 26046,"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": 2338707, "tid": 2338707, + "ts": 6197196620202.634, "dur": 2.030, + "args": { + "External id": 26047,"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": 2338707, "tid": 2338707, + "ts": 6197196620209.660, "dur": 0.828, + "args": { + "External id": 26048,"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": 2338707, "tid": 2338707, + "ts": 6197196620232.718, "dur": 15.205, + "args": { + "External id": 26049,"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": 2338707, "tid": 2338707, + "ts": 6197196620249.014, "dur": 13.470, + "args": { + "External id": 26050,"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": 2338707, "tid": 2338707, + "ts": 6197196620273.583, "dur": 2.504, + "args": { + "External id": 26051,"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": 2338707, "tid": 2338707, + "ts": 6197196620287.389, "dur": 4.490, + "args": { + "External id": 26052,"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": 2338707, "tid": 2338707, + "ts": 6197196620290.334, "dur": 0.587, + "args": { + "External id": 26053,"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": 2338707, "tid": 2338707, + "ts": 6197196620374.205, "dur": 68.664, + "args": { + "External id": 26054,"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": 2338707, "tid": 2338707, + "ts": 6197196620451.694, "dur": 5.683, + "args": { + "External id": 26055,"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": 2338707, "tid": 2338707, + "ts": 6197196620455.049, "dur": 0.802, + "args": { + "External id": 26056,"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": 2338707, "tid": 2338707, + "ts": 6197196620458.910, "dur": 30.271, + "args": { + "External id": 26057,"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": 2338707, "tid": 2338707, + "ts": 6197196620494.259, "dur": 6.444, + "args": { + "External id": 26058,"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": 2338707, "tid": 2338707, + "ts": 6197196620496.107, "dur": 3.582, + "args": { + "External id": 26059,"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": 2338707, "tid": 2338707, + "ts": 6197196620498.266, "dur": 1.210, + "args": { + "External id": 26060,"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": 2338707, "tid": 2338707, + "ts": 6197196620506.349, "dur": 48.933, + "args": { + "External id": 26061,"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": 2338707, "tid": 2338707, + "ts": 6197196620507.523, "dur": 46.750, + "args": { + "External id": 26062,"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": 2338707, "tid": 2338707, + "ts": 6197196620559.336, "dur": 17.647, + "args": { + "External id": 26063,"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": 2338707, "tid": 2338707, + "ts": 6197196620583.684, "dur": 4.278, + "args": { + "External id": 26064,"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": 2338707, "tid": 2338707, + "ts": 6197196620586.216, "dur": 0.470, + "args": { + "External id": 26065,"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": 2338707, "tid": 2338707, + "ts": 6197196620592.622, "dur": 56.109, + "args": { + "External id": 26066,"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": 2338707, "tid": 2338707, + "ts": 6197196620596.865, "dur": 6.427, + "args": { + "External id": 26067,"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": 2338707, "tid": 2338707, + "ts": 6197196620600.269, "dur": 2.338, + "args": { + "External id": 26068,"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": 2338707, "tid": 2338707, + "ts": 6197196620601.786, "dur": 0.661, + "args": { + "External id": 26069,"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": 2338707, "tid": 2338707, + "ts": 6197196620603.930, "dur": 44.368, + "args": { + "External id": 26070,"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": 2338707, "tid": 2338707, + "ts": 6197196620604.587, "dur": 42.936, + "args": { + "External id": 26071,"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": 2338707, "tid": 2338707, + "ts": 6197196620653.519, "dur": 4.525, + "args": { + "External id": 26072,"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": 2338707, "tid": 2338707, + "ts": 6197196620656.031, "dur": 0.643, + "args": { + "External id": 26073,"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": 2338707, "tid": 2338707, + "ts": 6197196620663.751, "dur": 1.753, + "args": { + "External id": 26074,"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": 2338707, "tid": 2338707, + "ts": 6197196620676.778, "dur": 10.574, + "args": { + "External id": 26075,"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": 2338707, "tid": 2338707, + "ts": 6197196620679.223, "dur": 7.681, + "args": { + "External id": 26076,"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": 2338707, "tid": 2338707, + "ts": 6197196620814.296, "dur": 203.326, + "args": { + "External id": 26077,"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": 2338707, "tid": 2338707, + "ts": 6197196620816.839, "dur": 3.178, + "args": { + "External id": 26078,"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": 2338707, "tid": 2338707, + "ts": 6197196620821.947, "dur": 195.271, + "args": { + "External id": 26079,"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": 2338707, "tid": 2338707, + "ts": 6197196620823.439, "dur": 0.432, + "args": { + "External id": 26080,"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": 2338707, "tid": 2338707, + "ts": 6197196620827.480, "dur": 29.622, + "args": { + "External id": 26081,"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": 2338707, "tid": 2338707, + "ts": 6197196620859.133, "dur": 3.765, + "args": { + "External id": 26082,"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": 2338707, "tid": 2338707, + "ts": 6197196620861.559, "dur": 1.049, + "args": { + "External id": 26083,"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": 2338707, "tid": 2338707, + "ts": 6197196620863.825, "dur": 25.200, + "args": { + "External id": 26084,"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": 2338707, "tid": 2338707, + "ts": 6197196620865.007, "dur": 1.404, + "args": { + "External id": 26085,"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": 2338707, "tid": 2338707, + "ts": 6197196620867.735, "dur": 20.942, + "args": { + "External id": 26086,"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": 2338707, "tid": 2338707, + "ts": 6197196620872.496, "dur": 2.863, + "args": { + "External id": 26087,"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": 2338707, "tid": 2338707, + "ts": 6197196620890.676, "dur": 22.946, + "args": { + "External id": 26088,"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": 2338707, "tid": 2338707, + "ts": 6197196620915.566, "dur": 14.272, + "args": { + "External id": 26089,"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": 2338707, "tid": 2338707, + "ts": 6197196620932.605, "dur": 15.614, + "args": { + "External id": 26090,"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": 2338707, "tid": 2338707, + "ts": 6197196620949.625, "dur": 13.194, + "args": { + "External id": 26091,"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": 2338707, "tid": 2338707, + "ts": 6197196620967.163, "dur": 21.354, + "args": { + "External id": 26092,"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": 2338707, "tid": 2338707, + "ts": 6197196620969.515, "dur": 2.137, + "args": { + "External id": 26093,"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": 2338707, "tid": 2338707, + "ts": 6197196620973.668, "dur": 0.455, + "args": { + "External id": 26094,"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": 2338707, "tid": 2338707, + "ts": 6197196620989.997, "dur": 13.433, + "args": { + "External id": 26095,"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": 2338707, "tid": 2338707, + "ts": 6197196621004.619, "dur": 11.395, + "args": { + "External id": 26096,"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": 2338707, "tid": 2338707, + "ts": 6197196621025.373, "dur": 2.108, + "args": { + "External id": 26097,"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": 2338707, "tid": 2338707, + "ts": 6197196621037.527, "dur": 4.069, + "args": { + "External id": 26098,"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": 2338707, "tid": 2338707, + "ts": 6197196621040.288, "dur": 0.412, + "args": { + "External id": 26099,"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": 2338707, "tid": 2338707, + "ts": 6197196621160.988, "dur": 68.119, + "args": { + "External id": 26100,"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": 2338707, "tid": 2338707, + "ts": 6197196621235.775, "dur": 7.840, + "args": { + "External id": 26101,"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": 2338707, "tid": 2338707, + "ts": 6197196621240.553, "dur": 1.200, + "args": { + "External id": 26102,"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": 2338707, "tid": 2338707, + "ts": 6197196621245.256, "dur": 29.265, + "args": { + "External id": 26103,"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": 2338707, "tid": 2338707, + "ts": 6197196621280.693, "dur": 9.163, + "args": { + "External id": 26104,"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": 2338707, "tid": 2338707, + "ts": 6197196621282.945, "dur": 5.975, + "args": { + "External id": 26105,"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": 2338707, "tid": 2338707, + "ts": 6197196621287.760, "dur": 0.931, + "args": { + "External id": 26106,"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": 2338707, "tid": 2338707, + "ts": 6197196621292.944, "dur": 47.186, + "args": { + "External id": 26107,"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": 2338707, "tid": 2338707, + "ts": 6197196621294.083, "dur": 45.283, + "args": { + "External id": 26108,"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": 2338707, "tid": 2338707, + "ts": 6197196621344.589, "dur": 17.072, + "args": { + "External id": 26109,"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": 2338707, "tid": 2338707, + "ts": 6197196621367.382, "dur": 29.399, + "args": { + "External id": 26110,"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": 2338707, "tid": 2338707, + "ts": 6197196621370.572, "dur": 25.637, + "args": { + "External id": 26111,"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": 2338707, "tid": 2338707, + "ts": 6197196621378.094, "dur": 0.614, + "args": { + "External id": 26112,"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": 2338707, "tid": 2338707, + "ts": 6197196621443.567, "dur": 33.348, + "args": { + "External id": 26113,"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": 2338707, "tid": 2338707, + "ts": 6197196621445.865, "dur": 30.745, + "args": { + "External id": 26114,"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": 2338707, "tid": 2338707, + "ts": 6197196621454.141, "dur": 4.834, + "args": { + "External id": 26115,"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": 2338707, "tid": 2338707, + "ts": 6197196621460.342, "dur": 15.527, + "args": { + "External id": 26116,"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": 2338707, "tid": 2338707, + "ts": 6197196621490.917, "dur": 5.378, + "args": { + "External id": 26117,"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": 2338707, "tid": 2338707, + "ts": 6197196621492.887, "dur": 3.073, + "args": { + "External id": 26118,"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": 2338707, "tid": 2338707, + "ts": 6197196621497.629, "dur": 1.198, + "args": { + "External id": 26119,"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": 2338707, "tid": 2338707, + "ts": 6197196621498.055, "dur": 0.686, + "args": { + "External id": 26120,"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": 2338707, "tid": 2338707, + "ts": 6197196621545.585, "dur": 25.820, + "args": { + "External id": 26121,"Sequence number": 479974, "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": 2338707, "tid": 2338707, + "ts": 6197196621576.329, "dur": 15.106, + "args": { + "External id": 26122,"Sequence number": 479975, "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": 2338707, "tid": 2338707, "ts": 6197196621576.329, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338707, "tid": 2338707, + "ts": 6197196621598.719, "dur": 7.059, + "args": { + "External id": 26123,"Sequence number": 479976, "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": 2338707, "tid": 2338707, + "ts": 6197196621602.805, "dur": 1.314, + "args": { + "External id": 26124,"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": 2338707, "tid": 2338707, + "ts": 6197196621609.097, "dur": 6.689, + "args": { + "External id": 26125,"Sequence number": 479976, "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": 2338707, "tid": 2338707, + "ts": 6197196621613.895, "dur": 0.389, + "args": { + "External id": 26126,"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": 2338707, "tid": 2338707, + "ts": 6197196621617.237, "dur": 4.924, + "args": { + "External id": 26127,"Sequence number": 479976, "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": 2338707, "tid": 2338707, + "ts": 6197196621621.074, "dur": 0.362, + "args": { + "External id": 26128,"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": 2338707, "tid": 2338707, + "ts": 6197196621626.605, "dur": 6.499, + "args": { + "External id": 26129,"Sequence number": 479976, "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": 2338707, "tid": 2338707, "ts": 6197196621626.605, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2338707, + "ts": 6197196621630.144, "dur": 1.277, + "args": { + "External id": 26130,"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": 2338707, "tid": 2338707, + "ts": 6197196621634.228, "dur": 6.679, + "args": { + "External id": 26131,"Sequence number": 479977, "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": 2338707, "tid": 2338707, "ts": 6197196621634.228, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2338707, + "ts": 6197196621639.720, "dur": 0.351, + "args": { + "External id": 26132,"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": 2338707, "tid": 2338707, + "ts": 6197196621641.929, "dur": 7.380, + "args": { + "External id": 26133,"Sequence number": 479978, "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": 2338707, "tid": 2338707, "ts": 6197196621641.929, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2338707, + "ts": 6197196621647.477, "dur": 0.587, + "args": { + "External id": 26134,"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": 2338707, "tid": 2338707, + "ts": 6197196621650.442, "dur": 7.631, + "args": { + "External id": 26135,"Sequence number": 479979, "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": 2338707, "tid": 2338707, "ts": 6197196621650.442, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2338707, + "ts": 6197196621653.801, "dur": 3.316, + "args": { + "External id": 26136,"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": 2338707, "tid": 2338707, + "ts": 6197196621662.781, "dur": 33.756, + "args": { + "External id": 26137,"Sequence number": 479980, "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": 2338707, "tid": 2338707, + "ts": 6197196621664.443, "dur": 31.860, + "args": { + "External id": 26138,"Sequence number": 479980, "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": 2338707, "tid": 2338707, + "ts": 6197196621667.571, "dur": 6.865, + "args": { + "External id": 26139,"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": 2338707, "tid": 2338707, + "ts": 6197196621670.072, "dur": 3.733, + "args": { + "External id": 26140,"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": 2338707, "tid": 2338707, + "ts": 6197196621675.332, "dur": 20.437, + "args": { + "External id": 26141,"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": 2338707, "tid": 2338707, + "ts": 6197196621756.574, "dur": 6.101, + "args": { + "External id": 26142,"Sequence number": 479980, "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": 2338707, "tid": 2338707, "ts": 6197196621756.574, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6197196621765.612, "dur": 1.242, + "args": { + "External id": 26143,"Sequence number": 479981, "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": 2338707, "tid": 2338707, + "ts": 6197196621807.026, "dur": 47404.401, + "args": { + "External id": 26144,"Sequence number": 479981, "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": 2338707, "tid": 2338707, "ts": 6197196621807.026, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338707, "tid": 2338707, + "ts": 6197196621824.880, "dur": 35.757, + "args": { + "External id": 26145,"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": 2338707, "tid": 2338707, + "ts": 6197196621825.973, "dur": 34.335, + "args": { + "External id": 26146,"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": 2338707, "tid": 2338707, + "ts": 6197196621827.463, "dur": 9.804, + "args": { + "External id": 26147,"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": 2338707, "tid": 2338707, + "ts": 6197196621831.840, "dur": 4.743, + "args": { + "External id": 26148,"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": 2338707, "tid": 2338707, + "ts": 6197196621838.033, "dur": 21.797, + "args": { + "External id": 26149,"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": 2338707, "tid": 2338707, + "ts": 6197196621879.455, "dur": 27.310, + "args": { + "External id": 26150,"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": 2338707, "tid": 2338707, + "ts": 6197196621881.192, "dur": 6.253, + "args": { + "External id": 26151,"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": 2338707, "tid": 2338707, + "ts": 6197196621883.101, "dur": 3.975, + "args": { + "External id": 26152,"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": 2338707, "tid": 2338707, + "ts": 6197196621889.001, "dur": 17.506, + "args": { + "External id": 26153,"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": 2338707, "tid": 2338707, + "ts": 6197196621891.193, "dur": 14.881, + "args": { + "External id": 26154,"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": 2338707, "tid": 2338707, + "ts": 6197196621911.389, "dur": 23.908, + "args": { + "External id": 26155,"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": 2338707, "tid": 2338707, + "ts": 6197196621912.084, "dur": 5.105, + "args": { + "External id": 26156,"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": 2338707, "tid": 2338707, + "ts": 6197196621913.843, "dur": 3.092, + "args": { + "External id": 26157,"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": 2338707, "tid": 2338707, + "ts": 6197196621917.785, "dur": 17.285, + "args": { + "External id": 26158,"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": 2338707, "tid": 2338707, + "ts": 6197196621921.187, "dur": 13.417, + "args": { + "External id": 26159,"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": 2338707, "tid": 2338707, + "ts": 6197196621942.582, "dur": 19.100, + "args": { + "External id": 26160,"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": 2338707, "tid": 2338707, + "ts": 6197196621944.688, "dur": 2.628, + "args": { + "External id": 26161,"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": 2338707, "tid": 2338707, + "ts": 6197196621948.010, "dur": 13.298, + "args": { + "External id": 26162,"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": 2338707, "tid": 2338707, + "ts": 6197196621949.880, "dur": 10.932, + "args": { + "External id": 26163,"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": 2338707, "tid": 2338707, + "ts": 6197196621967.506, "dur": 28.409, + "args": { + "External id": 26164,"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": 2338707, "tid": 2338707, + "ts": 6197196621999.316, "dur": 55.557, + "args": { + "External id": 26165,"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": 2338707, "tid": 2338707, + "ts": 6197196622001.418, "dur": 52.936, + "args": { + "External id": 26166,"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": 2338707, "tid": 2338707, + "ts": 6197196622006.740, "dur": 1.348, + "args": { + "External id": 26167,"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": 2338707, "tid": 2338707, + "ts": 6197196622012.224, "dur": 24.861, + "args": { + "External id": 26168,"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": 2338707, "tid": 2338707, + "ts": 6197196622014.325, "dur": 22.497, + "args": { + "External id": 26169,"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": 2338707, "tid": 2338707, + "ts": 6197196622018.558, "dur": 2.787, + "args": { + "External id": 26170,"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": 2338707, "tid": 2338707, + "ts": 6197196622022.170, "dur": 14.280, + "args": { + "External id": 26171,"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": 2338707, "tid": 2338707, + "ts": 6197196622100.040, "dur": 40264.205, + "args": { + "External id": 26172,"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": 2338707, "tid": 2338707, + "ts": 6197196622102.100, "dur": 40260.563, + "args": { + "External id": 26173,"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": 2338707, "tid": 2338707, + "ts": 6197196662380.592, "dur": 9.200, + "args": { + "External id": 26174,"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": 2338707, "tid": 2338707, + "ts": 6197196662386.135, "dur": 1.487, + "args": { + "External id": 26175,"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": 2338707, "tid": 2338707, + "ts": 6197196662396.098, "dur": 130.636, + "args": { + "External id": 26176,"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": 2338707, "tid": 2338707, + "ts": 6197196662400.204, "dur": 7.593, + "args": { + "External id": 26177,"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": 2338707, "tid": 2338707, + "ts": 6197196662403.206, "dur": 3.499, + "args": { + "External id": 26178,"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": 2338707, "tid": 2338707, + "ts": 6197196662405.599, "dur": 0.798, + "args": { + "External id": 26179,"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": 2338707, "tid": 2338707, + "ts": 6197196662409.442, "dur": 116.292, + "args": { + "External id": 26180,"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": 2338707, "tid": 2338707, + "ts": 6197196662411.649, "dur": 113.389, + "args": { + "External id": 26181,"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": 2338707, "tid": 2338707, + "ts": 6197196662531.718, "dur": 4.999, + "args": { + "External id": 26182,"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": 2338707, "tid": 2338707, + "ts": 6197196662534.038, "dur": 0.682, + "args": { + "External id": 26183,"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": 2338707, "tid": 2338707, + "ts": 6197196662548.344, "dur": 3.077, + "args": { + "External id": 26184,"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": 2338707, "tid": 2338707, + "ts": 6197196662564.025, "dur": 7.946, + "args": { + "External id": 26185,"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": 2338707, "tid": 2338707, + "ts": 6197196662566.875, "dur": 4.734, + "args": { + "External id": 26186,"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": 2338707, "tid": 2338707, + "ts": 6197196662748.232, "dur": 242.148, + "args": { + "External id": 26187,"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": 2338707, "tid": 2338707, + "ts": 6197196662752.739, "dur": 3.327, + "args": { + "External id": 26188,"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": 2338707, "tid": 2338707, + "ts": 6197196662758.293, "dur": 231.567, + "args": { + "External id": 26189,"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": 2338707, "tid": 2338707, + "ts": 6197196662763.126, "dur": 0.757, + "args": { + "External id": 26190,"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": 2338707, "tid": 2338707, + "ts": 6197196662767.430, "dur": 31.877, + "args": { + "External id": 26191,"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": 2338707, "tid": 2338707, + "ts": 6197196662801.593, "dur": 4.608, + "args": { + "External id": 26192,"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": 2338707, "tid": 2338707, + "ts": 6197196662804.908, "dur": 0.903, + "args": { + "External id": 26193,"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": 2338707, "tid": 2338707, + "ts": 6197196662807.512, "dur": 29.615, + "args": { + "External id": 26194,"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": 2338707, "tid": 2338707, + "ts": 6197196662808.841, "dur": 3.081, + "args": { + "External id": 26195,"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": 2338707, "tid": 2338707, + "ts": 6197196662813.434, "dur": 23.278, + "args": { + "External id": 26196,"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": 2338707, "tid": 2338707, + "ts": 6197196662817.766, "dur": 3.992, + "args": { + "External id": 26197,"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": 2338707, "tid": 2338707, + "ts": 6197196662839.332, "dur": 26.001, + "args": { + "External id": 26198,"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": 2338707, "tid": 2338707, + "ts": 6197196662867.631, "dur": 16.244, + "args": { + "External id": 26199,"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": 2338707, "tid": 2338707, + "ts": 6197196662890.130, "dur": 16.862, + "args": { + "External id": 26200,"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": 2338707, "tid": 2338707, + "ts": 6197196662908.866, "dur": 14.835, + "args": { + "External id": 26201,"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": 2338707, "tid": 2338707, + "ts": 6197196662926.434, "dur": 24.424, + "args": { + "External id": 26202,"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": 2338707, "tid": 2338707, + "ts": 6197196662929.017, "dur": 1.664, + "args": { + "External id": 26203,"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": 2338707, "tid": 2338707, + "ts": 6197196662933.631, "dur": 0.544, + "args": { + "External id": 26204,"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": 2338707, "tid": 2338707, + "ts": 6197196662952.833, "dur": 16.144, + "args": { + "External id": 26205,"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": 2338707, "tid": 2338707, + "ts": 6197196662972.932, "dur": 15.799, + "args": { + "External id": 26206,"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": 2338707, "tid": 2338707, + "ts": 6197196662999.491, "dur": 2.695, + "args": { + "External id": 26207,"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": 2338707, "tid": 2338707, + "ts": 6197196663010.668, "dur": 4.419, + "args": { + "External id": 26208,"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": 2338707, "tid": 2338707, + "ts": 6197196663013.726, "dur": 0.388, + "args": { + "External id": 26209,"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": 2338707, "tid": 2338707, + "ts": 6197196663151.116, "dur": 94.615, + "args": { + "External id": 26210,"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": 2338707, "tid": 2338707, + "ts": 6197196663253.279, "dur": 9.112, + "args": { + "External id": 26211,"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": 2338707, "tid": 2338707, + "ts": 6197196663257.743, "dur": 1.106, + "args": { + "External id": 26212,"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": 2338707, "tid": 2338707, + "ts": 6197196663264.227, "dur": 39.545, + "args": { + "External id": 26213,"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": 2338707, "tid": 2338707, + "ts": 6197196663313.432, "dur": 8.609, + "args": { + "External id": 26214,"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": 2338707, "tid": 2338707, + "ts": 6197196663315.461, "dur": 5.586, + "args": { + "External id": 26215,"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": 2338707, "tid": 2338707, + "ts": 6197196663318.090, "dur": 2.592, + "args": { + "External id": 26216,"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": 2338707, "tid": 2338707, + "ts": 6197196663325.907, "dur": 58.290, + "args": { + "External id": 26217,"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": 2338707, "tid": 2338707, + "ts": 6197196663327.469, "dur": 55.953, + "args": { + "External id": 26218,"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": 2338707, "tid": 2338707, + "ts": 6197196663389.495, "dur": 20.883, + "args": { + "External id": 26219,"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": 2338707, "tid": 2338707, + "ts": 6197196663418.129, "dur": 7.425, + "args": { + "External id": 26220,"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": 2338707, "tid": 2338707, + "ts": 6197196663423.692, "dur": 0.657, + "args": { + "External id": 26221,"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": 2338707, "tid": 2338707, + "ts": 6197196663431.369, "dur": 56.831, + "args": { + "External id": 26222,"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": 2338707, "tid": 2338707, + "ts": 6197196663432.440, "dur": 4.650, + "args": { + "External id": 26223,"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": 2338707, "tid": 2338707, + "ts": 6197196663433.163, "dur": 3.136, + "args": { + "External id": 26224,"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": 2338707, "tid": 2338707, + "ts": 6197196663435.495, "dur": 0.595, + "args": { + "External id": 26225,"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": 2338707, "tid": 2338707, + "ts": 6197196663437.695, "dur": 50.031, + "args": { + "External id": 26226,"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": 2338707, "tid": 2338707, + "ts": 6197196663440.982, "dur": 46.265, + "args": { + "External id": 26227,"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": 2338707, "tid": 2338707, + "ts": 6197196663492.984, "dur": 4.217, + "args": { + "External id": 26228,"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": 2338707, "tid": 2338707, + "ts": 6197196663495.325, "dur": 0.571, + "args": { + "External id": 26229,"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": 2338707, "tid": 2338707, + "ts": 6197196663504.571, "dur": 2.124, + "args": { + "External id": 26230,"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": 2338707, "tid": 2338707, + "ts": 6197196663517.047, "dur": 10.921, + "args": { + "External id": 26231,"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": 2338707, "tid": 2338707, + "ts": 6197196663522.522, "dur": 5.122, + "args": { + "External id": 26232,"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": 2338707, "tid": 2338707, + "ts": 6197196663645.937, "dur": 245.812, + "args": { + "External id": 26233,"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": 2338707, "tid": 2338707, + "ts": 6197196663648.857, "dur": 2.282, + "args": { + "External id": 26234,"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": 2338707, "tid": 2338707, + "ts": 6197196663654.561, "dur": 236.636, + "args": { + "External id": 26235,"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": 2338707, "tid": 2338707, + "ts": 6197196663656.183, "dur": 0.413, + "args": { + "External id": 26236,"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": 2338707, "tid": 2338707, + "ts": 6197196663658.340, "dur": 26.020, + "args": { + "External id": 26237,"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": 2338707, "tid": 2338707, + "ts": 6197196663686.276, "dur": 8.024, + "args": { + "External id": 26238,"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": 2338707, "tid": 2338707, + "ts": 6197196663689.146, "dur": 4.708, + "args": { + "External id": 26239,"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": 2338707, "tid": 2338707, + "ts": 6197196663695.475, "dur": 51.260, + "args": { + "External id": 26240,"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": 2338707, "tid": 2338707, + "ts": 6197196663698.844, "dur": 19.167, + "args": { + "External id": 26241,"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": 2338707, "tid": 2338707, + "ts": 6197196663720.591, "dur": 25.755, + "args": { + "External id": 26242,"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": 2338707, "tid": 2338707, + "ts": 6197196663724.942, "dur": 3.230, + "args": { + "External id": 26243,"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": 2338707, "tid": 2338707, + "ts": 6197196663748.977, "dur": 27.568, + "args": { + "External id": 26244,"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": 2338707, "tid": 2338707, + "ts": 6197196663778.227, "dur": 17.095, + "args": { + "External id": 26245,"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": 2338707, "tid": 2338707, + "ts": 6197196663798.220, "dur": 16.373, + "args": { + "External id": 26246,"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": 2338707, "tid": 2338707, + "ts": 6197196663816.579, "dur": 16.117, + "args": { + "External id": 26247,"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": 2338707, "tid": 2338707, + "ts": 6197196663834.962, "dur": 27.165, + "args": { + "External id": 26248,"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": 2338707, "tid": 2338707, + "ts": 6197196663837.823, "dur": 2.065, + "args": { + "External id": 26249,"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": 2338707, "tid": 2338707, + "ts": 6197196663844.954, "dur": 0.846, + "args": { + "External id": 26250,"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": 2338707, "tid": 2338707, + "ts": 6197196663863.836, "dur": 13.099, + "args": { + "External id": 26251,"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": 2338707, "tid": 2338707, + "ts": 6197196663878.360, "dur": 11.280, + "args": { + "External id": 26252,"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": 2338707, "tid": 2338707, + "ts": 6197196663901.631, "dur": 2.804, + "args": { + "External id": 26253,"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": 2338707, "tid": 2338707, + "ts": 6197196663916.073, "dur": 4.913, + "args": { + "External id": 26254,"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": 2338707, "tid": 2338707, + "ts": 6197196663919.326, "dur": 0.565, + "args": { + "External id": 26255,"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": 2338707, "tid": 2338707, + "ts": 6197196664008.668, "dur": 110.646, + "args": { + "External id": 26256,"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": 2338707, "tid": 2338707, + "ts": 6197196664129.168, "dur": 11.783, + "args": { + "External id": 26257,"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": 2338707, "tid": 2338707, + "ts": 6197196664136.381, "dur": 2.712, + "args": { + "External id": 26258,"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": 2338707, "tid": 2338707, + "ts": 6197196664142.713, "dur": 31.952, + "args": { + "External id": 26259,"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": 2338707, "tid": 2338707, + "ts": 6197196664181.867, "dur": 6.280, + "args": { + "External id": 26260,"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": 2338707, "tid": 2338707, + "ts": 6197196664183.886, "dur": 3.486, + "args": { + "External id": 26261,"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": 2338707, "tid": 2338707, + "ts": 6197196664186.167, "dur": 0.942, + "args": { + "External id": 26262,"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": 2338707, "tid": 2338707, + "ts": 6197196664191.650, "dur": 55.473, + "args": { + "External id": 26263,"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": 2338707, "tid": 2338707, + "ts": 6197196664192.871, "dur": 53.719, + "args": { + "External id": 26264,"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": 2338707, "tid": 2338707, + "ts": 6197196664251.596, "dur": 18.998, + "args": { + "External id": 26265,"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": 2338707, "tid": 2338707, + "ts": 6197196664283.631, "dur": 4.463, + "args": { + "External id": 26266,"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": 2338707, "tid": 2338707, + "ts": 6197196664286.222, "dur": 0.704, + "args": { + "External id": 26267,"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": 2338707, "tid": 2338707, + "ts": 6197196664293.126, "dur": 53.508, + "args": { + "External id": 26268,"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": 2338707, "tid": 2338707, + "ts": 6197196664294.341, "dur": 6.589, + "args": { + "External id": 26269,"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": 2338707, "tid": 2338707, + "ts": 6197196664295.337, "dur": 4.884, + "args": { + "External id": 26270,"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": 2338707, "tid": 2338707, + "ts": 6197196664299.214, "dur": 0.864, + "args": { + "External id": 26271,"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": 2338707, "tid": 2338707, + "ts": 6197196664301.589, "dur": 44.584, + "args": { + "External id": 26272,"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": 2338707, "tid": 2338707, + "ts": 6197196664302.130, "dur": 43.318, + "args": { + "External id": 26273,"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": 2338707, "tid": 2338707, + "ts": 6197196664351.798, "dur": 7.555, + "args": { + "External id": 26274,"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": 2338707, "tid": 2338707, + "ts": 6197196664354.373, "dur": 3.624, + "args": { + "External id": 26275,"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": 2338707, "tid": 2338707, + "ts": 6197196664367.451, "dur": 1.983, + "args": { + "External id": 26276,"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": 2338707, "tid": 2338707, + "ts": 6197196664379.778, "dur": 11.135, + "args": { + "External id": 26277,"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": 2338707, "tid": 2338707, + "ts": 6197196664384.989, "dur": 5.523, + "args": { + "External id": 26278,"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": 2338707, "tid": 2338707, + "ts": 6197196664501.241, "dur": 278.389, + "args": { + "External id": 26279,"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": 2338707, "tid": 2338707, + "ts": 6197196664503.671, "dur": 2.156, + "args": { + "External id": 26280,"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": 2338707, "tid": 2338707, + "ts": 6197196664507.946, "dur": 271.099, + "args": { + "External id": 26281,"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": 2338707, "tid": 2338707, + "ts": 6197196664509.787, "dur": 0.380, + "args": { + "External id": 26282,"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": 2338707, "tid": 2338707, + "ts": 6197196664511.503, "dur": 28.007, + "args": { + "External id": 26283,"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": 2338707, "tid": 2338707, + "ts": 6197196664541.710, "dur": 3.854, + "args": { + "External id": 26284,"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": 2338707, "tid": 2338707, + "ts": 6197196664544.362, "dur": 0.945, + "args": { + "External id": 26285,"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": 2338707, "tid": 2338707, + "ts": 6197196664546.608, "dur": 32.641, + "args": { + "External id": 26286,"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": 2338707, "tid": 2338707, + "ts": 6197196664550.807, "dur": 1.420, + "args": { + "External id": 26287,"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": 2338707, "tid": 2338707, + "ts": 6197196664553.611, "dur": 25.285, + "args": { + "External id": 26288,"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": 2338707, "tid": 2338707, + "ts": 6197196664558.844, "dur": 3.453, + "args": { + "External id": 26289,"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": 2338707, "tid": 2338707, + "ts": 6197196664581.313, "dur": 40.063, + "args": { + "External id": 26290,"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": 2338707, "tid": 2338707, + "ts": 6197196664623.521, "dur": 33.505, + "args": { + "External id": 26291,"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": 2338707, "tid": 2338707, + "ts": 6197196664660.595, "dur": 18.921, + "args": { + "External id": 26292,"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": 2338707, "tid": 2338707, + "ts": 6197196664681.251, "dur": 14.492, + "args": { + "External id": 26293,"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": 2338707, "tid": 2338707, + "ts": 6197196664697.943, "dur": 49.143, + "args": { + "External id": 26294,"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": 2338707, "tid": 2338707, + "ts": 6197196664718.146, "dur": 2.924, + "args": { + "External id": 26295,"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": 2338707, "tid": 2338707, + "ts": 6197196664726.825, "dur": 0.902, + "args": { + "External id": 26296,"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": 2338707, "tid": 2338707, + "ts": 6197196664748.862, "dur": 13.883, + "args": { + "External id": 26297,"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": 2338707, "tid": 2338707, + "ts": 6197196664763.956, "dur": 13.920, + "args": { + "External id": 26298,"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": 2338707, "tid": 2338707, + "ts": 6197196664789.131, "dur": 2.870, + "args": { + "External id": 26299,"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": 2338707, "tid": 2338707, + "ts": 6197196664802.940, "dur": 5.260, + "args": { + "External id": 26300,"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": 2338707, "tid": 2338707, + "ts": 6197196664806.513, "dur": 0.624, + "args": { + "External id": 26301,"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": 2338707, "tid": 2338707, + "ts": 6197196664888.446, "dur": 69.127, + "args": { + "External id": 26302,"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": 2338707, "tid": 2338707, + "ts": 6197196664965.825, "dur": 5.840, + "args": { + "External id": 26303,"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": 2338707, "tid": 2338707, + "ts": 6197196664969.455, "dur": 0.903, + "args": { + "External id": 26304,"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": 2338707, "tid": 2338707, + "ts": 6197196664973.471, "dur": 30.451, + "args": { + "External id": 26305,"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": 2338707, "tid": 2338707, + "ts": 6197196665009.636, "dur": 5.903, + "args": { + "External id": 26306,"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": 2338707, "tid": 2338707, + "ts": 6197196665011.332, "dur": 3.354, + "args": { + "External id": 26307,"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": 2338707, "tid": 2338707, + "ts": 6197196665013.459, "dur": 1.033, + "args": { + "External id": 26308,"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": 2338707, "tid": 2338707, + "ts": 6197196665020.684, "dur": 89.274, + "args": { + "External id": 26309,"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": 2338707, "tid": 2338707, + "ts": 6197196665021.765, "dur": 86.915, + "args": { + "External id": 26310,"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": 2338707, "tid": 2338707, + "ts": 6197196665116.980, "dur": 20.589, + "args": { + "External id": 26311,"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": 2338707, "tid": 2338707, + "ts": 6197196665145.994, "dur": 5.958, + "args": { + "External id": 26312,"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": 2338707, "tid": 2338707, + "ts": 6197196665149.291, "dur": 1.138, + "args": { + "External id": 26313,"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": 2338707, "tid": 2338707, + "ts": 6197196665156.681, "dur": 65.572, + "args": { + "External id": 26314,"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": 2338707, "tid": 2338707, + "ts": 6197196665157.892, "dur": 8.334, + "args": { + "External id": 26315,"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": 2338707, "tid": 2338707, + "ts": 6197196665161.599, "dur": 3.936, + "args": { + "External id": 26316,"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": 2338707, "tid": 2338707, + "ts": 6197196665163.426, "dur": 1.901, + "args": { + "External id": 26317,"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": 2338707, "tid": 2338707, + "ts": 6197196665166.853, "dur": 54.721, + "args": { + "External id": 26318,"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": 2338707, "tid": 2338707, + "ts": 6197196665171.567, "dur": 49.262, + "args": { + "External id": 26319,"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": 2338707, "tid": 2338707, + "ts": 6197196665226.713, "dur": 4.168, + "args": { + "External id": 26320,"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": 2338707, "tid": 2338707, + "ts": 6197196665229.088, "dur": 0.424, + "args": { + "External id": 26321,"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": 2338707, "tid": 2338707, + "ts": 6197196665241.006, "dur": 2.084, + "args": { + "External id": 26322,"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": 2338707, "tid": 2338707, + "ts": 6197196665252.513, "dur": 7.741, + "args": { + "External id": 26323,"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": 2338707, "tid": 2338707, + "ts": 6197196665255.053, "dur": 4.939, + "args": { + "External id": 26324,"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": 2338707, "tid": 2338707, + "ts": 6197196665365.904, "dur": 211.671, + "args": { + "External id": 26325,"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": 2338707, "tid": 2338707, + "ts": 6197196665370.142, "dur": 3.877, + "args": { + "External id": 26326,"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": 2338707, "tid": 2338707, + "ts": 6197196665376.054, "dur": 200.986, + "args": { + "External id": 26327,"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": 2338707, "tid": 2338707, + "ts": 6197196665379.608, "dur": 0.584, + "args": { + "External id": 26328,"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": 2338707, "tid": 2338707, + "ts": 6197196665381.367, "dur": 26.100, + "args": { + "External id": 26329,"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": 2338707, "tid": 2338707, + "ts": 6197196665409.583, "dur": 4.699, + "args": { + "External id": 26330,"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": 2338707, "tid": 2338707, + "ts": 6197196665413.044, "dur": 0.979, + "args": { + "External id": 26331,"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": 2338707, "tid": 2338707, + "ts": 6197196665415.554, "dur": 23.916, + "args": { + "External id": 26332,"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": 2338707, "tid": 2338707, + "ts": 6197196665416.824, "dur": 1.029, + "args": { + "External id": 26333,"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": 2338707, "tid": 2338707, + "ts": 6197196665418.991, "dur": 20.171, + "args": { + "External id": 26334,"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": 2338707, "tid": 2338707, + "ts": 6197196665421.747, "dur": 3.064, + "args": { + "External id": 26335,"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": 2338707, "tid": 2338707, + "ts": 6197196665441.156, "dur": 24.933, + "args": { + "External id": 26336,"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": 2338707, "tid": 2338707, + "ts": 6197196665467.690, "dur": 16.080, + "args": { + "External id": 26337,"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": 2338707, "tid": 2338707, + "ts": 6197196665488.544, "dur": 16.037, + "args": { + "External id": 26338,"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": 2338707, "tid": 2338707, + "ts": 6197196665506.474, "dur": 14.807, + "args": { + "External id": 26339,"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": 2338707, "tid": 2338707, + "ts": 6197196665523.704, "dur": 24.718, + "args": { + "External id": 26340,"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": 2338707, "tid": 2338707, + "ts": 6197196665528.004, "dur": 1.830, + "args": { + "External id": 26341,"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": 2338707, "tid": 2338707, + "ts": 6197196665532.511, "dur": 0.623, + "args": { + "External id": 26342,"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": 2338707, "tid": 2338707, + "ts": 6197196665550.107, "dur": 12.728, + "args": { + "External id": 26343,"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": 2338707, "tid": 2338707, + "ts": 6197196665564.101, "dur": 11.921, + "args": { + "External id": 26344,"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": 2338707, "tid": 2338707, + "ts": 6197196665588.332, "dur": 1.878, + "args": { + "External id": 26345,"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": 2338707, "tid": 2338707, + "ts": 6197196665599.956, "dur": 4.779, + "args": { + "External id": 26346,"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": 2338707, "tid": 2338707, + "ts": 6197196665603.006, "dur": 0.756, + "args": { + "External id": 26347,"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": 2338707, "tid": 2338707, + "ts": 6197196665683.344, "dur": 87.598, + "args": { + "External id": 26348,"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": 2338707, "tid": 2338707, + "ts": 6197196665779.072, "dur": 7.424, + "args": { + "External id": 26349,"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": 2338707, "tid": 2338707, + "ts": 6197196665783.492, "dur": 1.228, + "args": { + "External id": 26350,"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": 2338707, "tid": 2338707, + "ts": 6197196665788.196, "dur": 30.708, + "args": { + "External id": 26351,"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": 2338707, "tid": 2338707, + "ts": 6197196665825.267, "dur": 9.861, + "args": { + "External id": 26352,"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": 2338707, "tid": 2338707, + "ts": 6197196665827.211, "dur": 7.017, + "args": { + "External id": 26353,"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": 2338707, "tid": 2338707, + "ts": 6197196665832.367, "dur": 1.587, + "args": { + "External id": 26354,"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": 2338707, "tid": 2338707, + "ts": 6197196665839.150, "dur": 51.110, + "args": { + "External id": 26355,"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": 2338707, "tid": 2338707, + "ts": 6197196665840.170, "dur": 49.319, + "args": { + "External id": 26356,"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": 2338707, "tid": 2338707, + "ts": 6197196665895.038, "dur": 18.660, + "args": { + "External id": 26357,"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": 2338707, "tid": 2338707, + "ts": 6197196665920.432, "dur": 4.342, + "args": { + "External id": 26358,"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": 2338707, "tid": 2338707, + "ts": 6197196665923.003, "dur": 0.668, + "args": { + "External id": 26359,"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": 2338707, "tid": 2338707, + "ts": 6197196665932.288, "dur": 52.209, + "args": { + "External id": 26360,"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": 2338707, "tid": 2338707, + "ts": 6197196665933.411, "dur": 4.301, + "args": { + "External id": 26361,"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": 2338707, "tid": 2338707, + "ts": 6197196665934.381, "dur": 2.681, + "args": { + "External id": 26362,"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": 2338707, "tid": 2338707, + "ts": 6197196665936.212, "dur": 0.692, + "args": { + "External id": 26363,"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": 2338707, "tid": 2338707, + "ts": 6197196665938.223, "dur": 45.793, + "args": { + "External id": 26364,"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": 2338707, "tid": 2338707, + "ts": 6197196665938.933, "dur": 44.424, + "args": { + "External id": 26365,"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": 2338707, "tid": 2338707, + "ts": 6197196665989.523, "dur": 4.254, + "args": { + "External id": 26366,"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": 2338707, "tid": 2338707, + "ts": 6197196665991.809, "dur": 0.640, + "args": { + "External id": 26367,"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": 2338707, "tid": 2338707, + "ts": 6197196666003.422, "dur": 1.840, + "args": { + "External id": 26368,"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": 2338707, "tid": 2338707, + "ts": 6197196666014.542, "dur": 7.253, + "args": { + "External id": 26369,"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": 2338707, "tid": 2338707, + "ts": 6197196666016.987, "dur": 4.430, + "args": { + "External id": 26370,"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": 2338707, "tid": 2338707, + "ts": 6197196666172.412, "dur": 233.195, + "args": { + "External id": 26371,"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": 2338707, "tid": 2338707, + "ts": 6197196666177.077, "dur": 3.167, + "args": { + "External id": 26372,"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": 2338707, "tid": 2338707, + "ts": 6197196666182.592, "dur": 222.435, + "args": { + "External id": 26373,"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": 2338707, "tid": 2338707, + "ts": 6197196666186.882, "dur": 0.579, + "args": { + "External id": 26374,"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": 2338707, "tid": 2338707, + "ts": 6197196666189.120, "dur": 32.486, + "args": { + "External id": 26375,"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": 2338707, "tid": 2338707, + "ts": 6197196666223.820, "dur": 6.251, + "args": { + "External id": 26376,"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": 2338707, "tid": 2338707, + "ts": 6197196666228.605, "dur": 1.184, + "args": { + "External id": 26377,"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": 2338707, "tid": 2338707, + "ts": 6197196666231.252, "dur": 25.473, + "args": { + "External id": 26378,"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": 2338707, "tid": 2338707, + "ts": 6197196666232.551, "dur": 1.310, + "args": { + "External id": 26379,"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": 2338707, "tid": 2338707, + "ts": 6197196666235.645, "dur": 20.620, + "args": { + "External id": 26380,"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": 2338707, "tid": 2338707, + "ts": 6197196666239.312, "dur": 3.717, + "args": { + "External id": 26381,"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": 2338707, "tid": 2338707, + "ts": 6197196666258.203, "dur": 28.694, + "args": { + "External id": 26382,"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": 2338707, "tid": 2338707, + "ts": 6197196666288.988, "dur": 15.961, + "args": { + "External id": 26383,"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": 2338707, "tid": 2338707, + "ts": 6197196666310.840, "dur": 17.472, + "args": { + "External id": 26384,"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": 2338707, "tid": 2338707, + "ts": 6197196666330.282, "dur": 16.011, + "args": { + "External id": 26385,"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": 2338707, "tid": 2338707, + "ts": 6197196666348.713, "dur": 24.745, + "args": { + "External id": 26386,"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": 2338707, "tid": 2338707, + "ts": 6197196666351.136, "dur": 1.803, + "args": { + "External id": 26387,"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": 2338707, "tid": 2338707, + "ts": 6197196666355.708, "dur": 0.825, + "args": { + "External id": 26388,"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": 2338707, "tid": 2338707, + "ts": 6197196666374.953, "dur": 13.984, + "args": { + "External id": 26389,"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": 2338707, "tid": 2338707, + "ts": 6197196666392.156, "dur": 11.790, + "args": { + "External id": 26390,"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": 2338707, "tid": 2338707, + "ts": 6197196666414.133, "dur": 2.605, + "args": { + "External id": 26391,"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": 2338707, "tid": 2338707, + "ts": 6197196666428.013, "dur": 4.927, + "args": { + "External id": 26392,"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": 2338707, "tid": 2338707, + "ts": 6197196666431.230, "dur": 0.620, + "args": { + "External id": 26393,"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": 2338707, "tid": 2338707, + "ts": 6197196666509.142, "dur": 72.760, + "args": { + "External id": 26394,"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": 2338707, "tid": 2338707, + "ts": 6197196666587.711, "dur": 5.503, + "args": { + "External id": 26395,"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": 2338707, "tid": 2338707, + "ts": 6197196666590.862, "dur": 0.926, + "args": { + "External id": 26396,"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": 2338707, "tid": 2338707, + "ts": 6197196666594.848, "dur": 30.754, + "args": { + "External id": 26397,"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": 2338707, "tid": 2338707, + "ts": 6197196666633.756, "dur": 6.637, + "args": { + "External id": 26398,"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": 2338707, "tid": 2338707, + "ts": 6197196666635.528, "dur": 3.986, + "args": { + "External id": 26399,"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": 2338707, "tid": 2338707, + "ts": 6197196666638.113, "dur": 1.155, + "args": { + "External id": 26400,"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": 2338707, "tid": 2338707, + "ts": 6197196666643.490, "dur": 47.778, + "args": { + "External id": 26401,"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": 2338707, "tid": 2338707, + "ts": 6197196666644.681, "dur": 45.792, + "args": { + "External id": 26402,"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": 2338707, "tid": 2338707, + "ts": 6197196666695.993, "dur": 36.329, + "args": { + "External id": 26403,"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": 2338707, "tid": 2338707, + "ts": 6197196666742.279, "dur": 8.078, + "args": { + "External id": 26404,"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": 2338707, "tid": 2338707, + "ts": 6197196666747.792, "dur": 1.060, + "args": { + "External id": 26405,"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": 2338707, "tid": 2338707, + "ts": 6197196666755.432, "dur": 60.638, + "args": { + "External id": 26406,"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": 2338707, "tid": 2338707, + "ts": 6197196666756.577, "dur": 4.355, + "args": { + "External id": 26407,"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": 2338707, "tid": 2338707, + "ts": 6197196666757.615, "dur": 2.633, + "args": { + "External id": 26408,"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": 2338707, "tid": 2338707, + "ts": 6197196666759.357, "dur": 0.711, + "args": { + "External id": 26409,"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": 2338707, "tid": 2338707, + "ts": 6197196666761.621, "dur": 53.798, + "args": { + "External id": 26410,"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": 2338707, "tid": 2338707, + "ts": 6197196666765.170, "dur": 49.218, + "args": { + "External id": 26411,"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": 2338707, "tid": 2338707, + "ts": 6197196666820.435, "dur": 6.340, + "args": { + "External id": 26412,"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": 2338707, "tid": 2338707, + "ts": 6197196666822.921, "dur": 2.441, + "args": { + "External id": 26413,"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": 2338707, "tid": 2338707, + "ts": 6197196666833.886, "dur": 1.948, + "args": { + "External id": 26414,"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": 2338707, "tid": 2338707, + "ts": 6197196666845.414, "dur": 12.235, + "args": { + "External id": 26415,"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": 2338707, "tid": 2338707, + "ts": 6197196666850.480, "dur": 6.829, + "args": { + "External id": 26416,"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": 2338707, "tid": 2338707, + "ts": 6197196666956.631, "dur": 238.140, + "args": { + "External id": 26417,"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": 2338707, "tid": 2338707, + "ts": 6197196666958.965, "dur": 1.837, + "args": { + "External id": 26418,"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": 2338707, "tid": 2338707, + "ts": 6197196666962.545, "dur": 231.586, + "args": { + "External id": 26419,"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": 2338707, "tid": 2338707, + "ts": 6197196666963.928, "dur": 0.423, + "args": { + "External id": 26420,"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": 2338707, "tid": 2338707, + "ts": 6197196666965.571, "dur": 24.709, + "args": { + "External id": 26421,"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": 2338707, "tid": 2338707, + "ts": 6197196666992.007, "dur": 3.582, + "args": { + "External id": 26422,"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": 2338707, "tid": 2338707, + "ts": 6197196666994.608, "dur": 0.621, + "args": { + "External id": 26423,"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": 2338707, "tid": 2338707, + "ts": 6197196666996.597, "dur": 28.436, + "args": { + "External id": 26424,"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": 2338707, "tid": 2338707, + "ts": 6197196667000.590, "dur": 1.480, + "args": { + "External id": 26425,"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": 2338707, "tid": 2338707, + "ts": 6197196667003.459, "dur": 21.215, + "args": { + "External id": 26426,"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": 2338707, "tid": 2338707, + "ts": 6197196667008.359, "dur": 3.249, + "args": { + "External id": 26427,"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": 2338707, "tid": 2338707, + "ts": 6197196667026.922, "dur": 21.210, + "args": { + "External id": 26428,"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": 2338707, "tid": 2338707, + "ts": 6197196667049.718, "dur": 53.441, + "args": { + "External id": 26429,"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": 2338707, "tid": 2338707, + "ts": 6197196667107.583, "dur": 16.074, + "args": { + "External id": 26430,"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": 2338707, "tid": 2338707, + "ts": 6197196667125.290, "dur": 13.198, + "args": { + "External id": 26431,"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": 2338707, "tid": 2338707, + "ts": 6197196667140.923, "dur": 25.254, + "args": { + "External id": 26432,"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": 2338707, "tid": 2338707, + "ts": 6197196667143.225, "dur": 2.091, + "args": { + "External id": 26433,"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": 2338707, "tid": 2338707, + "ts": 6197196667150.134, "dur": 0.974, + "args": { + "External id": 26434,"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": 2338707, "tid": 2338707, + "ts": 6197196667167.567, "dur": 13.576, + "args": { + "External id": 26435,"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": 2338707, "tid": 2338707, + "ts": 6197196667182.268, "dur": 10.763, + "args": { + "External id": 26436,"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": 2338707, "tid": 2338707, + "ts": 6197196667204.345, "dur": 2.802, + "args": { + "External id": 26437,"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": 2338707, "tid": 2338707, + "ts": 6197196667217.501, "dur": 4.139, + "args": { + "External id": 26438,"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": 2338707, "tid": 2338707, + "ts": 6197196667220.327, "dur": 0.361, + "args": { + "External id": 26439,"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": 2338707, "tid": 2338707, + "ts": 6197196667300.983, "dur": 67.412, + "args": { + "External id": 26440,"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": 2338707, "tid": 2338707, + "ts": 6197196667374.526, "dur": 7.612, + "args": { + "External id": 26441,"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": 2338707, "tid": 2338707, + "ts": 6197196667380.085, "dur": 0.904, + "args": { + "External id": 26442,"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": 2338707, "tid": 2338707, + "ts": 6197196667383.867, "dur": 27.831, + "args": { + "External id": 26443,"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": 2338707, "tid": 2338707, + "ts": 6197196667416.345, "dur": 5.827, + "args": { + "External id": 26444,"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": 2338707, "tid": 2338707, + "ts": 6197196667418.113, "dur": 3.276, + "args": { + "External id": 26445,"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": 2338707, "tid": 2338707, + "ts": 6197196667420.351, "dur": 0.824, + "args": { + "External id": 26446,"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": 2338707, "tid": 2338707, + "ts": 6197196667424.907, "dur": 47.991, + "args": { + "External id": 26447,"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": 2338707, "tid": 2338707, + "ts": 6197196667426.217, "dur": 45.985, + "args": { + "External id": 26448,"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": 2338707, "tid": 2338707, + "ts": 6197196667477.088, "dur": 17.248, + "args": { + "External id": 26449,"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": 2338707, "tid": 2338707, + "ts": 6197196667503.349, "dur": 4.165, + "args": { + "External id": 26450,"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": 2338707, "tid": 2338707, + "ts": 6197196667505.950, "dur": 0.583, + "args": { + "External id": 26451,"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": 2338707, "tid": 2338707, + "ts": 6197196667511.799, "dur": 57.689, + "args": { + "External id": 26452,"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": 2338707, "tid": 2338707, + "ts": 6197196667512.670, "dur": 8.635, + "args": { + "External id": 26453,"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": 2338707, "tid": 2338707, + "ts": 6197196667513.521, "dur": 7.087, + "args": { + "External id": 26454,"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": 2338707, "tid": 2338707, + "ts": 6197196667519.855, "dur": 0.603, + "args": { + "External id": 26455,"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": 2338707, "tid": 2338707, + "ts": 6197196667522.003, "dur": 46.952, + "args": { + "External id": 26456,"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": 2338707, "tid": 2338707, + "ts": 6197196667522.838, "dur": 45.571, + "args": { + "External id": 26457,"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": 2338707, "tid": 2338707, + "ts": 6197196667573.998, "dur": 4.125, + "args": { + "External id": 26458,"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": 2338707, "tid": 2338707, + "ts": 6197196667576.206, "dur": 0.587, + "args": { + "External id": 26459,"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": 2338707, "tid": 2338707, + "ts": 6197196667584.648, "dur": 1.632, + "args": { + "External id": 26460,"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": 2338707, "tid": 2338707, + "ts": 6197196667595.147, "dur": 9.302, + "args": { + "External id": 26461,"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": 2338707, "tid": 2338707, + "ts": 6197196667600.125, "dur": 3.985, + "args": { + "External id": 26462,"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": 2338707, "tid": 2338707, + "ts": 6197196667696.043, "dur": 245.213, + "args": { + "External id": 26463,"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": 2338707, "tid": 2338707, + "ts": 6197196667698.367, "dur": 18.706, + "args": { + "External id": 26464,"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": 2338707, "tid": 2338707, + "ts": 6197196667719.980, "dur": 220.848, + "args": { + "External id": 26465,"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": 2338707, "tid": 2338707, + "ts": 6197196667722.752, "dur": 0.353, + "args": { + "External id": 26466,"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": 2338707, "tid": 2338707, + "ts": 6197196667724.549, "dur": 29.138, + "args": { + "External id": 26467,"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": 2338707, "tid": 2338707, + "ts": 6197196667755.500, "dur": 3.954, + "args": { + "External id": 26468,"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": 2338707, "tid": 2338707, + "ts": 6197196667757.959, "dur": 1.201, + "args": { + "External id": 26469,"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": 2338707, "tid": 2338707, + "ts": 6197196667760.609, "dur": 30.413, + "args": { + "External id": 26470,"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": 2338707, "tid": 2338707, + "ts": 6197196667766.215, "dur": 1.304, + "args": { + "External id": 26471,"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": 2338707, "tid": 2338707, + "ts": 6197196667768.804, "dur": 21.786, + "args": { + "External id": 26472,"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": 2338707, "tid": 2338707, + "ts": 6197196667772.237, "dur": 3.933, + "args": { + "External id": 26473,"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": 2338707, "tid": 2338707, + "ts": 6197196667792.752, "dur": 27.155, + "args": { + "External id": 26474,"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": 2338707, "tid": 2338707, + "ts": 6197196667821.572, "dur": 15.151, + "args": { + "External id": 26475,"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": 2338707, "tid": 2338707, + "ts": 6197196667839.823, "dur": 24.077, + "args": { + "External id": 26476,"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": 2338707, "tid": 2338707, + "ts": 6197196667865.501, "dur": 14.972, + "args": { + "External id": 26477,"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": 2338707, "tid": 2338707, + "ts": 6197196667882.531, "dur": 25.852, + "args": { + "External id": 26478,"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": 2338707, "tid": 2338707, + "ts": 6197196667884.901, "dur": 1.540, + "args": { + "External id": 26479,"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": 2338707, "tid": 2338707, + "ts": 6197196667891.166, "dur": 0.760, + "args": { + "External id": 26480,"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": 2338707, "tid": 2338707, + "ts": 6197196667909.873, "dur": 14.669, + "args": { + "External id": 26481,"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": 2338707, "tid": 2338707, + "ts": 6197196667925.858, "dur": 13.765, + "args": { + "External id": 26482,"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": 2338707, "tid": 2338707, + "ts": 6197196667949.761, "dur": 2.486, + "args": { + "External id": 26483,"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": 2338707, "tid": 2338707, + "ts": 6197196667962.399, "dur": 4.857, + "args": { + "External id": 26484,"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": 2338707, "tid": 2338707, + "ts": 6197196667965.768, "dur": 0.550, + "args": { + "External id": 26485,"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": 2338707, "tid": 2338707, + "ts": 6197196668041.567, "dur": 107.729, + "args": { + "External id": 26486,"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": 2338707, "tid": 2338707, + "ts": 6197196668160.625, "dur": 9.445, + "args": { + "External id": 26487,"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": 2338707, "tid": 2338707, + "ts": 6197196668165.014, "dur": 3.084, + "args": { + "External id": 26488,"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": 2338707, "tid": 2338707, + "ts": 6197196668171.788, "dur": 30.285, + "args": { + "External id": 26489,"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": 2338707, "tid": 2338707, + "ts": 6197196668208.443, "dur": 6.160, + "args": { + "External id": 26490,"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": 2338707, "tid": 2338707, + "ts": 6197196668210.160, "dur": 3.527, + "args": { + "External id": 26491,"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": 2338707, "tid": 2338707, + "ts": 6197196668212.611, "dur": 0.803, + "args": { + "External id": 26492,"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": 2338707, "tid": 2338707, + "ts": 6197196668220.629, "dur": 50.456, + "args": { + "External id": 26493,"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": 2338707, "tid": 2338707, + "ts": 6197196668222.203, "dur": 48.182, + "args": { + "External id": 26494,"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": 2338707, "tid": 2338707, + "ts": 6197196668275.206, "dur": 17.475, + "args": { + "External id": 26495,"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": 2338707, "tid": 2338707, + "ts": 6197196668299.225, "dur": 3.761, + "args": { + "External id": 26496,"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": 2338707, "tid": 2338707, + "ts": 6197196668301.485, "dur": 0.500, + "args": { + "External id": 26497,"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": 2338707, "tid": 2338707, + "ts": 6197196668307.545, "dur": 54.466, + "args": { + "External id": 26498,"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": 2338707, "tid": 2338707, + "ts": 6197196668308.418, "dur": 7.208, + "args": { + "External id": 26499,"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": 2338707, "tid": 2338707, + "ts": 6197196668312.193, "dur": 2.731, + "args": { + "External id": 26500,"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": 2338707, "tid": 2338707, + "ts": 6197196668314.023, "dur": 0.735, + "args": { + "External id": 26501,"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": 2338707, "tid": 2338707, + "ts": 6197196668316.284, "dur": 45.206, + "args": { + "External id": 26502,"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": 2338707, "tid": 2338707, + "ts": 6197196668317.089, "dur": 43.756, + "args": { + "External id": 26503,"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": 2338707, "tid": 2338707, + "ts": 6197196668366.264, "dur": 4.311, + "args": { + "External id": 26504,"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": 2338707, "tid": 2338707, + "ts": 6197196668368.517, "dur": 0.793, + "args": { + "External id": 26505,"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": 2338707, "tid": 2338707, + "ts": 6197196668380.740, "dur": 1.744, + "args": { + "External id": 26506,"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": 2338707, "tid": 2338707, + "ts": 6197196668391.297, "dur": 10.486, + "args": { + "External id": 26507,"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": 2338707, "tid": 2338707, + "ts": 6197196668394.254, "dur": 7.235, + "args": { + "External id": 26508,"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": 2338707, "tid": 2338707, + "ts": 6197196668504.604, "dur": 230.902, + "args": { + "External id": 26509,"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": 2338707, "tid": 2338707, + "ts": 6197196668507.058, "dur": 3.474, + "args": { + "External id": 26510,"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": 2338707, "tid": 2338707, + "ts": 6197196668512.189, "dur": 222.669, + "args": { + "External id": 26511,"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": 2338707, "tid": 2338707, + "ts": 6197196668516.065, "dur": 0.360, + "args": { + "External id": 26512,"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": 2338707, "tid": 2338707, + "ts": 6197196668517.842, "dur": 25.582, + "args": { + "External id": 26513,"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": 2338707, "tid": 2338707, + "ts": 6197196668545.034, "dur": 5.371, + "args": { + "External id": 26514,"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": 2338707, "tid": 2338707, + "ts": 6197196668549.346, "dur": 0.809, + "args": { + "External id": 26515,"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": 2338707, "tid": 2338707, + "ts": 6197196668551.558, "dur": 23.812, + "args": { + "External id": 26516,"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": 2338707, "tid": 2338707, + "ts": 6197196668552.538, "dur": 1.056, + "args": { + "External id": 26517,"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": 2338707, "tid": 2338707, + "ts": 6197196668554.920, "dur": 20.007, + "args": { + "External id": 26518,"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": 2338707, "tid": 2338707, + "ts": 6197196668558.018, "dur": 2.783, + "args": { + "External id": 26519,"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": 2338707, "tid": 2338707, + "ts": 6197196668576.937, "dur": 23.955, + "args": { + "External id": 26520,"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": 2338707, "tid": 2338707, + "ts": 6197196668602.386, "dur": 17.339, + "args": { + "External id": 26521,"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": 2338707, "tid": 2338707, + "ts": 6197196668624.741, "dur": 15.003, + "args": { + "External id": 26522,"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": 2338707, "tid": 2338707, + "ts": 6197196668641.562, "dur": 15.123, + "args": { + "External id": 26523,"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": 2338707, "tid": 2338707, + "ts": 6197196668659.062, "dur": 25.565, + "args": { + "External id": 26524,"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": 2338707, "tid": 2338707, + "ts": 6197196668663.057, "dur": 1.759, + "args": { + "External id": 26525,"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": 2338707, "tid": 2338707, + "ts": 6197196668667.264, "dur": 0.657, + "args": { + "External id": 26526,"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": 2338707, "tid": 2338707, + "ts": 6197196668686.082, "dur": 30.252, + "args": { + "External id": 26527,"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": 2338707, "tid": 2338707, + "ts": 6197196668718.802, "dur": 14.252, + "args": { + "External id": 26528,"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": 2338707, "tid": 2338707, + "ts": 6197196668747.240, "dur": 2.339, + "args": { + "External id": 26529,"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": 2338707, "tid": 2338707, + "ts": 6197196668760.467, "dur": 4.686, + "args": { + "External id": 26530,"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": 2338707, "tid": 2338707, + "ts": 6197196668763.379, "dur": 0.770, + "args": { + "External id": 26531,"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": 2338707, "tid": 2338707, + "ts": 6197196668840.320, "dur": 66.380, + "args": { + "External id": 26532,"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": 2338707, "tid": 2338707, + "ts": 6197196668912.647, "dur": 5.721, + "args": { + "External id": 26533,"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": 2338707, "tid": 2338707, + "ts": 6197196668916.016, "dur": 1.031, + "args": { + "External id": 26534,"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": 2338707, "tid": 2338707, + "ts": 6197196668919.921, "dur": 30.654, + "args": { + "External id": 26535,"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": 2338707, "tid": 2338707, + "ts": 6197196668955.619, "dur": 8.931, + "args": { + "External id": 26536,"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": 2338707, "tid": 2338707, + "ts": 6197196668957.447, "dur": 6.357, + "args": { + "External id": 26537,"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": 2338707, "tid": 2338707, + "ts": 6197196668962.457, "dur": 1.097, + "args": { + "External id": 26538,"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": 2338707, "tid": 2338707, + "ts": 6197196668967.307, "dur": 48.251, + "args": { + "External id": 26539,"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": 2338707, "tid": 2338707, + "ts": 6197196668968.528, "dur": 46.228, + "args": { + "External id": 26540,"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": 2338707, "tid": 2338707, + "ts": 6197196669019.941, "dur": 16.841, + "args": { + "External id": 26541,"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": 2338707, "tid": 2338707, + "ts": 6197196669041.728, "dur": 68.791, + "args": { + "External id": 26542,"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": 2338707, "tid": 2338707, + "ts": 6197196669044.311, "dur": 65.388, + "args": { + "External id": 26543,"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": 2338707, "tid": 2338707, + "ts": 6197196669050.102, "dur": 0.949, + "args": { + "External id": 26544,"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": 2338707, "tid": 2338707, + "ts": 6197196669118.981, "dur": 38.630, + "args": { + "External id": 26545,"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": 2338707, "tid": 2338707, + "ts": 6197196669123.521, "dur": 33.728, + "args": { + "External id": 26546,"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": 2338707, "tid": 2338707, + "ts": 6197196669129.470, "dur": 4.756, + "args": { + "External id": 26547,"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": 2338707, "tid": 2338707, + "ts": 6197196669135.549, "dur": 21.093, + "args": { + "External id": 26548,"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": 2338707, "tid": 2338707, + "ts": 6197196669170.769, "dur": 5.899, + "args": { + "External id": 26549,"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": 2338707, "tid": 2338707, + "ts": 6197196669173.014, "dur": 3.392, + "args": { + "External id": 26550,"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": 2338707, "tid": 2338707, + "ts": 6197196669178.008, "dur": 3.905, + "args": { + "External id": 26551,"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": 2338707, "tid": 2338707, + "ts": 6197196669181.018, "dur": 0.760, + "args": { + "External id": 26552,"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": 2338707, "tid": 2338707, + "ts": 6197196669234.269, "dur": 29.014, + "args": { + "External id": 26553,"Sequence number": 479982, "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": 2338707, "tid": 2338707, + "ts": 6197196669265.519, "dur": 17.195, + "args": { + "External id": 26554,"Sequence number": 479983, "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": 2338707, "tid": 2338707, "ts": 6197196669265.519, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338707, "tid": 2338707, + "ts": 6197196669289.996, "dur": 7.435, + "args": { + "External id": 26555,"Sequence number": 479984, "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": 2338707, "tid": 2338707, + "ts": 6197196669294.076, "dur": 1.765, + "args": { + "External id": 26556,"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": 2338707, "tid": 2338707, + "ts": 6197196669300.547, "dur": 9.496, + "args": { + "External id": 26557,"Sequence number": 479984, "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": 2338707, "tid": 2338707, + "ts": 6197196669307.844, "dur": 0.705, + "args": { + "External id": 26558,"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": 2338707, "tid": 2338707, + "ts": 6197196669311.474, "dur": 2.992, + "args": { + "External id": 26559,"Sequence number": 479984, "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": 2338707, "tid": 2338707, + "ts": 6197196669313.216, "dur": 0.517, + "args": { + "External id": 26560,"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": 2338707, "tid": 2338707, + "ts": 6197196669319.566, "dur": 6.590, + "args": { + "External id": 26561,"Sequence number": 479984, "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": 2338707, "tid": 2338707, "ts": 6197196669319.566, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2338707, + "ts": 6197196669323.724, "dur": 0.832, + "args": { + "External id": 26562,"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": 2338707, "tid": 2338707, + "ts": 6197196669327.404, "dur": 7.210, + "args": { + "External id": 26563,"Sequence number": 479985, "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": 2338707, "tid": 2338707, "ts": 6197196669327.404, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2338707, + "ts": 6197196669333.197, "dur": 0.462, + "args": { + "External id": 26564,"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": 2338707, "tid": 2338707, + "ts": 6197196669335.946, "dur": 12.630, + "args": { + "External id": 26565,"Sequence number": 479986, "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": 2338707, "tid": 2338707, "ts": 6197196669335.946, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2338707, + "ts": 6197196669343.889, "dur": 3.641, + "args": { + "External id": 26566,"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": 2338707, "tid": 2338707, + "ts": 6197196669349.764, "dur": 6.011, + "args": { + "External id": 26567,"Sequence number": 479987, "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": 2338707, "tid": 2338707, "ts": 6197196669349.764, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2338707, + "ts": 6197196669352.921, "dur": 1.906, + "args": { + "External id": 26568,"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": 2338707, "tid": 2338707, + "ts": 6197196669360.215, "dur": 37.353, + "args": { + "External id": 26569,"Sequence number": 479988, "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": 2338707, "tid": 2338707, + "ts": 6197196669361.953, "dur": 35.306, + "args": { + "External id": 26570,"Sequence number": 479988, "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": 2338707, "tid": 2338707, + "ts": 6197196669365.113, "dur": 9.878, + "args": { + "External id": 26571,"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": 2338707, "tid": 2338707, + "ts": 6197196669369.804, "dur": 4.490, + "args": { + "External id": 26572,"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": 2338707, "tid": 2338707, + "ts": 6197196669376.433, "dur": 20.238, + "args": { + "External id": 26573,"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": 2338707, "tid": 2338707, + "ts": 6197196669428.355, "dur": 4.623, + "args": { + "External id": 26574,"Sequence number": 479988, "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": 2338707, "tid": 2338707, "ts": 6197196669428.355, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6197196669435.704, "dur": 1.411, + "args": { + "External id": 26575,"Sequence number": 479989, "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": 2338707, "tid": 2338707, + "ts": 6197196669478.204, "dur": 47671.081, + "args": { + "External id": 26576,"Sequence number": 479989, "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": 2338707, "tid": 2338707, "ts": 6197196669478.204, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338707, "tid": 2338707, + "ts": 6197196669496.830, "dur": 31.315, + "args": { + "External id": 26577,"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": 2338707, "tid": 2338707, + "ts": 6197196669497.603, "dur": 30.305, + "args": { + "External id": 26578,"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": 2338707, "tid": 2338707, + "ts": 6197196669499.350, "dur": 7.116, + "args": { + "External id": 26579,"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": 2338707, "tid": 2338707, + "ts": 6197196669501.110, "dur": 4.920, + "args": { + "External id": 26580,"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": 2338707, "tid": 2338707, + "ts": 6197196669507.177, "dur": 20.301, + "args": { + "External id": 26581,"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": 2338707, "tid": 2338707, + "ts": 6197196669548.555, "dur": 28.671, + "args": { + "External id": 26582,"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": 2338707, "tid": 2338707, + "ts": 6197196669549.826, "dur": 5.929, + "args": { + "External id": 26583,"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": 2338707, "tid": 2338707, + "ts": 6197196669551.790, "dur": 3.654, + "args": { + "External id": 26584,"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": 2338707, "tid": 2338707, + "ts": 6197196669557.293, "dur": 19.679, + "args": { + "External id": 26585,"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": 2338707, "tid": 2338707, + "ts": 6197196669559.428, "dur": 17.115, + "args": { + "External id": 26586,"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": 2338707, "tid": 2338707, + "ts": 6197196669586.357, "dur": 26.337, + "args": { + "External id": 26587,"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": 2338707, "tid": 2338707, + "ts": 6197196669587.284, "dur": 8.035, + "args": { + "External id": 26588,"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": 2338707, "tid": 2338707, + "ts": 6197196669590.782, "dur": 4.233, + "args": { + "External id": 26589,"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": 2338707, "tid": 2338707, + "ts": 6197196669595.893, "dur": 16.569, + "args": { + "External id": 26590,"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": 2338707, "tid": 2338707, + "ts": 6197196669596.501, "dur": 15.615, + "args": { + "External id": 26591,"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": 2338707, "tid": 2338707, + "ts": 6197196669619.798, "dur": 24.103, + "args": { + "External id": 26592,"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": 2338707, "tid": 2338707, + "ts": 6197196669621.695, "dur": 6.966, + "args": { + "External id": 26593,"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": 2338707, "tid": 2338707, + "ts": 6197196669629.276, "dur": 14.045, + "args": { + "External id": 26594,"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": 2338707, "tid": 2338707, + "ts": 6197196669630.210, "dur": 12.768, + "args": { + "External id": 26595,"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": 2338707, "tid": 2338707, + "ts": 6197196669652.123, "dur": 26.621, + "args": { + "External id": 26596,"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": 2338707, "tid": 2338707, + "ts": 6197196669682.384, "dur": 81.769, + "args": { + "External id": 26597,"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": 2338707, "tid": 2338707, + "ts": 6197196669684.318, "dur": 79.334, + "args": { + "External id": 26598,"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": 2338707, "tid": 2338707, + "ts": 6197196669689.505, "dur": 0.975, + "args": { + "External id": 26599,"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": 2338707, "tid": 2338707, + "ts": 6197196669692.125, "dur": 53.046, + "args": { + "External id": 26600,"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": 2338707, "tid": 2338707, + "ts": 6197196669694.051, "dur": 50.786, + "args": { + "External id": 26601,"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": 2338707, "tid": 2338707, + "ts": 6197196669698.383, "dur": 23.114, + "args": { + "External id": 26602,"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": 2338707, "tid": 2338707, + "ts": 6197196669723.591, "dur": 20.725, + "args": { + "External id": 26603,"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": 2338707, "tid": 2338707, + "ts": 6197196669769.589, "dur": 40338.705, + "args": { + "External id": 26604,"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": 2338707, "tid": 2338707, + "ts": 6197196669771.527, "dur": 40334.934, + "args": { + "External id": 26605,"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": 2338707, "tid": 2338707, + "ts": 6197196710121.233, "dur": 10.757, + "args": { + "External id": 26606,"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": 2338707, "tid": 2338707, + "ts": 6197196710128.517, "dur": 1.373, + "args": { + "External id": 26607,"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": 2338707, "tid": 2338707, + "ts": 6197196710137.840, "dur": 127.387, + "args": { + "External id": 26608,"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": 2338707, "tid": 2338707, + "ts": 6197196710139.548, "dur": 7.326, + "args": { + "External id": 26609,"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": 2338707, "tid": 2338707, + "ts": 6197196710142.021, "dur": 3.866, + "args": { + "External id": 26610,"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": 2338707, "tid": 2338707, + "ts": 6197196710144.636, "dur": 0.935, + "args": { + "External id": 26611,"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": 2338707, "tid": 2338707, + "ts": 6197196710148.407, "dur": 115.813, + "args": { + "External id": 26612,"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": 2338707, "tid": 2338707, + "ts": 6197196710152.997, "dur": 110.452, + "args": { + "External id": 26613,"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": 2338707, "tid": 2338707, + "ts": 6197196710270.208, "dur": 5.010, + "args": { + "External id": 26614,"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": 2338707, "tid": 2338707, + "ts": 6197196710272.581, "dur": 0.797, + "args": { + "External id": 26615,"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": 2338707, "tid": 2338707, + "ts": 6197196710284.457, "dur": 2.581, + "args": { + "External id": 26616,"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": 2338707, "tid": 2338707, + "ts": 6197196710298.716, "dur": 7.611, + "args": { + "External id": 26617,"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": 2338707, "tid": 2338707, + "ts": 6197196710301.185, "dur": 4.710, + "args": { + "External id": 26618,"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": 2338707, "tid": 2338707, + "ts": 6197196710468.719, "dur": 289.961, + "args": { + "External id": 26619,"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": 2338707, "tid": 2338707, + "ts": 6197196710472.606, "dur": 4.634, + "args": { + "External id": 26620,"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": 2338707, "tid": 2338707, + "ts": 6197196710479.350, "dur": 278.703, + "args": { + "External id": 26621,"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": 2338707, "tid": 2338707, + "ts": 6197196710481.288, "dur": 0.699, + "args": { + "External id": 26622,"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": 2338707, "tid": 2338707, + "ts": 6197196710486.089, "dur": 27.821, + "args": { + "External id": 26623,"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": 2338707, "tid": 2338707, + "ts": 6197196710516.141, "dur": 41.340, + "args": { + "External id": 26624,"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": 2338707, "tid": 2338707, + "ts": 6197196710556.254, "dur": 0.834, + "args": { + "External id": 26625,"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": 2338707, "tid": 2338707, + "ts": 6197196710558.918, "dur": 32.497, + "args": { + "External id": 26626,"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": 2338707, "tid": 2338707, + "ts": 6197196710563.869, "dur": 3.168, + "args": { + "External id": 26627,"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": 2338707, "tid": 2338707, + "ts": 6197196710568.573, "dur": 22.462, + "args": { + "External id": 26628,"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": 2338707, "tid": 2338707, + "ts": 6197196710572.962, "dur": 3.838, + "args": { + "External id": 26629,"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": 2338707, "tid": 2338707, + "ts": 6197196710593.760, "dur": 25.716, + "args": { + "External id": 26630,"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": 2338707, "tid": 2338707, + "ts": 6197196710621.527, "dur": 17.005, + "args": { + "External id": 26631,"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": 2338707, "tid": 2338707, + "ts": 6197196710642.461, "dur": 15.928, + "args": { + "External id": 26632,"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": 2338707, "tid": 2338707, + "ts": 6197196710660.329, "dur": 17.378, + "args": { + "External id": 26633,"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": 2338707, "tid": 2338707, + "ts": 6197196710680.047, "dur": 43.393, + "args": { + "External id": 26634,"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": 2338707, "tid": 2338707, + "ts": 6197196710682.578, "dur": 1.578, + "args": { + "External id": 26635,"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": 2338707, "tid": 2338707, + "ts": 6197196710689.101, "dur": 0.506, + "args": { + "External id": 26636,"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": 2338707, "tid": 2338707, + "ts": 6197196710726.622, "dur": 16.318, + "args": { + "External id": 26637,"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": 2338707, "tid": 2338707, + "ts": 6197196710744.589, "dur": 11.961, + "args": { + "External id": 26638,"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": 2338707, "tid": 2338707, + "ts": 6197196710769.645, "dur": 3.143, + "args": { + "External id": 26639,"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": 2338707, "tid": 2338707, + "ts": 6197196710781.605, "dur": 4.829, + "args": { + "External id": 26640,"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": 2338707, "tid": 2338707, + "ts": 6197196710784.597, "dur": 0.627, + "args": { + "External id": 26641,"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": 2338707, "tid": 2338707, + "ts": 6197196710884.955, "dur": 90.139, + "args": { + "External id": 26642,"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": 2338707, "tid": 2338707, + "ts": 6197196710984.993, "dur": 7.556, + "args": { + "External id": 26643,"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": 2338707, "tid": 2338707, + "ts": 6197196710988.926, "dur": 0.839, + "args": { + "External id": 26644,"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": 2338707, "tid": 2338707, + "ts": 6197196710994.814, "dur": 31.400, + "args": { + "External id": 26645,"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": 2338707, "tid": 2338707, + "ts": 6197196711032.896, "dur": 8.127, + "args": { + "External id": 26646,"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": 2338707, "tid": 2338707, + "ts": 6197196711035.356, "dur": 4.755, + "args": { + "External id": 26647,"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": 2338707, "tid": 2338707, + "ts": 6197196711038.173, "dur": 1.633, + "args": { + "External id": 26648,"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": 2338707, "tid": 2338707, + "ts": 6197196711047.423, "dur": 103.722, + "args": { + "External id": 26649,"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": 2338707, "tid": 2338707, + "ts": 6197196711048.787, "dur": 101.059, + "args": { + "External id": 26650,"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": 2338707, "tid": 2338707, + "ts": 6197196711158.957, "dur": 19.860, + "args": { + "External id": 26651,"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": 2338707, "tid": 2338707, + "ts": 6197196711187.625, "dur": 5.982, + "args": { + "External id": 26652,"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": 2338707, "tid": 2338707, + "ts": 6197196711191.159, "dur": 0.991, + "args": { + "External id": 26653,"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": 2338707, "tid": 2338707, + "ts": 6197196711199.172, "dur": 61.364, + "args": { + "External id": 26654,"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": 2338707, "tid": 2338707, + "ts": 6197196711200.475, "dur": 11.916, + "args": { + "External id": 26655,"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": 2338707, "tid": 2338707, + "ts": 6197196711204.194, "dur": 7.382, + "args": { + "External id": 26656,"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": 2338707, "tid": 2338707, + "ts": 6197196711208.590, "dur": 2.805, + "args": { + "External id": 26657,"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": 2338707, "tid": 2338707, + "ts": 6197196711213.189, "dur": 46.861, + "args": { + "External id": 26658,"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": 2338707, "tid": 2338707, + "ts": 6197196711214.051, "dur": 45.241, + "args": { + "External id": 26659,"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": 2338707, "tid": 2338707, + "ts": 6197196711265.904, "dur": 4.734, + "args": { + "External id": 26660,"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": 2338707, "tid": 2338707, + "ts": 6197196711268.521, "dur": 0.652, + "args": { + "External id": 26661,"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": 2338707, "tid": 2338707, + "ts": 6197196711281.712, "dur": 2.473, + "args": { + "External id": 26662,"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": 2338707, "tid": 2338707, + "ts": 6197196711295.248, "dur": 8.907, + "args": { + "External id": 26663,"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": 2338707, "tid": 2338707, + "ts": 6197196711297.967, "dur": 5.777, + "args": { + "External id": 26664,"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": 2338707, "tid": 2338707, + "ts": 6197196711425.307, "dur": 220.403, + "args": { + "External id": 26665,"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": 2338707, "tid": 2338707, + "ts": 6197196711428.298, "dur": 2.234, + "args": { + "External id": 26666,"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": 2338707, "tid": 2338707, + "ts": 6197196711432.571, "dur": 212.591, + "args": { + "External id": 26667,"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": 2338707, "tid": 2338707, + "ts": 6197196711438.069, "dur": 0.446, + "args": { + "External id": 26668,"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": 2338707, "tid": 2338707, + "ts": 6197196711440.589, "dur": 24.521, + "args": { + "External id": 26669,"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": 2338707, "tid": 2338707, + "ts": 6197196711467.381, "dur": 4.601, + "args": { + "External id": 26670,"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": 2338707, "tid": 2338707, + "ts": 6197196711470.493, "dur": 1.241, + "args": { + "External id": 26671,"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": 2338707, "tid": 2338707, + "ts": 6197196711473.307, "dur": 28.539, + "args": { + "External id": 26672,"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": 2338707, "tid": 2338707, + "ts": 6197196711476.440, "dur": 1.154, + "args": { + "External id": 26673,"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": 2338707, "tid": 2338707, + "ts": 6197196711479.131, "dur": 22.357, + "args": { + "External id": 26674,"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": 2338707, "tid": 2338707, + "ts": 6197196711482.870, "dur": 3.518, + "args": { + "External id": 26675,"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": 2338707, "tid": 2338707, + "ts": 6197196711503.717, "dur": 28.186, + "args": { + "External id": 26676,"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": 2338707, "tid": 2338707, + "ts": 6197196711533.571, "dur": 17.019, + "args": { + "External id": 26677,"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": 2338707, "tid": 2338707, + "ts": 6197196711556.845, "dur": 16.071, + "args": { + "External id": 26678,"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": 2338707, "tid": 2338707, + "ts": 6197196711574.786, "dur": 13.717, + "args": { + "External id": 26679,"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": 2338707, "tid": 2338707, + "ts": 6197196711590.843, "dur": 23.927, + "args": { + "External id": 26680,"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": 2338707, "tid": 2338707, + "ts": 6197196711593.420, "dur": 2.607, + "args": { + "External id": 26681,"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": 2338707, "tid": 2338707, + "ts": 6197196711598.276, "dur": 0.676, + "args": { + "External id": 26682,"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": 2338707, "tid": 2338707, + "ts": 6197196711616.697, "dur": 13.756, + "args": { + "External id": 26683,"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": 2338707, "tid": 2338707, + "ts": 6197196711631.906, "dur": 11.934, + "args": { + "External id": 26684,"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": 2338707, "tid": 2338707, + "ts": 6197196711656.109, "dur": 1.941, + "args": { + "External id": 26685,"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": 2338707, "tid": 2338707, + "ts": 6197196711669.077, "dur": 4.529, + "args": { + "External id": 26686,"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": 2338707, "tid": 2338707, + "ts": 6197196711672.181, "dur": 0.454, + "args": { + "External id": 26687,"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": 2338707, "tid": 2338707, + "ts": 6197196711776.220, "dur": 72.205, + "args": { + "External id": 26688,"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": 2338707, "tid": 2338707, + "ts": 6197196711855.260, "dur": 6.695, + "args": { + "External id": 26689,"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": 2338707, "tid": 2338707, + "ts": 6197196711859.145, "dur": 0.838, + "args": { + "External id": 26690,"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": 2338707, "tid": 2338707, + "ts": 6197196711863.979, "dur": 30.934, + "args": { + "External id": 26691,"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": 2338707, "tid": 2338707, + "ts": 6197196711901.410, "dur": 11.450, + "args": { + "External id": 26692,"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": 2338707, "tid": 2338707, + "ts": 6197196711903.281, "dur": 8.610, + "args": { + "External id": 26693,"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": 2338707, "tid": 2338707, + "ts": 6197196711908.766, "dur": 2.809, + "args": { + "External id": 26694,"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": 2338707, "tid": 2338707, + "ts": 6197196711923.941, "dur": 50.609, + "args": { + "External id": 26695,"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": 2338707, "tid": 2338707, + "ts": 6197196711925.162, "dur": 48.635, + "args": { + "External id": 26696,"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": 2338707, "tid": 2338707, + "ts": 6197196711979.313, "dur": 16.884, + "args": { + "External id": 26697,"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": 2338707, "tid": 2338707, + "ts": 6197196712002.937, "dur": 5.131, + "args": { + "External id": 26698,"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": 2338707, "tid": 2338707, + "ts": 6197196712006.237, "dur": 0.718, + "args": { + "External id": 26699,"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": 2338707, "tid": 2338707, + "ts": 6197196712016.326, "dur": 91.779, + "args": { + "External id": 26700,"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": 2338707, "tid": 2338707, + "ts": 6197196712017.303, "dur": 4.211, + "args": { + "External id": 26701,"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": 2338707, "tid": 2338707, + "ts": 6197196712018.420, "dur": 2.364, + "args": { + "External id": 26702,"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": 2338707, "tid": 2338707, + "ts": 6197196712019.884, "dur": 0.706, + "args": { + "External id": 26703,"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": 2338707, "tid": 2338707, + "ts": 6197196712022.411, "dur": 85.084, + "args": { + "External id": 26704,"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": 2338707, "tid": 2338707, + "ts": 6197196712023.426, "dur": 82.666, + "args": { + "External id": 26705,"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": 2338707, "tid": 2338707, + "ts": 6197196712117.723, "dur": 5.680, + "args": { + "External id": 26706,"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": 2338707, "tid": 2338707, + "ts": 6197196712120.860, "dur": 0.897, + "args": { + "External id": 26707,"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": 2338707, "tid": 2338707, + "ts": 6197196712134.219, "dur": 2.010, + "args": { + "External id": 26708,"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": 2338707, "tid": 2338707, + "ts": 6197196712146.992, "dur": 11.417, + "args": { + "External id": 26709,"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": 2338707, "tid": 2338707, + "ts": 6197196712149.599, "dur": 8.449, + "args": { + "External id": 26710,"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": 2338707, "tid": 2338707, + "ts": 6197196712276.477, "dur": 250.583, + "args": { + "External id": 26711,"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": 2338707, "tid": 2338707, + "ts": 6197196712279.126, "dur": 2.039, + "args": { + "External id": 26712,"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": 2338707, "tid": 2338707, + "ts": 6197196712283.856, "dur": 242.502, + "args": { + "External id": 26713,"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": 2338707, "tid": 2338707, + "ts": 6197196712288.312, "dur": 0.777, + "args": { + "External id": 26714,"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": 2338707, "tid": 2338707, + "ts": 6197196712290.507, "dur": 29.339, + "args": { + "External id": 26715,"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": 2338707, "tid": 2338707, + "ts": 6197196712322.270, "dur": 4.149, + "args": { + "External id": 26716,"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": 2338707, "tid": 2338707, + "ts": 6197196712325.281, "dur": 0.875, + "args": { + "External id": 26717,"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": 2338707, "tid": 2338707, + "ts": 6197196712327.650, "dur": 35.219, + "args": { + "External id": 26718,"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": 2338707, "tid": 2338707, + "ts": 6197196712328.803, "dur": 1.513, + "args": { + "External id": 26719,"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": 2338707, "tid": 2338707, + "ts": 6197196712332.032, "dur": 30.385, + "args": { + "External id": 26720,"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": 2338707, "tid": 2338707, + "ts": 6197196712337.683, "dur": 3.240, + "args": { + "External id": 26721,"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": 2338707, "tid": 2338707, + "ts": 6197196712364.673, "dur": 35.424, + "args": { + "External id": 26722,"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": 2338707, "tid": 2338707, + "ts": 6197196712401.886, "dur": 19.785, + "args": { + "External id": 26723,"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": 2338707, "tid": 2338707, + "ts": 6197196712427.464, "dur": 18.236, + "args": { + "External id": 26724,"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": 2338707, "tid": 2338707, + "ts": 6197196712447.356, "dur": 17.268, + "args": { + "External id": 26725,"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": 2338707, "tid": 2338707, + "ts": 6197196712467.192, "dur": 24.448, + "args": { + "External id": 26726,"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": 2338707, "tid": 2338707, + "ts": 6197196712469.765, "dur": 1.823, + "args": { + "External id": 26727,"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": 2338707, "tid": 2338707, + "ts": 6197196712474.151, "dur": 0.586, + "args": { + "External id": 26728,"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": 2338707, "tid": 2338707, + "ts": 6197196712493.230, "dur": 15.221, + "args": { + "External id": 26729,"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": 2338707, "tid": 2338707, + "ts": 6197196712512.266, "dur": 12.769, + "args": { + "External id": 26730,"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": 2338707, "tid": 2338707, + "ts": 6197196712534.528, "dur": 2.201, + "args": { + "External id": 26731,"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": 2338707, "tid": 2338707, + "ts": 6197196712547.031, "dur": 4.329, + "args": { + "External id": 26732,"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": 2338707, "tid": 2338707, + "ts": 6197196712550.059, "dur": 0.439, + "args": { + "External id": 26733,"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": 2338707, "tid": 2338707, + "ts": 6197196712630.892, "dur": 85.880, + "args": { + "External id": 26734,"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": 2338707, "tid": 2338707, + "ts": 6197196712725.208, "dur": 7.328, + "args": { + "External id": 26735,"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": 2338707, "tid": 2338707, + "ts": 6197196712729.346, "dur": 1.390, + "args": { + "External id": 26736,"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": 2338707, "tid": 2338707, + "ts": 6197196712734.635, "dur": 34.067, + "args": { + "External id": 26737,"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": 2338707, "tid": 2338707, + "ts": 6197196712777.895, "dur": 6.571, + "args": { + "External id": 26738,"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": 2338707, "tid": 2338707, + "ts": 6197196712779.579, "dur": 3.822, + "args": { + "External id": 26739,"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": 2338707, "tid": 2338707, + "ts": 6197196712781.804, "dur": 1.349, + "args": { + "External id": 26740,"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": 2338707, "tid": 2338707, + "ts": 6197196712788.213, "dur": 54.527, + "args": { + "External id": 26741,"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": 2338707, "tid": 2338707, + "ts": 6197196712789.528, "dur": 52.518, + "args": { + "External id": 26742,"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": 2338707, "tid": 2338707, + "ts": 6197196712847.216, "dur": 18.824, + "args": { + "External id": 26743,"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": 2338707, "tid": 2338707, + "ts": 6197196712873.488, "dur": 9.254, + "args": { + "External id": 26744,"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": 2338707, "tid": 2338707, + "ts": 6197196712881.183, "dur": 0.548, + "args": { + "External id": 26745,"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": 2338707, "tid": 2338707, + "ts": 6197196712887.867, "dur": 55.897, + "args": { + "External id": 26746,"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": 2338707, "tid": 2338707, + "ts": 6197196712888.830, "dur": 4.350, + "args": { + "External id": 26747,"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": 2338707, "tid": 2338707, + "ts": 6197196712889.983, "dur": 2.477, + "args": { + "External id": 26748,"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": 2338707, "tid": 2338707, + "ts": 6197196712891.673, "dur": 0.559, + "args": { + "External id": 26749,"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": 2338707, "tid": 2338707, + "ts": 6197196712894.095, "dur": 49.277, + "args": { + "External id": 26750,"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": 2338707, "tid": 2338707, + "ts": 6197196712897.276, "dur": 45.430, + "args": { + "External id": 26751,"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": 2338707, "tid": 2338707, + "ts": 6197196712948.460, "dur": 6.187, + "args": { + "External id": 26752,"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": 2338707, "tid": 2338707, + "ts": 6197196712950.838, "dur": 2.471, + "args": { + "External id": 26753,"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": 2338707, "tid": 2338707, + "ts": 6197196712961.500, "dur": 2.272, + "args": { + "External id": 26754,"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": 2338707, "tid": 2338707, + "ts": 6197196712973.151, "dur": 12.051, + "args": { + "External id": 26755,"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": 2338707, "tid": 2338707, + "ts": 6197196712978.148, "dur": 6.724, + "args": { + "External id": 26756,"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": 2338707, "tid": 2338707, + "ts": 6197196713134.687, "dur": 225.843, + "args": { + "External id": 26757,"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": 2338707, "tid": 2338707, + "ts": 6197196713137.605, "dur": 3.506, + "args": { + "External id": 26758,"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": 2338707, "tid": 2338707, + "ts": 6197196713143.914, "dur": 216.114, + "args": { + "External id": 26759,"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": 2338707, "tid": 2338707, + "ts": 6197196713145.389, "dur": 0.494, + "args": { + "External id": 26760,"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": 2338707, "tid": 2338707, + "ts": 6197196713147.617, "dur": 30.298, + "args": { + "External id": 26761,"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": 2338707, "tid": 2338707, + "ts": 6197196713179.995, "dur": 4.451, + "args": { + "External id": 26762,"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": 2338707, "tid": 2338707, + "ts": 6197196713183.081, "dur": 0.850, + "args": { + "External id": 26763,"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": 2338707, "tid": 2338707, + "ts": 6197196713185.576, "dur": 31.027, + "args": { + "External id": 26764,"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": 2338707, "tid": 2338707, + "ts": 6197196713189.837, "dur": 1.198, + "args": { + "External id": 26765,"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": 2338707, "tid": 2338707, + "ts": 6197196713192.533, "dur": 23.716, + "args": { + "External id": 26766,"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": 2338707, "tid": 2338707, + "ts": 6197196713198.103, "dur": 3.258, + "args": { + "External id": 26767,"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": 2338707, "tid": 2338707, + "ts": 6197196713218.309, "dur": 26.076, + "args": { + "External id": 26768,"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": 2338707, "tid": 2338707, + "ts": 6197196713246.021, "dur": 15.994, + "args": { + "External id": 26769,"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": 2338707, "tid": 2338707, + "ts": 6197196713265.051, "dur": 17.864, + "args": { + "External id": 26770,"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": 2338707, "tid": 2338707, + "ts": 6197196713284.821, "dur": 15.066, + "args": { + "External id": 26771,"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": 2338707, "tid": 2338707, + "ts": 6197196713301.996, "dur": 28.095, + "args": { + "External id": 26772,"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": 2338707, "tid": 2338707, + "ts": 6197196713304.692, "dur": 2.222, + "args": { + "External id": 26773,"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": 2338707, "tid": 2338707, + "ts": 6197196713312.389, "dur": 0.682, + "args": { + "External id": 26774,"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": 2338707, "tid": 2338707, + "ts": 6197196713331.551, "dur": 13.758, + "args": { + "External id": 26775,"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": 2338707, "tid": 2338707, + "ts": 6197196713346.735, "dur": 11.703, + "args": { + "External id": 26776,"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": 2338707, "tid": 2338707, + "ts": 6197196713369.306, "dur": 2.410, + "args": { + "External id": 26777,"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": 2338707, "tid": 2338707, + "ts": 6197196713384.016, "dur": 4.722, + "args": { + "External id": 26778,"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": 2338707, "tid": 2338707, + "ts": 6197196713387.136, "dur": 0.576, + "args": { + "External id": 26779,"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": 2338707, "tid": 2338707, + "ts": 6197196713469.721, "dur": 71.355, + "args": { + "External id": 26780,"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": 2338707, "tid": 2338707, + "ts": 6197196713547.692, "dur": 8.188, + "args": { + "External id": 26781,"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": 2338707, "tid": 2338707, + "ts": 6197196713553.397, "dur": 1.171, + "args": { + "External id": 26782,"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": 2338707, "tid": 2338707, + "ts": 6197196713557.707, "dur": 27.785, + "args": { + "External id": 26783,"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": 2338707, "tid": 2338707, + "ts": 6197196713590.506, "dur": 6.078, + "args": { + "External id": 26784,"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": 2338707, "tid": 2338707, + "ts": 6197196713592.371, "dur": 3.412, + "args": { + "External id": 26785,"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": 2338707, "tid": 2338707, + "ts": 6197196713594.657, "dur": 0.905, + "args": { + "External id": 26786,"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": 2338707, "tid": 2338707, + "ts": 6197196713599.677, "dur": 48.074, + "args": { + "External id": 26787,"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": 2338707, "tid": 2338707, + "ts": 6197196713601.062, "dur": 45.852, + "args": { + "External id": 26788,"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": 2338707, "tid": 2338707, + "ts": 6197196713651.682, "dur": 16.222, + "args": { + "External id": 26789,"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": 2338707, "tid": 2338707, + "ts": 6197196713676.989, "dur": 4.162, + "args": { + "External id": 26790,"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": 2338707, "tid": 2338707, + "ts": 6197196713679.393, "dur": 0.848, + "args": { + "External id": 26791,"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": 2338707, "tid": 2338707, + "ts": 6197196713686.015, "dur": 81.823, + "args": { + "External id": 26792,"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": 2338707, "tid": 2338707, + "ts": 6197196713686.798, "dur": 8.983, + "args": { + "External id": 26793,"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": 2338707, "tid": 2338707, + "ts": 6197196713687.693, "dur": 7.377, + "args": { + "External id": 26794,"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": 2338707, "tid": 2338707, + "ts": 6197196713694.377, "dur": 0.553, + "args": { + "External id": 26795,"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": 2338707, "tid": 2338707, + "ts": 6197196713697.073, "dur": 70.215, + "args": { + "External id": 26796,"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": 2338707, "tid": 2338707, + "ts": 6197196713698.069, "dur": 68.196, + "args": { + "External id": 26797,"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": 2338707, "tid": 2338707, + "ts": 6197196713775.355, "dur": 5.932, + "args": { + "External id": 26798,"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": 2338707, "tid": 2338707, + "ts": 6197196713778.681, "dur": 0.773, + "args": { + "External id": 26799,"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": 2338707, "tid": 2338707, + "ts": 6197196713788.607, "dur": 2.244, + "args": { + "External id": 26800,"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": 2338707, "tid": 2338707, + "ts": 6197196713800.648, "dur": 10.284, + "args": { + "External id": 26801,"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": 2338707, "tid": 2338707, + "ts": 6197196713805.759, "dur": 4.752, + "args": { + "External id": 26802,"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": 2338707, "tid": 2338707, + "ts": 6197196713917.292, "dur": 268.562, + "args": { + "External id": 26803,"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": 2338707, "tid": 2338707, + "ts": 6197196713920.259, "dur": 1.944, + "args": { + "External id": 26804,"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": 2338707, "tid": 2338707, + "ts": 6197196713923.882, "dur": 261.367, + "args": { + "External id": 26805,"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": 2338707, "tid": 2338707, + "ts": 6197196713927.487, "dur": 0.430, + "args": { + "External id": 26806,"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": 2338707, "tid": 2338707, + "ts": 6197196713929.246, "dur": 35.062, + "args": { + "External id": 26807,"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": 2338707, "tid": 2338707, + "ts": 6197196713966.291, "dur": 3.984, + "args": { + "External id": 26808,"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": 2338707, "tid": 2338707, + "ts": 6197196713969.039, "dur": 0.967, + "args": { + "External id": 26809,"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": 2338707, "tid": 2338707, + "ts": 6197196713971.532, "dur": 31.125, + "args": { + "External id": 26810,"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": 2338707, "tid": 2338707, + "ts": 6197196713978.261, "dur": 1.271, + "args": { + "External id": 26811,"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": 2338707, "tid": 2338707, + "ts": 6197196713980.903, "dur": 21.372, + "args": { + "External id": 26812,"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": 2338707, "tid": 2338707, + "ts": 6197196713984.576, "dur": 3.447, + "args": { + "External id": 26813,"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": 2338707, "tid": 2338707, + "ts": 6197196714004.296, "dur": 24.383, + "args": { + "External id": 26814,"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": 2338707, "tid": 2338707, + "ts": 6197196714030.859, "dur": 14.754, + "args": { + "External id": 26815,"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": 2338707, "tid": 2338707, + "ts": 6197196714049.027, "dur": 57.800, + "args": { + "External id": 26816,"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": 2338707, "tid": 2338707, + "ts": 6197196714109.981, "dur": 15.782, + "args": { + "External id": 26817,"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": 2338707, "tid": 2338707, + "ts": 6197196714128.377, "dur": 27.756, + "args": { + "External id": 26818,"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": 2338707, "tid": 2338707, + "ts": 6197196714130.854, "dur": 2.566, + "args": { + "External id": 26819,"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": 2338707, "tid": 2338707, + "ts": 6197196714138.465, "dur": 0.914, + "args": { + "External id": 26820,"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": 2338707, "tid": 2338707, + "ts": 6197196714157.700, "dur": 12.962, + "args": { + "External id": 26821,"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": 2338707, "tid": 2338707, + "ts": 6197196714171.962, "dur": 11.680, + "args": { + "External id": 26822,"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": 2338707, "tid": 2338707, + "ts": 6197196714194.987, "dur": 2.690, + "args": { + "External id": 26823,"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": 2338707, "tid": 2338707, + "ts": 6197196714210.236, "dur": 4.718, + "args": { + "External id": 26824,"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": 2338707, "tid": 2338707, + "ts": 6197196714213.397, "dur": 0.550, + "args": { + "External id": 26825,"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": 2338707, "tid": 2338707, + "ts": 6197196714301.187, "dur": 71.398, + "args": { + "External id": 26826,"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": 2338707, "tid": 2338707, + "ts": 6197196714381.094, "dur": 7.058, + "args": { + "External id": 26827,"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": 2338707, "tid": 2338707, + "ts": 6197196714384.197, "dur": 2.424, + "args": { + "External id": 26828,"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": 2338707, "tid": 2338707, + "ts": 6197196714390.181, "dur": 30.091, + "args": { + "External id": 26829,"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": 2338707, "tid": 2338707, + "ts": 6197196714425.702, "dur": 6.678, + "args": { + "External id": 26830,"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": 2338707, "tid": 2338707, + "ts": 6197196714427.770, "dur": 3.646, + "args": { + "External id": 26831,"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": 2338707, "tid": 2338707, + "ts": 6197196714430.324, "dur": 0.866, + "args": { + "External id": 26832,"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": 2338707, "tid": 2338707, + "ts": 6197196714437.988, "dur": 47.029, + "args": { + "External id": 26833,"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": 2338707, "tid": 2338707, + "ts": 6197196714439.280, "dur": 45.028, + "args": { + "External id": 26834,"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": 2338707, "tid": 2338707, + "ts": 6197196714489.802, "dur": 18.707, + "args": { + "External id": 26835,"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": 2338707, "tid": 2338707, + "ts": 6197196714515.449, "dur": 4.511, + "args": { + "External id": 26836,"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": 2338707, "tid": 2338707, + "ts": 6197196714518.052, "dur": 0.870, + "args": { + "External id": 26837,"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": 2338707, "tid": 2338707, + "ts": 6197196714524.876, "dur": 52.396, + "args": { + "External id": 26838,"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": 2338707, "tid": 2338707, + "ts": 6197196714525.625, "dur": 7.057, + "args": { + "External id": 26839,"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": 2338707, "tid": 2338707, + "ts": 6197196714529.417, "dur": 2.586, + "args": { + "External id": 26840,"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": 2338707, "tid": 2338707, + "ts": 6197196714530.929, "dur": 0.873, + "args": { + "External id": 26841,"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": 2338707, "tid": 2338707, + "ts": 6197196714533.522, "dur": 43.114, + "args": { + "External id": 26842,"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": 2338707, "tid": 2338707, + "ts": 6197196714534.375, "dur": 41.652, + "args": { + "External id": 26843,"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": 2338707, "tid": 2338707, + "ts": 6197196714581.977, "dur": 4.400, + "args": { + "External id": 26844,"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": 2338707, "tid": 2338707, + "ts": 6197196714584.396, "dur": 0.675, + "args": { + "External id": 26845,"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": 2338707, "tid": 2338707, + "ts": 6197196714595.569, "dur": 1.712, + "args": { + "External id": 26846,"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": 2338707, "tid": 2338707, + "ts": 6197196714606.533, "dur": 8.589, + "args": { + "External id": 26847,"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": 2338707, "tid": 2338707, + "ts": 6197196714608.699, "dur": 6.087, + "args": { + "External id": 26848,"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": 2338707, "tid": 2338707, + "ts": 6197196714740.016, "dur": 227.916, + "args": { + "External id": 26849,"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": 2338707, "tid": 2338707, + "ts": 6197196714742.943, "dur": 5.085, + "args": { + "External id": 26850,"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": 2338707, "tid": 2338707, + "ts": 6197196714749.757, "dur": 217.433, + "args": { + "External id": 26851,"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": 2338707, "tid": 2338707, + "ts": 6197196714753.693, "dur": 0.575, + "args": { + "External id": 26852,"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": 2338707, "tid": 2338707, + "ts": 6197196714755.912, "dur": 29.523, + "args": { + "External id": 26853,"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": 2338707, "tid": 2338707, + "ts": 6197196714787.264, "dur": 6.671, + "args": { + "External id": 26854,"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": 2338707, "tid": 2338707, + "ts": 6197196714792.531, "dur": 1.130, + "args": { + "External id": 26855,"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": 2338707, "tid": 2338707, + "ts": 6197196714795.095, "dur": 25.043, + "args": { + "External id": 26856,"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": 2338707, "tid": 2338707, + "ts": 6197196714796.097, "dur": 1.359, + "args": { + "External id": 26857,"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": 2338707, "tid": 2338707, + "ts": 6197196714799.114, "dur": 20.648, + "args": { + "External id": 26858,"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": 2338707, "tid": 2338707, + "ts": 6197196714802.878, "dur": 2.772, + "args": { + "External id": 26859,"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": 2338707, "tid": 2338707, + "ts": 6197196714821.717, "dur": 27.359, + "args": { + "External id": 26860,"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": 2338707, "tid": 2338707, + "ts": 6197196714850.748, "dur": 16.108, + "args": { + "External id": 26861,"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": 2338707, "tid": 2338707, + "ts": 6197196714872.464, "dur": 17.231, + "args": { + "External id": 26862,"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": 2338707, "tid": 2338707, + "ts": 6197196714891.374, "dur": 15.389, + "args": { + "External id": 26863,"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": 2338707, "tid": 2338707, + "ts": 6197196714909.024, "dur": 26.445, + "args": { + "External id": 26864,"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": 2338707, "tid": 2338707, + "ts": 6197196714911.915, "dur": 1.996, + "args": { + "External id": 26865,"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": 2338707, "tid": 2338707, + "ts": 6197196714915.878, "dur": 2.683, + "args": { + "External id": 26866,"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": 2338707, "tid": 2338707, + "ts": 6197196714937.264, "dur": 14.493, + "args": { + "External id": 26867,"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": 2338707, "tid": 2338707, + "ts": 6197196714952.828, "dur": 12.970, + "args": { + "External id": 26868,"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": 2338707, "tid": 2338707, + "ts": 6197196714978.615, "dur": 2.807, + "args": { + "External id": 26869,"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": 2338707, "tid": 2338707, + "ts": 6197196714993.388, "dur": 4.533, + "args": { + "External id": 26870,"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": 2338707, "tid": 2338707, + "ts": 6197196714996.299, "dur": 0.512, + "args": { + "External id": 26871,"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": 2338707, "tid": 2338707, + "ts": 6197196715120.498, "dur": 74.537, + "args": { + "External id": 26872,"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": 2338707, "tid": 2338707, + "ts": 6197196715202.740, "dur": 7.213, + "args": { + "External id": 26873,"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": 2338707, "tid": 2338707, + "ts": 6197196715206.877, "dur": 1.125, + "args": { + "External id": 26874,"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": 2338707, "tid": 2338707, + "ts": 6197196715211.866, "dur": 31.982, + "args": { + "External id": 26875,"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": 2338707, "tid": 2338707, + "ts": 6197196715250.279, "dur": 9.106, + "args": { + "External id": 26876,"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": 2338707, "tid": 2338707, + "ts": 6197196715251.984, "dur": 6.529, + "args": { + "External id": 26877,"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": 2338707, "tid": 2338707, + "ts": 6197196715257.007, "dur": 1.284, + "args": { + "External id": 26878,"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": 2338707, "tid": 2338707, + "ts": 6197196715262.632, "dur": 48.846, + "args": { + "External id": 26879,"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": 2338707, "tid": 2338707, + "ts": 6197196715263.780, "dur": 46.996, + "args": { + "External id": 26880,"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": 2338707, "tid": 2338707, + "ts": 6197196715315.889, "dur": 19.361, + "args": { + "External id": 26881,"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": 2338707, "tid": 2338707, + "ts": 6197196715341.683, "dur": 4.543, + "args": { + "External id": 26882,"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": 2338707, "tid": 2338707, + "ts": 6197196715344.608, "dur": 0.617, + "args": { + "External id": 26883,"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": 2338707, "tid": 2338707, + "ts": 6197196715353.182, "dur": 50.836, + "args": { + "External id": 26884,"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": 2338707, "tid": 2338707, + "ts": 6197196715354.148, "dur": 3.576, + "args": { + "External id": 26885,"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": 2338707, "tid": 2338707, + "ts": 6197196715355.025, "dur": 2.018, + "args": { + "External id": 26886,"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": 2338707, "tid": 2338707, + "ts": 6197196715356.387, "dur": 0.501, + "args": { + "External id": 26887,"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": 2338707, "tid": 2338707, + "ts": 6197196715358.498, "dur": 45.067, + "args": { + "External id": 26888,"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": 2338707, "tid": 2338707, + "ts": 6197196715358.964, "dur": 44.003, + "args": { + "External id": 26889,"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": 2338707, "tid": 2338707, + "ts": 6197196715408.988, "dur": 6.769, + "args": { + "External id": 26890,"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": 2338707, "tid": 2338707, + "ts": 6197196715411.452, "dur": 3.034, + "args": { + "External id": 26891,"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": 2338707, "tid": 2338707, + "ts": 6197196715425.256, "dur": 1.887, + "args": { + "External id": 26892,"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": 2338707, "tid": 2338707, + "ts": 6197196715436.769, "dur": 6.872, + "args": { + "External id": 26893,"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": 2338707, "tid": 2338707, + "ts": 6197196715438.958, "dur": 4.343, + "args": { + "External id": 26894,"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": 2338707, "tid": 2338707, + "ts": 6197196715542.594, "dur": 265.403, + "args": { + "External id": 26895,"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": 2338707, "tid": 2338707, + "ts": 6197196715546.416, "dur": 2.192, + "args": { + "External id": 26896,"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": 2338707, "tid": 2338707, + "ts": 6197196715550.928, "dur": 256.576, + "args": { + "External id": 26897,"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": 2338707, "tid": 2338707, + "ts": 6197196715554.955, "dur": 0.515, + "args": { + "External id": 26898,"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": 2338707, "tid": 2338707, + "ts": 6197196715556.877, "dur": 25.687, + "args": { + "External id": 26899,"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": 2338707, "tid": 2338707, + "ts": 6197196715584.466, "dur": 4.730, + "args": { + "External id": 26900,"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": 2338707, "tid": 2338707, + "ts": 6197196715588.222, "dur": 0.730, + "args": { + "External id": 26901,"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": 2338707, "tid": 2338707, + "ts": 6197196715590.288, "dur": 30.960, + "args": { + "External id": 26902,"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": 2338707, "tid": 2338707, + "ts": 6197196715591.708, "dur": 1.754, + "args": { + "External id": 26903,"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": 2338707, "tid": 2338707, + "ts": 6197196715594.794, "dur": 26.107, + "args": { + "External id": 26904,"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": 2338707, "tid": 2338707, + "ts": 6197196715598.181, "dur": 3.739, + "args": { + "External id": 26905,"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": 2338707, "tid": 2338707, + "ts": 6197196715622.694, "dur": 26.655, + "args": { + "External id": 26906,"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": 2338707, "tid": 2338707, + "ts": 6197196715650.868, "dur": 16.489, + "args": { + "External id": 26907,"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": 2338707, "tid": 2338707, + "ts": 6197196715672.658, "dur": 16.111, + "args": { + "External id": 26908,"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": 2338707, "tid": 2338707, + "ts": 6197196715690.156, "dur": 48.948, + "args": { + "External id": 26909,"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": 2338707, "tid": 2338707, + "ts": 6197196715743.008, "dur": 29.188, + "args": { + "External id": 26910,"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": 2338707, "tid": 2338707, + "ts": 6197196715747.658, "dur": 2.434, + "args": { + "External id": 26911,"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": 2338707, "tid": 2338707, + "ts": 6197196715752.485, "dur": 1.118, + "args": { + "External id": 26912,"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": 2338707, "tid": 2338707, + "ts": 6197196715774.185, "dur": 14.290, + "args": { + "External id": 26913,"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": 2338707, "tid": 2338707, + "ts": 6197196715792.654, "dur": 13.456, + "args": { + "External id": 26914,"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": 2338707, "tid": 2338707, + "ts": 6197196715817.419, "dur": 2.718, + "args": { + "External id": 26915,"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": 2338707, "tid": 2338707, + "ts": 6197196715831.619, "dur": 4.852, + "args": { + "External id": 26916,"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": 2338707, "tid": 2338707, + "ts": 6197196715835.029, "dur": 0.409, + "args": { + "External id": 26917,"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": 2338707, "tid": 2338707, + "ts": 6197196715918.728, "dur": 68.905, + "args": { + "External id": 26918,"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": 2338707, "tid": 2338707, + "ts": 6197196715993.954, "dur": 5.596, + "args": { + "External id": 26919,"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": 2338707, "tid": 2338707, + "ts": 6197196715997.371, "dur": 0.786, + "args": { + "External id": 26920,"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": 2338707, "tid": 2338707, + "ts": 6197196716001.322, "dur": 29.215, + "args": { + "External id": 26921,"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": 2338707, "tid": 2338707, + "ts": 6197196716038.317, "dur": 6.398, + "args": { + "External id": 26922,"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": 2338707, "tid": 2338707, + "ts": 6197196716040.269, "dur": 3.635, + "args": { + "External id": 26923,"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": 2338707, "tid": 2338707, + "ts": 6197196716042.398, "dur": 1.297, + "args": { + "External id": 26924,"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": 2338707, "tid": 2338707, + "ts": 6197196716047.636, "dur": 120.213, + "args": { + "External id": 26925,"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": 2338707, "tid": 2338707, + "ts": 6197196716048.653, "dur": 117.805, + "args": { + "External id": 26926,"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": 2338707, "tid": 2338707, + "ts": 6197196716175.761, "dur": 19.352, + "args": { + "External id": 26927,"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": 2338707, "tid": 2338707, + "ts": 6197196716204.218, "dur": 8.975, + "args": { + "External id": 26928,"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": 2338707, "tid": 2338707, + "ts": 6197196716210.638, "dur": 1.092, + "args": { + "External id": 26929,"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": 2338707, "tid": 2338707, + "ts": 6197196716218.357, "dur": 59.335, + "args": { + "External id": 26930,"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": 2338707, "tid": 2338707, + "ts": 6197196716219.469, "dur": 5.326, + "args": { + "External id": 26931,"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": 2338707, "tid": 2338707, + "ts": 6197196716220.852, "dur": 3.251, + "args": { + "External id": 26932,"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": 2338707, "tid": 2338707, + "ts": 6197196716222.988, "dur": 0.956, + "args": { + "External id": 26933,"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": 2338707, "tid": 2338707, + "ts": 6197196716225.551, "dur": 51.641, + "args": { + "External id": 26934,"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": 2338707, "tid": 2338707, + "ts": 6197196716228.669, "dur": 47.783, + "args": { + "External id": 26935,"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": 2338707, "tid": 2338707, + "ts": 6197196716282.404, "dur": 4.451, + "args": { + "External id": 26936,"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": 2338707, "tid": 2338707, + "ts": 6197196716284.800, "dur": 0.645, + "args": { + "External id": 26937,"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": 2338707, "tid": 2338707, + "ts": 6197196716294.792, "dur": 1.953, + "args": { + "External id": 26938,"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": 2338707, "tid": 2338707, + "ts": 6197196716307.209, "dur": 9.440, + "args": { + "External id": 26939,"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": 2338707, "tid": 2338707, + "ts": 6197196716312.238, "dur": 4.066, + "args": { + "External id": 26940,"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": 2338707, "tid": 2338707, + "ts": 6197196716425.197, "dur": 209.904, + "args": { + "External id": 26941,"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": 2338707, "tid": 2338707, + "ts": 6197196716430.220, "dur": 4.433, + "args": { + "External id": 26942,"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": 2338707, "tid": 2338707, + "ts": 6197196716436.301, "dur": 198.386, + "args": { + "External id": 26943,"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": 2338707, "tid": 2338707, + "ts": 6197196716437.979, "dur": 0.400, + "args": { + "External id": 26944,"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": 2338707, "tid": 2338707, + "ts": 6197196716439.856, "dur": 25.729, + "args": { + "External id": 26945,"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": 2338707, "tid": 2338707, + "ts": 6197196716467.512, "dur": 5.521, + "args": { + "External id": 26946,"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": 2338707, "tid": 2338707, + "ts": 6197196716472.042, "dur": 0.767, + "args": { + "External id": 26947,"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": 2338707, "tid": 2338707, + "ts": 6197196716474.173, "dur": 26.451, + "args": { + "External id": 26948,"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": 2338707, "tid": 2338707, + "ts": 6197196716478.271, "dur": 1.018, + "args": { + "External id": 26949,"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": 2338707, "tid": 2338707, + "ts": 6197196716480.625, "dur": 19.575, + "args": { + "External id": 26950,"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": 2338707, "tid": 2338707, + "ts": 6197196716484.088, "dur": 3.378, + "args": { + "External id": 26951,"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": 2338707, "tid": 2338707, + "ts": 6197196716502.195, "dur": 24.038, + "args": { + "External id": 26952,"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": 2338707, "tid": 2338707, + "ts": 6197196716528.092, "dur": 17.282, + "args": { + "External id": 26953,"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": 2338707, "tid": 2338707, + "ts": 6197196716548.427, "dur": 15.306, + "args": { + "External id": 26954,"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": 2338707, "tid": 2338707, + "ts": 6197196716565.261, "dur": 13.858, + "args": { + "External id": 26955,"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": 2338707, "tid": 2338707, + "ts": 6197196716581.146, "dur": 24.928, + "args": { + "External id": 26956,"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": 2338707, "tid": 2338707, + "ts": 6197196716584.365, "dur": 1.955, + "args": { + "External id": 26957,"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": 2338707, "tid": 2338707, + "ts": 6197196716590.630, "dur": 0.527, + "args": { + "External id": 26958,"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": 2338707, "tid": 2338707, + "ts": 6197196716608.025, "dur": 12.602, + "args": { + "External id": 26959,"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": 2338707, "tid": 2338707, + "ts": 6197196716621.885, "dur": 11.436, + "args": { + "External id": 26960,"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": 2338707, "tid": 2338707, + "ts": 6197196716642.886, "dur": 1.675, + "args": { + "External id": 26961,"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": 2338707, "tid": 2338707, + "ts": 6197196716654.894, "dur": 5.101, + "args": { + "External id": 26962,"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": 2338707, "tid": 2338707, + "ts": 6197196716658.326, "dur": 0.675, + "args": { + "External id": 26963,"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": 2338707, "tid": 2338707, + "ts": 6197196716763.504, "dur": 72.751, + "args": { + "External id": 26964,"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": 2338707, "tid": 2338707, + "ts": 6197196716843.577, "dur": 9.013, + "args": { + "External id": 26965,"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": 2338707, "tid": 2338707, + "ts": 6197196716849.940, "dur": 1.000, + "args": { + "External id": 26966,"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": 2338707, "tid": 2338707, + "ts": 6197196716854.559, "dur": 32.826, + "args": { + "External id": 26967,"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": 2338707, "tid": 2338707, + "ts": 6197196716894.021, "dur": 6.328, + "args": { + "External id": 26968,"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": 2338707, "tid": 2338707, + "ts": 6197196716895.873, "dur": 3.609, + "args": { + "External id": 26969,"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": 2338707, "tid": 2338707, + "ts": 6197196716898.060, "dur": 1.249, + "args": { + "External id": 26970,"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": 2338707, "tid": 2338707, + "ts": 6197196716903.734, "dur": 49.085, + "args": { + "External id": 26971,"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": 2338707, "tid": 2338707, + "ts": 6197196716905.035, "dur": 47.048, + "args": { + "External id": 26972,"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": 2338707, "tid": 2338707, + "ts": 6197196716957.045, "dur": 18.654, + "args": { + "External id": 26973,"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": 2338707, "tid": 2338707, + "ts": 6197196716983.882, "dur": 30.627, + "args": { + "External id": 26974,"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": 2338707, "tid": 2338707, + "ts": 6197196716986.832, "dur": 27.208, + "args": { + "External id": 26975,"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": 2338707, "tid": 2338707, + "ts": 6197196716992.597, "dur": 2.959, + "args": { + "External id": 26976,"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": 2338707, "tid": 2338707, + "ts": 6197196717021.103, "dur": 30.608, + "args": { + "External id": 26977,"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": 2338707, "tid": 2338707, + "ts": 6197196717023.663, "dur": 27.739, + "args": { + "External id": 26978,"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": 2338707, "tid": 2338707, + "ts": 6197196717029.334, "dur": 3.757, + "args": { + "External id": 26979,"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": 2338707, "tid": 2338707, + "ts": 6197196717034.792, "dur": 16.007, + "args": { + "External id": 26980,"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": 2338707, "tid": 2338707, + "ts": 6197196717109.963, "dur": 8.722, + "args": { + "External id": 26981,"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": 2338707, "tid": 2338707, + "ts": 6197196717114.546, "dur": 3.704, + "args": { + "External id": 26982,"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": 2338707, "tid": 2338707, + "ts": 6197196717120.507, "dur": 1.226, + "args": { + "External id": 26983,"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": 2338707, "tid": 2338707, + "ts": 6197196717120.882, "dur": 0.762, + "args": { + "External id": 26984,"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": 2338707, "tid": 2338707, + "ts": 6197196717171.741, "dur": 29.669, + "args": { + "External id": 26985,"Sequence number": 479990, "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": 2338707, "tid": 2338707, + "ts": 6197196717203.572, "dur": 15.292, + "args": { + "External id": 26986,"Sequence number": 479991, "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": 2338707, "tid": 2338707, "ts": 6197196717203.572, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward", "pid": 2338707, "tid": 2338707, + "ts": 6197196717352.684, "dur": 49.179, + "args": { + "External id": 26987,"Record function id": 0, "Ev Idx": 16303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::div", "pid": 2338707, "tid": 2338707, + "ts": 6197196717522.550, "dur": 38.436, + "args": { + "External id": 26988,"Sequence number": 479992, "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": 2338707, "tid": 2338707, "ts": 6197196717522.550, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ones_like", "pid": 2338707, "tid": 2338707, + "ts": 6197196717653.249, "dur": 43.231, + "args": { + "External id": 26989,"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": 2338707, "tid": 2338707, + "ts": 6197196717665.120, "dur": 10.671, + "args": { + "External id": 26990,"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": 2338707, "tid": 2338707, + "ts": 6197196717670.245, "dur": 4.729, + "args": { + "External id": 26991,"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": 2338707, "tid": 2338707, + "ts": 6197196717677.880, "dur": 18.280, + "args": { + "External id": 26992,"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": 2338707, "tid": 2338707, + "ts": 6197198866039.956, "dur": 128.751, + "args": { + "External id": 26993,"Sequence number": 479993, "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": 2338707, "tid": 2338707, + "ts": 6197198866188.150, "dur": 25.441, + "args": { + "External id": 26994,"Sequence number": 479994, "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": 2338707, "tid": 2338707, + "ts": 6197198866263.328, "dur": 2983.385, + "args": { + "External id": 26995,"Record function id": 0, "Ev Idx": 16311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6197198867959.484, "dur": 6.994, + "args": { + "External id": 26996,"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": 2338707, "tid": 2338707, + "ts": 6197198867981.331, "dur": 8.958, + "args": { + "External id": 26997,"Sequence number": 479995, "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": 2338707, "tid": 2338707, + "ts": 6197198868577.763, "dur": 6.414, + "args": { + "External id": 26998,"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": 2338707, "tid": 2338707, + "ts": 6197198868591.848, "dur": 3.412, + "args": { + "External id": 26999,"Sequence number": 479995, "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": 2338707, "tid": 2338707, + "ts": 6197198869085.870, "dur": 5.136, + "args": { + "External id": 27000,"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": 2338707, "tid": 2338707, + "ts": 6197198869100.977, "dur": 2.513, + "args": { + "External id": 27001,"Sequence number": 479995, "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": 2338707, "tid": 2338707, + "ts": 6197198869589.421, "dur": 15.930, + "args": { + "External id": 27002,"Sequence number": 479995, "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": 2338707, "tid": 2338707, + "ts": 6197198869597.469, "dur": 3.310, + "args": { + "External id": 27003,"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": 2338707, "tid": 2338707, + "ts": 6197198869607.253, "dur": 6.157, + "args": { + "External id": 27004,"Sequence number": 479995, "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": 2338707, "tid": 2338707, + "ts": 6197198869610.485, "dur": 1.736, + "args": { + "External id": 27005,"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": 2338707, "tid": 2338707, + "ts": 6197198869649.181, "dur": 14559.000, + "args": { + "External id": 27006,"Sequence number": 479995, "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": 2338707, "tid": 2338707, + "ts": 6197198869657.544, "dur": 14549.748, + "args": { + "External id": 27007,"Sequence number": 479995, "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": 2338707, "tid": 2338707, + "ts": 6197198869664.496, "dur": 11.579, + "args": { + "External id": 27008,"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": 2338707, "tid": 2338707, + "ts": 6197198869678.496, "dur": 14526.959, + "args": { + "External id": 27009,"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": 2338707, "tid": 2338707, + "ts": 6197198869689.977, "dur": 0.552, + "args": { + "External id": 27010,"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": 2338707, "tid": 2338707, + "ts": 6197198869694.425, "dur": 29.230, + "args": { + "External id": 27011,"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": 2338707, "tid": 2338707, + "ts": 6197198869698.006, "dur": 25.420, + "args": { + "External id": 27012,"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": 2338707, "tid": 2338707, + "ts": 6197198869721.564, "dur": 1.270, + "args": { + "External id": 27013,"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": 2338707, "tid": 2338707, + "ts": 6197198869726.198, "dur": 133.620, + "args": { + "External id": 27014,"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": 2338707, "tid": 2338707, + "ts": 6197198869728.052, "dur": 131.420, + "args": { + "External id": 27015,"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": 2338707, "tid": 2338707, + "ts": 6197198869730.274, "dur": 9.846, + "args": { + "External id": 27016,"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": 2338707, "tid": 2338707, + "ts": 6197198869733.655, "dur": 5.861, + "args": { + "External id": 27017,"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": 2338707, "tid": 2338707, + "ts": 6197198869741.417, "dur": 117.564, + "args": { + "External id": 27018,"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": 2338707, "tid": 2338707, + "ts": 6197198869862.088, "dur": 14337.393, + "args": { + "External id": 27019,"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": 2338707, "tid": 2338707, + "ts": 6197198884233.134, "dur": 374.143, + "args": { + "External id": 27020,"Sequence number": 479995, "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": 2338707, "tid": 2338707, + "ts": 6197198884235.191, "dur": 371.657, + "args": { + "External id": 27021,"Sequence number": 479995, "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": 2338707, "tid": 2338707, + "ts": 6197198884243.115, "dur": 12.584, + "args": { + "External id": 27022,"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": 2338707, "tid": 2338707, + "ts": 6197198884257.515, "dur": 348.049, + "args": { + "External id": 27023,"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": 2338707, "tid": 2338707, + "ts": 6197198884631.353, "dur": 56.125, + "args": { + "External id": 27024,"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": 2338707, "tid": 2338707, + "ts": 6197198884636.497, "dur": 6.494, + "args": { + "External id": 27025,"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": 2338707, "tid": 2338707, + "ts": 6197198884645.959, "dur": 41.071, + "args": { + "External id": 27026,"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": 2338707, "tid": 2338707, + "ts": 6197198884650.884, "dur": 7.274, + "args": { + "External id": 27027,"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": 2338707, "tid": 2338707, + "ts": 6197198884720.425, "dur": 79.547, + "args": { + "External id": 27028,"Sequence number": 479995, "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": 2338707, "tid": 2338707, + "ts": 6197198884725.976, "dur": 6.222, + "args": { + "External id": 27029,"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": 2338707, "tid": 2338707, + "ts": 6197198884729.400, "dur": 2.124, + "args": { + "External id": 27030,"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": 2338707, "tid": 2338707, + "ts": 6197198884734.114, "dur": 4.788, + "args": { + "External id": 27031,"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": 2338707, "tid": 2338707, + "ts": 6197198884740.784, "dur": 2.274, + "args": { + "External id": 27032,"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": 2338707, "tid": 2338707, + "ts": 6197198884748.883, "dur": 7.833, + "args": { + "External id": 27033,"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": 2338707, "tid": 2338707, + "ts": 6197198884755.648, "dur": 0.893, + "args": { + "External id": 27034,"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": 2338707, "tid": 2338707, + "ts": 6197198884757.872, "dur": 3.711, + "args": { + "External id": 27035,"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": 2338707, "tid": 2338707, + "ts": 6197198884760.225, "dur": 1.262, + "args": { + "External id": 27036,"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": 2338707, "tid": 2338707, + "ts": 6197198884763.973, "dur": 5.297, + "args": { + "External id": 27037,"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": 2338707, "tid": 2338707, + "ts": 6197198884765.609, "dur": 3.492, + "args": { + "External id": 27038,"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": 2338707, "tid": 2338707, + "ts": 6197198884767.845, "dur": 1.141, + "args": { + "External id": 27039,"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": 2338707, "tid": 2338707, + "ts": 6197198884770.338, "dur": 28.834, + "args": { + "External id": 27040,"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": 2338707, "tid": 2338707, + "ts": 6197198884812.581, "dur": 34.291, + "args": { + "External id": 27041,"Sequence number": 479995, "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": 2338707, "tid": 2338707, + "ts": 6197198884814.269, "dur": 32.396, + "args": { + "External id": 27042,"Sequence number": 479995, "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": 2338707, "tid": 2338707, + "ts": 6197198884820.621, "dur": 4.118, + "args": { + "External id": 27043,"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": 2338707, "tid": 2338707, + "ts": 6197198884825.846, "dur": 20.308, + "args": { + "External id": 27044,"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": 2338707, "tid": 2338707, + "ts": 6197198884997.212, "dur": 236.196, + "args": { + "External id": 27045,"Record function id": 0, "Ev Idx": 16361 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::inputs_to_device", "pid": 2338707, "tid": 2338707, + "ts": 6197198885142.892, "dur": 76.757, + "args": { + "External id": 27046,"Record function id": 0, "Ev Idx": 16362 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6197198885243.159, "dur": 57.297, + "args": { + "External id": 27047,"Record function id": 0, "Ev Idx": 16363 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward", "pid": 2338707, "tid": 2338707, + "ts": 6197198885310.637, "dur": 13858.037, + "args": { + "External id": 27048,"Record function id": 0, "Ev Idx": 16364 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather", "pid": 2338707, "tid": 2338707, + "ts": 6197198885319.877, "dur": 2003.901, + "args": { + "External id": 27049,"Record function id": 0, "Ev Idx": 16365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6197198885484.876, "dur": 15.839, + "args": { + "External id": 27050,"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": 2338707, "tid": 2338707, + "ts": 6197198885522.301, "dur": 147.662, + "args": { + "External id": 27051,"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": 2338707, "tid": 2338707, + "ts": 6197198885529.233, "dur": 2.146, + "args": { + "External id": 27052,"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": 2338707, "tid": 2338707, + "ts": 6197198885536.122, "dur": 0.547, + "args": { + "External id": 27053,"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": 2338707, "tid": 2338707, + "ts": 6197198885538.800, "dur": 0.575, + "args": { + "External id": 27054,"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": 2338707, "tid": 2338707, + "ts": 6197198885541.191, "dur": 2.321, + "args": { + "External id": 27055,"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": 2338707, "tid": 2338707, + "ts": 6197198885545.274, "dur": 0.774, + "args": { + "External id": 27056,"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": 2338707, "tid": 2338707, + "ts": 6197198885547.846, "dur": 0.583, + "args": { + "External id": 27057,"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": 2338707, "tid": 2338707, + "ts": 6197198885552.719, "dur": 0.417, + "args": { + "External id": 27058,"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": 2338707, "tid": 2338707, + "ts": 6197198885555.063, "dur": 3.022, + "args": { + "External id": 27059,"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": 2338707, "tid": 2338707, + "ts": 6197198885559.997, "dur": 0.523, + "args": { + "External id": 27060,"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": 2338707, "tid": 2338707, + "ts": 6197198885564.538, "dur": 0.764, + "args": { + "External id": 27061,"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": 2338707, "tid": 2338707, + "ts": 6197198885567.171, "dur": 0.575, + "args": { + "External id": 27062,"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": 2338707, "tid": 2338707, + "ts": 6197198885569.343, "dur": 2.401, + "args": { + "External id": 27063,"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": 2338707, "tid": 2338707, + "ts": 6197198885573.008, "dur": 0.662, + "args": { + "External id": 27064,"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": 2338707, "tid": 2338707, + "ts": 6197198885575.491, "dur": 0.508, + "args": { + "External id": 27065,"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": 2338707, "tid": 2338707, + "ts": 6197198885580.614, "dur": 0.315, + "args": { + "External id": 27066,"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": 2338707, "tid": 2338707, + "ts": 6197198885582.716, "dur": 2.486, + "args": { + "External id": 27067,"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": 2338707, "tid": 2338707, + "ts": 6197198885587.556, "dur": 0.375, + "args": { + "External id": 27068,"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": 2338707, "tid": 2338707, + "ts": 6197198885591.384, "dur": 0.351, + "args": { + "External id": 27069,"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": 2338707, "tid": 2338707, + "ts": 6197198885593.589, "dur": 0.287, + "args": { + "External id": 27070,"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": 2338707, "tid": 2338707, + "ts": 6197198885595.436, "dur": 2.533, + "args": { + "External id": 27071,"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": 2338707, "tid": 2338707, + "ts": 6197198885599.463, "dur": 0.436, + "args": { + "External id": 27072,"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": 2338707, "tid": 2338707, + "ts": 6197198885601.650, "dur": 0.390, + "args": { + "External id": 27073,"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": 2338707, "tid": 2338707, + "ts": 6197198885606.078, "dur": 0.287, + "args": { + "External id": 27074,"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": 2338707, "tid": 2338707, + "ts": 6197198885607.643, "dur": 3.485, + "args": { + "External id": 27075,"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": 2338707, "tid": 2338707, + "ts": 6197198885612.796, "dur": 0.349, + "args": { + "External id": 27076,"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": 2338707, "tid": 2338707, + "ts": 6197198885616.136, "dur": 0.423, + "args": { + "External id": 27077,"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": 2338707, "tid": 2338707, + "ts": 6197198885617.705, "dur": 0.411, + "args": { + "External id": 27078,"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": 2338707, "tid": 2338707, + "ts": 6197198885619.282, "dur": 2.370, + "args": { + "External id": 27079,"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": 2338707, "tid": 2338707, + "ts": 6197198885622.774, "dur": 0.268, + "args": { + "External id": 27080,"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": 2338707, "tid": 2338707, + "ts": 6197198885624.811, "dur": 0.465, + "args": { + "External id": 27081,"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": 2338707, "tid": 2338707, + "ts": 6197198885629.442, "dur": 0.280, + "args": { + "External id": 27082,"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": 2338707, "tid": 2338707, + "ts": 6197198885631.332, "dur": 2.636, + "args": { + "External id": 27083,"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": 2338707, "tid": 2338707, + "ts": 6197198885635.273, "dur": 0.383, + "args": { + "External id": 27084,"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": 2338707, "tid": 2338707, + "ts": 6197198885638.848, "dur": 0.423, + "args": { + "External id": 27085,"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": 2338707, "tid": 2338707, + "ts": 6197198885641.443, "dur": 0.389, + "args": { + "External id": 27086,"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": 2338707, "tid": 2338707, + "ts": 6197198885642.929, "dur": 2.034, + "args": { + "External id": 27087,"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": 2338707, "tid": 2338707, + "ts": 6197198885646.562, "dur": 0.352, + "args": { + "External id": 27088,"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": 2338707, "tid": 2338707, + "ts": 6197198885648.231, "dur": 0.372, + "args": { + "External id": 27089,"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": 2338707, "tid": 2338707, + "ts": 6197198885652.373, "dur": 0.370, + "args": { + "External id": 27090,"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": 2338707, "tid": 2338707, + "ts": 6197198885733.151, "dur": 165.664, + "args": { + "External id": 27091,"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": 2338707, "tid": 2338707, + "ts": 6197198886006.612, "dur": 483.739, + "args": { + "External id": 27092,"Record function id": 0, "Concrete Inputs": ["", "", "141824512", "8", "1", "15", ""], "Input type": ["TensorList", "", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], []], "Ev Idx": 16408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6197198886029.041, "dur": 10.504, + "args": { + "External id": 27093,"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": 2338707, "tid": 2338707, + "ts": 6197198886047.297, "dur": 74.562, + "args": { + "External id": 27094,"Record function id": 0, "Concrete Inputs": ["", "0", "141824512", "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": 2338707, "tid": 2338707, + "ts": 6197198886109.100, "dur": 12.211, + "args": { + "External id": 27095,"Record function id": 0, "Concrete Inputs": ["", "0", "141824512", "283649024", "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": 2338707, "tid": 2338707, + "ts": 6197198886115.057, "dur": 1.121, + "args": { + "External id": 27096,"Record function id": 0, "Concrete Inputs": ["", "[141824512]", "[1]", "141824512"], "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": 2338707, "tid": 2338707, + "ts": 6197198886134.318, "dur": 146.890, + "args": { + "External id": 27097,"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": 2338707, "tid": 2338707, + "ts": 6197198886137.021, "dur": 0.464, + "args": { + "External id": 27098,"Record function id": 0, "Concrete Inputs": ["", "[16384000]", "[1]", "141824512"], "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": 2338707, "tid": 2338707, + "ts": 6197198886139.133, "dur": 2.217, + "args": { + "External id": 27099,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "158208512"], "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": 2338707, "tid": 2338707, + "ts": 6197198886143.159, "dur": 0.516, + "args": { + "External id": 27100,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "158209024"], "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": 2338707, "tid": 2338707, + "ts": 6197198886145.448, "dur": 0.582, + "args": { + "External id": 27101,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "160306176"], "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": 2338707, "tid": 2338707, + "ts": 6197198886149.243, "dur": 0.443, + "args": { + "External id": 27102,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "160830464"], "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": 2338707, "tid": 2338707, + "ts": 6197198886151.577, "dur": 0.669, + "args": { + "External id": 27103,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "161354752"], "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": 2338707, "tid": 2338707, + "ts": 6197198886154.511, "dur": 2.266, + "args": { + "External id": 27104,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "163451904"], "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": 2338707, "tid": 2338707, + "ts": 6197198886160.128, "dur": 0.517, + "args": { + "External id": 27105,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "163452416"], "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": 2338707, "tid": 2338707, + "ts": 6197198886161.996, "dur": 0.407, + "args": { + "External id": 27106,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "170792448"], "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": 2338707, "tid": 2338707, + "ts": 6197198886164.311, "dur": 2.632, + "args": { + "External id": 27107,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "178132480"], "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": 2338707, "tid": 2338707, + "ts": 6197198886168.133, "dur": 0.315, + "args": { + "External id": 27108,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "185472512"], "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": 2338707, "tid": 2338707, + "ts": 6197198886170.099, "dur": 0.255, + "args": { + "External id": 27109,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "185473024"], "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": 2338707, "tid": 2338707, + "ts": 6197198886173.419, "dur": 0.541, + "args": { + "External id": 27110,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "187570176"], "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": 2338707, "tid": 2338707, + "ts": 6197198886175.651, "dur": 0.428, + "args": { + "External id": 27111,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "188094464"], "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": 2338707, "tid": 2338707, + "ts": 6197198886177.337, "dur": 2.945, + "args": { + "External id": 27112,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "188618752"], "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": 2338707, "tid": 2338707, + "ts": 6197198886184.215, "dur": 0.399, + "args": { + "External id": 27113,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "190715904"], "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": 2338707, "tid": 2338707, + "ts": 6197198886186.213, "dur": 0.247, + "args": { + "External id": 27114,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "190716416"], "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": 2338707, "tid": 2338707, + "ts": 6197198886187.984, "dur": 2.138, + "args": { + "External id": 27115,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "198056448"], "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": 2338707, "tid": 2338707, + "ts": 6197198886191.700, "dur": 0.377, + "args": { + "External id": 27116,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "205396480"], "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": 2338707, "tid": 2338707, + "ts": 6197198886193.729, "dur": 0.334, + "args": { + "External id": 27117,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "212736512"], "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": 2338707, "tid": 2338707, + "ts": 6197198886197.600, "dur": 0.322, + "args": { + "External id": 27118,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "212737024"], "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": 2338707, "tid": 2338707, + "ts": 6197198886199.482, "dur": 0.399, + "args": { + "External id": 27119,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "214834176"], "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": 2338707, "tid": 2338707, + "ts": 6197198886201.507, "dur": 2.450, + "args": { + "External id": 27120,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "215358464"], "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": 2338707, "tid": 2338707, + "ts": 6197198886206.803, "dur": 0.352, + "args": { + "External id": 27121,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "215882752"], "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": 2338707, "tid": 2338707, + "ts": 6197198886208.779, "dur": 0.314, + "args": { + "External id": 27122,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "217979904"], "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": 2338707, "tid": 2338707, + "ts": 6197198886210.522, "dur": 1.540, + "args": { + "External id": 27123,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "217980416"], "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": 2338707, "tid": 2338707, + "ts": 6197198886213.751, "dur": 0.464, + "args": { + "External id": 27124,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "225320448"], "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": 2338707, "tid": 2338707, + "ts": 6197198886215.832, "dur": 0.815, + "args": { + "External id": 27125,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "232660480"], "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": 2338707, "tid": 2338707, + "ts": 6197198886220.026, "dur": 0.321, + "args": { + "External id": 27126,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "240000512"], "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": 2338707, "tid": 2338707, + "ts": 6197198886222.253, "dur": 0.475, + "args": { + "External id": 27127,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "240001024"], "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": 2338707, "tid": 2338707, + "ts": 6197198886224.202, "dur": 2.636, + "args": { + "External id": 27128,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "242098176"], "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": 2338707, "tid": 2338707, + "ts": 6197198886230.513, "dur": 0.295, + "args": { + "External id": 27129,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "242622464"], "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": 2338707, "tid": 2338707, + "ts": 6197198886232.347, "dur": 0.608, + "args": { + "External id": 27130,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "243146752"], "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": 2338707, "tid": 2338707, + "ts": 6197198886234.242, "dur": 1.921, + "args": { + "External id": 27131,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "245243904"], "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": 2338707, "tid": 2338707, + "ts": 6197198886237.773, "dur": 0.714, + "args": { + "External id": 27132,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "245244416"], "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": 2338707, "tid": 2338707, + "ts": 6197198886240.091, "dur": 0.483, + "args": { + "External id": 27133,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "252584448"], "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": 2338707, "tid": 2338707, + "ts": 6197198886244.689, "dur": 0.392, + "args": { + "External id": 27134,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "259924480"], "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": 2338707, "tid": 2338707, + "ts": 6197198886246.403, "dur": 0.671, + "args": { + "External id": 27135,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "267264512"], "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": 2338707, "tid": 2338707, + "ts": 6197198886249.019, "dur": 2.660, + "args": { + "External id": 27136,"Record function id": 0, "Concrete Inputs": ["", "[16384000]", "[1]", "267265024"], "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": 2338707, "tid": 2338707, + "ts": 6197198886341.500, "dur": 128.087, + "args": { + "External id": 33281,"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": 2338707, "tid": 2338707, + "ts": 6197198886571.088, "dur": 588.385, + "args": { + "External id": 33282,"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": 2338707, "tid": 2338707, + "ts": 6197198886612.018, "dur": 539.965, + "args": { + "External id": 33283,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2338707, + "ts": 6197198886627.549, "dur": 513.580, + "args": { + "External id": 33284,"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": 2338707, "tid": 2338707, + "ts": 6197198887201.296, "dur": 3.292, + "args": { + "External id": 33285,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out", "pid": 2338707, "tid": 2338707, + "ts": 6197198887344.479, "dur": 11505.224, + "args": { + "External id": 33286,"Record function id": 0, "Ev Idx": 16458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6197198887625.338, "dur": 8.520, + "args": { + "External id": 33287,"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": 2338707, "tid": 2338707, + "ts": 6197198887638.421, "dur": 1.668, + "args": { + "External id": 33288,"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": 2338707, "tid": 2338707, + "ts": 6197198887642.172, "dur": 1.594, + "args": { + "External id": 33289,"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": 2338707, "tid": 2338707, + "ts": 6197198887646.435, "dur": 1.247, + "args": { + "External id": 33290,"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": 2338707, "tid": 2338707, + "ts": 6197198887649.313, "dur": 1.014, + "args": { + "External id": 33291,"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": 2338707, "tid": 2338707, + "ts": 6197198887651.766, "dur": 1.402, + "args": { + "External id": 33292,"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": 2338707, "tid": 2338707, + "ts": 6197198887658.294, "dur": 1.274, + "args": { + "External id": 33293,"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": 2338707, "tid": 2338707, + "ts": 6197198887661.279, "dur": 6.282, + "args": { + "External id": 33294,"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": 2338707, "tid": 2338707, + "ts": 6197198887669.518, "dur": 1.324, + "args": { + "External id": 33295,"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": 2338707, "tid": 2338707, + "ts": 6197198887672.360, "dur": 1.123, + "args": { + "External id": 33296,"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": 2338707, "tid": 2338707, + "ts": 6197198887678.138, "dur": 1.030, + "args": { + "External id": 33297,"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": 2338707, "tid": 2338707, + "ts": 6197198887680.928, "dur": 0.961, + "args": { + "External id": 33298,"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": 2338707, "tid": 2338707, + "ts": 6197198887683.937, "dur": 0.807, + "args": { + "External id": 33299,"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": 2338707, "tid": 2338707, + "ts": 6197198887686.247, "dur": 0.892, + "args": { + "External id": 33300,"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": 2338707, "tid": 2338707, + "ts": 6197198887691.355, "dur": 0.996, + "args": { + "External id": 33301,"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": 2338707, "tid": 2338707, + "ts": 6197198887694.104, "dur": 37.124, + "args": { + "External id": 33302,"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": 2338707, "tid": 2338707, + "ts": 6197198887736.075, "dur": 1.467, + "args": { + "External id": 33303,"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": 2338707, "tid": 2338707, + "ts": 6197198887739.035, "dur": 1.038, + "args": { + "External id": 33304,"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": 2338707, "tid": 2338707, + "ts": 6197198887747.097, "dur": 0.956, + "args": { + "External id": 33305,"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": 2338707, "tid": 2338707, + "ts": 6197198887749.890, "dur": 1.094, + "args": { + "External id": 33306,"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": 2338707, "tid": 2338707, + "ts": 6197198887752.687, "dur": 0.793, + "args": { + "External id": 33307,"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": 2338707, "tid": 2338707, + "ts": 6197198887755.396, "dur": 1.057, + "args": { + "External id": 33308,"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": 2338707, "tid": 2338707, + "ts": 6197198887760.288, "dur": 1.429, + "args": { + "External id": 33309,"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": 2338707, "tid": 2338707, + "ts": 6197198887763.158, "dur": 4.821, + "args": { + "External id": 33310,"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": 2338707, "tid": 2338707, + "ts": 6197198887769.795, "dur": 0.908, + "args": { + "External id": 33311,"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": 2338707, "tid": 2338707, + "ts": 6197198887772.258, "dur": 0.980, + "args": { + "External id": 33312,"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": 2338707, "tid": 2338707, + "ts": 6197198887777.470, "dur": 1.197, + "args": { + "External id": 33313,"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": 2338707, "tid": 2338707, + "ts": 6197198887780.041, "dur": 0.903, + "args": { + "External id": 33314,"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": 2338707, "tid": 2338707, + "ts": 6197198887782.558, "dur": 0.996, + "args": { + "External id": 33315,"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": 2338707, "tid": 2338707, + "ts": 6197198887784.951, "dur": 1.060, + "args": { + "External id": 33316,"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": 2338707, "tid": 2338707, + "ts": 6197198887789.763, "dur": 1.100, + "args": { + "External id": 33317,"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": 2338707, "tid": 2338707, + "ts": 6197198887792.286, "dur": 5.289, + "args": { + "External id": 33318,"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": 2338707, "tid": 2338707, + "ts": 6197198887799.094, "dur": 0.920, + "args": { + "External id": 33319,"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": 2338707, "tid": 2338707, + "ts": 6197198887801.257, "dur": 1.279, + "args": { + "External id": 33320,"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": 2338707, "tid": 2338707, + "ts": 6197198887807.032, "dur": 0.981, + "args": { + "External id": 33321,"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": 2338707, "tid": 2338707, + "ts": 6197198887809.618, "dur": 1.311, + "args": { + "External id": 33322,"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": 2338707, "tid": 2338707, + "ts": 6197198887812.565, "dur": 1.058, + "args": { + "External id": 33323,"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": 2338707, "tid": 2338707, + "ts": 6197198887815.336, "dur": 1.147, + "args": { + "External id": 33324,"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": 2338707, "tid": 2338707, + "ts": 6197198887820.829, "dur": 1.014, + "args": { + "External id": 33325,"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": 2338707, "tid": 2338707, + "ts": 6197198887823.289, "dur": 4.400, + "args": { + "External id": 33326,"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": 2338707, "tid": 2338707, + "ts": 6197198887864.554, "dur": 10918.119, + "args": { + "External id": 33327,"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": 2338707, "tid": 2338707, + "ts": 6197198887896.027, "dur": 10874.359, + "args": { + "External id": 33328,"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": 2338707, "tid": 2338707, + "ts": 6197198887921.923, "dur": 19.339, + "args": { + "External id": 33329,"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": 2338707, "tid": 2338707, + "ts": 6197198887949.718, "dur": 10769.505, + "args": { + "External id": 33330,"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": 2338707, "tid": 2338707, + "ts": 6197198887952.563, "dur": 10765.380, + "args": { + "External id": 33331,"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": 2338707, "tid": 2338707, + "ts": 6197198887959.095, "dur": 7.353, + "args": { + "External id": 33332,"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": 2338707, "tid": 2338707, + "ts": 6197198887971.288, "dur": 10726.369, + "args": { + "External id": 33333,"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": 2338707, "tid": 2338707, + "ts": 6197198899282.893, "dur": 46.389, + "args": { + "External id": 33334,"Record function id": 0, "Ev Idx": 16506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 0/0", "pid": 2338707, "tid": 2338707, + "ts": 6197198899330.984, "dur": 266.157, + "args": { + "External id": 33335,"Record function id": 0, "Ev Idx": 16507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197198899389.618, "dur": 196.158, + "args": { + "External id": 33336,"Sequence number": 479995, "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": 2338707, "tid": 2338707, "ts": 6197198899389.618, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_embedding_0", "pid": 2338707, "tid": 2338707, + "ts": 6197198899476.524, "dur": 63.458, + "args": { + "External id": 33337,"kernel_hash": "coj4cw2xx67czwyji56kkta4pwcipuxvxsnrrkf7vsjjhsb6mejv", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/oj/coj4cw2xx67czwyji56kkta4pwcipuxvxsnrrkf7vsjjhsb6mejv.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": 2338707, "tid": 2338707, + "ts": 6197198899673.927, "dur": 89.968, + "args": { + "External id": 33338,"Record function id": 0, "Ev Idx": 16510 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.0)", "pid": 2338707, "tid": 2338707, + "ts": 6197198899778.666, "dur": 7731.250, + "args": { + "External id": 33339,"Record function id": 0, "Ev Idx": 16511 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.0)", "pid": 2338707, "tid": 2338707, + "ts": 6197198899791.198, "dur": 1048.669, + "args": { + "External id": 33340,"Record function id": 0, "Ev Idx": 16512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6197198899886.832, "dur": 13.288, + "args": { + "External id": 33341,"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": 2338707, "tid": 2338707, + "ts": 6197198899916.783, "dur": 46.574, + "args": { + "External id": 33342,"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": 2338707, "tid": 2338707, + "ts": 6197198899926.203, "dur": 3.060, + "args": { + "External id": 33343,"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": 2338707, "tid": 2338707, + "ts": 6197198899931.470, "dur": 0.604, + "args": { + "External id": 33344,"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": 2338707, "tid": 2338707, + "ts": 6197198899933.812, "dur": 2.509, + "args": { + "External id": 33345,"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": 2338707, "tid": 2338707, + "ts": 6197198899937.838, "dur": 3.153, + "args": { + "External id": 33346,"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": 2338707, "tid": 2338707, + "ts": 6197198899942.500, "dur": 0.409, + "args": { + "External id": 33347,"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": 2338707, "tid": 2338707, + "ts": 6197198899946.329, "dur": 0.396, + "args": { + "External id": 33348,"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": 2338707, "tid": 2338707, + "ts": 6197198899948.258, "dur": 0.538, + "args": { + "External id": 33349,"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": 2338707, "tid": 2338707, + "ts": 6197198899950.603, "dur": 0.544, + "args": { + "External id": 33350,"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": 2338707, "tid": 2338707, + "ts": 6197198899954.503, "dur": 0.620, + "args": { + "External id": 33351,"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": 2338707, "tid": 2338707, + "ts": 6197198899977.858, "dur": 61.966, + "args": { + "External id": 33352,"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": 2338707, "tid": 2338707, + "ts": 6197198900124.277, "dur": 161.292, + "args": { + "External id": 33353,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2338707, + "ts": 6197198900139.628, "dur": 7.839, + "args": { + "External id": 33354,"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": 2338707, "tid": 2338707, + "ts": 6197198900154.872, "dur": 13.220, + "args": { + "External id": 33355,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2338707, + "ts": 6197198900160.118, "dur": 7.465, + "args": { + "External id": 33356,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2338707, + "ts": 6197198900164.586, "dur": 0.963, + "args": { + "External id": 33357,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197198900176.145, "dur": 38.170, + "args": { + "External id": 33358,"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": 2338707, "tid": 2338707, + "ts": 6197198900178.836, "dur": 3.526, + "args": { + "External id": 33359,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197198900184.222, "dur": 0.683, + "args": { + "External id": 33360,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2338707, + "ts": 6197198900188.731, "dur": 0.668, + "args": { + "External id": 33361,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2338707, + "ts": 6197198900191.187, "dur": 0.632, + "args": { + "External id": 33362,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2338707, + "ts": 6197198900192.825, "dur": 2.502, + "args": { + "External id": 33363,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2338707, + "ts": 6197198900197.012, "dur": 0.481, + "args": { + "External id": 33364,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2338707, + "ts": 6197198900198.888, "dur": 0.602, + "args": { + "External id": 33365,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2338707, + "ts": 6197198900203.698, "dur": 0.443, + "args": { + "External id": 33366,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2338707, + "ts": 6197198900205.231, "dur": 3.617, + "args": { + "External id": 33367,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2338707, + "ts": 6197198900228.905, "dur": 45.487, + "args": { + "External id": 33368,"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": 2338707, "tid": 2338707, + "ts": 6197198900350.813, "dur": 345.745, + "args": { + "External id": 33369,"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": 2338707, "tid": 2338707, + "ts": 6197198900389.525, "dur": 301.548, + "args": { + "External id": 33370,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2338707, + "ts": 6197198900401.272, "dur": 283.195, + "args": { + "External id": 33371,"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": 2338707, "tid": 2338707, + "ts": 6197198900751.074, "dur": 3.574, + "args": { + "External id": 33372,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.0)", "pid": 2338707, "tid": 2338707, + "ts": 6197198900866.073, "dur": 6386.538, + "args": { + "External id": 33373,"Record function id": 0, "Ev Idx": 16545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6197198900994.284, "dur": 7.703, + "args": { + "External id": 33374,"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": 2338707, "tid": 2338707, + "ts": 6197198901006.314, "dur": 1.398, + "args": { + "External id": 33375,"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": 2338707, "tid": 2338707, + "ts": 6197198901009.534, "dur": 1.343, + "args": { + "External id": 33376,"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": 2338707, "tid": 2338707, + "ts": 6197198901012.896, "dur": 1.297, + "args": { + "External id": 33377,"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": 2338707, "tid": 2338707, + "ts": 6197198901015.538, "dur": 1.268, + "args": { + "External id": 33378,"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": 2338707, "tid": 2338707, + "ts": 6197198901020.669, "dur": 1.074, + "args": { + "External id": 33379,"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": 2338707, "tid": 2338707, + "ts": 6197198901023.916, "dur": 0.935, + "args": { + "External id": 33380,"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": 2338707, "tid": 2338707, + "ts": 6197198901026.308, "dur": 5.467, + "args": { + "External id": 33381,"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": 2338707, "tid": 2338707, + "ts": 6197198901033.585, "dur": 0.904, + "args": { + "External id": 33382,"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": 2338707, "tid": 2338707, + "ts": 6197198901038.906, "dur": 1.093, + "args": { + "External id": 33383,"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": 2338707, "tid": 2338707, + "ts": 6197198901125.469, "dur": 6081.641, + "args": { + "External id": 33384,"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": 2338707, "tid": 2338707, + "ts": 6197198901146.282, "dur": 6052.419, + "args": { + "External id": 33385,"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": 2338707, "tid": 2338707, + "ts": 6197198901165.218, "dur": 18.289, + "args": { + "External id": 33386,"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": 2338707, "tid": 2338707, + "ts": 6197198901190.351, "dur": 5963.735, + "args": { + "External id": 33387,"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": 2338707, "tid": 2338707, + "ts": 6197198901193.239, "dur": 5960.316, + "args": { + "External id": 33388,"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": 2338707, "tid": 2338707, + "ts": 6197198901202.286, "dur": 7.531, + "args": { + "External id": 33389,"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": 2338707, "tid": 2338707, + "ts": 6197198901211.958, "dur": 5938.003, + "args": { + "External id": 33390,"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": 2338707, "tid": 2338707, + "ts": 6197198907442.949, "dur": 37.805, + "args": { + "External id": 33391,"Sequence number": 479996, "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": 2338707, "tid": 2338707, "ts": 6197198907442.949, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6197198907466.032, "dur": 9.316, + "args": { + "External id": 33392,"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": 2338707, "tid": 2338707, + "ts": 6197198907470.154, "dur": 4.925, + "args": { + "External id": 33393,"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": 2338707, "tid": 2338707, + "ts": 6197198907561.720, "dur": 120.516, + "args": { + "External id": 33394,"Record function id": 0, "Ev Idx": 16566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6197198907683.676, "dur": 1458.789, + "args": { + "External id": 33395,"Record function id": 0, "Ev Idx": 16567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197198907753.281, "dur": 1370.293, + "args": { + "External id": 33396,"Sequence number": 479997, "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": 2338707, "tid": 2338707, "ts": 6197198907753.281, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6197198907844.726, "dur": 62.071, + "args": { + "External id": 33397,"kernel_hash": "cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/du/cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs.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": 2338707, "tid": 2338707, + "ts": 6197198907922.967, "dur": 125.871, + "args": { + "External id": 33398,"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": 2338707, "tid": 2338707, + "ts": 6197198908105.268, "dur": 54.290, + "args": { + "External id": 33399,"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": 2338707, "tid": 2338707, + "ts": 6197198908171.589, "dur": 35.715, + "args": { + "External id": 33400,"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": 2338707, "tid": 2338707, + "ts": 6197198908244.309, "dur": 35.760, + "args": { + "External id": 33401,"kernel_hash": "cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5", "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/jw/cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5.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": 2338707, "tid": 2338707, + "ts": 6197198908304.653, "dur": 23.396, + "args": { + "External id": 33402,"kernel_hash": "cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi", "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/xw/cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi.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": 2338707, "tid": 2338707, + "ts": 6197198908353.520, "dur": 175.024, + "args": { + "External id": 33403,"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": 2338707, "tid": 2338707, + "ts": 6197198908425.260, "dur": 19.181, + "args": { + "External id": 33404,"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": 2338707, "tid": 2338707, + "ts": 6197198908432.060, "dur": 11.657, + "args": { + "External id": 33405,"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": 2338707, "tid": 2338707, + "ts": 6197198908447.977, "dur": 5.177, + "args": { + "External id": 33406,"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": 2338707, "tid": 2338707, + "ts": 6197198908454.900, "dur": 1.732, + "args": { + "External id": 33407,"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": 2338707, "tid": 2338707, + "ts": 6197198908459.612, "dur": 4.608, + "args": { + "External id": 33408,"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": 2338707, "tid": 2338707, + "ts": 6197198908541.604, "dur": 60.356, + "args": { + "External id": 33409,"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": 2338707, "tid": 2338707, + "ts": 6197198908639.160, "dur": 38.486, + "args": { + "External id": 33410,"kernel_hash": "cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/dm/cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43.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": 2338707, "tid": 2338707, + "ts": 6197198908689.585, "dur": 79.999, + "args": { + "External id": 33411,"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": 2338707, "tid": 2338707, + "ts": 6197198908783.893, "dur": 42.266, + "args": { + "External id": 33412,"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": 2338707, "tid": 2338707, + "ts": 6197198908857.788, "dur": 35.448, + "args": { + "External id": 33413,"kernel_hash": "cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/b7/cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu.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": 2338707, "tid": 2338707, + "ts": 6197198908902.248, "dur": 43.279, + "args": { + "External id": 33414,"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": 2338707, "tid": 2338707, + "ts": 6197198908968.051, "dur": 23.329, + "args": { + "External id": 33415,"kernel_hash": "cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/gi/cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb.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": 2338707, "tid": 2338707, + "ts": 6197198909225.287, "dur": 110.582, + "args": { + "External id": 33416,"Record function id": 0, "Ev Idx": 16588 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6197198909425.249, "dur": 54.870, + "args": { + "External id": 33417,"Record function id": 0, "Ev Idx": 16589 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.1)", "pid": 2338707, "tid": 2338707, + "ts": 6197198909490.826, "dur": 27409.584, + "args": { + "External id": 33418,"Record function id": 0, "Ev Idx": 16590 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.1)", "pid": 2338707, "tid": 2338707, + "ts": 6197198909500.460, "dur": 1166.766, + "args": { + "External id": 33419,"Record function id": 0, "Ev Idx": 16591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6197198909606.785, "dur": 11.866, + "args": { + "External id": 33420,"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": 2338707, "tid": 2338707, + "ts": 6197198909634.543, "dur": 46.370, + "args": { + "External id": 33421,"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": 2338707, "tid": 2338707, + "ts": 6197198909641.576, "dur": 4.626, + "args": { + "External id": 33422,"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": 2338707, "tid": 2338707, + "ts": 6197198909649.486, "dur": 0.918, + "args": { + "External id": 33423,"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": 2338707, "tid": 2338707, + "ts": 6197198909651.830, "dur": 0.594, + "args": { + "External id": 33424,"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": 2338707, "tid": 2338707, + "ts": 6197198909656.876, "dur": 0.801, + "args": { + "External id": 33425,"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": 2338707, "tid": 2338707, + "ts": 6197198909658.941, "dur": 1.007, + "args": { + "External id": 33426,"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": 2338707, "tid": 2338707, + "ts": 6197198909661.314, "dur": 0.366, + "args": { + "External id": 33427,"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": 2338707, "tid": 2338707, + "ts": 6197198909664.951, "dur": 2.751, + "args": { + "External id": 33428,"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": 2338707, "tid": 2338707, + "ts": 6197198909669.406, "dur": 0.589, + "args": { + "External id": 33429,"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": 2338707, "tid": 2338707, + "ts": 6197198909671.591, "dur": 2.438, + "args": { + "External id": 33430,"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": 2338707, "tid": 2338707, + "ts": 6197198909721.658, "dur": 71.707, + "args": { + "External id": 33431,"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": 2338707, "tid": 2338707, + "ts": 6197198909838.532, "dur": 147.640, + "args": { + "External id": 33432,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2338707, + "ts": 6197198909852.626, "dur": 7.949, + "args": { + "External id": 33433,"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": 2338707, "tid": 2338707, + "ts": 6197198909867.034, "dur": 13.282, + "args": { + "External id": 33434,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2338707, + "ts": 6197198909872.505, "dur": 7.200, + "args": { + "External id": 33435,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2338707, + "ts": 6197198909876.836, "dur": 0.815, + "args": { + "External id": 33436,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197198909888.358, "dur": 33.782, + "args": { + "External id": 33437,"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": 2338707, "tid": 2338707, + "ts": 6197198909890.766, "dur": 0.693, + "args": { + "External id": 33438,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197198909893.631, "dur": 2.942, + "args": { + "External id": 33439,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2338707, + "ts": 6197198909898.010, "dur": 0.560, + "args": { + "External id": 33440,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2338707, + "ts": 6197198909900.604, "dur": 2.943, + "args": { + "External id": 33441,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2338707, + "ts": 6197198909907.604, "dur": 0.442, + "args": { + "External id": 33442,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2338707, + "ts": 6197198909909.719, "dur": 0.334, + "args": { + "External id": 33443,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2338707, + "ts": 6197198909911.366, "dur": 0.510, + "args": { + "External id": 33444,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2338707, + "ts": 6197198909915.434, "dur": 0.338, + "args": { + "External id": 33445,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2338707, + "ts": 6197198909916.985, "dur": 0.590, + "args": { + "External id": 33446,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2338707, + "ts": 6197198909939.249, "dur": 37.944, + "args": { + "External id": 33447,"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": 2338707, "tid": 2338707, + "ts": 6197198910050.035, "dur": 497.860, + "args": { + "External id": 33448,"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": 2338707, "tid": 2338707, + "ts": 6197198910129.522, "dur": 411.490, + "args": { + "External id": 33449,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2338707, + "ts": 6197198910143.371, "dur": 390.917, + "args": { + "External id": 33450,"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": 2338707, "tid": 2338707, + "ts": 6197198910577.835, "dur": 2.999, + "args": { + "External id": 33451,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.1)", "pid": 2338707, "tid": 2338707, + "ts": 6197198910693.116, "dur": 25948.093, + "args": { + "External id": 33452,"Record function id": 0, "Ev Idx": 16624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6197198910847.442, "dur": 8.091, + "args": { + "External id": 33453,"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": 2338707, "tid": 2338707, + "ts": 6197198910860.304, "dur": 1.461, + "args": { + "External id": 33454,"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": 2338707, "tid": 2338707, + "ts": 6197198910863.753, "dur": 4.245, + "args": { + "External id": 33455,"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": 2338707, "tid": 2338707, + "ts": 6197198910869.995, "dur": 1.036, + "args": { + "External id": 33456,"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": 2338707, "tid": 2338707, + "ts": 6197198910872.587, "dur": 1.078, + "args": { + "External id": 33457,"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": 2338707, "tid": 2338707, + "ts": 6197198910878.066, "dur": 1.079, + "args": { + "External id": 33458,"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": 2338707, "tid": 2338707, + "ts": 6197198910881.044, "dur": 1.073, + "args": { + "External id": 33459,"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": 2338707, "tid": 2338707, + "ts": 6197198910883.675, "dur": 2.408, + "args": { + "External id": 33460,"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": 2338707, "tid": 2338707, + "ts": 6197198910887.771, "dur": 0.981, + "args": { + "External id": 33461,"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": 2338707, "tid": 2338707, + "ts": 6197198910892.767, "dur": 1.012, + "args": { + "External id": 33462,"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": 2338707, "tid": 2338707, + "ts": 6197198910915.765, "dur": 25675.850, + "args": { + "External id": 33463,"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": 2338707, "tid": 2338707, + "ts": 6197198910935.182, "dur": 25647.084, + "args": { + "External id": 33464,"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": 2338707, "tid": 2338707, + "ts": 6197198910955.346, "dur": 19.486, + "args": { + "External id": 33465,"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": 2338707, "tid": 2338707, + "ts": 6197198910979.836, "dur": 25558.568, + "args": { + "External id": 33466,"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": 2338707, "tid": 2338707, + "ts": 6197198910983.020, "dur": 25554.559, + "args": { + "External id": 33467,"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": 2338707, "tid": 2338707, + "ts": 6197198910990.805, "dur": 6.967, + "args": { + "External id": 33468,"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": 2338707, "tid": 2338707, + "ts": 6197198910999.839, "dur": 25534.022, + "args": { + "External id": 33469,"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": 2338707, "tid": 2338707, + "ts": 6197198936829.594, "dur": 41.837, + "args": { + "External id": 33470,"Sequence number": 479998, "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": 2338707, "tid": 2338707, "ts": 6197198936829.594, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6197198936852.128, "dur": 13.401, + "args": { + "External id": 33471,"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": 2338707, "tid": 2338707, + "ts": 6197198936859.494, "dur": 5.603, + "args": { + "External id": 33472,"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": 2338707, "tid": 2338707, + "ts": 6197198936948.426, "dur": 94.755, + "args": { + "External id": 33473,"Record function id": 0, "Ev Idx": 16645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6197198937044.736, "dur": 1346.350, + "args": { + "External id": 33474,"Record function id": 0, "Ev Idx": 16646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197198937127.937, "dur": 1246.246, + "args": { + "External id": 33475,"Sequence number": 479999, "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": 2338707, "tid": 2338707, "ts": 6197198937127.937, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6197198937211.565, "dur": 60.221, + "args": { + "External id": 33476,"kernel_hash": "cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/du/cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs.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": 2338707, "tid": 2338707, + "ts": 6197198937286.261, "dur": 125.071, + "args": { + "External id": 33477,"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": 2338707, "tid": 2338707, + "ts": 6197198937426.950, "dur": 42.584, + "args": { + "External id": 33478,"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": 2338707, "tid": 2338707, + "ts": 6197198937477.980, "dur": 33.675, + "args": { + "External id": 33479,"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": 2338707, "tid": 2338707, + "ts": 6197198937543.321, "dur": 30.346, + "args": { + "External id": 33480,"kernel_hash": "cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5", "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/jw/cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5.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": 2338707, "tid": 2338707, + "ts": 6197198937593.306, "dur": 21.701, + "args": { + "External id": 33481,"kernel_hash": "cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi", "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/xw/cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi.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": 2338707, "tid": 2338707, + "ts": 6197198937642.627, "dur": 186.877, + "args": { + "External id": 33482,"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": 2338707, "tid": 2338707, + "ts": 6197198937722.445, "dur": 18.143, + "args": { + "External id": 33483,"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": 2338707, "tid": 2338707, + "ts": 6197198937728.890, "dur": 10.453, + "args": { + "External id": 33484,"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": 2338707, "tid": 2338707, + "ts": 6197198937743.989, "dur": 4.999, + "args": { + "External id": 33485,"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": 2338707, "tid": 2338707, + "ts": 6197198937750.820, "dur": 1.285, + "args": { + "External id": 33486,"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": 2338707, "tid": 2338707, + "ts": 6197198937756.796, "dur": 7.555, + "args": { + "External id": 33487,"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": 2338707, "tid": 2338707, + "ts": 6197198937843.026, "dur": 62.579, + "args": { + "External id": 33488,"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": 2338707, "tid": 2338707, + "ts": 6197198937943.096, "dur": 33.646, + "args": { + "External id": 33489,"kernel_hash": "cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/dm/cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43.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": 2338707, "tid": 2338707, + "ts": 6197198937987.624, "dur": 49.147, + "args": { + "External id": 33490,"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": 2338707, "tid": 2338707, + "ts": 6197198938044.772, "dur": 83.222, + "args": { + "External id": 33491,"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": 2338707, "tid": 2338707, + "ts": 6197198938163.522, "dur": 35.859, + "args": { + "External id": 33492,"kernel_hash": "cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/b7/cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu.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": 2338707, "tid": 2338707, + "ts": 6197198938206.170, "dur": 43.374, + "args": { + "External id": 33493,"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": 2338707, "tid": 2338707, + "ts": 6197198938270.022, "dur": 20.731, + "args": { + "External id": 33494,"kernel_hash": "cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/gi/cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb.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": 2338707, "tid": 2338707, + "ts": 6197198938472.175, "dur": 99.703, + "args": { + "External id": 33495,"Record function id": 0, "Ev Idx": 16667 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6197198938661.409, "dur": 77.178, + "args": { + "External id": 33496,"Record function id": 0, "Ev Idx": 16668 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.2)", "pid": 2338707, "tid": 2338707, + "ts": 6197198938751.490, "dur": 28368.086, + "args": { + "External id": 33497,"Record function id": 0, "Ev Idx": 16669 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.2)", "pid": 2338707, "tid": 2338707, + "ts": 6197198938761.476, "dur": 1132.999, + "args": { + "External id": 33498,"Record function id": 0, "Ev Idx": 16670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6197198938868.021, "dur": 10.962, + "args": { + "External id": 33499,"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": 2338707, "tid": 2338707, + "ts": 6197198938894.474, "dur": 45.327, + "args": { + "External id": 33500,"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": 2338707, "tid": 2338707, + "ts": 6197198938901.428, "dur": 2.928, + "args": { + "External id": 33501,"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": 2338707, "tid": 2338707, + "ts": 6197198938909.510, "dur": 0.520, + "args": { + "External id": 33502,"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": 2338707, "tid": 2338707, + "ts": 6197198938911.338, "dur": 0.723, + "args": { + "External id": 33503,"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": 2338707, "tid": 2338707, + "ts": 6197198938913.601, "dur": 0.910, + "args": { + "External id": 33504,"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": 2338707, "tid": 2338707, + "ts": 6197198938918.537, "dur": 0.653, + "args": { + "External id": 33505,"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": 2338707, "tid": 2338707, + "ts": 6197198938920.561, "dur": 0.800, + "args": { + "External id": 33506,"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": 2338707, "tid": 2338707, + "ts": 6197198938923.155, "dur": 4.926, + "args": { + "External id": 33507,"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": 2338707, "tid": 2338707, + "ts": 6197198938929.601, "dur": 0.546, + "args": { + "External id": 33508,"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": 2338707, "tid": 2338707, + "ts": 6197198938931.811, "dur": 0.578, + "args": { + "External id": 33509,"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": 2338707, "tid": 2338707, + "ts": 6197198938954.095, "dur": 63.546, + "args": { + "External id": 33510,"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": 2338707, "tid": 2338707, + "ts": 6197198939099.594, "dur": 161.929, + "args": { + "External id": 33511,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2338707, + "ts": 6197198939114.218, "dur": 6.338, + "args": { + "External id": 33512,"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": 2338707, "tid": 2338707, + "ts": 6197198939127.545, "dur": 13.945, + "args": { + "External id": 33513,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2338707, + "ts": 6197198939133.515, "dur": 7.496, + "args": { + "External id": 33514,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2338707, + "ts": 6197198939137.961, "dur": 1.037, + "args": { + "External id": 33515,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197198939150.602, "dur": 37.720, + "args": { + "External id": 33516,"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": 2338707, "tid": 2338707, + "ts": 6197198939153.390, "dur": 3.652, + "args": { + "External id": 33517,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197198939158.732, "dur": 0.564, + "args": { + "External id": 33518,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2338707, + "ts": 6197198939160.633, "dur": 0.701, + "args": { + "External id": 33519,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2338707, + "ts": 6197198939165.253, "dur": 2.812, + "args": { + "External id": 33520,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2338707, + "ts": 6197198939169.226, "dur": 0.720, + "args": { + "External id": 33521,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2338707, + "ts": 6197198939171.436, "dur": 0.694, + "args": { + "External id": 33522,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2338707, + "ts": 6197198939175.527, "dur": 0.323, + "args": { + "External id": 33523,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2338707, + "ts": 6197198939177.519, "dur": 0.773, + "args": { + "External id": 33524,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2338707, + "ts": 6197198939179.710, "dur": 2.559, + "args": { + "External id": 33525,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2338707, + "ts": 6197198939206.421, "dur": 45.632, + "args": { + "External id": 33526,"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": 2338707, "tid": 2338707, + "ts": 6197198939326.192, "dur": 450.596, + "args": { + "External id": 33527,"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": 2338707, "tid": 2338707, + "ts": 6197198939362.910, "dur": 407.338, + "args": { + "External id": 33528,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2338707, + "ts": 6197198939380.056, "dur": 383.269, + "args": { + "External id": 33529,"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": 2338707, "tid": 2338707, + "ts": 6197198939807.706, "dur": 2.914, + "args": { + "External id": 33530,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.2)", "pid": 2338707, "tid": 2338707, + "ts": 6197198939920.717, "dur": 26930.289, + "args": { + "External id": 33531,"Record function id": 0, "Ev Idx": 16703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6197198940046.400, "dur": 47.573, + "args": { + "External id": 33532,"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": 2338707, "tid": 2338707, + "ts": 6197198940101.532, "dur": 1.556, + "args": { + "External id": 33533,"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": 2338707, "tid": 2338707, + "ts": 6197198940105.220, "dur": 3.628, + "args": { + "External id": 33534,"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": 2338707, "tid": 2338707, + "ts": 6197198940110.984, "dur": 1.266, + "args": { + "External id": 33535,"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": 2338707, "tid": 2338707, + "ts": 6197198940113.964, "dur": 1.093, + "args": { + "External id": 33536,"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": 2338707, "tid": 2338707, + "ts": 6197198940116.467, "dur": 1.254, + "args": { + "External id": 33537,"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": 2338707, "tid": 2338707, + "ts": 6197198940122.179, "dur": 0.864, + "args": { + "External id": 33538,"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": 2338707, "tid": 2338707, + "ts": 6197198940124.818, "dur": 1.958, + "args": { + "External id": 33539,"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": 2338707, "tid": 2338707, + "ts": 6197198940128.369, "dur": 0.799, + "args": { + "External id": 33540,"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": 2338707, "tid": 2338707, + "ts": 6197198940130.795, "dur": 0.792, + "args": { + "External id": 33541,"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": 2338707, "tid": 2338707, + "ts": 6197198940156.627, "dur": 26642.525, + "args": { + "External id": 33542,"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": 2338707, "tid": 2338707, + "ts": 6197198940174.295, "dur": 26615.167, + "args": { + "External id": 33543,"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": 2338707, "tid": 2338707, + "ts": 6197198940196.177, "dur": 20.648, + "args": { + "External id": 33544,"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": 2338707, "tid": 2338707, + "ts": 6197198940221.024, "dur": 26528.555, + "args": { + "External id": 33545,"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": 2338707, "tid": 2338707, + "ts": 6197198940224.231, "dur": 26524.700, + "args": { + "External id": 33546,"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": 2338707, "tid": 2338707, + "ts": 6197198940230.984, "dur": 6.599, + "args": { + "External id": 33547,"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": 2338707, "tid": 2338707, + "ts": 6197198940239.682, "dur": 26505.574, + "args": { + "External id": 33548,"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": 2338707, "tid": 2338707, + "ts": 6197198967017.118, "dur": 68.775, + "args": { + "External id": 33549,"Sequence number": 480000, "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": 2338707, "tid": 2338707, "ts": 6197198967017.118, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6197198967040.521, "dur": 10.003, + "args": { + "External id": 33550,"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": 2338707, "tid": 2338707, + "ts": 6197198967044.747, "dur": 5.522, + "args": { + "External id": 33551,"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": 2338707, "tid": 2338707, + "ts": 6197198967170.619, "dur": 91.307, + "args": { + "External id": 33552,"Record function id": 0, "Ev Idx": 16724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6197198967263.667, "dur": 1308.315, + "args": { + "External id": 33553,"Record function id": 0, "Ev Idx": 16725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197198967313.993, "dur": 1242.278, + "args": { + "External id": 33554,"Sequence number": 480001, "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": 2338707, "tid": 2338707, "ts": 6197198967313.993, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6197198967393.936, "dur": 60.905, + "args": { + "External id": 33555,"kernel_hash": "cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/du/cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs.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": 2338707, "tid": 2338707, + "ts": 6197198967469.514, "dur": 121.083, + "args": { + "External id": 33556,"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": 2338707, "tid": 2338707, + "ts": 6197198967605.276, "dur": 41.902, + "args": { + "External id": 33557,"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": 2338707, "tid": 2338707, + "ts": 6197198967657.540, "dur": 34.001, + "args": { + "External id": 33558,"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": 2338707, "tid": 2338707, + "ts": 6197198967742.502, "dur": 31.566, + "args": { + "External id": 33559,"kernel_hash": "cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5", "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/jw/cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5.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": 2338707, "tid": 2338707, + "ts": 6197198967799.449, "dur": 20.395, + "args": { + "External id": 33560,"kernel_hash": "cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi", "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/xw/cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi.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": 2338707, "tid": 2338707, + "ts": 6197198967847.841, "dur": 159.237, + "args": { + "External id": 33561,"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": 2338707, "tid": 2338707, + "ts": 6197198967909.151, "dur": 13.312, + "args": { + "External id": 33562,"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": 2338707, "tid": 2338707, + "ts": 6197198967915.375, "dur": 6.173, + "args": { + "External id": 33563,"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": 2338707, "tid": 2338707, + "ts": 6197198967926.171, "dur": 4.883, + "args": { + "External id": 33564,"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": 2338707, "tid": 2338707, + "ts": 6197198967932.491, "dur": 1.188, + "args": { + "External id": 33565,"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": 2338707, "tid": 2338707, + "ts": 6197198967936.669, "dur": 9.562, + "args": { + "External id": 33566,"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": 2338707, "tid": 2338707, + "ts": 6197198968020.090, "dur": 104.896, + "args": { + "External id": 33567,"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": 2338707, "tid": 2338707, + "ts": 6197198968169.622, "dur": 35.920, + "args": { + "External id": 33568,"kernel_hash": "cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/dm/cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43.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": 2338707, "tid": 2338707, + "ts": 6197198968217.170, "dur": 54.372, + "args": { + "External id": 33569,"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": 2338707, "tid": 2338707, + "ts": 6197198968283.557, "dur": 39.762, + "args": { + "External id": 33570,"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": 2338707, "tid": 2338707, + "ts": 6197198968351.470, "dur": 33.306, + "args": { + "External id": 33571,"kernel_hash": "cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/b7/cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu.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": 2338707, "tid": 2338707, + "ts": 6197198968394.302, "dur": 40.385, + "args": { + "External id": 33572,"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": 2338707, "tid": 2338707, + "ts": 6197198968456.543, "dur": 20.132, + "args": { + "External id": 33573,"kernel_hash": "cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/gi/cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb.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": 2338707, "tid": 2338707, + "ts": 6197198968649.584, "dur": 119.849, + "args": { + "External id": 33574,"Record function id": 0, "Ev Idx": 16746 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6197198968862.091, "dur": 54.746, + "args": { + "External id": 33575,"Record function id": 0, "Ev Idx": 16747 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.3)", "pid": 2338707, "tid": 2338707, + "ts": 6197198968928.202, "dur": 30052.042, + "args": { + "External id": 33576,"Record function id": 0, "Ev Idx": 16748 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.3)", "pid": 2338707, "tid": 2338707, + "ts": 6197198968938.773, "dur": 1160.478, + "args": { + "External id": 33577,"Record function id": 0, "Ev Idx": 16749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6197198969040.543, "dur": 10.982, + "args": { + "External id": 33578,"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": 2338707, "tid": 2338707, + "ts": 6197198969108.623, "dur": 46.126, + "args": { + "External id": 33579,"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": 2338707, "tid": 2338707, + "ts": 6197198969115.643, "dur": 3.228, + "args": { + "External id": 33580,"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": 2338707, "tid": 2338707, + "ts": 6197198969124.060, "dur": 0.488, + "args": { + "External id": 33581,"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": 2338707, "tid": 2338707, + "ts": 6197198969126.544, "dur": 0.665, + "args": { + "External id": 33582,"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": 2338707, "tid": 2338707, + "ts": 6197198969128.697, "dur": 0.772, + "args": { + "External id": 33583,"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": 2338707, "tid": 2338707, + "ts": 6197198969133.926, "dur": 0.600, + "args": { + "External id": 33584,"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": 2338707, "tid": 2338707, + "ts": 6197198969135.757, "dur": 0.800, + "args": { + "External id": 33585,"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": 2338707, "tid": 2338707, + "ts": 6197198969138.265, "dur": 5.043, + "args": { + "External id": 33586,"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": 2338707, "tid": 2338707, + "ts": 6197198969144.854, "dur": 0.371, + "args": { + "External id": 33587,"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": 2338707, "tid": 2338707, + "ts": 6197198969146.475, "dur": 0.562, + "args": { + "External id": 33588,"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": 2338707, "tid": 2338707, + "ts": 6197198969168.444, "dur": 69.347, + "args": { + "External id": 33589,"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": 2338707, "tid": 2338707, + "ts": 6197198969279.506, "dur": 145.605, + "args": { + "External id": 33590,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2338707, + "ts": 6197198969293.224, "dur": 5.674, + "args": { + "External id": 33591,"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": 2338707, "tid": 2338707, + "ts": 6197198969305.029, "dur": 12.484, + "args": { + "External id": 33592,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2338707, + "ts": 6197198969310.897, "dur": 6.092, + "args": { + "External id": 33593,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2338707, + "ts": 6197198969314.805, "dur": 0.700, + "args": { + "External id": 33594,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197198969325.569, "dur": 36.625, + "args": { + "External id": 33595,"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": 2338707, "tid": 2338707, + "ts": 6197198969327.760, "dur": 2.551, + "args": { + "External id": 33596,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197198969331.971, "dur": 0.577, + "args": { + "External id": 33597,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2338707, + "ts": 6197198969334.219, "dur": 0.623, + "args": { + "External id": 33598,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2338707, + "ts": 6197198969339.089, "dur": 2.937, + "args": { + "External id": 33599,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2338707, + "ts": 6197198969343.932, "dur": 0.674, + "args": { + "External id": 33600,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2338707, + "ts": 6197198969345.736, "dur": 0.518, + "args": { + "External id": 33601,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2338707, + "ts": 6197198969350.165, "dur": 0.656, + "args": { + "External id": 33602,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2338707, + "ts": 6197198969352.145, "dur": 0.399, + "args": { + "External id": 33603,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2338707, + "ts": 6197198969354.322, "dur": 2.719, + "args": { + "External id": 33604,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2338707, + "ts": 6197198969377.996, "dur": 37.316, + "args": { + "External id": 33605,"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": 2338707, "tid": 2338707, + "ts": 6197198969489.397, "dur": 445.802, + "args": { + "External id": 33606,"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": 2338707, "tid": 2338707, + "ts": 6197198969528.657, "dur": 399.551, + "args": { + "External id": 33607,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2338707, + "ts": 6197198969541.078, "dur": 380.196, + "args": { + "External id": 33608,"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": 2338707, "tid": 2338707, + "ts": 6197198969969.118, "dur": 3.245, + "args": { + "External id": 33609,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.3)", "pid": 2338707, "tid": 2338707, + "ts": 6197198970130.318, "dur": 28610.441, + "args": { + "External id": 33610,"Record function id": 0, "Ev Idx": 16782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6197198970263.843, "dur": 8.127, + "args": { + "External id": 33611,"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": 2338707, "tid": 2338707, + "ts": 6197198970276.263, "dur": 1.238, + "args": { + "External id": 33612,"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": 2338707, "tid": 2338707, + "ts": 6197198970279.373, "dur": 3.784, + "args": { + "External id": 33613,"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": 2338707, "tid": 2338707, + "ts": 6197198970284.994, "dur": 1.042, + "args": { + "External id": 33614,"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": 2338707, "tid": 2338707, + "ts": 6197198970287.616, "dur": 1.434, + "args": { + "External id": 33615,"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": 2338707, "tid": 2338707, + "ts": 6197198970290.554, "dur": 1.150, + "args": { + "External id": 33616,"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": 2338707, "tid": 2338707, + "ts": 6197198970295.968, "dur": 1.086, + "args": { + "External id": 33617,"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": 2338707, "tid": 2338707, + "ts": 6197198970298.779, "dur": 2.545, + "args": { + "External id": 33618,"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": 2338707, "tid": 2338707, + "ts": 6197198970302.894, "dur": 0.655, + "args": { + "External id": 33619,"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": 2338707, "tid": 2338707, + "ts": 6197198970305.374, "dur": 1.026, + "args": { + "External id": 33620,"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": 2338707, "tid": 2338707, + "ts": 6197198970328.976, "dur": 28348.495, + "args": { + "External id": 33621,"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": 2338707, "tid": 2338707, + "ts": 6197198970347.828, "dur": 28319.897, + "args": { + "External id": 33622,"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": 2338707, "tid": 2338707, + "ts": 6197198970366.890, "dur": 20.741, + "args": { + "External id": 33623,"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": 2338707, "tid": 2338707, + "ts": 6197198970392.059, "dur": 28235.065, + "args": { + "External id": 33624,"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": 2338707, "tid": 2338707, + "ts": 6197198970395.203, "dur": 28231.275, + "args": { + "External id": 33625,"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": 2338707, "tid": 2338707, + "ts": 6197198970403.300, "dur": 7.064, + "args": { + "External id": 33626,"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": 2338707, "tid": 2338707, + "ts": 6197198970412.426, "dur": 28210.344, + "args": { + "External id": 33627,"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": 2338707, "tid": 2338707, + "ts": 6197198998912.365, "dur": 36.076, + "args": { + "External id": 33628,"Sequence number": 480002, "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": 2338707, "tid": 2338707, "ts": 6197198998912.365, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6197198998933.044, "dur": 9.862, + "args": { + "External id": 33629,"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": 2338707, "tid": 2338707, + "ts": 6197198998937.124, "dur": 5.540, + "args": { + "External id": 33630,"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": 2338707, "tid": 2338707, + "ts": 6197198999028.478, "dur": 122.487, + "args": { + "External id": 33631,"Record function id": 0, "Ev Idx": 16803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6197198999154.245, "dur": 1317.244, + "args": { + "External id": 33632,"Record function id": 0, "Ev Idx": 16804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197198999202.980, "dur": 1252.994, + "args": { + "External id": 33633,"Sequence number": 480003, "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": 2338707, "tid": 2338707, "ts": 6197198999202.980, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6197198999285.165, "dur": 60.173, + "args": { + "External id": 33634,"kernel_hash": "cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/du/cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs.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": 2338707, "tid": 2338707, + "ts": 6197198999364.245, "dur": 121.178, + "args": { + "External id": 33635,"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": 2338707, "tid": 2338707, + "ts": 6197198999500.467, "dur": 42.723, + "args": { + "External id": 33636,"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": 2338707, "tid": 2338707, + "ts": 6197198999553.726, "dur": 33.741, + "args": { + "External id": 33637,"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": 2338707, "tid": 2338707, + "ts": 6197198999619.945, "dur": 30.085, + "args": { + "External id": 33638,"kernel_hash": "cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5", "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/jw/cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5.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": 2338707, "tid": 2338707, + "ts": 6197198999673.033, "dur": 20.057, + "args": { + "External id": 33639,"kernel_hash": "cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi", "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/xw/cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi.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": 2338707, "tid": 2338707, + "ts": 6197198999738.738, "dur": 158.654, + "args": { + "External id": 33640,"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": 2338707, "tid": 2338707, + "ts": 6197198999801.117, "dur": 14.563, + "args": { + "External id": 33641,"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": 2338707, "tid": 2338707, + "ts": 6197198999807.510, "dur": 6.827, + "args": { + "External id": 33642,"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": 2338707, "tid": 2338707, + "ts": 6197198999818.860, "dur": 4.630, + "args": { + "External id": 33643,"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": 2338707, "tid": 2338707, + "ts": 6197198999825.067, "dur": 1.090, + "args": { + "External id": 33644,"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": 2338707, "tid": 2338707, + "ts": 6197198999829.025, "dur": 5.896, + "args": { + "External id": 33645,"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": 2338707, "tid": 2338707, + "ts": 6197198999909.812, "dur": 65.412, + "args": { + "External id": 33646,"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": 2338707, "tid": 2338707, + "ts": 6197199000017.121, "dur": 73.577, + "args": { + "External id": 33647,"kernel_hash": "cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/dm/cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43.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": 2338707, "tid": 2338707, + "ts": 6197199000107.106, "dur": 57.939, + "args": { + "External id": 33648,"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": 2338707, "tid": 2338707, + "ts": 6197199000176.174, "dur": 40.879, + "args": { + "External id": 33649,"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": 2338707, "tid": 2338707, + "ts": 6197199000244.290, "dur": 32.534, + "args": { + "External id": 33650,"kernel_hash": "cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/b7/cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu.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": 2338707, "tid": 2338707, + "ts": 6197199000286.020, "dur": 42.240, + "args": { + "External id": 33651,"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": 2338707, "tid": 2338707, + "ts": 6197199000352.365, "dur": 22.381, + "args": { + "External id": 33652,"kernel_hash": "cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/gi/cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb.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": 2338707, "tid": 2338707, + "ts": 6197199000548.979, "dur": 93.990, + "args": { + "External id": 33653,"Record function id": 0, "Ev Idx": 16825 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6197199000752.634, "dur": 60.020, + "args": { + "External id": 33654,"Record function id": 0, "Ev Idx": 16826 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.4)", "pid": 2338707, "tid": 2338707, + "ts": 6197199000824.770, "dur": 31957.980, + "args": { + "External id": 33655,"Record function id": 0, "Ev Idx": 16827 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.4)", "pid": 2338707, "tid": 2338707, + "ts": 6197199000834.785, "dur": 1171.888, + "args": { + "External id": 33656,"Record function id": 0, "Ev Idx": 16828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6197199000938.321, "dur": 11.211, + "args": { + "External id": 33657,"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": 2338707, "tid": 2338707, + "ts": 6197199000966.395, "dur": 44.736, + "args": { + "External id": 33658,"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": 2338707, "tid": 2338707, + "ts": 6197199000973.666, "dur": 2.455, + "args": { + "External id": 33659,"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": 2338707, "tid": 2338707, + "ts": 6197199000981.282, "dur": 0.484, + "args": { + "External id": 33660,"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": 2338707, "tid": 2338707, + "ts": 6197199000983.882, "dur": 0.410, + "args": { + "External id": 33661,"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": 2338707, "tid": 2338707, + "ts": 6197199000985.626, "dur": 0.570, + "args": { + "External id": 33662,"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": 2338707, "tid": 2338707, + "ts": 6197199000989.729, "dur": 0.723, + "args": { + "External id": 33663,"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": 2338707, "tid": 2338707, + "ts": 6197199000991.936, "dur": 0.659, + "args": { + "External id": 33664,"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": 2338707, "tid": 2338707, + "ts": 6197199000994.199, "dur": 5.648, + "args": { + "External id": 33665,"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": 2338707, "tid": 2338707, + "ts": 6197199001001.565, "dur": 0.581, + "args": { + "External id": 33666,"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": 2338707, "tid": 2338707, + "ts": 6197199001003.738, "dur": 0.377, + "args": { + "External id": 33667,"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": 2338707, "tid": 2338707, + "ts": 6197199001026.159, "dur": 106.778, + "args": { + "External id": 33668,"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": 2338707, "tid": 2338707, + "ts": 6197199001181.285, "dur": 145.641, + "args": { + "External id": 33669,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2338707, + "ts": 6197199001196.118, "dur": 8.564, + "args": { + "External id": 33670,"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": 2338707, "tid": 2338707, + "ts": 6197199001211.569, "dur": 13.637, + "args": { + "External id": 33671,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2338707, + "ts": 6197199001217.211, "dur": 7.486, + "args": { + "External id": 33672,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2338707, + "ts": 6197199001221.639, "dur": 0.984, + "args": { + "External id": 33673,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197199001233.112, "dur": 32.758, + "args": { + "External id": 33674,"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": 2338707, "tid": 2338707, + "ts": 6197199001235.606, "dur": 0.342, + "args": { + "External id": 33675,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197199001237.704, "dur": 2.513, + "args": { + "External id": 33676,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2338707, + "ts": 6197199001242.006, "dur": 0.477, + "args": { + "External id": 33677,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2338707, + "ts": 6197199001243.801, "dur": 3.314, + "args": { + "External id": 33678,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2338707, + "ts": 6197199001250.856, "dur": 0.348, + "args": { + "External id": 33679,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2338707, + "ts": 6197199001253.146, "dur": 0.624, + "args": { + "External id": 33680,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2338707, + "ts": 6197199001255.050, "dur": 0.367, + "args": { + "External id": 33681,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2338707, + "ts": 6197199001259.492, "dur": 0.426, + "args": { + "External id": 33682,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2338707, + "ts": 6197199001261.493, "dur": 0.291, + "args": { + "External id": 33683,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2338707, + "ts": 6197199001279.737, "dur": 37.129, + "args": { + "External id": 33684,"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": 2338707, "tid": 2338707, + "ts": 6197199001394.045, "dur": 491.755, + "args": { + "External id": 33685,"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": 2338707, "tid": 2338707, + "ts": 6197199001432.398, "dur": 446.063, + "args": { + "External id": 33686,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2338707, + "ts": 6197199001444.517, "dur": 426.784, + "args": { + "External id": 33687,"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": 2338707, "tid": 2338707, + "ts": 6197199001917.152, "dur": 2.774, + "args": { + "External id": 33688,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.4)", "pid": 2338707, "tid": 2338707, + "ts": 6197199002032.465, "dur": 30502.936, + "args": { + "External id": 33689,"Record function id": 0, "Ev Idx": 16861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6197199002206.058, "dur": 8.391, + "args": { + "External id": 33690,"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": 2338707, "tid": 2338707, + "ts": 6197199002218.451, "dur": 1.158, + "args": { + "External id": 33691,"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": 2338707, "tid": 2338707, + "ts": 6197199002222.097, "dur": 3.800, + "args": { + "External id": 33692,"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": 2338707, "tid": 2338707, + "ts": 6197199002228.269, "dur": 1.028, + "args": { + "External id": 33693,"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": 2338707, "tid": 2338707, + "ts": 6197199002231.142, "dur": 1.097, + "args": { + "External id": 33694,"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": 2338707, "tid": 2338707, + "ts": 6197199002233.732, "dur": 1.062, + "args": { + "External id": 33695,"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": 2338707, "tid": 2338707, + "ts": 6197199002239.662, "dur": 0.923, + "args": { + "External id": 33696,"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": 2338707, "tid": 2338707, + "ts": 6197199002242.611, "dur": 2.167, + "args": { + "External id": 33697,"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": 2338707, "tid": 2338707, + "ts": 6197199002246.252, "dur": 1.041, + "args": { + "External id": 33698,"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": 2338707, "tid": 2338707, + "ts": 6197199002248.912, "dur": 0.837, + "args": { + "External id": 33699,"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": 2338707, "tid": 2338707, + "ts": 6197199002274.037, "dur": 30211.570, + "args": { + "External id": 33700,"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": 2338707, "tid": 2338707, + "ts": 6197199002292.166, "dur": 30183.476, + "args": { + "External id": 33701,"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": 2338707, "tid": 2338707, + "ts": 6197199002312.701, "dur": 19.362, + "args": { + "External id": 33702,"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": 2338707, "tid": 2338707, + "ts": 6197199002336.204, "dur": 30096.760, + "args": { + "External id": 33703,"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": 2338707, "tid": 2338707, + "ts": 6197199002339.533, "dur": 30092.630, + "args": { + "External id": 33704,"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": 2338707, "tid": 2338707, + "ts": 6197199002346.226, "dur": 6.445, + "args": { + "External id": 33705,"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": 2338707, "tid": 2338707, + "ts": 6197199002354.877, "dur": 30073.564, + "args": { + "External id": 33706,"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": 2338707, "tid": 2338707, + "ts": 6197199032714.635, "dur": 38.537, + "args": { + "External id": 33707,"Sequence number": 480004, "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": 2338707, "tid": 2338707, "ts": 6197199032714.635, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6197199032736.700, "dur": 10.609, + "args": { + "External id": 33708,"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": 2338707, "tid": 2338707, + "ts": 6197199032740.907, "dur": 6.005, + "args": { + "External id": 33709,"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": 2338707, "tid": 2338707, + "ts": 6197199032833.080, "dur": 93.322, + "args": { + "External id": 33710,"Record function id": 0, "Ev Idx": 16882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6197199032927.939, "dur": 1377.205, + "args": { + "External id": 33711,"Record function id": 0, "Ev Idx": 16883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197199032976.294, "dur": 1312.634, + "args": { + "External id": 33712,"Sequence number": 480005, "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": 2338707, "tid": 2338707, "ts": 6197199032976.294, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6197199033104.865, "dur": 62.090, + "args": { + "External id": 33713,"kernel_hash": "cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/du/cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs.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": 2338707, "tid": 2338707, + "ts": 6197199033186.179, "dur": 122.797, + "args": { + "External id": 33714,"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": 2338707, "tid": 2338707, + "ts": 6197199033322.877, "dur": 43.677, + "args": { + "External id": 33715,"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": 2338707, "tid": 2338707, + "ts": 6197199033378.319, "dur": 35.794, + "args": { + "External id": 33716,"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": 2338707, "tid": 2338707, + "ts": 6197199033446.901, "dur": 33.223, + "args": { + "External id": 33717,"kernel_hash": "cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5", "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/jw/cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5.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": 2338707, "tid": 2338707, + "ts": 6197199033502.995, "dur": 22.413, + "args": { + "External id": 33718,"kernel_hash": "cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi", "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/xw/cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi.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": 2338707, "tid": 2338707, + "ts": 6197199033552.422, "dur": 176.009, + "args": { + "External id": 33719,"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": 2338707, "tid": 2338707, + "ts": 6197199033613.078, "dur": 13.621, + "args": { + "External id": 33720,"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": 2338707, "tid": 2338707, + "ts": 6197199033619.536, "dur": 6.153, + "args": { + "External id": 33721,"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": 2338707, "tid": 2338707, + "ts": 6197199033630.070, "dur": 5.089, + "args": { + "External id": 33722,"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": 2338707, "tid": 2338707, + "ts": 6197199033636.729, "dur": 1.064, + "args": { + "External id": 33723,"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": 2338707, "tid": 2338707, + "ts": 6197199033640.796, "dur": 8.414, + "args": { + "External id": 33724,"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": 2338707, "tid": 2338707, + "ts": 6197199033743.624, "dur": 66.836, + "args": { + "External id": 33725,"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": 2338707, "tid": 2338707, + "ts": 6197199033849.878, "dur": 35.974, + "args": { + "External id": 33726,"kernel_hash": "cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/dm/cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43.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": 2338707, "tid": 2338707, + "ts": 6197199033897.656, "dur": 52.085, + "args": { + "External id": 33727,"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": 2338707, "tid": 2338707, + "ts": 6197199033960.058, "dur": 39.677, + "args": { + "External id": 33728,"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": 2338707, "tid": 2338707, + "ts": 6197199034026.840, "dur": 71.387, + "args": { + "External id": 33729,"kernel_hash": "cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/b7/cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu.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": 2338707, "tid": 2338707, + "ts": 6197199034110.270, "dur": 50.183, + "args": { + "External id": 33730,"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": 2338707, "tid": 2338707, + "ts": 6197199034184.188, "dur": 23.218, + "args": { + "External id": 33731,"kernel_hash": "cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/gi/cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb.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": 2338707, "tid": 2338707, + "ts": 6197199034385.402, "dur": 101.168, + "args": { + "External id": 33732,"Record function id": 0, "Ev Idx": 16904 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6197199034578.005, "dur": 56.110, + "args": { + "External id": 33733,"Record function id": 0, "Ev Idx": 16905 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.5)", "pid": 2338707, "tid": 2338707, + "ts": 6197199034645.232, "dur": 31043.705, + "args": { + "External id": 33734,"Record function id": 0, "Ev Idx": 16906 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.5)", "pid": 2338707, "tid": 2338707, + "ts": 6197199034655.107, "dur": 1151.328, + "args": { + "External id": 33735,"Record function id": 0, "Ev Idx": 16907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6197199034781.525, "dur": 11.233, + "args": { + "External id": 33736,"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": 2338707, "tid": 2338707, + "ts": 6197199034810.700, "dur": 51.663, + "args": { + "External id": 33737,"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": 2338707, "tid": 2338707, + "ts": 6197199034818.023, "dur": 2.968, + "args": { + "External id": 33738,"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": 2338707, "tid": 2338707, + "ts": 6197199034826.345, "dur": 0.617, + "args": { + "External id": 33739,"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": 2338707, "tid": 2338707, + "ts": 6197199034828.561, "dur": 0.713, + "args": { + "External id": 33740,"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": 2338707, "tid": 2338707, + "ts": 6197199034830.932, "dur": 0.373, + "args": { + "External id": 33741,"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": 2338707, "tid": 2338707, + "ts": 6197199034835.622, "dur": 0.453, + "args": { + "External id": 33742,"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": 2338707, "tid": 2338707, + "ts": 6197199034837.895, "dur": 0.563, + "args": { + "External id": 33743,"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": 2338707, "tid": 2338707, + "ts": 6197199034839.992, "dur": 4.583, + "args": { + "External id": 33744,"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": 2338707, "tid": 2338707, + "ts": 6197199034846.021, "dur": 0.680, + "args": { + "External id": 33745,"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": 2338707, "tid": 2338707, + "ts": 6197199034855.013, "dur": 0.570, + "args": { + "External id": 33746,"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": 2338707, "tid": 2338707, + "ts": 6197199034877.358, "dur": 63.223, + "args": { + "External id": 33747,"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": 2338707, "tid": 2338707, + "ts": 6197199034980.325, "dur": 195.821, + "args": { + "External id": 33748,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2338707, + "ts": 6197199034993.252, "dur": 4.156, + "args": { + "External id": 33749,"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": 2338707, "tid": 2338707, + "ts": 6197199035003.632, "dur": 14.661, + "args": { + "External id": 33750,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2338707, + "ts": 6197199035009.425, "dur": 8.336, + "args": { + "External id": 33751,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2338707, + "ts": 6197199035013.580, "dur": 2.772, + "args": { + "External id": 33752,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197199035025.993, "dur": 77.588, + "args": { + "External id": 33753,"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": 2338707, "tid": 2338707, + "ts": 6197199035028.319, "dur": 0.605, + "args": { + "External id": 33754,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197199035030.205, "dur": 0.550, + "args": { + "External id": 33755,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2338707, + "ts": 6197199035032.989, "dur": 0.376, + "args": { + "External id": 33756,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2338707, + "ts": 6197199035036.506, "dur": 3.635, + "args": { + "External id": 33757,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2338707, + "ts": 6197199035041.886, "dur": 0.682, + "args": { + "External id": 33758,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2338707, + "ts": 6197199035044.027, "dur": 2.596, + "args": { + "External id": 33759,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2338707, + "ts": 6197199035048.394, "dur": 0.458, + "args": { + "External id": 33760,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2338707, + "ts": 6197199035050.598, "dur": 0.406, + "args": { + "External id": 33761,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2338707, + "ts": 6197199035097.505, "dur": 0.903, + "args": { + "External id": 33762,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2338707, + "ts": 6197199035125.487, "dur": 41.283, + "args": { + "External id": 33763,"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": 2338707, "tid": 2338707, + "ts": 6197199035240.666, "dur": 425.268, + "args": { + "External id": 33764,"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": 2338707, "tid": 2338707, + "ts": 6197199035277.737, "dur": 382.420, + "args": { + "External id": 33765,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2338707, + "ts": 6197199035289.477, "dur": 364.123, + "args": { + "External id": 33766,"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": 2338707, "tid": 2338707, + "ts": 6197199035692.751, "dur": 2.584, + "args": { + "External id": 33767,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.5)", "pid": 2338707, "tid": 2338707, + "ts": 6197199035833.025, "dur": 29621.619, + "args": { + "External id": 33768,"Record function id": 0, "Ev Idx": 16940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6197199035957.832, "dur": 7.759, + "args": { + "External id": 33769,"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": 2338707, "tid": 2338707, + "ts": 6197199035969.769, "dur": 1.441, + "args": { + "External id": 33770,"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": 2338707, "tid": 2338707, + "ts": 6197199035973.258, "dur": 3.733, + "args": { + "External id": 33771,"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": 2338707, "tid": 2338707, + "ts": 6197199035978.953, "dur": 1.046, + "args": { + "External id": 33772,"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": 2338707, "tid": 2338707, + "ts": 6197199035981.791, "dur": 1.174, + "args": { + "External id": 33773,"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": 2338707, "tid": 2338707, + "ts": 6197199035986.751, "dur": 0.830, + "args": { + "External id": 33774,"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": 2338707, "tid": 2338707, + "ts": 6197199035989.258, "dur": 1.273, + "args": { + "External id": 33775,"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": 2338707, "tid": 2338707, + "ts": 6197199035992.466, "dur": 2.237, + "args": { + "External id": 33776,"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": 2338707, "tid": 2338707, + "ts": 6197199035996.724, "dur": 1.009, + "args": { + "External id": 33777,"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": 2338707, "tid": 2338707, + "ts": 6197199036001.796, "dur": 0.868, + "args": { + "External id": 33778,"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": 2338707, "tid": 2338707, + "ts": 6197199036023.317, "dur": 29380.373, + "args": { + "External id": 33779,"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": 2338707, "tid": 2338707, + "ts": 6197199036041.845, "dur": 29352.377, + "args": { + "External id": 33780,"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": 2338707, "tid": 2338707, + "ts": 6197199036100.537, "dur": 21.070, + "args": { + "External id": 33781,"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": 2338707, "tid": 2338707, + "ts": 6197199036126.298, "dur": 29226.910, + "args": { + "External id": 33782,"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": 2338707, "tid": 2338707, + "ts": 6197199036129.532, "dur": 29223.091, + "args": { + "External id": 33783,"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": 2338707, "tid": 2338707, + "ts": 6197199036138.432, "dur": 7.240, + "args": { + "External id": 33784,"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": 2338707, "tid": 2338707, + "ts": 6197199036148.061, "dur": 29200.994, + "args": { + "External id": 33785,"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": 2338707, "tid": 2338707, + "ts": 6197199065618.514, "dur": 37.662, + "args": { + "External id": 33786,"Sequence number": 480006, "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": 2338707, "tid": 2338707, "ts": 6197199065618.514, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6197199065639.854, "dur": 10.454, + "args": { + "External id": 33787,"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": 2338707, "tid": 2338707, + "ts": 6197199065644.690, "dur": 5.347, + "args": { + "External id": 33788,"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": 2338707, "tid": 2338707, + "ts": 6197199065753.418, "dur": 86.086, + "args": { + "External id": 33789,"Record function id": 0, "Ev Idx": 16961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6197199065841.738, "dur": 1394.730, + "args": { + "External id": 33790,"Record function id": 0, "Ev Idx": 16962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197199065889.984, "dur": 1330.658, + "args": { + "External id": 33791,"Sequence number": 480007, "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": 2338707, "tid": 2338707, "ts": 6197199065889.984, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6197199065971.989, "dur": 60.515, + "args": { + "External id": 33792,"kernel_hash": "cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/du/cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs.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": 2338707, "tid": 2338707, + "ts": 6197199066120.125, "dur": 120.923, + "args": { + "External id": 33793,"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": 2338707, "tid": 2338707, + "ts": 6197199066262.742, "dur": 42.512, + "args": { + "External id": 33794,"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": 2338707, "tid": 2338707, + "ts": 6197199066316.723, "dur": 32.690, + "args": { + "External id": 33795,"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": 2338707, "tid": 2338707, + "ts": 6197199066385.134, "dur": 33.511, + "args": { + "External id": 33796,"kernel_hash": "cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5", "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/jw/cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5.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": 2338707, "tid": 2338707, + "ts": 6197199066443.590, "dur": 19.064, + "args": { + "External id": 33797,"kernel_hash": "cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi", "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/xw/cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi.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": 2338707, "tid": 2338707, + "ts": 6197199066490.986, "dur": 160.889, + "args": { + "External id": 33798,"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": 2338707, "tid": 2338707, + "ts": 6197199066553.775, "dur": 13.110, + "args": { + "External id": 33799,"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": 2338707, "tid": 2338707, + "ts": 6197199066560.081, "dur": 5.830, + "args": { + "External id": 33800,"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": 2338707, "tid": 2338707, + "ts": 6197199066570.309, "dur": 5.133, + "args": { + "External id": 33801,"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": 2338707, "tid": 2338707, + "ts": 6197199066577.264, "dur": 1.071, + "args": { + "External id": 33802,"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": 2338707, "tid": 2338707, + "ts": 6197199066581.296, "dur": 10.462, + "args": { + "External id": 33803,"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": 2338707, "tid": 2338707, + "ts": 6197199066664.450, "dur": 76.709, + "args": { + "External id": 33804,"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": 2338707, "tid": 2338707, + "ts": 6197199066782.930, "dur": 37.033, + "args": { + "External id": 33805,"kernel_hash": "cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/dm/cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43.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": 2338707, "tid": 2338707, + "ts": 6197199066832.456, "dur": 52.875, + "args": { + "External id": 33806,"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": 2338707, "tid": 2338707, + "ts": 6197199066895.311, "dur": 39.653, + "args": { + "External id": 33807,"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": 2338707, "tid": 2338707, + "ts": 6197199066962.641, "dur": 31.149, + "args": { + "External id": 33808,"kernel_hash": "cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/b7/cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu.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": 2338707, "tid": 2338707, + "ts": 6197199067004.241, "dur": 41.777, + "args": { + "External id": 33809,"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": 2338707, "tid": 2338707, + "ts": 6197199067108.964, "dur": 27.102, + "args": { + "External id": 33810,"kernel_hash": "cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/gi/cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb.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": 2338707, "tid": 2338707, + "ts": 6197199067314.543, "dur": 98.742, + "args": { + "External id": 33811,"Record function id": 0, "Ev Idx": 16983 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6197199067499.213, "dur": 56.468, + "args": { + "External id": 33812,"Record function id": 0, "Ev Idx": 16984 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.6)", "pid": 2338707, "tid": 2338707, + "ts": 6197199067566.007, "dur": 32567.431, + "args": { + "External id": 33813,"Record function id": 0, "Ev Idx": 16985 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.6)", "pid": 2338707, "tid": 2338707, + "ts": 6197199067576.379, "dur": 1109.986, + "args": { + "External id": 33814,"Record function id": 0, "Ev Idx": 16986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6197199067676.269, "dur": 10.216, + "args": { + "External id": 33815,"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": 2338707, "tid": 2338707, + "ts": 6197199067721.232, "dur": 47.377, + "args": { + "External id": 33816,"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": 2338707, "tid": 2338707, + "ts": 6197199067728.274, "dur": 2.812, + "args": { + "External id": 33817,"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": 2338707, "tid": 2338707, + "ts": 6197199067736.199, "dur": 0.548, + "args": { + "External id": 33818,"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": 2338707, "tid": 2338707, + "ts": 6197199067738.346, "dur": 0.563, + "args": { + "External id": 33819,"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": 2338707, "tid": 2338707, + "ts": 6197199067740.153, "dur": 0.649, + "args": { + "External id": 33820,"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": 2338707, "tid": 2338707, + "ts": 6197199067745.046, "dur": 0.814, + "args": { + "External id": 33821,"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": 2338707, "tid": 2338707, + "ts": 6197199067750.426, "dur": 0.716, + "args": { + "External id": 33822,"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": 2338707, "tid": 2338707, + "ts": 6197199067752.362, "dur": 5.297, + "args": { + "External id": 33823,"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": 2338707, "tid": 2338707, + "ts": 6197199067759.011, "dur": 0.584, + "args": { + "External id": 33824,"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": 2338707, "tid": 2338707, + "ts": 6197199067761.213, "dur": 0.392, + "args": { + "External id": 33825,"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": 2338707, "tid": 2338707, + "ts": 6197199067784.582, "dur": 64.076, + "args": { + "External id": 33826,"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": 2338707, "tid": 2338707, + "ts": 6197199067888.355, "dur": 144.357, + "args": { + "External id": 33827,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2338707, + "ts": 6197199067902.145, "dur": 5.640, + "args": { + "External id": 33828,"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": 2338707, "tid": 2338707, + "ts": 6197199067914.058, "dur": 12.297, + "args": { + "External id": 33829,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2338707, + "ts": 6197199067919.425, "dur": 6.425, + "args": { + "External id": 33830,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2338707, + "ts": 6197199067923.828, "dur": 0.551, + "args": { + "External id": 33831,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197199067934.136, "dur": 33.381, + "args": { + "External id": 33832,"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": 2338707, "tid": 2338707, + "ts": 6197199067936.447, "dur": 2.339, + "args": { + "External id": 33833,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197199067940.339, "dur": 0.413, + "args": { + "External id": 33834,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2338707, + "ts": 6197199067942.683, "dur": 0.516, + "args": { + "External id": 33835,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2338707, + "ts": 6197199067946.537, "dur": 3.121, + "args": { + "External id": 33836,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2338707, + "ts": 6197199067950.871, "dur": 0.757, + "args": { + "External id": 33837,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2338707, + "ts": 6197199067953.014, "dur": 0.310, + "args": { + "External id": 33838,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2338707, + "ts": 6197199067956.490, "dur": 0.482, + "args": { + "External id": 33839,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2338707, + "ts": 6197199067958.454, "dur": 0.391, + "args": { + "External id": 33840,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2338707, + "ts": 6197199067960.673, "dur": 2.530, + "args": { + "External id": 33841,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2338707, + "ts": 6197199067984.059, "dur": 39.296, + "args": { + "External id": 33842,"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": 2338707, "tid": 2338707, + "ts": 6197199068145.517, "dur": 430.837, + "args": { + "External id": 33843,"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": 2338707, "tid": 2338707, + "ts": 6197199068183.468, "dur": 386.870, + "args": { + "External id": 33844,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2338707, + "ts": 6197199068196.744, "dur": 367.357, + "args": { + "External id": 33845,"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": 2338707, "tid": 2338707, + "ts": 6197199068603.193, "dur": 2.859, + "args": { + "External id": 33846,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.6)", "pid": 2338707, "tid": 2338707, + "ts": 6197199068731.655, "dur": 31130.555, + "args": { + "External id": 33847,"Record function id": 0, "Ev Idx": 17019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6197199068858.720, "dur": 8.182, + "args": { + "External id": 33848,"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": 2338707, "tid": 2338707, + "ts": 6197199068871.258, "dur": 1.190, + "args": { + "External id": 33849,"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": 2338707, "tid": 2338707, + "ts": 6197199068874.319, "dur": 3.493, + "args": { + "External id": 33850,"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": 2338707, "tid": 2338707, + "ts": 6197199068879.773, "dur": 0.969, + "args": { + "External id": 33851,"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": 2338707, "tid": 2338707, + "ts": 6197199068882.037, "dur": 0.907, + "args": { + "External id": 33852,"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": 2338707, "tid": 2338707, + "ts": 6197199068884.655, "dur": 0.977, + "args": { + "External id": 33853,"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": 2338707, "tid": 2338707, + "ts": 6197199068890.022, "dur": 1.034, + "args": { + "External id": 33854,"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": 2338707, "tid": 2338707, + "ts": 6197199068892.706, "dur": 2.096, + "args": { + "External id": 33855,"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": 2338707, "tid": 2338707, + "ts": 6197199068896.425, "dur": 1.050, + "args": { + "External id": 33856,"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": 2338707, "tid": 2338707, + "ts": 6197199068899.853, "dur": 0.951, + "args": { + "External id": 33857,"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": 2338707, "tid": 2338707, + "ts": 6197199068923.795, "dur": 30888.264, + "args": { + "External id": 33858,"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": 2338707, "tid": 2338707, + "ts": 6197199068941.455, "dur": 30861.666, + "args": { + "External id": 33859,"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": 2338707, "tid": 2338707, + "ts": 6197199068962.058, "dur": 19.051, + "args": { + "External id": 33860,"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": 2338707, "tid": 2338707, + "ts": 6197199068985.032, "dur": 30775.609, + "args": { + "External id": 33861,"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": 2338707, "tid": 2338707, + "ts": 6197199068987.968, "dur": 30771.960, + "args": { + "External id": 33862,"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": 2338707, "tid": 2338707, + "ts": 6197199068994.637, "dur": 8.604, + "args": { + "External id": 33863,"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": 2338707, "tid": 2338707, + "ts": 6197199069005.419, "dur": 30750.594, + "args": { + "External id": 33864,"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": 2338707, "tid": 2338707, + "ts": 6197199100029.140, "dur": 70.673, + "args": { + "External id": 33865,"Sequence number": 480008, "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": 2338707, "tid": 2338707, "ts": 6197199100029.140, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6197199100051.045, "dur": 42.258, + "args": { + "External id": 33866,"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": 2338707, "tid": 2338707, + "ts": 6197199100087.682, "dur": 5.218, + "args": { + "External id": 33867,"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": 2338707, "tid": 2338707, + "ts": 6197199100184.062, "dur": 86.222, + "args": { + "External id": 33868,"Record function id": 0, "Ev Idx": 17040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6197199100271.518, "dur": 1303.820, + "args": { + "External id": 33869,"Record function id": 0, "Ev Idx": 17041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197199100320.339, "dur": 1238.962, + "args": { + "External id": 33870,"Sequence number": 480009, "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": 2338707, "tid": 2338707, "ts": 6197199100320.339, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6197199100404.558, "dur": 59.986, + "args": { + "External id": 33871,"kernel_hash": "cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/du/cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs.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": 2338707, "tid": 2338707, + "ts": 6197199100480.692, "dur": 121.389, + "args": { + "External id": 33872,"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": 2338707, "tid": 2338707, + "ts": 6197199100615.403, "dur": 43.001, + "args": { + "External id": 33873,"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": 2338707, "tid": 2338707, + "ts": 6197199100668.730, "dur": 51.587, + "args": { + "External id": 33874,"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": 2338707, "tid": 2338707, + "ts": 6197199100757.776, "dur": 32.491, + "args": { + "External id": 33875,"kernel_hash": "cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5", "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/jw/cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5.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": 2338707, "tid": 2338707, + "ts": 6197199100813.431, "dur": 22.465, + "args": { + "External id": 33876,"kernel_hash": "cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi", "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/xw/cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi.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": 2338707, "tid": 2338707, + "ts": 6197199100862.530, "dur": 157.919, + "args": { + "External id": 33877,"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": 2338707, "tid": 2338707, + "ts": 6197199100924.977, "dur": 13.096, + "args": { + "External id": 33878,"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": 2338707, "tid": 2338707, + "ts": 6197199100931.120, "dur": 5.965, + "args": { + "External id": 33879,"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": 2338707, "tid": 2338707, + "ts": 6197199100941.212, "dur": 4.589, + "args": { + "External id": 33880,"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": 2338707, "tid": 2338707, + "ts": 6197199100947.455, "dur": 1.178, + "args": { + "External id": 33881,"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": 2338707, "tid": 2338707, + "ts": 6197199100951.801, "dur": 6.786, + "args": { + "External id": 33882,"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": 2338707, "tid": 2338707, + "ts": 6197199101032.818, "dur": 103.729, + "args": { + "External id": 33883,"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": 2338707, "tid": 2338707, + "ts": 6197199101181.889, "dur": 35.171, + "args": { + "External id": 33884,"kernel_hash": "cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/dm/cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43.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": 2338707, "tid": 2338707, + "ts": 6197199101228.716, "dur": 52.118, + "args": { + "External id": 33885,"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": 2338707, "tid": 2338707, + "ts": 6197199101291.149, "dur": 39.390, + "args": { + "External id": 33886,"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": 2338707, "tid": 2338707, + "ts": 6197199101356.499, "dur": 31.196, + "args": { + "External id": 33887,"kernel_hash": "cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/b7/cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu.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": 2338707, "tid": 2338707, + "ts": 6197199101396.718, "dur": 41.208, + "args": { + "External id": 33888,"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": 2338707, "tid": 2338707, + "ts": 6197199101461.109, "dur": 20.380, + "args": { + "External id": 33889,"kernel_hash": "cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/gi/cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb.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": 2338707, "tid": 2338707, + "ts": 6197199101653.320, "dur": 114.806, + "args": { + "External id": 33890,"Record function id": 0, "Ev Idx": 17062 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6197199101859.737, "dur": 57.468, + "args": { + "External id": 33891,"Record function id": 0, "Ev Idx": 17063 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.7)", "pid": 2338707, "tid": 2338707, + "ts": 6197199101928.220, "dur": 36246.749, + "args": { + "External id": 33892,"Record function id": 0, "Ev Idx": 17064 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.7)", "pid": 2338707, "tid": 2338707, + "ts": 6197199101939.147, "dur": 1184.948, + "args": { + "External id": 33893,"Record function id": 0, "Ev Idx": 17065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6197199102040.684, "dur": 11.090, + "args": { + "External id": 33894,"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": 2338707, "tid": 2338707, + "ts": 6197199102106.862, "dur": 46.737, + "args": { + "External id": 33895,"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": 2338707, "tid": 2338707, + "ts": 6197199102114.196, "dur": 3.070, + "args": { + "External id": 33896,"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": 2338707, "tid": 2338707, + "ts": 6197199102122.905, "dur": 0.742, + "args": { + "External id": 33897,"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": 2338707, "tid": 2338707, + "ts": 6197199102125.460, "dur": 0.714, + "args": { + "External id": 33898,"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": 2338707, "tid": 2338707, + "ts": 6197199102127.819, "dur": 0.708, + "args": { + "External id": 33899,"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": 2338707, "tid": 2338707, + "ts": 6197199102132.438, "dur": 0.576, + "args": { + "External id": 33900,"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": 2338707, "tid": 2338707, + "ts": 6197199102134.488, "dur": 0.567, + "args": { + "External id": 33901,"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": 2338707, "tid": 2338707, + "ts": 6197199102137.019, "dur": 4.875, + "args": { + "External id": 33902,"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": 2338707, "tid": 2338707, + "ts": 6197199102143.400, "dur": 0.400, + "args": { + "External id": 33903,"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": 2338707, "tid": 2338707, + "ts": 6197199102145.739, "dur": 0.281, + "args": { + "External id": 33904,"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": 2338707, "tid": 2338707, + "ts": 6197199102167.684, "dur": 77.566, + "args": { + "External id": 33905,"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": 2338707, "tid": 2338707, + "ts": 6197199102297.928, "dur": 152.046, + "args": { + "External id": 33906,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2338707, + "ts": 6197199102314.095, "dur": 8.205, + "args": { + "External id": 33907,"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": 2338707, "tid": 2338707, + "ts": 6197199102328.938, "dur": 12.560, + "args": { + "External id": 33908,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2338707, + "ts": 6197199102334.586, "dur": 6.403, + "args": { + "External id": 33909,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2338707, + "ts": 6197199102338.523, "dur": 0.955, + "args": { + "External id": 33910,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197199102349.809, "dur": 33.710, + "args": { + "External id": 33911,"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": 2338707, "tid": 2338707, + "ts": 6197199102352.241, "dur": 0.621, + "args": { + "External id": 33912,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197199102354.898, "dur": 2.844, + "args": { + "External id": 33913,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2338707, + "ts": 6197199102359.264, "dur": 0.611, + "args": { + "External id": 33914,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2338707, + "ts": 6197199102361.698, "dur": 2.748, + "args": { + "External id": 33915,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2338707, + "ts": 6197199102368.295, "dur": 0.635, + "args": { + "External id": 33916,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2338707, + "ts": 6197199102370.730, "dur": 0.528, + "args": { + "External id": 33917,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2338707, + "ts": 6197199102372.900, "dur": 0.499, + "args": { + "External id": 33918,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2338707, + "ts": 6197199102377.015, "dur": 0.404, + "args": { + "External id": 33919,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2338707, + "ts": 6197199102378.611, "dur": 0.314, + "args": { + "External id": 33920,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2338707, + "ts": 6197199102401.275, "dur": 40.065, + "args": { + "External id": 33921,"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": 2338707, "tid": 2338707, + "ts": 6197199102515.463, "dur": 447.769, + "args": { + "External id": 33922,"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": 2338707, "tid": 2338707, + "ts": 6197199102550.323, "dur": 406.883, + "args": { + "External id": 33923,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2338707, + "ts": 6197199102563.240, "dur": 384.043, + "args": { + "External id": 33924,"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": 2338707, "tid": 2338707, + "ts": 6197199102993.683, "dur": 3.114, + "args": { + "External id": 33925,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.7)", "pid": 2338707, "tid": 2338707, + "ts": 6197199103153.200, "dur": 34758.486, + "args": { + "External id": 33926,"Record function id": 0, "Ev Idx": 17098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6197199103285.297, "dur": 8.112, + "args": { + "External id": 33927,"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": 2338707, "tid": 2338707, + "ts": 6197199103297.601, "dur": 1.126, + "args": { + "External id": 33928,"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": 2338707, "tid": 2338707, + "ts": 6197199103300.727, "dur": 3.395, + "args": { + "External id": 33929,"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": 2338707, "tid": 2338707, + "ts": 6197199103306.310, "dur": 1.017, + "args": { + "External id": 33930,"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": 2338707, "tid": 2338707, + "ts": 6197199103308.867, "dur": 1.181, + "args": { + "External id": 33931,"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": 2338707, "tid": 2338707, + "ts": 6197199103311.468, "dur": 1.333, + "args": { + "External id": 33932,"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": 2338707, "tid": 2338707, + "ts": 6197199103317.168, "dur": 0.820, + "args": { + "External id": 33933,"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": 2338707, "tid": 2338707, + "ts": 6197199103319.475, "dur": 2.637, + "args": { + "External id": 33934,"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": 2338707, "tid": 2338707, + "ts": 6197199103323.913, "dur": 0.900, + "args": { + "External id": 33935,"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": 2338707, "tid": 2338707, + "ts": 6197199103326.908, "dur": 0.790, + "args": { + "External id": 33936,"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": 2338707, "tid": 2338707, + "ts": 6197199103351.914, "dur": 34510.907, + "args": { + "External id": 33937,"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": 2338707, "tid": 2338707, + "ts": 6197199103371.048, "dur": 34482.221, + "args": { + "External id": 33938,"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": 2338707, "tid": 2338707, + "ts": 6197199103390.515, "dur": 19.338, + "args": { + "External id": 33939,"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": 2338707, "tid": 2338707, + "ts": 6197199103413.837, "dur": 34395.447, + "args": { + "External id": 33940,"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": 2338707, "tid": 2338707, + "ts": 6197199103416.862, "dur": 34391.704, + "args": { + "External id": 33941,"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": 2338707, "tid": 2338707, + "ts": 6197199103424.750, "dur": 8.803, + "args": { + "External id": 33942,"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": 2338707, "tid": 2338707, + "ts": 6197199103436.011, "dur": 34369.069, + "args": { + "External id": 33943,"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": 2338707, "tid": 2338707, + "ts": 6197199138104.100, "dur": 38.852, + "args": { + "External id": 33944,"Sequence number": 480010, "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": 2338707, "tid": 2338707, "ts": 6197199138104.100, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6197199138126.661, "dur": 10.262, + "args": { + "External id": 33945,"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": 2338707, "tid": 2338707, + "ts": 6197199138130.908, "dur": 5.580, + "args": { + "External id": 33946,"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": 2338707, "tid": 2338707, + "ts": 6197199138225.463, "dur": 89.714, + "args": { + "External id": 33947,"Record function id": 0, "Ev Idx": 17119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6197199138316.597, "dur": 1332.787, + "args": { + "External id": 33948,"Record function id": 0, "Ev Idx": 17120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197199138361.902, "dur": 1271.275, + "args": { + "External id": 33949,"Sequence number": 480011, "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": 2338707, "tid": 2338707, "ts": 6197199138361.902, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6197199138440.124, "dur": 58.757, + "args": { + "External id": 33950,"kernel_hash": "cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/du/cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs.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": 2338707, "tid": 2338707, + "ts": 6197199138514.092, "dur": 121.554, + "args": { + "External id": 33951,"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": 2338707, "tid": 2338707, + "ts": 6197199138649.814, "dur": 42.383, + "args": { + "External id": 33952,"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": 2338707, "tid": 2338707, + "ts": 6197199138720.876, "dur": 39.095, + "args": { + "External id": 33953,"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": 2338707, "tid": 2338707, + "ts": 6197199138793.965, "dur": 34.913, + "args": { + "External id": 33954,"kernel_hash": "cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5", "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/jw/cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5.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": 2338707, "tid": 2338707, + "ts": 6197199138851.864, "dur": 19.633, + "args": { + "External id": 33955,"kernel_hash": "cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi", "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/xw/cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi.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": 2338707, "tid": 2338707, + "ts": 6197199138897.545, "dur": 210.992, + "args": { + "External id": 33956,"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": 2338707, "tid": 2338707, + "ts": 6197199138966.124, "dur": 13.841, + "args": { + "External id": 33957,"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": 2338707, "tid": 2338707, + "ts": 6197199138972.357, "dur": 6.510, + "args": { + "External id": 33958,"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": 2338707, "tid": 2338707, + "ts": 6197199138983.247, "dur": 5.307, + "args": { + "External id": 33959,"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": 2338707, "tid": 2338707, + "ts": 6197199138990.041, "dur": 1.004, + "args": { + "External id": 33960,"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": 2338707, "tid": 2338707, + "ts": 6197199138996.762, "dur": 9.332, + "args": { + "External id": 33961,"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": 2338707, "tid": 2338707, + "ts": 6197199139124.465, "dur": 69.538, + "args": { + "External id": 33962,"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": 2338707, "tid": 2338707, + "ts": 6197199139235.816, "dur": 39.742, + "args": { + "External id": 33963,"kernel_hash": "cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/dm/cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43.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": 2338707, "tid": 2338707, + "ts": 6197199139287.636, "dur": 53.741, + "args": { + "External id": 33964,"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": 2338707, "tid": 2338707, + "ts": 6197199139352.029, "dur": 41.279, + "args": { + "External id": 33965,"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": 2338707, "tid": 2338707, + "ts": 6197199139424.843, "dur": 35.453, + "args": { + "External id": 33966,"kernel_hash": "cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/b7/cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu.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": 2338707, "tid": 2338707, + "ts": 6197199139466.694, "dur": 42.653, + "args": { + "External id": 33967,"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": 2338707, "tid": 2338707, + "ts": 6197199139529.466, "dur": 26.057, + "args": { + "External id": 33968,"kernel_hash": "cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/gi/cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb.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": 2338707, "tid": 2338707, + "ts": 6197199139747.605, "dur": 98.936, + "args": { + "External id": 33969,"Record function id": 0, "Ev Idx": 17141 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6197199139936.797, "dur": 55.239, + "args": { + "External id": 33970,"Record function id": 0, "Ev Idx": 17142 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.8)", "pid": 2338707, "tid": 2338707, + "ts": 6197199140002.740, "dur": 33091.006, + "args": { + "External id": 33971,"Record function id": 0, "Ev Idx": 17143 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.8)", "pid": 2338707, "tid": 2338707, + "ts": 6197199140014.820, "dur": 1185.904, + "args": { + "External id": 33972,"Record function id": 0, "Ev Idx": 17144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6197199140159.373, "dur": 11.933, + "args": { + "External id": 33973,"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": 2338707, "tid": 2338707, + "ts": 6197199140188.347, "dur": 45.555, + "args": { + "External id": 33974,"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": 2338707, "tid": 2338707, + "ts": 6197199140195.598, "dur": 2.568, + "args": { + "External id": 33975,"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": 2338707, "tid": 2338707, + "ts": 6197199140204.156, "dur": 0.517, + "args": { + "External id": 33976,"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": 2338707, "tid": 2338707, + "ts": 6197199140206.273, "dur": 0.494, + "args": { + "External id": 33977,"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": 2338707, "tid": 2338707, + "ts": 6197199140208.822, "dur": 0.530, + "args": { + "External id": 33978,"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": 2338707, "tid": 2338707, + "ts": 6197199140213.372, "dur": 0.402, + "args": { + "External id": 33979,"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": 2338707, "tid": 2338707, + "ts": 6197199140215.034, "dur": 0.568, + "args": { + "External id": 33980,"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": 2338707, "tid": 2338707, + "ts": 6197199140217.089, "dur": 5.228, + "args": { + "External id": 33981,"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": 2338707, "tid": 2338707, + "ts": 6197199140223.839, "dur": 0.523, + "args": { + "External id": 33982,"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": 2338707, "tid": 2338707, + "ts": 6197199140226.383, "dur": 0.293, + "args": { + "External id": 33983,"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": 2338707, "tid": 2338707, + "ts": 6197199140249.094, "dur": 70.494, + "args": { + "External id": 33984,"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": 2338707, "tid": 2338707, + "ts": 6197199140359.802, "dur": 147.507, + "args": { + "External id": 33985,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2338707, + "ts": 6197199140372.958, "dur": 4.729, + "args": { + "External id": 33986,"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": 2338707, "tid": 2338707, + "ts": 6197199140383.828, "dur": 16.390, + "args": { + "External id": 33987,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2338707, + "ts": 6197199140393.244, "dur": 6.465, + "args": { + "External id": 33988,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2338707, + "ts": 6197199140397.384, "dur": 0.751, + "args": { + "External id": 33989,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197199140407.366, "dur": 35.590, + "args": { + "External id": 33990,"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": 2338707, "tid": 2338707, + "ts": 6197199140410.574, "dur": 2.485, + "args": { + "External id": 33991,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197199140414.834, "dur": 0.582, + "args": { + "External id": 33992,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2338707, + "ts": 6197199140416.994, "dur": 0.561, + "args": { + "External id": 33993,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2338707, + "ts": 6197199140421.258, "dur": 3.039, + "args": { + "External id": 33994,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2338707, + "ts": 6197199140425.598, "dur": 0.520, + "args": { + "External id": 33995,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2338707, + "ts": 6197199140428.178, "dur": 0.480, + "args": { + "External id": 33996,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2338707, + "ts": 6197199140431.848, "dur": 0.512, + "args": { + "External id": 33997,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2338707, + "ts": 6197199140433.885, "dur": 0.507, + "args": { + "External id": 33998,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2338707, + "ts": 6197199140435.738, "dur": 2.560, + "args": { + "External id": 33999,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2338707, + "ts": 6197199140455.742, "dur": 42.362, + "args": { + "External id": 34000,"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": 2338707, "tid": 2338707, + "ts": 6197199140571.229, "dur": 458.210, + "args": { + "External id": 34001,"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": 2338707, "tid": 2338707, + "ts": 6197199140607.571, "dur": 411.928, + "args": { + "External id": 34002,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2338707, + "ts": 6197199140620.090, "dur": 391.831, + "args": { + "External id": 34003,"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": 2338707, "tid": 2338707, + "ts": 6197199141101.605, "dur": 4.939, + "args": { + "External id": 34004,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.8)", "pid": 2338707, "tid": 2338707, + "ts": 6197199141227.847, "dur": 31607.731, + "args": { + "External id": 34005,"Record function id": 0, "Ev Idx": 17177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6197199141350.471, "dur": 7.903, + "args": { + "External id": 34006,"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": 2338707, "tid": 2338707, + "ts": 6197199141362.333, "dur": 1.217, + "args": { + "External id": 34007,"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": 2338707, "tid": 2338707, + "ts": 6197199141365.301, "dur": 4.074, + "args": { + "External id": 34008,"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": 2338707, "tid": 2338707, + "ts": 6197199141371.446, "dur": 1.361, + "args": { + "External id": 34009,"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": 2338707, "tid": 2338707, + "ts": 6197199141374.422, "dur": 1.042, + "args": { + "External id": 34010,"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": 2338707, "tid": 2338707, + "ts": 6197199141376.966, "dur": 1.005, + "args": { + "External id": 34011,"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": 2338707, "tid": 2338707, + "ts": 6197199141382.096, "dur": 1.103, + "args": { + "External id": 34012,"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": 2338707, "tid": 2338707, + "ts": 6197199141385.271, "dur": 2.498, + "args": { + "External id": 34013,"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": 2338707, "tid": 2338707, + "ts": 6197199141389.243, "dur": 0.909, + "args": { + "External id": 34014,"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": 2338707, "tid": 2338707, + "ts": 6197199141392.035, "dur": 0.750, + "args": { + "External id": 34015,"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": 2338707, "tid": 2338707, + "ts": 6197199141416.781, "dur": 31369.630, + "args": { + "External id": 34016,"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": 2338707, "tid": 2338707, + "ts": 6197199141434.891, "dur": 31341.567, + "args": { + "External id": 34017,"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": 2338707, "tid": 2338707, + "ts": 6197199141454.370, "dur": 20.244, + "args": { + "External id": 34018,"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": 2338707, "tid": 2338707, + "ts": 6197199141478.657, "dur": 31255.247, + "args": { + "External id": 34019,"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": 2338707, "tid": 2338707, + "ts": 6197199141481.626, "dur": 31251.470, + "args": { + "External id": 34020,"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": 2338707, "tid": 2338707, + "ts": 6197199141488.387, "dur": 6.315, + "args": { + "External id": 34021,"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": 2338707, "tid": 2338707, + "ts": 6197199141496.860, "dur": 31232.302, + "args": { + "External id": 34022,"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": 2338707, "tid": 2338707, + "ts": 6197199172997.644, "dur": 34.860, + "args": { + "External id": 34023,"Sequence number": 480012, "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": 2338707, "tid": 2338707, "ts": 6197199172997.644, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6197199173017.184, "dur": 9.973, + "args": { + "External id": 34024,"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": 2338707, "tid": 2338707, + "ts": 6197199173021.307, "dur": 5.593, + "args": { + "External id": 34025,"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": 2338707, "tid": 2338707, + "ts": 6197199173142.870, "dur": 92.624, + "args": { + "External id": 34026,"Record function id": 0, "Ev Idx": 17198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6197199173236.957, "dur": 1340.415, + "args": { + "External id": 34027,"Record function id": 0, "Ev Idx": 17199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197199173283.916, "dur": 1276.842, + "args": { + "External id": 34028,"Sequence number": 480013, "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": 2338707, "tid": 2338707, "ts": 6197199173283.916, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6197199173365.560, "dur": 58.305, + "args": { + "External id": 34029,"kernel_hash": "cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/du/cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs.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": 2338707, "tid": 2338707, + "ts": 6197199173438.884, "dur": 124.351, + "args": { + "External id": 34030,"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": 2338707, "tid": 2338707, + "ts": 6197199173579.826, "dur": 42.728, + "args": { + "External id": 34031,"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": 2338707, "tid": 2338707, + "ts": 6197199173632.610, "dur": 34.606, + "args": { + "External id": 34032,"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": 2338707, "tid": 2338707, + "ts": 6197199173697.629, "dur": 50.509, + "args": { + "External id": 34033,"kernel_hash": "cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5", "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/jw/cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5.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": 2338707, "tid": 2338707, + "ts": 6197199173777.058, "dur": 22.042, + "args": { + "External id": 34034,"kernel_hash": "cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi", "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/xw/cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi.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": 2338707, "tid": 2338707, + "ts": 6197199173826.799, "dur": 159.012, + "args": { + "External id": 34035,"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": 2338707, "tid": 2338707, + "ts": 6197199173890.127, "dur": 13.402, + "args": { + "External id": 34036,"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": 2338707, "tid": 2338707, + "ts": 6197199173896.160, "dur": 6.309, + "args": { + "External id": 34037,"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": 2338707, "tid": 2338707, + "ts": 6197199173906.887, "dur": 5.069, + "args": { + "External id": 34038,"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": 2338707, "tid": 2338707, + "ts": 6197199173913.458, "dur": 1.120, + "args": { + "External id": 34039,"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": 2338707, "tid": 2338707, + "ts": 6197199173917.771, "dur": 6.649, + "args": { + "External id": 34040,"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": 2338707, "tid": 2338707, + "ts": 6197199173999.358, "dur": 111.041, + "args": { + "External id": 34041,"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": 2338707, "tid": 2338707, + "ts": 6197199174157.713, "dur": 40.150, + "args": { + "External id": 34042,"kernel_hash": "cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/dm/cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43.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": 2338707, "tid": 2338707, + "ts": 6197199174210.160, "dur": 56.592, + "args": { + "External id": 34043,"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": 2338707, "tid": 2338707, + "ts": 6197199174277.901, "dur": 39.908, + "args": { + "External id": 34044,"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": 2338707, "tid": 2338707, + "ts": 6197199174345.778, "dur": 32.441, + "args": { + "External id": 34045,"kernel_hash": "cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/b7/cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu.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": 2338707, "tid": 2338707, + "ts": 6197199174387.389, "dur": 46.379, + "args": { + "External id": 34046,"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": 2338707, "tid": 2338707, + "ts": 6197199174458.810, "dur": 21.307, + "args": { + "External id": 34047,"kernel_hash": "cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/gi/cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb.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": 2338707, "tid": 2338707, + "ts": 6197199174657.007, "dur": 115.019, + "args": { + "External id": 34048,"Record function id": 0, "Ev Idx": 17220 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6197199174861.559, "dur": 58.423, + "args": { + "External id": 34049,"Record function id": 0, "Ev Idx": 17221 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.9)", "pid": 2338707, "tid": 2338707, + "ts": 6197199174931.197, "dur": 32715.410, + "args": { + "External id": 34050,"Record function id": 0, "Ev Idx": 17222 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.9)", "pid": 2338707, "tid": 2338707, + "ts": 6197199174941.985, "dur": 1223.073, + "args": { + "External id": 34051,"Record function id": 0, "Ev Idx": 17223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6197199175046.650, "dur": 49.938, + "args": { + "External id": 34052,"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": 2338707, "tid": 2338707, + "ts": 6197199175115.328, "dur": 45.102, + "args": { + "External id": 34053,"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": 2338707, "tid": 2338707, + "ts": 6197199175122.687, "dur": 2.930, + "args": { + "External id": 34054,"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": 2338707, "tid": 2338707, + "ts": 6197199175130.800, "dur": 0.357, + "args": { + "External id": 34055,"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": 2338707, "tid": 2338707, + "ts": 6197199175133.182, "dur": 0.683, + "args": { + "External id": 34056,"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": 2338707, "tid": 2338707, + "ts": 6197199175135.071, "dur": 0.752, + "args": { + "External id": 34057,"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": 2338707, "tid": 2338707, + "ts": 6197199175139.665, "dur": 0.594, + "args": { + "External id": 34058,"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": 2338707, "tid": 2338707, + "ts": 6197199175141.702, "dur": 0.619, + "args": { + "External id": 34059,"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": 2338707, "tid": 2338707, + "ts": 6197199175144.088, "dur": 5.115, + "args": { + "External id": 34060,"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": 2338707, "tid": 2338707, + "ts": 6197199175150.621, "dur": 0.595, + "args": { + "External id": 34061,"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": 2338707, "tid": 2338707, + "ts": 6197199175153.046, "dur": 0.522, + "args": { + "External id": 34062,"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": 2338707, "tid": 2338707, + "ts": 6197199175175.454, "dur": 71.525, + "args": { + "External id": 34063,"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": 2338707, "tid": 2338707, + "ts": 6197199175291.708, "dur": 148.325, + "args": { + "External id": 34064,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2338707, + "ts": 6197199175305.548, "dur": 5.360, + "args": { + "External id": 34065,"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": 2338707, "tid": 2338707, + "ts": 6197199175317.046, "dur": 14.975, + "args": { + "External id": 34066,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2338707, + "ts": 6197199175325.351, "dur": 6.151, + "args": { + "External id": 34067,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2338707, + "ts": 6197199175329.248, "dur": 0.775, + "args": { + "External id": 34068,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197199175339.681, "dur": 34.838, + "args": { + "External id": 34069,"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": 2338707, "tid": 2338707, + "ts": 6197199175342.390, "dur": 2.767, + "args": { + "External id": 34070,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197199175347.226, "dur": 0.329, + "args": { + "External id": 34071,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2338707, + "ts": 6197199175349.509, "dur": 0.470, + "args": { + "External id": 34072,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2338707, + "ts": 6197199175353.579, "dur": 2.702, + "args": { + "External id": 34073,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2338707, + "ts": 6197199175358.127, "dur": 0.391, + "args": { + "External id": 34074,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2338707, + "ts": 6197199175359.989, "dur": 0.470, + "args": { + "External id": 34075,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2338707, + "ts": 6197199175364.304, "dur": 0.474, + "args": { + "External id": 34076,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2338707, + "ts": 6197199175366.072, "dur": 0.481, + "args": { + "External id": 34077,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2338707, + "ts": 6197199175368.077, "dur": 2.074, + "args": { + "External id": 34078,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2338707, + "ts": 6197199175391.008, "dur": 39.277, + "args": { + "External id": 34079,"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": 2338707, "tid": 2338707, + "ts": 6197199175506.273, "dur": 490.191, + "args": { + "External id": 34080,"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": 2338707, "tid": 2338707, + "ts": 6197199175542.898, "dur": 446.343, + "args": { + "External id": 34081,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2338707, + "ts": 6197199175555.316, "dur": 426.829, + "args": { + "External id": 34082,"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": 2338707, "tid": 2338707, + "ts": 6197199176029.915, "dur": 3.244, + "args": { + "External id": 34083,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.9)", "pid": 2338707, "tid": 2338707, + "ts": 6197199176193.330, "dur": 31227.173, + "args": { + "External id": 34084,"Record function id": 0, "Ev Idx": 17256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6197199176316.923, "dur": 8.200, + "args": { + "External id": 34085,"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": 2338707, "tid": 2338707, + "ts": 6197199176329.185, "dur": 1.342, + "args": { + "External id": 34086,"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": 2338707, "tid": 2338707, + "ts": 6197199176336.082, "dur": 3.449, + "args": { + "External id": 34087,"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": 2338707, "tid": 2338707, + "ts": 6197199176341.899, "dur": 1.201, + "args": { + "External id": 34088,"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": 2338707, "tid": 2338707, + "ts": 6197199176344.643, "dur": 1.073, + "args": { + "External id": 34089,"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": 2338707, "tid": 2338707, + "ts": 6197199176347.199, "dur": 0.965, + "args": { + "External id": 34090,"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": 2338707, "tid": 2338707, + "ts": 6197199176352.440, "dur": 0.838, + "args": { + "External id": 34091,"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": 2338707, "tid": 2338707, + "ts": 6197199176354.996, "dur": 2.448, + "args": { + "External id": 34092,"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": 2338707, "tid": 2338707, + "ts": 6197199176359.064, "dur": 0.878, + "args": { + "External id": 34093,"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": 2338707, "tid": 2338707, + "ts": 6197199176361.804, "dur": 0.903, + "args": { + "External id": 34094,"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": 2338707, "tid": 2338707, + "ts": 6197199176386.531, "dur": 30984.512, + "args": { + "External id": 34095,"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": 2338707, "tid": 2338707, + "ts": 6197199176408.489, "dur": 30952.653, + "args": { + "External id": 34096,"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": 2338707, "tid": 2338707, + "ts": 6197199176427.609, "dur": 24.789, + "args": { + "External id": 34097,"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": 2338707, "tid": 2338707, + "ts": 6197199176456.530, "dur": 30861.953, + "args": { + "External id": 34098,"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": 2338707, "tid": 2338707, + "ts": 6197199176459.877, "dur": 30857.873, + "args": { + "External id": 34099,"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": 2338707, "tid": 2338707, + "ts": 6197199176468.419, "dur": 6.633, + "args": { + "External id": 34100,"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": 2338707, "tid": 2338707, + "ts": 6197199176477.166, "dur": 30836.581, + "args": { + "External id": 34101,"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": 2338707, "tid": 2338707, + "ts": 6197199207582.851, "dur": 34.782, + "args": { + "External id": 34102,"Sequence number": 480014, "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": 2338707, "tid": 2338707, "ts": 6197199207582.851, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6197199207602.410, "dur": 9.899, + "args": { + "External id": 34103,"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": 2338707, "tid": 2338707, + "ts": 6197199207606.629, "dur": 5.480, + "args": { + "External id": 34104,"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": 2338707, "tid": 2338707, + "ts": 6197199207696.022, "dur": 100.886, + "args": { + "External id": 34105,"Record function id": 0, "Ev Idx": 17277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6197199207800.082, "dur": 1365.244, + "args": { + "External id": 34106,"Record function id": 0, "Ev Idx": 17278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197199207848.086, "dur": 1299.536, + "args": { + "External id": 34107,"Sequence number": 480015, "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": 2338707, "tid": 2338707, "ts": 6197199207848.086, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6197199207926.994, "dur": 62.646, + "args": { + "External id": 34108,"kernel_hash": "cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/du/cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs.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": 2338707, "tid": 2338707, + "ts": 6197199208004.332, "dur": 156.699, + "args": { + "External id": 34109,"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": 2338707, "tid": 2338707, + "ts": 6197199208183.392, "dur": 47.635, + "args": { + "External id": 34110,"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": 2338707, "tid": 2338707, + "ts": 6197199208241.872, "dur": 33.748, + "args": { + "External id": 34111,"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": 2338707, "tid": 2338707, + "ts": 6197199208307.101, "dur": 36.139, + "args": { + "External id": 34112,"kernel_hash": "cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5", "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/jw/cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5.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": 2338707, "tid": 2338707, + "ts": 6197199208367.053, "dur": 20.500, + "args": { + "External id": 34113,"kernel_hash": "cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi", "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/xw/cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi.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": 2338707, "tid": 2338707, + "ts": 6197199208417.312, "dur": 162.687, + "args": { + "External id": 34114,"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": 2338707, "tid": 2338707, + "ts": 6197199208479.632, "dur": 12.931, + "args": { + "External id": 34115,"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": 2338707, "tid": 2338707, + "ts": 6197199208485.523, "dur": 6.270, + "args": { + "External id": 34116,"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": 2338707, "tid": 2338707, + "ts": 6197199208495.929, "dur": 5.208, + "args": { + "External id": 34117,"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": 2338707, "tid": 2338707, + "ts": 6197199208503.116, "dur": 1.315, + "args": { + "External id": 34118,"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": 2338707, "tid": 2338707, + "ts": 6197199208507.196, "dur": 7.510, + "args": { + "External id": 34119,"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": 2338707, "tid": 2338707, + "ts": 6197199208595.757, "dur": 63.540, + "args": { + "External id": 34120,"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": 2338707, "tid": 2338707, + "ts": 6197199208720.449, "dur": 39.183, + "args": { + "External id": 34121,"kernel_hash": "cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/dm/cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43.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": 2338707, "tid": 2338707, + "ts": 6197199208774.031, "dur": 54.741, + "args": { + "External id": 34122,"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": 2338707, "tid": 2338707, + "ts": 6197199208838.677, "dur": 40.148, + "args": { + "External id": 34123,"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": 2338707, "tid": 2338707, + "ts": 6197199208907.793, "dur": 30.779, + "args": { + "External id": 34124,"kernel_hash": "cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/b7/cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu.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": 2338707, "tid": 2338707, + "ts": 6197199208945.930, "dur": 39.669, + "args": { + "External id": 34125,"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": 2338707, "tid": 2338707, + "ts": 6197199209007.787, "dur": 21.045, + "args": { + "External id": 34126,"kernel_hash": "cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/gi/cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb.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": 2338707, "tid": 2338707, + "ts": 6197199209245.617, "dur": 106.095, + "args": { + "External id": 34127,"Record function id": 0, "Ev Idx": 17299 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6197199209442.857, "dur": 54.201, + "args": { + "External id": 34128,"Record function id": 0, "Ev Idx": 17300 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.10)", "pid": 2338707, "tid": 2338707, + "ts": 6197199209507.350, "dur": 30268.475, + "args": { + "External id": 34129,"Record function id": 0, "Ev Idx": 17301 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.10)", "pid": 2338707, "tid": 2338707, + "ts": 6197199209517.111, "dur": 1107.064, + "args": { + "External id": 34130,"Record function id": 0, "Ev Idx": 17302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6197199209618.676, "dur": 10.519, + "args": { + "External id": 34131,"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": 2338707, "tid": 2338707, + "ts": 6197199209645.184, "dur": 42.846, + "args": { + "External id": 34132,"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": 2338707, "tid": 2338707, + "ts": 6197199209652.164, "dur": 2.538, + "args": { + "External id": 34133,"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": 2338707, "tid": 2338707, + "ts": 6197199209659.795, "dur": 0.809, + "args": { + "External id": 34134,"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": 2338707, "tid": 2338707, + "ts": 6197199209661.969, "dur": 0.523, + "args": { + "External id": 34135,"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": 2338707, "tid": 2338707, + "ts": 6197199209664.076, "dur": 0.519, + "args": { + "External id": 34136,"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": 2338707, "tid": 2338707, + "ts": 6197199209668.830, "dur": 0.648, + "args": { + "External id": 34137,"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": 2338707, "tid": 2338707, + "ts": 6197199209670.851, "dur": 0.785, + "args": { + "External id": 34138,"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": 2338707, "tid": 2338707, + "ts": 6197199209673.404, "dur": 4.428, + "args": { + "External id": 34139,"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": 2338707, "tid": 2338707, + "ts": 6197199209679.142, "dur": 0.494, + "args": { + "External id": 34140,"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": 2338707, "tid": 2338707, + "ts": 6197199209680.794, "dur": 0.502, + "args": { + "External id": 34141,"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": 2338707, "tid": 2338707, + "ts": 6197199209718.361, "dur": 69.103, + "args": { + "External id": 34142,"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": 2338707, "tid": 2338707, + "ts": 6197199209829.509, "dur": 145.605, + "args": { + "External id": 34143,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2338707, + "ts": 6197199209843.030, "dur": 6.234, + "args": { + "External id": 34144,"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": 2338707, "tid": 2338707, + "ts": 6197199209855.575, "dur": 15.644, + "args": { + "External id": 34145,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2338707, + "ts": 6197199209863.414, "dur": 7.295, + "args": { + "External id": 34146,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2338707, + "ts": 6197199209868.025, "dur": 0.747, + "args": { + "External id": 34147,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197199209879.339, "dur": 34.576, + "args": { + "External id": 34148,"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": 2338707, "tid": 2338707, + "ts": 6197199209881.733, "dur": 2.507, + "args": { + "External id": 34149,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197199209886.117, "dur": 0.310, + "args": { + "External id": 34150,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2338707, + "ts": 6197199209887.620, "dur": 0.520, + "args": { + "External id": 34151,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2338707, + "ts": 6197199209892.114, "dur": 2.848, + "args": { + "External id": 34152,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2338707, + "ts": 6197199209896.471, "dur": 0.620, + "args": { + "External id": 34153,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2338707, + "ts": 6197199209899.111, "dur": 0.424, + "args": { + "External id": 34154,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2338707, + "ts": 6197199209902.518, "dur": 0.560, + "args": { + "External id": 34155,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2338707, + "ts": 6197199209904.926, "dur": 0.384, + "args": { + "External id": 34156,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2338707, + "ts": 6197199209906.699, "dur": 2.834, + "args": { + "External id": 34157,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2338707, + "ts": 6197199209928.083, "dur": 37.575, + "args": { + "External id": 34158,"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": 2338707, "tid": 2338707, + "ts": 6197199210037.567, "dur": 466.562, + "args": { + "External id": 34159,"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": 2338707, "tid": 2338707, + "ts": 6197199210112.980, "dur": 385.039, + "args": { + "External id": 34160,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2338707, + "ts": 6197199210128.396, "dur": 362.650, + "args": { + "External id": 34161,"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": 2338707, "tid": 2338707, + "ts": 6197199210534.146, "dur": 2.607, + "args": { + "External id": 34162,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.10)", "pid": 2338707, "tid": 2338707, + "ts": 6197199210649.749, "dur": 28866.254, + "args": { + "External id": 34163,"Record function id": 0, "Ev Idx": 17335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6197199210800.930, "dur": 7.939, + "args": { + "External id": 34164,"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": 2338707, "tid": 2338707, + "ts": 6197199210813.188, "dur": 1.438, + "args": { + "External id": 34165,"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": 2338707, "tid": 2338707, + "ts": 6197199210816.739, "dur": 3.750, + "args": { + "External id": 34166,"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": 2338707, "tid": 2338707, + "ts": 6197199210822.545, "dur": 1.024, + "args": { + "External id": 34167,"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": 2338707, "tid": 2338707, + "ts": 6197199210825.114, "dur": 0.970, + "args": { + "External id": 34168,"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": 2338707, "tid": 2338707, + "ts": 6197199210827.685, "dur": 0.901, + "args": { + "External id": 34169,"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": 2338707, "tid": 2338707, + "ts": 6197199210832.775, "dur": 1.003, + "args": { + "External id": 34170,"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": 2338707, "tid": 2338707, + "ts": 6197199210835.489, "dur": 2.409, + "args": { + "External id": 34171,"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": 2338707, "tid": 2338707, + "ts": 6197199210839.279, "dur": 1.110, + "args": { + "External id": 34172,"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": 2338707, "tid": 2338707, + "ts": 6197199210842.188, "dur": 0.927, + "args": { + "External id": 34173,"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": 2338707, "tid": 2338707, + "ts": 6197199210868.407, "dur": 28597.070, + "args": { + "External id": 34174,"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": 2338707, "tid": 2338707, + "ts": 6197199210886.748, "dur": 28569.042, + "args": { + "External id": 34175,"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": 2338707, "tid": 2338707, + "ts": 6197199210907.080, "dur": 19.212, + "args": { + "External id": 34176,"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": 2338707, "tid": 2338707, + "ts": 6197199210930.310, "dur": 28482.338, + "args": { + "External id": 34177,"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": 2338707, "tid": 2338707, + "ts": 6197199210933.246, "dur": 28478.819, + "args": { + "External id": 34178,"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": 2338707, "tid": 2338707, + "ts": 6197199210947.674, "dur": 6.781, + "args": { + "External id": 34179,"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": 2338707, "tid": 2338707, + "ts": 6197199210956.391, "dur": 28451.845, + "args": { + "External id": 34180,"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": 2338707, "tid": 2338707, + "ts": 6197199239685.285, "dur": 58.772, + "args": { + "External id": 34181,"Sequence number": 480016, "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": 2338707, "tid": 2338707, "ts": 6197199239685.285, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6197199239727.786, "dur": 10.171, + "args": { + "External id": 34182,"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": 2338707, "tid": 2338707, + "ts": 6197199239732.124, "dur": 5.397, + "args": { + "External id": 34183,"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": 2338707, "tid": 2338707, + "ts": 6197199239828.089, "dur": 89.230, + "args": { + "External id": 34184,"Record function id": 0, "Ev Idx": 17356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6197199239919.231, "dur": 1353.738, + "args": { + "External id": 34185,"Record function id": 0, "Ev Idx": 17357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197199239967.611, "dur": 1288.823, + "args": { + "External id": 34186,"Sequence number": 480017, "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": 2338707, "tid": 2338707, "ts": 6197199239967.611, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6197199240048.983, "dur": 93.513, + "args": { + "External id": 34187,"kernel_hash": "cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/du/cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs.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": 2338707, "tid": 2338707, + "ts": 6197199240161.767, "dur": 119.128, + "args": { + "External id": 34188,"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": 2338707, "tid": 2338707, + "ts": 6197199240296.815, "dur": 42.546, + "args": { + "External id": 34189,"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": 2338707, "tid": 2338707, + "ts": 6197199240350.652, "dur": 39.273, + "args": { + "External id": 34190,"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": 2338707, "tid": 2338707, + "ts": 6197199240423.816, "dur": 31.566, + "args": { + "External id": 34191,"kernel_hash": "cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5", "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/jw/cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5.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": 2338707, "tid": 2338707, + "ts": 6197199240478.807, "dur": 19.134, + "args": { + "External id": 34192,"kernel_hash": "cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi", "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/xw/cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi.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": 2338707, "tid": 2338707, + "ts": 6197199240525.403, "dur": 154.541, + "args": { + "External id": 34193,"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": 2338707, "tid": 2338707, + "ts": 6197199240585.110, "dur": 13.906, + "args": { + "External id": 34194,"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": 2338707, "tid": 2338707, + "ts": 6197199240591.357, "dur": 6.784, + "args": { + "External id": 34195,"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": 2338707, "tid": 2338707, + "ts": 6197199240601.970, "dur": 5.339, + "args": { + "External id": 34196,"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": 2338707, "tid": 2338707, + "ts": 6197199240608.707, "dur": 1.389, + "args": { + "External id": 34197,"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": 2338707, "tid": 2338707, + "ts": 6197199240613.116, "dur": 6.717, + "args": { + "External id": 34198,"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": 2338707, "tid": 2338707, + "ts": 6197199240693.376, "dur": 84.732, + "args": { + "External id": 34199,"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": 2338707, "tid": 2338707, + "ts": 6197199240823.190, "dur": 37.302, + "args": { + "External id": 34200,"kernel_hash": "cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/dm/cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43.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": 2338707, "tid": 2338707, + "ts": 6197199240871.534, "dur": 51.961, + "args": { + "External id": 34201,"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": 2338707, "tid": 2338707, + "ts": 6197199240934.010, "dur": 39.970, + "args": { + "External id": 34202,"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": 2338707, "tid": 2338707, + "ts": 6197199241001.701, "dur": 31.205, + "args": { + "External id": 34203,"kernel_hash": "cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/b7/cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu.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": 2338707, "tid": 2338707, + "ts": 6197199241042.364, "dur": 82.596, + "args": { + "External id": 34204,"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": 2338707, "tid": 2338707, + "ts": 6197199241152.206, "dur": 21.765, + "args": { + "External id": 34205,"kernel_hash": "cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/gi/cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb.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": 2338707, "tid": 2338707, + "ts": 6197199241351.049, "dur": 100.424, + "args": { + "External id": 34206,"Record function id": 0, "Ev Idx": 17378 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6197199241544.722, "dur": 55.866, + "args": { + "External id": 34207,"Record function id": 0, "Ev Idx": 17379 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.11)", "pid": 2338707, "tid": 2338707, + "ts": 6197199241610.914, "dur": 32801.576, + "args": { + "External id": 34208,"Record function id": 0, "Ev Idx": 17380 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.11)", "pid": 2338707, "tid": 2338707, + "ts": 6197199241621.392, "dur": 1131.880, + "args": { + "External id": 34209,"Record function id": 0, "Ev Idx": 17381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6197199241744.624, "dur": 12.586, + "args": { + "External id": 34210,"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": 2338707, "tid": 2338707, + "ts": 6197199241772.693, "dur": 44.630, + "args": { + "External id": 34211,"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": 2338707, "tid": 2338707, + "ts": 6197199241779.832, "dur": 3.047, + "args": { + "External id": 34212,"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": 2338707, "tid": 2338707, + "ts": 6197199241787.941, "dur": 0.400, + "args": { + "External id": 34213,"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": 2338707, "tid": 2338707, + "ts": 6197199241790.100, "dur": 0.502, + "args": { + "External id": 34214,"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": 2338707, "tid": 2338707, + "ts": 6197199241792.002, "dur": 0.700, + "args": { + "External id": 34215,"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": 2338707, "tid": 2338707, + "ts": 6197199241796.444, "dur": 0.707, + "args": { + "External id": 34216,"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": 2338707, "tid": 2338707, + "ts": 6197199241798.602, "dur": 0.809, + "args": { + "External id": 34217,"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": 2338707, "tid": 2338707, + "ts": 6197199241801.068, "dur": 5.224, + "args": { + "External id": 34218,"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": 2338707, "tid": 2338707, + "ts": 6197199241807.476, "dur": 0.741, + "args": { + "External id": 34219,"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": 2338707, "tid": 2338707, + "ts": 6197199241809.698, "dur": 0.671, + "args": { + "External id": 34220,"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": 2338707, "tid": 2338707, + "ts": 6197199241832.210, "dur": 65.597, + "args": { + "External id": 34221,"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": 2338707, "tid": 2338707, + "ts": 6197199241937.842, "dur": 202.652, + "args": { + "External id": 34222,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2338707, + "ts": 6197199241954.652, "dur": 4.783, + "args": { + "External id": 34223,"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": 2338707, "tid": 2338707, + "ts": 6197199241965.523, "dur": 14.962, + "args": { + "External id": 34224,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2338707, + "ts": 6197199241973.789, "dur": 6.181, + "args": { + "External id": 34225,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2338707, + "ts": 6197199241977.726, "dur": 0.799, + "args": { + "External id": 34226,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197199241988.232, "dur": 39.275, + "args": { + "External id": 34227,"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": 2338707, "tid": 2338707, + "ts": 6197199241990.677, "dur": 2.779, + "args": { + "External id": 34228,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197199241995.187, "dur": 0.445, + "args": { + "External id": 34229,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2338707, + "ts": 6197199241997.417, "dur": 4.260, + "args": { + "External id": 34230,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2338707, + "ts": 6197199242005.464, "dur": 2.914, + "args": { + "External id": 34231,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2338707, + "ts": 6197199242010.298, "dur": 0.444, + "args": { + "External id": 34232,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2338707, + "ts": 6197199242011.947, "dur": 0.435, + "args": { + "External id": 34233,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2338707, + "ts": 6197199242016.362, "dur": 0.390, + "args": { + "External id": 34234,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2338707, + "ts": 6197199242018.473, "dur": 0.340, + "args": { + "External id": 34235,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2338707, + "ts": 6197199242020.515, "dur": 2.817, + "args": { + "External id": 34236,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2338707, + "ts": 6197199242042.776, "dur": 85.296, + "args": { + "External id": 34237,"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": 2338707, "tid": 2338707, + "ts": 6197199242207.604, "dur": 418.649, + "args": { + "External id": 34238,"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": 2338707, "tid": 2338707, + "ts": 6197199242244.258, "dur": 376.192, + "args": { + "External id": 34239,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2338707, + "ts": 6197199242256.625, "dur": 356.770, + "args": { + "External id": 34240,"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": 2338707, "tid": 2338707, + "ts": 6197199242652.158, "dur": 2.864, + "args": { + "External id": 34241,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.11)", "pid": 2338707, "tid": 2338707, + "ts": 6197199242780.968, "dur": 31406.948, + "args": { + "External id": 34242,"Record function id": 0, "Ev Idx": 17414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6197199242900.788, "dur": 8.054, + "args": { + "External id": 34243,"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": 2338707, "tid": 2338707, + "ts": 6197199242912.802, "dur": 1.540, + "args": { + "External id": 34244,"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": 2338707, "tid": 2338707, + "ts": 6197199242916.216, "dur": 3.686, + "args": { + "External id": 34245,"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": 2338707, "tid": 2338707, + "ts": 6197199242921.968, "dur": 0.901, + "args": { + "External id": 34246,"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": 2338707, "tid": 2338707, + "ts": 6197199242924.378, "dur": 0.912, + "args": { + "External id": 34247,"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": 2338707, "tid": 2338707, + "ts": 6197199242926.725, "dur": 0.786, + "args": { + "External id": 34248,"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": 2338707, "tid": 2338707, + "ts": 6197199242931.467, "dur": 0.978, + "args": { + "External id": 34249,"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": 2338707, "tid": 2338707, + "ts": 6197199242934.077, "dur": 2.430, + "args": { + "External id": 34250,"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": 2338707, "tid": 2338707, + "ts": 6197199242938.317, "dur": 1.157, + "args": { + "External id": 34251,"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": 2338707, "tid": 2338707, + "ts": 6197199242941.356, "dur": 0.928, + "args": { + "External id": 34252,"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": 2338707, "tid": 2338707, + "ts": 6197199242964.768, "dur": 31172.300, + "args": { + "External id": 34253,"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": 2338707, "tid": 2338707, + "ts": 6197199242983.116, "dur": 31144.306, + "args": { + "External id": 34254,"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": 2338707, "tid": 2338707, + "ts": 6197199243001.468, "dur": 19.738, + "args": { + "External id": 34255,"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": 2338707, "tid": 2338707, + "ts": 6197199243025.503, "dur": 31059.330, + "args": { + "External id": 34256,"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": 2338707, "tid": 2338707, + "ts": 6197199243028.683, "dur": 31055.531, + "args": { + "External id": 34257,"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": 2338707, "tid": 2338707, + "ts": 6197199243037.113, "dur": 6.869, + "args": { + "External id": 34258,"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": 2338707, "tid": 2338707, + "ts": 6197199243046.170, "dur": 31034.052, + "args": { + "External id": 34259,"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": 2338707, "tid": 2338707, + "ts": 6197199274348.638, "dur": 36.067, + "args": { + "External id": 34260,"Sequence number": 480018, "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": 2338707, "tid": 2338707, "ts": 6197199274348.638, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6197199274368.945, "dur": 9.833, + "args": { + "External id": 34261,"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": 2338707, "tid": 2338707, + "ts": 6197199274373.585, "dur": 5.001, + "args": { + "External id": 34262,"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": 2338707, "tid": 2338707, + "ts": 6197199274460.592, "dur": 88.362, + "args": { + "External id": 34263,"Record function id": 0, "Ev Idx": 17435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6197199274550.680, "dur": 1343.157, + "args": { + "External id": 34264,"Record function id": 0, "Ev Idx": 17436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197199274598.066, "dur": 1279.991, + "args": { + "External id": 34265,"Sequence number": 480019, "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": 2338707, "tid": 2338707, "ts": 6197199274598.066, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6197199274674.736, "dur": 77.009, + "args": { + "External id": 34266,"kernel_hash": "cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/du/cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs.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": 2338707, "tid": 2338707, + "ts": 6197199274770.446, "dur": 124.359, + "args": { + "External id": 34267,"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": 2338707, "tid": 2338707, + "ts": 6197199274911.880, "dur": 42.637, + "args": { + "External id": 34268,"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": 2338707, "tid": 2338707, + "ts": 6197199274964.964, "dur": 33.914, + "args": { + "External id": 34269,"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": 2338707, "tid": 2338707, + "ts": 6197199275033.561, "dur": 75.000, + "args": { + "External id": 34270,"kernel_hash": "cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5", "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/jw/cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5.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": 2338707, "tid": 2338707, + "ts": 6197199275135.049, "dur": 22.648, + "args": { + "External id": 34271,"kernel_hash": "cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi", "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/xw/cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi.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": 2338707, "tid": 2338707, + "ts": 6197199275185.529, "dur": 157.163, + "args": { + "External id": 34272,"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": 2338707, "tid": 2338707, + "ts": 6197199275249.143, "dur": 13.637, + "args": { + "External id": 34273,"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": 2338707, "tid": 2338707, + "ts": 6197199275255.564, "dur": 6.244, + "args": { + "External id": 34274,"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": 2338707, "tid": 2338707, + "ts": 6197199275266.135, "dur": 4.544, + "args": { + "External id": 34275,"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": 2338707, "tid": 2338707, + "ts": 6197199275272.481, "dur": 1.600, + "args": { + "External id": 34276,"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": 2338707, "tid": 2338707, + "ts": 6197199275276.833, "dur": 7.613, + "args": { + "External id": 34277,"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": 2338707, "tid": 2338707, + "ts": 6197199275355.841, "dur": 67.344, + "args": { + "External id": 34278,"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": 2338707, "tid": 2338707, + "ts": 6197199275464.041, "dur": 36.823, + "args": { + "External id": 34279,"kernel_hash": "cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/dm/cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43.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": 2338707, "tid": 2338707, + "ts": 6197199275516.017, "dur": 49.811, + "args": { + "External id": 34280,"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": 2338707, "tid": 2338707, + "ts": 6197199275573.941, "dur": 39.300, + "args": { + "External id": 34281,"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": 2338707, "tid": 2338707, + "ts": 6197199275639.447, "dur": 29.424, + "args": { + "External id": 34282,"kernel_hash": "cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/b7/cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu.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": 2338707, "tid": 2338707, + "ts": 6197199275679.955, "dur": 59.902, + "args": { + "External id": 34283,"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": 2338707, "tid": 2338707, + "ts": 6197199275768.392, "dur": 27.705, + "args": { + "External id": 34284,"kernel_hash": "cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/gi/cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb.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": 2338707, "tid": 2338707, + "ts": 6197199275972.739, "dur": 138.440, + "args": { + "External id": 34285,"Record function id": 0, "Ev Idx": 17457 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6197199276205.437, "dur": 58.313, + "args": { + "External id": 34286,"Record function id": 0, "Ev Idx": 17458 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.12)", "pid": 2338707, "tid": 2338707, + "ts": 6197199276274.282, "dur": 31690.641, + "args": { + "External id": 34287,"Record function id": 0, "Ev Idx": 17459 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.12)", "pid": 2338707, "tid": 2338707, + "ts": 6197199276284.948, "dur": 1153.558, + "args": { + "External id": 34288,"Record function id": 0, "Ev Idx": 17460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6197199276388.091, "dur": 11.666, + "args": { + "External id": 34289,"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": 2338707, "tid": 2338707, + "ts": 6197199276415.336, "dur": 44.586, + "args": { + "External id": 34290,"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": 2338707, "tid": 2338707, + "ts": 6197199276422.162, "dur": 2.578, + "args": { + "External id": 34291,"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": 2338707, "tid": 2338707, + "ts": 6197199276430.096, "dur": 0.508, + "args": { + "External id": 34292,"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": 2338707, "tid": 2338707, + "ts": 6197199276432.192, "dur": 0.738, + "args": { + "External id": 34293,"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": 2338707, "tid": 2338707, + "ts": 6197199276434.607, "dur": 0.531, + "args": { + "External id": 34294,"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": 2338707, "tid": 2338707, + "ts": 6197199276439.148, "dur": 0.418, + "args": { + "External id": 34295,"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": 2338707, "tid": 2338707, + "ts": 6197199276440.730, "dur": 0.483, + "args": { + "External id": 34296,"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": 2338707, "tid": 2338707, + "ts": 6197199276443.023, "dur": 5.228, + "args": { + "External id": 34297,"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": 2338707, "tid": 2338707, + "ts": 6197199276449.454, "dur": 0.628, + "args": { + "External id": 34298,"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": 2338707, "tid": 2338707, + "ts": 6197199276452.207, "dur": 0.485, + "args": { + "External id": 34299,"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": 2338707, "tid": 2338707, + "ts": 6197199276474.377, "dur": 62.776, + "args": { + "External id": 34300,"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": 2338707, "tid": 2338707, + "ts": 6197199276573.616, "dur": 214.176, + "args": { + "External id": 34301,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2338707, + "ts": 6197199276586.417, "dur": 4.316, + "args": { + "External id": 34302,"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": 2338707, "tid": 2338707, + "ts": 6197199276596.851, "dur": 58.678, + "args": { + "External id": 34303,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2338707, + "ts": 6197199276605.242, "dur": 49.731, + "args": { + "External id": 34304,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2338707, + "ts": 6197199276652.314, "dur": 0.908, + "args": { + "External id": 34305,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197199276665.682, "dur": 51.603, + "args": { + "External id": 34306,"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": 2338707, "tid": 2338707, + "ts": 6197199276667.772, "dur": 2.787, + "args": { + "External id": 34307,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197199276672.102, "dur": 0.465, + "args": { + "External id": 34308,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2338707, + "ts": 6197199276673.990, "dur": 0.328, + "args": { + "External id": 34309,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2338707, + "ts": 6197199276678.670, "dur": 2.832, + "args": { + "External id": 34310,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2338707, + "ts": 6197199276682.570, "dur": 0.272, + "args": { + "External id": 34311,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2338707, + "ts": 6197199276684.631, "dur": 0.272, + "args": { + "External id": 34312,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2338707, + "ts": 6197199276688.335, "dur": 0.423, + "args": { + "External id": 34313,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2338707, + "ts": 6197199276690.534, "dur": 0.258, + "args": { + "External id": 34314,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2338707, + "ts": 6197199276692.365, "dur": 2.907, + "args": { + "External id": 34315,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2338707, + "ts": 6197199276734.072, "dur": 44.319, + "args": { + "External id": 34316,"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": 2338707, "tid": 2338707, + "ts": 6197199276852.453, "dur": 465.995, + "args": { + "External id": 34317,"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": 2338707, "tid": 2338707, + "ts": 6197199276888.606, "dur": 423.400, + "args": { + "External id": 34318,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2338707, + "ts": 6197199276900.595, "dur": 403.425, + "args": { + "External id": 34319,"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": 2338707, "tid": 2338707, + "ts": 6197199277348.519, "dur": 3.160, + "args": { + "External id": 34320,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.12)", "pid": 2338707, "tid": 2338707, + "ts": 6197199277463.127, "dur": 30268.703, + "args": { + "External id": 34321,"Record function id": 0, "Ev Idx": 17493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6197199277587.728, "dur": 8.225, + "args": { + "External id": 34322,"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": 2338707, "tid": 2338707, + "ts": 6197199277599.851, "dur": 1.189, + "args": { + "External id": 34323,"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": 2338707, "tid": 2338707, + "ts": 6197199277603.036, "dur": 3.693, + "args": { + "External id": 34324,"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": 2338707, "tid": 2338707, + "ts": 6197199277608.763, "dur": 0.940, + "args": { + "External id": 34325,"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": 2338707, "tid": 2338707, + "ts": 6197199277611.363, "dur": 1.171, + "args": { + "External id": 34326,"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": 2338707, "tid": 2338707, + "ts": 6197199277614.106, "dur": 1.346, + "args": { + "External id": 34327,"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": 2338707, "tid": 2338707, + "ts": 6197199277619.776, "dur": 1.086, + "args": { + "External id": 34328,"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": 2338707, "tid": 2338707, + "ts": 6197199277622.854, "dur": 2.489, + "args": { + "External id": 34329,"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": 2338707, "tid": 2338707, + "ts": 6197199277627.003, "dur": 1.230, + "args": { + "External id": 34330,"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": 2338707, "tid": 2338707, + "ts": 6197199277629.888, "dur": 0.829, + "args": { + "External id": 34331,"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": 2338707, "tid": 2338707, + "ts": 6197199277654.983, "dur": 30015.645, + "args": { + "External id": 34332,"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": 2338707, "tid": 2338707, + "ts": 6197199277672.849, "dur": 29988.388, + "args": { + "External id": 34333,"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": 2338707, "tid": 2338707, + "ts": 6197199277693.140, "dur": 40.560, + "args": { + "External id": 34334,"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": 2338707, "tid": 2338707, + "ts": 6197199277739.064, "dur": 29881.605, + "args": { + "External id": 34335,"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": 2338707, "tid": 2338707, + "ts": 6197199277742.593, "dur": 29877.549, + "args": { + "External id": 34336,"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": 2338707, "tid": 2338707, + "ts": 6197199277749.915, "dur": 6.422, + "args": { + "External id": 34337,"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": 2338707, "tid": 2338707, + "ts": 6197199277758.521, "dur": 29857.948, + "args": { + "External id": 34338,"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": 2338707, "tid": 2338707, + "ts": 6197199307899.578, "dur": 36.772, + "args": { + "External id": 34339,"Sequence number": 480020, "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": 2338707, "tid": 2338707, "ts": 6197199307899.578, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6197199307920.794, "dur": 9.934, + "args": { + "External id": 34340,"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": 2338707, "tid": 2338707, + "ts": 6197199307925.415, "dur": 5.033, + "args": { + "External id": 34341,"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": 2338707, "tid": 2338707, + "ts": 6197199308015.230, "dur": 129.885, + "args": { + "External id": 34342,"Record function id": 0, "Ev Idx": 17514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6197199308148.098, "dur": 1298.971, + "args": { + "External id": 34343,"Record function id": 0, "Ev Idx": 17515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197199308198.131, "dur": 1232.480, + "args": { + "External id": 34344,"Sequence number": 480021, "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": 2338707, "tid": 2338707, "ts": 6197199308198.131, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6197199308278.565, "dur": 57.955, + "args": { + "External id": 34345,"kernel_hash": "cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/du/cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs.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": 2338707, "tid": 2338707, + "ts": 6197199308351.451, "dur": 118.774, + "args": { + "External id": 34346,"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": 2338707, "tid": 2338707, + "ts": 6197199308486.331, "dur": 42.228, + "args": { + "External id": 34347,"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": 2338707, "tid": 2338707, + "ts": 6197199308539.452, "dur": 32.949, + "args": { + "External id": 34348,"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": 2338707, "tid": 2338707, + "ts": 6197199308602.303, "dur": 27.416, + "args": { + "External id": 34349,"kernel_hash": "cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5", "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/jw/cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5.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": 2338707, "tid": 2338707, + "ts": 6197199308652.664, "dur": 20.099, + "args": { + "External id": 34350,"kernel_hash": "cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi", "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/xw/cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi.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": 2338707, "tid": 2338707, + "ts": 6197199308716.672, "dur": 161.932, + "args": { + "External id": 34351,"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": 2338707, "tid": 2338707, + "ts": 6197199308779.865, "dur": 15.063, + "args": { + "External id": 34352,"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": 2338707, "tid": 2338707, + "ts": 6197199308786.223, "dur": 7.314, + "args": { + "External id": 34353,"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": 2338707, "tid": 2338707, + "ts": 6197199308798.100, "dur": 4.657, + "args": { + "External id": 34354,"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": 2338707, "tid": 2338707, + "ts": 6197199308803.971, "dur": 1.150, + "args": { + "External id": 34355,"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": 2338707, "tid": 2338707, + "ts": 6197199308808.070, "dur": 6.774, + "args": { + "External id": 34356,"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": 2338707, "tid": 2338707, + "ts": 6197199308892.282, "dur": 60.819, + "args": { + "External id": 34357,"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": 2338707, "tid": 2338707, + "ts": 6197199308992.311, "dur": 32.351, + "args": { + "External id": 34358,"kernel_hash": "cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/dm/cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43.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": 2338707, "tid": 2338707, + "ts": 6197199309036.700, "dur": 94.951, + "args": { + "External id": 34359,"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": 2338707, "tid": 2338707, + "ts": 6197199309147.963, "dur": 44.270, + "args": { + "External id": 34360,"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": 2338707, "tid": 2338707, + "ts": 6197199309221.810, "dur": 32.316, + "args": { + "External id": 34361,"kernel_hash": "cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/b7/cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu.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": 2338707, "tid": 2338707, + "ts": 6197199309263.147, "dur": 42.452, + "args": { + "External id": 34362,"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": 2338707, "tid": 2338707, + "ts": 6197199309327.076, "dur": 22.230, + "args": { + "External id": 34363,"kernel_hash": "cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/gi/cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb.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": 2338707, "tid": 2338707, + "ts": 6197199309525.313, "dur": 97.429, + "args": { + "External id": 34364,"Record function id": 0, "Ev Idx": 17536 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6197199309732.315, "dur": 59.663, + "args": { + "External id": 34365,"Record function id": 0, "Ev Idx": 17537 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.13)", "pid": 2338707, "tid": 2338707, + "ts": 6197199309803.783, "dur": 31815.671, + "args": { + "External id": 34366,"Record function id": 0, "Ev Idx": 17538 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.13)", "pid": 2338707, "tid": 2338707, + "ts": 6197199309813.397, "dur": 1149.153, + "args": { + "External id": 34367,"Record function id": 0, "Ev Idx": 17539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6197199309916.357, "dur": 10.770, + "args": { + "External id": 34368,"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": 2338707, "tid": 2338707, + "ts": 6197199309943.343, "dur": 44.657, + "args": { + "External id": 34369,"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": 2338707, "tid": 2338707, + "ts": 6197199309950.533, "dur": 2.951, + "args": { + "External id": 34370,"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": 2338707, "tid": 2338707, + "ts": 6197199309958.674, "dur": 0.592, + "args": { + "External id": 34371,"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": 2338707, "tid": 2338707, + "ts": 6197199309960.984, "dur": 0.527, + "args": { + "External id": 34372,"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": 2338707, "tid": 2338707, + "ts": 6197199309963.266, "dur": 0.467, + "args": { + "External id": 34373,"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": 2338707, "tid": 2338707, + "ts": 6197199309968.309, "dur": 0.563, + "args": { + "External id": 34374,"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": 2338707, "tid": 2338707, + "ts": 6197199309970.222, "dur": 0.855, + "args": { + "External id": 34375,"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": 2338707, "tid": 2338707, + "ts": 6197199309972.850, "dur": 3.342, + "args": { + "External id": 34376,"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": 2338707, "tid": 2338707, + "ts": 6197199309977.280, "dur": 0.747, + "args": { + "External id": 34377,"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": 2338707, "tid": 2338707, + "ts": 6197199309979.890, "dur": 0.499, + "args": { + "External id": 34378,"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": 2338707, "tid": 2338707, + "ts": 6197199310002.185, "dur": 106.181, + "args": { + "External id": 34379,"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": 2338707, "tid": 2338707, + "ts": 6197199310164.382, "dur": 156.832, + "args": { + "External id": 34380,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2338707, + "ts": 6197199310180.898, "dur": 7.627, + "args": { + "External id": 34381,"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": 2338707, "tid": 2338707, + "ts": 6197199310195.047, "dur": 13.952, + "args": { + "External id": 34382,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2338707, + "ts": 6197199310200.567, "dur": 7.891, + "args": { + "External id": 34383,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2338707, + "ts": 6197199310205.031, "dur": 1.169, + "args": { + "External id": 34384,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197199310217.128, "dur": 34.535, + "args": { + "External id": 34385,"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": 2338707, "tid": 2338707, + "ts": 6197199310220.005, "dur": 0.647, + "args": { + "External id": 34386,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197199310222.394, "dur": 2.579, + "args": { + "External id": 34387,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2338707, + "ts": 6197199310226.517, "dur": 0.880, + "args": { + "External id": 34388,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2338707, + "ts": 6197199310229.269, "dur": 2.971, + "args": { + "External id": 34389,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2338707, + "ts": 6197199310235.973, "dur": 0.362, + "args": { + "External id": 34390,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2338707, + "ts": 6197199310238.085, "dur": 0.514, + "args": { + "External id": 34391,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2338707, + "ts": 6197199310240.185, "dur": 0.395, + "args": { + "External id": 34392,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2338707, + "ts": 6197199310244.697, "dur": 0.302, + "args": { + "External id": 34393,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2338707, + "ts": 6197199310246.539, "dur": 0.474, + "args": { + "External id": 34394,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2338707, + "ts": 6197199310268.865, "dur": 43.029, + "args": { + "External id": 34395,"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": 2338707, "tid": 2338707, + "ts": 6197199310390.661, "dur": 450.746, + "args": { + "External id": 34396,"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": 2338707, "tid": 2338707, + "ts": 6197199310427.380, "dur": 407.089, + "args": { + "External id": 34397,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2338707, + "ts": 6197199310443.527, "dur": 383.799, + "args": { + "External id": 34398,"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": 2338707, "tid": 2338707, + "ts": 6197199310871.949, "dur": 3.245, + "args": { + "External id": 34399,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.13)", "pid": 2338707, "tid": 2338707, + "ts": 6197199310987.758, "dur": 30393.635, + "args": { + "External id": 34400,"Record function id": 0, "Ev Idx": 17572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6197199311152.663, "dur": 8.717, + "args": { + "External id": 34401,"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": 2338707, "tid": 2338707, + "ts": 6197199311166.517, "dur": 1.190, + "args": { + "External id": 34402,"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": 2338707, "tid": 2338707, + "ts": 6197199311169.739, "dur": 3.905, + "args": { + "External id": 34403,"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": 2338707, "tid": 2338707, + "ts": 6197199311175.497, "dur": 0.987, + "args": { + "External id": 34404,"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": 2338707, "tid": 2338707, + "ts": 6197199311178.094, "dur": 1.039, + "args": { + "External id": 34405,"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": 2338707, "tid": 2338707, + "ts": 6197199311182.800, "dur": 0.856, + "args": { + "External id": 34406,"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": 2338707, "tid": 2338707, + "ts": 6197199311185.713, "dur": 1.012, + "args": { + "External id": 34407,"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": 2338707, "tid": 2338707, + "ts": 6197199311188.479, "dur": 2.223, + "args": { + "External id": 34408,"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": 2338707, "tid": 2338707, + "ts": 6197199311192.634, "dur": 0.921, + "args": { + "External id": 34409,"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": 2338707, "tid": 2338707, + "ts": 6197199311197.874, "dur": 0.749, + "args": { + "External id": 34410,"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": 2338707, "tid": 2338707, + "ts": 6197199311221.612, "dur": 30107.917, + "args": { + "External id": 34411,"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": 2338707, "tid": 2338707, + "ts": 6197199311240.684, "dur": 30079.842, + "args": { + "External id": 34412,"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": 2338707, "tid": 2338707, + "ts": 6197199311260.309, "dur": 20.874, + "args": { + "External id": 34413,"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": 2338707, "tid": 2338707, + "ts": 6197199311285.311, "dur": 29990.528, + "args": { + "External id": 34414,"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": 2338707, "tid": 2338707, + "ts": 6197199311288.246, "dur": 29986.893, + "args": { + "External id": 34415,"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": 2338707, "tid": 2338707, + "ts": 6197199311296.647, "dur": 6.767, + "args": { + "External id": 34416,"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": 2338707, "tid": 2338707, + "ts": 6197199311305.746, "dur": 29965.972, + "args": { + "External id": 34417,"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": 2338707, "tid": 2338707, + "ts": 6197199341551.249, "dur": 36.342, + "args": { + "External id": 34418,"Sequence number": 480022, "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": 2338707, "tid": 2338707, "ts": 6197199341551.249, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6197199341572.734, "dur": 9.341, + "args": { + "External id": 34419,"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": 2338707, "tid": 2338707, + "ts": 6197199341576.734, "dur": 5.100, + "args": { + "External id": 34420,"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": 2338707, "tid": 2338707, + "ts": 6197199341668.320, "dur": 103.086, + "args": { + "External id": 34421,"Record function id": 0, "Ev Idx": 17593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6197199341774.709, "dur": 1373.407, + "args": { + "External id": 34422,"Record function id": 0, "Ev Idx": 17594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197199341828.488, "dur": 1300.472, + "args": { + "External id": 34423,"Sequence number": 480023, "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": 2338707, "tid": 2338707, "ts": 6197199341828.488, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6197199341910.522, "dur": 60.113, + "args": { + "External id": 34424,"kernel_hash": "cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/du/cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs.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": 2338707, "tid": 2338707, + "ts": 6197199341985.025, "dur": 156.420, + "args": { + "External id": 34425,"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": 2338707, "tid": 2338707, + "ts": 6197199342162.091, "dur": 49.330, + "args": { + "External id": 34426,"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": 2338707, "tid": 2338707, + "ts": 6197199342222.902, "dur": 33.723, + "args": { + "External id": 34427,"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": 2338707, "tid": 2338707, + "ts": 6197199342291.161, "dur": 35.811, + "args": { + "External id": 34428,"kernel_hash": "cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5", "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/jw/cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5.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": 2338707, "tid": 2338707, + "ts": 6197199342348.855, "dur": 19.657, + "args": { + "External id": 34429,"kernel_hash": "cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi", "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/xw/cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi.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": 2338707, "tid": 2338707, + "ts": 6197199342399.032, "dur": 162.682, + "args": { + "External id": 34430,"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": 2338707, "tid": 2338707, + "ts": 6197199342463.755, "dur": 13.380, + "args": { + "External id": 34431,"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": 2338707, "tid": 2338707, + "ts": 6197199342469.986, "dur": 6.261, + "args": { + "External id": 34432,"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": 2338707, "tid": 2338707, + "ts": 6197199342480.175, "dur": 4.855, + "args": { + "External id": 34433,"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": 2338707, "tid": 2338707, + "ts": 6197199342486.625, "dur": 1.020, + "args": { + "External id": 34434,"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": 2338707, "tid": 2338707, + "ts": 6197199342493.243, "dur": 7.187, + "args": { + "External id": 34435,"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": 2338707, "tid": 2338707, + "ts": 6197199342574.844, "dur": 59.266, + "args": { + "External id": 34436,"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": 2338707, "tid": 2338707, + "ts": 6197199342671.602, "dur": 55.066, + "args": { + "External id": 34437,"kernel_hash": "cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/dm/cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43.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": 2338707, "tid": 2338707, + "ts": 6197199342745.504, "dur": 53.669, + "args": { + "External id": 34438,"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": 2338707, "tid": 2338707, + "ts": 6197199342807.266, "dur": 38.818, + "args": { + "External id": 34439,"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": 2338707, "tid": 2338707, + "ts": 6197199342874.718, "dur": 32.275, + "args": { + "External id": 34440,"kernel_hash": "cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/b7/cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu.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": 2338707, "tid": 2338707, + "ts": 6197199342913.040, "dur": 40.097, + "args": { + "External id": 34441,"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": 2338707, "tid": 2338707, + "ts": 6197199342972.663, "dur": 21.182, + "args": { + "External id": 34442,"kernel_hash": "cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/gi/cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb.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": 2338707, "tid": 2338707, + "ts": 6197199343229.295, "dur": 95.261, + "args": { + "External id": 34443,"Record function id": 0, "Ev Idx": 17615 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6197199343411.319, "dur": 57.829, + "args": { + "External id": 34444,"Record function id": 0, "Ev Idx": 17616 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.14)", "pid": 2338707, "tid": 2338707, + "ts": 6197199343480.358, "dur": 32656.899, + "args": { + "External id": 34445,"Record function id": 0, "Ev Idx": 17617 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.14)", "pid": 2338707, "tid": 2338707, + "ts": 6197199343490.430, "dur": 1120.364, + "args": { + "External id": 34446,"Record function id": 0, "Ev Idx": 17618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6197199343593.412, "dur": 11.061, + "args": { + "External id": 34447,"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": 2338707, "tid": 2338707, + "ts": 6197199343620.333, "dur": 47.448, + "args": { + "External id": 34448,"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": 2338707, "tid": 2338707, + "ts": 6197199343627.369, "dur": 3.020, + "args": { + "External id": 34449,"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": 2338707, "tid": 2338707, + "ts": 6197199343635.497, "dur": 0.630, + "args": { + "External id": 34450,"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": 2338707, "tid": 2338707, + "ts": 6197199343640.246, "dur": 0.721, + "args": { + "External id": 34451,"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": 2338707, "tid": 2338707, + "ts": 6197199343642.660, "dur": 0.835, + "args": { + "External id": 34452,"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": 2338707, "tid": 2338707, + "ts": 6197199343647.376, "dur": 0.859, + "args": { + "External id": 34453,"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": 2338707, "tid": 2338707, + "ts": 6197199343649.157, "dur": 1.061, + "args": { + "External id": 34454,"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": 2338707, "tid": 2338707, + "ts": 6197199343651.662, "dur": 5.156, + "args": { + "External id": 34455,"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": 2338707, "tid": 2338707, + "ts": 6197199343658.152, "dur": 0.645, + "args": { + "External id": 34456,"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": 2338707, "tid": 2338707, + "ts": 6197199343660.185, "dur": 0.478, + "args": { + "External id": 34457,"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": 2338707, "tid": 2338707, + "ts": 6197199343682.463, "dur": 83.810, + "args": { + "External id": 34458,"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": 2338707, "tid": 2338707, + "ts": 6197199343809.554, "dur": 151.102, + "args": { + "External id": 34459,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2338707, + "ts": 6197199343823.564, "dur": 5.986, + "args": { + "External id": 34460,"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": 2338707, "tid": 2338707, + "ts": 6197199343838.948, "dur": 14.062, + "args": { + "External id": 34461,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2338707, + "ts": 6197199343844.946, "dur": 7.574, + "args": { + "External id": 34462,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2338707, + "ts": 6197199343849.718, "dur": 1.083, + "args": { + "External id": 34463,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197199343861.273, "dur": 36.247, + "args": { + "External id": 34464,"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": 2338707, "tid": 2338707, + "ts": 6197199343863.827, "dur": 2.590, + "args": { + "External id": 34465,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197199343868.096, "dur": 0.904, + "args": { + "External id": 34466,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2338707, + "ts": 6197199343870.474, "dur": 0.346, + "args": { + "External id": 34467,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2338707, + "ts": 6197199343875.241, "dur": 3.204, + "args": { + "External id": 34468,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2338707, + "ts": 6197199343879.681, "dur": 0.590, + "args": { + "External id": 34469,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2338707, + "ts": 6197199343881.940, "dur": 0.369, + "args": { + "External id": 34470,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2338707, + "ts": 6197199343885.719, "dur": 0.677, + "args": { + "External id": 34471,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2338707, + "ts": 6197199343888.352, "dur": 0.538, + "args": { + "External id": 34472,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2338707, + "ts": 6197199343890.166, "dur": 2.458, + "args": { + "External id": 34473,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2338707, + "ts": 6197199343911.684, "dur": 39.277, + "args": { + "External id": 34474,"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": 2338707, "tid": 2338707, + "ts": 6197199344022.918, "dur": 470.231, + "args": { + "External id": 34475,"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": 2338707, "tid": 2338707, + "ts": 6197199344100.361, "dur": 385.216, + "args": { + "External id": 34476,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2338707, + "ts": 6197199344118.622, "dur": 360.115, + "args": { + "External id": 34477,"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": 2338707, "tid": 2338707, + "ts": 6197199344521.254, "dur": 2.853, + "args": { + "External id": 34478,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.14)", "pid": 2338707, "tid": 2338707, + "ts": 6197199344636.165, "dur": 31231.448, + "args": { + "External id": 34479,"Record function id": 0, "Ev Idx": 17651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6197199344780.863, "dur": 7.935, + "args": { + "External id": 34480,"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": 2338707, "tid": 2338707, + "ts": 6197199344793.467, "dur": 1.197, + "args": { + "External id": 34481,"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": 2338707, "tid": 2338707, + "ts": 6197199344796.729, "dur": 3.508, + "args": { + "External id": 34482,"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": 2338707, "tid": 2338707, + "ts": 6197199344802.512, "dur": 1.101, + "args": { + "External id": 34483,"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": 2338707, "tid": 2338707, + "ts": 6197199344805.227, "dur": 1.360, + "args": { + "External id": 34484,"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": 2338707, "tid": 2338707, + "ts": 6197199344808.213, "dur": 1.157, + "args": { + "External id": 34485,"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": 2338707, "tid": 2338707, + "ts": 6197199344813.682, "dur": 1.236, + "args": { + "External id": 34486,"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": 2338707, "tid": 2338707, + "ts": 6197199344816.636, "dur": 2.036, + "args": { + "External id": 34487,"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": 2338707, "tid": 2338707, + "ts": 6197199344820.212, "dur": 0.981, + "args": { + "External id": 34488,"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": 2338707, "tid": 2338707, + "ts": 6197199344823.020, "dur": 1.016, + "args": { + "External id": 34489,"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": 2338707, "tid": 2338707, + "ts": 6197199344848.910, "dur": 30969.468, + "args": { + "External id": 34490,"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": 2338707, "tid": 2338707, + "ts": 6197199344868.142, "dur": 30940.766, + "args": { + "External id": 34491,"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": 2338707, "tid": 2338707, + "ts": 6197199344887.420, "dur": 18.611, + "args": { + "External id": 34492,"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": 2338707, "tid": 2338707, + "ts": 6197199344910.517, "dur": 30858.141, + "args": { + "External id": 34493,"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": 2338707, "tid": 2338707, + "ts": 6197199344913.302, "dur": 30854.737, + "args": { + "External id": 34494,"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": 2338707, "tid": 2338707, + "ts": 6197199344921.579, "dur": 6.075, + "args": { + "External id": 34495,"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": 2338707, "tid": 2338707, + "ts": 6197199344929.659, "dur": 30834.784, + "args": { + "External id": 34496,"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": 2338707, "tid": 2338707, + "ts": 6197199376036.824, "dur": 67.420, + "args": { + "External id": 34497,"Sequence number": 480024, "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": 2338707, "tid": 2338707, "ts": 6197199376036.824, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6197199376087.206, "dur": 10.581, + "args": { + "External id": 34498,"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": 2338707, "tid": 2338707, + "ts": 6197199376091.596, "dur": 5.784, + "args": { + "External id": 34499,"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": 2338707, "tid": 2338707, + "ts": 6197199376187.934, "dur": 90.760, + "args": { + "External id": 34500,"Record function id": 0, "Ev Idx": 17672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6197199376280.186, "dur": 1299.306, + "args": { + "External id": 34501,"Record function id": 0, "Ev Idx": 17673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197199376329.993, "dur": 1234.280, + "args": { + "External id": 34502,"Sequence number": 480025, "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": 2338707, "tid": 2338707, "ts": 6197199376329.993, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6197199376411.391, "dur": 60.719, + "args": { + "External id": 34503,"kernel_hash": "cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/du/cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs.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": 2338707, "tid": 2338707, + "ts": 6197199376486.805, "dur": 119.910, + "args": { + "External id": 34504,"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": 2338707, "tid": 2338707, + "ts": 6197199376620.452, "dur": 42.322, + "args": { + "External id": 34505,"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": 2338707, "tid": 2338707, + "ts": 6197199376675.905, "dur": 51.426, + "args": { + "External id": 34506,"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": 2338707, "tid": 2338707, + "ts": 6197199376762.813, "dur": 33.965, + "args": { + "External id": 34507,"kernel_hash": "cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5", "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/jw/cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5.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": 2338707, "tid": 2338707, + "ts": 6197199376818.726, "dur": 19.126, + "args": { + "External id": 34508,"kernel_hash": "cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi", "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/xw/cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi.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": 2338707, "tid": 2338707, + "ts": 6197199376865.686, "dur": 153.405, + "args": { + "External id": 34509,"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": 2338707, "tid": 2338707, + "ts": 6197199376927.112, "dur": 13.147, + "args": { + "External id": 34510,"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": 2338707, "tid": 2338707, + "ts": 6197199376933.466, "dur": 5.959, + "args": { + "External id": 34511,"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": 2338707, "tid": 2338707, + "ts": 6197199376943.412, "dur": 4.759, + "args": { + "External id": 34512,"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": 2338707, "tid": 2338707, + "ts": 6197199376950.240, "dur": 1.337, + "args": { + "External id": 34513,"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": 2338707, "tid": 2338707, + "ts": 6197199376954.406, "dur": 6.940, + "args": { + "External id": 34514,"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": 2338707, "tid": 2338707, + "ts": 6197199377031.372, "dur": 107.467, + "args": { + "External id": 34515,"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": 2338707, "tid": 2338707, + "ts": 6197199377182.940, "dur": 36.747, + "args": { + "External id": 34516,"kernel_hash": "cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/dm/cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43.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": 2338707, "tid": 2338707, + "ts": 6197199377233.340, "dur": 52.287, + "args": { + "External id": 34517,"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": 2338707, "tid": 2338707, + "ts": 6197199377295.201, "dur": 39.329, + "args": { + "External id": 34518,"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": 2338707, "tid": 2338707, + "ts": 6197199377363.100, "dur": 31.463, + "args": { + "External id": 34519,"kernel_hash": "cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/b7/cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu.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": 2338707, "tid": 2338707, + "ts": 6197199377403.742, "dur": 41.633, + "args": { + "External id": 34520,"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": 2338707, "tid": 2338707, + "ts": 6197199377465.545, "dur": 21.222, + "args": { + "External id": 34521,"kernel_hash": "cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/gi/cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb.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": 2338707, "tid": 2338707, + "ts": 6197199377657.316, "dur": 114.128, + "args": { + "External id": 34522,"Record function id": 0, "Ev Idx": 17694 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6197199377864.731, "dur": 58.780, + "args": { + "External id": 34523,"Record function id": 0, "Ev Idx": 17695 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.15)", "pid": 2338707, "tid": 2338707, + "ts": 6197199377934.440, "dur": 31703.571, + "args": { + "External id": 34524,"Record function id": 0, "Ev Idx": 17696 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.15)", "pid": 2338707, "tid": 2338707, + "ts": 6197199377942.964, "dur": 1204.653, + "args": { + "External id": 34525,"Record function id": 0, "Ev Idx": 17697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6197199378044.100, "dur": 11.296, + "args": { + "External id": 34526,"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": 2338707, "tid": 2338707, + "ts": 6197199378115.840, "dur": 44.749, + "args": { + "External id": 34527,"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": 2338707, "tid": 2338707, + "ts": 6197199378123.291, "dur": 2.898, + "args": { + "External id": 34528,"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": 2338707, "tid": 2338707, + "ts": 6197199378130.085, "dur": 0.762, + "args": { + "External id": 34529,"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": 2338707, "tid": 2338707, + "ts": 6197199378132.752, "dur": 0.762, + "args": { + "External id": 34530,"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": 2338707, "tid": 2338707, + "ts": 6197199378134.715, "dur": 0.500, + "args": { + "External id": 34531,"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": 2338707, "tid": 2338707, + "ts": 6197199378138.907, "dur": 0.472, + "args": { + "External id": 34532,"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": 2338707, "tid": 2338707, + "ts": 6197199378140.512, "dur": 0.474, + "args": { + "External id": 34533,"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": 2338707, "tid": 2338707, + "ts": 6197199378142.525, "dur": 7.140, + "args": { + "External id": 34534,"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": 2338707, "tid": 2338707, + "ts": 6197199378150.977, "dur": 0.354, + "args": { + "External id": 34535,"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": 2338707, "tid": 2338707, + "ts": 6197199378153.532, "dur": 0.460, + "args": { + "External id": 34536,"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": 2338707, "tid": 2338707, + "ts": 6197199378175.616, "dur": 70.323, + "args": { + "External id": 34537,"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": 2338707, "tid": 2338707, + "ts": 6197199378288.609, "dur": 138.288, + "args": { + "External id": 34538,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2338707, + "ts": 6197199378302.076, "dur": 5.377, + "args": { + "External id": 34539,"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": 2338707, "tid": 2338707, + "ts": 6197199378313.703, "dur": 12.503, + "args": { + "External id": 34540,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2338707, + "ts": 6197199378319.415, "dur": 6.291, + "args": { + "External id": 34541,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2338707, + "ts": 6197199378323.492, "dur": 0.763, + "args": { + "External id": 34542,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197199378333.184, "dur": 33.083, + "args": { + "External id": 34543,"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": 2338707, "tid": 2338707, + "ts": 6197199378335.697, "dur": 2.276, + "args": { + "External id": 34544,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197199378339.699, "dur": 0.817, + "args": { + "External id": 34545,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2338707, + "ts": 6197199378341.787, "dur": 0.692, + "args": { + "External id": 34546,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2338707, + "ts": 6197199378346.120, "dur": 3.091, + "args": { + "External id": 34547,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2338707, + "ts": 6197199378350.813, "dur": 0.484, + "args": { + "External id": 34548,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2338707, + "ts": 6197199378352.999, "dur": 0.577, + "args": { + "External id": 34549,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2338707, + "ts": 6197199378356.055, "dur": 0.471, + "args": { + "External id": 34550,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2338707, + "ts": 6197199378358.352, "dur": 0.674, + "args": { + "External id": 34551,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2338707, + "ts": 6197199378360.312, "dur": 1.844, + "args": { + "External id": 34552,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2338707, + "ts": 6197199378380.630, "dur": 37.230, + "args": { + "External id": 34553,"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": 2338707, "tid": 2338707, + "ts": 6197199378489.757, "dur": 496.742, + "args": { + "External id": 34554,"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": 2338707, "tid": 2338707, + "ts": 6197199378525.051, "dur": 454.231, + "args": { + "External id": 34555,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2338707, + "ts": 6197199378537.272, "dur": 431.521, + "args": { + "External id": 34556,"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": 2338707, "tid": 2338707, + "ts": 6197199379018.148, "dur": 3.351, + "args": { + "External id": 34557,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.15)", "pid": 2338707, "tid": 2338707, + "ts": 6197199379175.878, "dur": 30225.969, + "args": { + "External id": 34558,"Record function id": 0, "Ev Idx": 17730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6197199379303.892, "dur": 8.098, + "args": { + "External id": 34559,"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": 2338707, "tid": 2338707, + "ts": 6197199379315.987, "dur": 1.265, + "args": { + "External id": 34560,"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": 2338707, "tid": 2338707, + "ts": 6197199379319.448, "dur": 4.091, + "args": { + "External id": 34561,"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": 2338707, "tid": 2338707, + "ts": 6197199379325.428, "dur": 0.847, + "args": { + "External id": 34562,"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": 2338707, "tid": 2338707, + "ts": 6197199379327.935, "dur": 0.959, + "args": { + "External id": 34563,"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": 2338707, "tid": 2338707, + "ts": 6197199379330.277, "dur": 1.350, + "args": { + "External id": 34564,"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": 2338707, "tid": 2338707, + "ts": 6197199379335.878, "dur": 1.330, + "args": { + "External id": 34565,"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": 2338707, "tid": 2338707, + "ts": 6197199379339.272, "dur": 2.216, + "args": { + "External id": 34566,"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": 2338707, "tid": 2338707, + "ts": 6197199379343.038, "dur": 0.754, + "args": { + "External id": 34567,"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": 2338707, "tid": 2338707, + "ts": 6197199379345.661, "dur": 0.755, + "args": { + "External id": 34568,"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": 2338707, "tid": 2338707, + "ts": 6197199379374.342, "dur": 29976.321, + "args": { + "External id": 34569,"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": 2338707, "tid": 2338707, + "ts": 6197199379393.075, "dur": 29947.667, + "args": { + "External id": 34570,"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": 2338707, "tid": 2338707, + "ts": 6197199379411.712, "dur": 20.736, + "args": { + "External id": 34571,"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": 2338707, "tid": 2338707, + "ts": 6197199379436.551, "dur": 29861.855, + "args": { + "External id": 34572,"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": 2338707, "tid": 2338707, + "ts": 6197199379440.151, "dur": 29857.560, + "args": { + "External id": 34573,"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": 2338707, "tid": 2338707, + "ts": 6197199379447.453, "dur": 6.025, + "args": { + "External id": 34574,"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": 2338707, "tid": 2338707, + "ts": 6197199379455.426, "dur": 29838.077, + "args": { + "External id": 34575,"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": 2338707, "tid": 2338707, + "ts": 6197199409573.344, "dur": 36.740, + "args": { + "External id": 34576,"Sequence number": 480026, "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": 2338707, "tid": 2338707, "ts": 6197199409573.344, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6197199409594.228, "dur": 9.837, + "args": { + "External id": 34577,"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": 2338707, "tid": 2338707, + "ts": 6197199409598.631, "dur": 5.213, + "args": { + "External id": 34578,"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": 2338707, "tid": 2338707, + "ts": 6197199409686.724, "dur": 101.946, + "args": { + "External id": 34579,"Record function id": 0, "Ev Idx": 17751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6197199409791.839, "dur": 1353.961, + "args": { + "External id": 34580,"Record function id": 0, "Ev Idx": 17752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197199409840.660, "dur": 1287.808, + "args": { + "External id": 34581,"Sequence number": 480027, "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": 2338707, "tid": 2338707, "ts": 6197199409840.660, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6197199409920.263, "dur": 59.967, + "args": { + "External id": 34582,"kernel_hash": "cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/du/cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs.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": 2338707, "tid": 2338707, + "ts": 6197199409995.704, "dur": 156.906, + "args": { + "External id": 34583,"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": 2338707, "tid": 2338707, + "ts": 6197199410175.470, "dur": 47.798, + "args": { + "External id": 34584,"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": 2338707, "tid": 2338707, + "ts": 6197199410234.732, "dur": 33.548, + "args": { + "External id": 34585,"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": 2338707, "tid": 2338707, + "ts": 6197199410303.332, "dur": 32.907, + "args": { + "External id": 34586,"kernel_hash": "cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5", "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/jw/cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5.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": 2338707, "tid": 2338707, + "ts": 6197199410358.406, "dur": 20.927, + "args": { + "External id": 34587,"kernel_hash": "cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi", "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/xw/cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi.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": 2338707, "tid": 2338707, + "ts": 6197199410406.419, "dur": 161.444, + "args": { + "External id": 34588,"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": 2338707, "tid": 2338707, + "ts": 6197199410468.206, "dur": 14.007, + "args": { + "External id": 34589,"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": 2338707, "tid": 2338707, + "ts": 6197199410474.521, "dur": 6.814, + "args": { + "External id": 34590,"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": 2338707, "tid": 2338707, + "ts": 6197199410486.210, "dur": 4.950, + "args": { + "External id": 34591,"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": 2338707, "tid": 2338707, + "ts": 6197199410492.875, "dur": 1.554, + "args": { + "External id": 34592,"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": 2338707, "tid": 2338707, + "ts": 6197199410499.637, "dur": 6.915, + "args": { + "External id": 34593,"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": 2338707, "tid": 2338707, + "ts": 6197199410580.380, "dur": 58.893, + "args": { + "External id": 34594,"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": 2338707, "tid": 2338707, + "ts": 6197199410677.779, "dur": 53.244, + "args": { + "External id": 34595,"kernel_hash": "cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/dm/cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43.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": 2338707, "tid": 2338707, + "ts": 6197199410747.406, "dur": 56.056, + "args": { + "External id": 34596,"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": 2338707, "tid": 2338707, + "ts": 6197199410815.170, "dur": 40.799, + "args": { + "External id": 34597,"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": 2338707, "tid": 2338707, + "ts": 6197199410884.555, "dur": 35.367, + "args": { + "External id": 34598,"kernel_hash": "cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/b7/cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu.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": 2338707, "tid": 2338707, + "ts": 6197199410926.775, "dur": 42.977, + "args": { + "External id": 34599,"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": 2338707, "tid": 2338707, + "ts": 6197199410990.191, "dur": 22.287, + "args": { + "External id": 34600,"kernel_hash": "cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/gi/cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb.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": 2338707, "tid": 2338707, + "ts": 6197199411225.094, "dur": 100.302, + "args": { + "External id": 34601,"Record function id": 0, "Ev Idx": 17773 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6197199411413.193, "dur": 57.944, + "args": { + "External id": 34602,"Record function id": 0, "Ev Idx": 17774 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.16)", "pid": 2338707, "tid": 2338707, + "ts": 6197199411482.839, "dur": 32755.865, + "args": { + "External id": 34603,"Record function id": 0, "Ev Idx": 17775 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.16)", "pid": 2338707, "tid": 2338707, + "ts": 6197199411493.640, "dur": 1025.821, + "args": { + "External id": 34604,"Record function id": 0, "Ev Idx": 17776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6197199411593.793, "dur": 10.473, + "args": { + "External id": 34605,"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": 2338707, "tid": 2338707, + "ts": 6197199411620.480, "dur": 48.822, + "args": { + "External id": 34606,"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": 2338707, "tid": 2338707, + "ts": 6197199411627.356, "dur": 2.630, + "args": { + "External id": 34607,"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": 2338707, "tid": 2338707, + "ts": 6197199411635.264, "dur": 0.643, + "args": { + "External id": 34608,"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": 2338707, "tid": 2338707, + "ts": 6197199411637.316, "dur": 0.520, + "args": { + "External id": 34609,"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": 2338707, "tid": 2338707, + "ts": 6197199411639.160, "dur": 0.529, + "args": { + "External id": 34610,"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": 2338707, "tid": 2338707, + "ts": 6197199411643.450, "dur": 0.793, + "args": { + "External id": 34611,"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": 2338707, "tid": 2338707, + "ts": 6197199411649.953, "dur": 0.489, + "args": { + "External id": 34612,"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": 2338707, "tid": 2338707, + "ts": 6197199411651.926, "dur": 3.959, + "args": { + "External id": 34613,"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": 2338707, "tid": 2338707, + "ts": 6197199411657.259, "dur": 0.507, + "args": { + "External id": 34614,"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": 2338707, "tid": 2338707, + "ts": 6197199411661.791, "dur": 0.607, + "args": { + "External id": 34615,"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": 2338707, "tid": 2338707, + "ts": 6197199411683.326, "dur": 85.090, + "args": { + "External id": 34616,"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": 2338707, "tid": 2338707, + "ts": 6197199411811.129, "dur": 143.712, + "args": { + "External id": 34617,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2338707, + "ts": 6197199411825.486, "dur": 6.292, + "args": { + "External id": 34618,"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": 2338707, "tid": 2338707, + "ts": 6197199411840.356, "dur": 14.575, + "args": { + "External id": 34619,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2338707, + "ts": 6197199411845.767, "dur": 8.630, + "args": { + "External id": 34620,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2338707, + "ts": 6197199411849.962, "dur": 2.374, + "args": { + "External id": 34621,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197199411863.014, "dur": 31.728, + "args": { + "External id": 34622,"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": 2338707, "tid": 2338707, + "ts": 6197199411865.201, "dur": 0.392, + "args": { + "External id": 34623,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197199411867.285, "dur": 1.171, + "args": { + "External id": 34624,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2338707, + "ts": 6197199411869.961, "dur": 0.545, + "args": { + "External id": 34625,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2338707, + "ts": 6197199411873.863, "dur": 3.405, + "args": { + "External id": 34626,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2338707, + "ts": 6197199411878.607, "dur": 0.394, + "args": { + "External id": 34627,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2338707, + "ts": 6197199411880.964, "dur": 2.006, + "args": { + "External id": 34628,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2338707, + "ts": 6197199411884.400, "dur": 0.296, + "args": { + "External id": 34629,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2338707, + "ts": 6197199411886.246, "dur": 0.409, + "args": { + "External id": 34630,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2338707, + "ts": 6197199411889.654, "dur": 0.663, + "args": { + "External id": 34631,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2338707, + "ts": 6197199411908.617, "dur": 37.259, + "args": { + "External id": 34632,"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": 2338707, "tid": 2338707, + "ts": 6197199412020.458, "dur": 387.964, + "args": { + "External id": 34633,"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": 2338707, "tid": 2338707, + "ts": 6197199412094.718, "dur": 307.903, + "args": { + "External id": 34634,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2338707, + "ts": 6197199412108.450, "dur": 287.990, + "args": { + "External id": 34635,"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": 2338707, "tid": 2338707, + "ts": 6197199412436.375, "dur": 2.454, + "args": { + "External id": 34636,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.16)", "pid": 2338707, "tid": 2338707, + "ts": 6197199412543.388, "dur": 31424.557, + "args": { + "External id": 34637,"Record function id": 0, "Ev Idx": 17809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6197199412659.672, "dur": 7.097, + "args": { + "External id": 34638,"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": 2338707, "tid": 2338707, + "ts": 6197199412670.863, "dur": 1.356, + "args": { + "External id": 34639,"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": 2338707, "tid": 2338707, + "ts": 6197199412674.520, "dur": 3.945, + "args": { + "External id": 34640,"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": 2338707, "tid": 2338707, + "ts": 6197199412680.192, "dur": 1.180, + "args": { + "External id": 34641,"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": 2338707, "tid": 2338707, + "ts": 6197199412683.297, "dur": 1.025, + "args": { + "External id": 34642,"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": 2338707, "tid": 2338707, + "ts": 6197199412688.127, "dur": 0.765, + "args": { + "External id": 34643,"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": 2338707, "tid": 2338707, + "ts": 6197199412690.704, "dur": 0.921, + "args": { + "External id": 34644,"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": 2338707, "tid": 2338707, + "ts": 6197199412693.336, "dur": 2.266, + "args": { + "External id": 34645,"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": 2338707, "tid": 2338707, + "ts": 6197199412697.175, "dur": 1.020, + "args": { + "External id": 34646,"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": 2338707, "tid": 2338707, + "ts": 6197199412721.865, "dur": 1.627, + "args": { + "External id": 34647,"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": 2338707, "tid": 2338707, + "ts": 6197199412746.032, "dur": 31171.101, + "args": { + "External id": 34648,"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": 2338707, "tid": 2338707, + "ts": 6197199412765.246, "dur": 31141.927, + "args": { + "External id": 34649,"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": 2338707, "tid": 2338707, + "ts": 6197199412786.366, "dur": 18.781, + "args": { + "External id": 34650,"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": 2338707, "tid": 2338707, + "ts": 6197199412809.732, "dur": 31051.253, + "args": { + "External id": 34651,"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": 2338707, "tid": 2338707, + "ts": 6197199412813.080, "dur": 31047.244, + "args": { + "External id": 34652,"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": 2338707, "tid": 2338707, + "ts": 6197199412819.361, "dur": 6.565, + "args": { + "External id": 34653,"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": 2338707, "tid": 2338707, + "ts": 6197199412827.979, "dur": 31028.563, + "args": { + "External id": 34654,"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": 2338707, "tid": 2338707, + "ts": 6197199444165.652, "dur": 40.485, + "args": { + "External id": 34655,"Sequence number": 480028, "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": 2338707, "tid": 2338707, "ts": 6197199444165.652, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6197199444189.164, "dur": 11.241, + "args": { + "External id": 34656,"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": 2338707, "tid": 2338707, + "ts": 6197199444193.571, "dur": 6.358, + "args": { + "External id": 34657,"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": 2338707, "tid": 2338707, + "ts": 6197199444287.629, "dur": 87.986, + "args": { + "External id": 34658,"Record function id": 0, "Ev Idx": 17830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6197199444377.488, "dur": 1297.498, + "args": { + "External id": 34659,"Record function id": 0, "Ev Idx": 17831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197199444422.048, "dur": 1237.055, + "args": { + "External id": 34660,"Sequence number": 480029, "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": 2338707, "tid": 2338707, "ts": 6197199444422.048, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6197199444498.512, "dur": 60.042, + "args": { + "External id": 34661,"kernel_hash": "cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/du/cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs.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": 2338707, "tid": 2338707, + "ts": 6197199444572.948, "dur": 118.868, + "args": { + "External id": 34662,"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": 2338707, "tid": 2338707, + "ts": 6197199444728.239, "dur": 48.400, + "args": { + "External id": 34663,"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": 2338707, "tid": 2338707, + "ts": 6197199444790.958, "dur": 34.547, + "args": { + "External id": 34664,"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": 2338707, "tid": 2338707, + "ts": 6197199444856.185, "dur": 30.804, + "args": { + "External id": 34665,"kernel_hash": "cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5", "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/jw/cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5.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": 2338707, "tid": 2338707, + "ts": 6197199444908.534, "dur": 22.048, + "args": { + "External id": 34666,"kernel_hash": "cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi", "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/xw/cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi.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": 2338707, "tid": 2338707, + "ts": 6197199444957.354, "dur": 205.174, + "args": { + "External id": 34667,"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": 2338707, "tid": 2338707, + "ts": 6197199445018.845, "dur": 14.169, + "args": { + "External id": 34668,"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": 2338707, "tid": 2338707, + "ts": 6197199445025.430, "dur": 6.385, + "args": { + "External id": 34669,"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": 2338707, "tid": 2338707, + "ts": 6197199445035.960, "dur": 5.460, + "args": { + "External id": 34670,"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": 2338707, "tid": 2338707, + "ts": 6197199445042.784, "dur": 1.326, + "args": { + "External id": 34671,"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": 2338707, "tid": 2338707, + "ts": 6197199445047.324, "dur": 46.553, + "args": { + "External id": 34672,"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": 2338707, "tid": 2338707, + "ts": 6197199445177.640, "dur": 66.701, + "args": { + "External id": 34673,"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": 2338707, "tid": 2338707, + "ts": 6197199445284.234, "dur": 34.787, + "args": { + "External id": 34674,"kernel_hash": "cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/dm/cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43.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": 2338707, "tid": 2338707, + "ts": 6197199445333.309, "dur": 49.392, + "args": { + "External id": 34675,"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": 2338707, "tid": 2338707, + "ts": 6197199445392.836, "dur": 39.079, + "args": { + "External id": 34676,"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": 2338707, "tid": 2338707, + "ts": 6197199445458.595, "dur": 31.276, + "args": { + "External id": 34677,"kernel_hash": "cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/b7/cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu.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": 2338707, "tid": 2338707, + "ts": 6197199445498.605, "dur": 40.039, + "args": { + "External id": 34678,"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": 2338707, "tid": 2338707, + "ts": 6197199445559.239, "dur": 19.569, + "args": { + "External id": 34679,"kernel_hash": "cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/gi/cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb.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": 2338707, "tid": 2338707, + "ts": 6197199445770.961, "dur": 105.138, + "args": { + "External id": 34680,"Record function id": 0, "Ev Idx": 17852 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6197199445968.625, "dur": 56.294, + "args": { + "External id": 34681,"Record function id": 0, "Ev Idx": 17853 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.17)", "pid": 2338707, "tid": 2338707, + "ts": 6197199446036.029, "dur": 31405.396, + "args": { + "External id": 34682,"Record function id": 0, "Ev Idx": 17854 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.17)", "pid": 2338707, "tid": 2338707, + "ts": 6197199446045.515, "dur": 1149.490, + "args": { + "External id": 34683,"Record function id": 0, "Ev Idx": 17855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6197199446188.224, "dur": 11.425, + "args": { + "External id": 34684,"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": 2338707, "tid": 2338707, + "ts": 6197199446216.480, "dur": 42.008, + "args": { + "External id": 34685,"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": 2338707, "tid": 2338707, + "ts": 6197199446224.039, "dur": 3.022, + "args": { + "External id": 34686,"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": 2338707, "tid": 2338707, + "ts": 6197199446231.551, "dur": 0.515, + "args": { + "External id": 34687,"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": 2338707, "tid": 2338707, + "ts": 6197199446233.269, "dur": 0.712, + "args": { + "External id": 34688,"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": 2338707, "tid": 2338707, + "ts": 6197199446235.026, "dur": 0.467, + "args": { + "External id": 34689,"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": 2338707, "tid": 2338707, + "ts": 6197199446239.091, "dur": 0.660, + "args": { + "External id": 34690,"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": 2338707, "tid": 2338707, + "ts": 6197199446241.280, "dur": 0.441, + "args": { + "External id": 34691,"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": 2338707, "tid": 2338707, + "ts": 6197199446243.608, "dur": 4.115, + "args": { + "External id": 34692,"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": 2338707, "tid": 2338707, + "ts": 6197199446248.912, "dur": 0.646, + "args": { + "External id": 34693,"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": 2338707, "tid": 2338707, + "ts": 6197199446251.570, "dur": 0.386, + "args": { + "External id": 34694,"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": 2338707, "tid": 2338707, + "ts": 6197199446272.629, "dur": 63.905, + "args": { + "External id": 34695,"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": 2338707, "tid": 2338707, + "ts": 6197199446375.701, "dur": 145.580, + "args": { + "External id": 34696,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2338707, + "ts": 6197199446389.394, "dur": 5.021, + "args": { + "External id": 34697,"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": 2338707, "tid": 2338707, + "ts": 6197199446400.656, "dur": 12.335, + "args": { + "External id": 34698,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2338707, + "ts": 6197199446406.187, "dur": 6.296, + "args": { + "External id": 34699,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2338707, + "ts": 6197199446410.096, "dur": 0.755, + "args": { + "External id": 34700,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197199446420.796, "dur": 34.558, + "args": { + "External id": 34701,"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": 2338707, "tid": 2338707, + "ts": 6197199446423.236, "dur": 1.986, + "args": { + "External id": 34702,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197199446426.886, "dur": 0.596, + "args": { + "External id": 34703,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2338707, + "ts": 6197199446429.264, "dur": 0.609, + "args": { + "External id": 34704,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2338707, + "ts": 6197199446433.556, "dur": 2.862, + "args": { + "External id": 34705,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2338707, + "ts": 6197199446438.121, "dur": 0.613, + "args": { + "External id": 34706,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2338707, + "ts": 6197199446440.192, "dur": 0.329, + "args": { + "External id": 34707,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2338707, + "ts": 6197199446444.129, "dur": 0.764, + "args": { + "External id": 34708,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2338707, + "ts": 6197199446446.072, "dur": 0.463, + "args": { + "External id": 34709,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2338707, + "ts": 6197199446448.580, "dur": 2.188, + "args": { + "External id": 34710,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2338707, + "ts": 6197199446469.580, "dur": 42.357, + "args": { + "External id": 34711,"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": 2338707, "tid": 2338707, + "ts": 6197199446583.993, "dur": 447.844, + "args": { + "External id": 34712,"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": 2338707, "tid": 2338707, + "ts": 6197199446620.835, "dur": 404.456, + "args": { + "External id": 34713,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2338707, + "ts": 6197199446633.555, "dur": 383.941, + "args": { + "External id": 34714,"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": 2338707, "tid": 2338707, + "ts": 6197199447098.960, "dur": 4.753, + "args": { + "External id": 34715,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.17)", "pid": 2338707, "tid": 2338707, + "ts": 6197199447220.350, "dur": 29988.046, + "args": { + "External id": 34716,"Record function id": 0, "Ev Idx": 17888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6197199447342.154, "dur": 7.718, + "args": { + "External id": 34717,"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": 2338707, "tid": 2338707, + "ts": 6197199447353.512, "dur": 1.382, + "args": { + "External id": 34718,"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": 2338707, "tid": 2338707, + "ts": 6197199447357.053, "dur": 4.003, + "args": { + "External id": 34719,"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": 2338707, "tid": 2338707, + "ts": 6197199447363.078, "dur": 0.994, + "args": { + "External id": 34720,"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": 2338707, "tid": 2338707, + "ts": 6197199447365.764, "dur": 1.120, + "args": { + "External id": 34721,"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": 2338707, "tid": 2338707, + "ts": 6197199447368.505, "dur": 1.127, + "args": { + "External id": 34722,"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": 2338707, "tid": 2338707, + "ts": 6197199447373.721, "dur": 1.046, + "args": { + "External id": 34723,"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": 2338707, "tid": 2338707, + "ts": 6197199447376.858, "dur": 2.169, + "args": { + "External id": 34724,"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": 2338707, "tid": 2338707, + "ts": 6197199447380.822, "dur": 0.964, + "args": { + "External id": 34725,"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": 2338707, "tid": 2338707, + "ts": 6197199447383.697, "dur": 0.859, + "args": { + "External id": 34726,"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": 2338707, "tid": 2338707, + "ts": 6197199447415.505, "dur": 29742.174, + "args": { + "External id": 34727,"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": 2338707, "tid": 2338707, + "ts": 6197199447433.736, "dur": 29714.297, + "args": { + "External id": 34728,"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": 2338707, "tid": 2338707, + "ts": 6197199447453.316, "dur": 18.995, + "args": { + "External id": 34729,"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": 2338707, "tid": 2338707, + "ts": 6197199447476.559, "dur": 29629.679, + "args": { + "External id": 34730,"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": 2338707, "tid": 2338707, + "ts": 6197199447479.807, "dur": 29625.837, + "args": { + "External id": 34731,"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": 2338707, "tid": 2338707, + "ts": 6197199447486.243, "dur": 7.162, + "args": { + "External id": 34732,"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": 2338707, "tid": 2338707, + "ts": 6197199447495.476, "dur": 29606.469, + "args": { + "External id": 34733,"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": 2338707, "tid": 2338707, + "ts": 6197199477374.181, "dur": 36.685, + "args": { + "External id": 34734,"Sequence number": 480030, "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": 2338707, "tid": 2338707, "ts": 6197199477374.181, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6197199477395.497, "dur": 10.052, + "args": { + "External id": 34735,"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": 2338707, "tid": 2338707, + "ts": 6197199477399.897, "dur": 5.377, + "args": { + "External id": 34736,"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": 2338707, "tid": 2338707, + "ts": 6197199477489.561, "dur": 87.819, + "args": { + "External id": 34737,"Record function id": 0, "Ev Idx": 17909 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6197199477578.979, "dur": 1322.992, + "args": { + "External id": 34738,"Record function id": 0, "Ev Idx": 17910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197199477626.049, "dur": 1259.757, + "args": { + "External id": 34739,"Sequence number": 480031, "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": 2338707, "tid": 2338707, "ts": 6197199477626.049, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6197199477699.409, "dur": 76.755, + "args": { + "External id": 34740,"kernel_hash": "cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/du/cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs.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": 2338707, "tid": 2338707, + "ts": 6197199477793.876, "dur": 122.298, + "args": { + "External id": 34741,"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": 2338707, "tid": 2338707, + "ts": 6197199477931.244, "dur": 41.598, + "args": { + "External id": 34742,"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": 2338707, "tid": 2338707, + "ts": 6197199477984.193, "dur": 33.377, + "args": { + "External id": 34743,"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": 2338707, "tid": 2338707, + "ts": 6197199478051.291, "dur": 72.816, + "args": { + "External id": 34744,"kernel_hash": "cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5", "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/jw/cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5.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": 2338707, "tid": 2338707, + "ts": 6197199478152.742, "dur": 22.363, + "args": { + "External id": 34745,"kernel_hash": "cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi", "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/xw/cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi.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": 2338707, "tid": 2338707, + "ts": 6197199478202.120, "dur": 154.656, + "args": { + "External id": 34746,"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": 2338707, "tid": 2338707, + "ts": 6197199478263.070, "dur": 13.920, + "args": { + "External id": 34747,"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": 2338707, "tid": 2338707, + "ts": 6197199478269.592, "dur": 6.482, + "args": { + "External id": 34748,"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": 2338707, "tid": 2338707, + "ts": 6197199478280.069, "dur": 5.230, + "args": { + "External id": 34749,"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": 2338707, "tid": 2338707, + "ts": 6197199478286.916, "dur": 1.174, + "args": { + "External id": 34750,"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": 2338707, "tid": 2338707, + "ts": 6197199478290.839, "dur": 6.471, + "args": { + "External id": 34751,"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": 2338707, "tid": 2338707, + "ts": 6197199478369.857, "dur": 66.901, + "args": { + "External id": 34752,"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": 2338707, "tid": 2338707, + "ts": 6197199478475.003, "dur": 34.986, + "args": { + "External id": 34753,"kernel_hash": "cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/dm/cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43.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": 2338707, "tid": 2338707, + "ts": 6197199478521.980, "dur": 50.784, + "args": { + "External id": 34754,"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": 2338707, "tid": 2338707, + "ts": 6197199478585.333, "dur": 40.292, + "args": { + "External id": 34755,"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": 2338707, "tid": 2338707, + "ts": 6197199478652.529, "dur": 30.786, + "args": { + "External id": 34756,"kernel_hash": "cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/b7/cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu.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": 2338707, "tid": 2338707, + "ts": 6197199478692.363, "dur": 62.177, + "args": { + "External id": 34757,"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": 2338707, "tid": 2338707, + "ts": 6197199478780.772, "dur": 23.733, + "args": { + "External id": 34758,"kernel_hash": "cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/gi/cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb.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": 2338707, "tid": 2338707, + "ts": 6197199478976.175, "dur": 134.600, + "args": { + "External id": 34759,"Record function id": 0, "Ev Idx": 17931 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6197199479207.426, "dur": 57.009, + "args": { + "External id": 34760,"Record function id": 0, "Ev Idx": 17932 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.18)", "pid": 2338707, "tid": 2338707, + "ts": 6197199479276.665, "dur": 31516.548, + "args": { + "External id": 34761,"Record function id": 0, "Ev Idx": 17933 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.18)", "pid": 2338707, "tid": 2338707, + "ts": 6197199479286.785, "dur": 1120.005, + "args": { + "External id": 34762,"Record function id": 0, "Ev Idx": 17934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6197199479387.179, "dur": 10.473, + "args": { + "External id": 34763,"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": 2338707, "tid": 2338707, + "ts": 6197199479413.452, "dur": 47.050, + "args": { + "External id": 34764,"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": 2338707, "tid": 2338707, + "ts": 6197199479421.092, "dur": 2.552, + "args": { + "External id": 34765,"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": 2338707, "tid": 2338707, + "ts": 6197199479428.404, "dur": 0.415, + "args": { + "External id": 34766,"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": 2338707, "tid": 2338707, + "ts": 6197199479430.575, "dur": 0.548, + "args": { + "External id": 34767,"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": 2338707, "tid": 2338707, + "ts": 6197199479432.908, "dur": 0.564, + "args": { + "External id": 34768,"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": 2338707, "tid": 2338707, + "ts": 6197199479437.912, "dur": 0.480, + "args": { + "External id": 34769,"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": 2338707, "tid": 2338707, + "ts": 6197199479440.092, "dur": 0.843, + "args": { + "External id": 34770,"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": 2338707, "tid": 2338707, + "ts": 6197199479442.552, "dur": 6.158, + "args": { + "External id": 34771,"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": 2338707, "tid": 2338707, + "ts": 6197199479450.536, "dur": 0.607, + "args": { + "External id": 34772,"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": 2338707, "tid": 2338707, + "ts": 6197199479452.838, "dur": 0.694, + "args": { + "External id": 34773,"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": 2338707, "tid": 2338707, + "ts": 6197199479474.655, "dur": 67.083, + "args": { + "External id": 34774,"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": 2338707, "tid": 2338707, + "ts": 6197199479581.374, "dur": 159.967, + "args": { + "External id": 34775,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2338707, + "ts": 6197199479595.021, "dur": 6.682, + "args": { + "External id": 34776,"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": 2338707, "tid": 2338707, + "ts": 6197199479607.871, "dur": 12.535, + "args": { + "External id": 34777,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2338707, + "ts": 6197199479613.585, "dur": 6.316, + "args": { + "External id": 34778,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2338707, + "ts": 6197199479617.760, "dur": 0.557, + "args": { + "External id": 34779,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197199479628.440, "dur": 34.769, + "args": { + "External id": 34780,"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": 2338707, "tid": 2338707, + "ts": 6197199479631.034, "dur": 0.561, + "args": { + "External id": 34781,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197199479633.778, "dur": 2.562, + "args": { + "External id": 34782,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2338707, + "ts": 6197199479637.504, "dur": 0.585, + "args": { + "External id": 34783,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2338707, + "ts": 6197199479640.041, "dur": 3.339, + "args": { + "External id": 34784,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2338707, + "ts": 6197199479647.100, "dur": 0.398, + "args": { + "External id": 34785,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2338707, + "ts": 6197199479649.020, "dur": 0.347, + "args": { + "External id": 34786,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2338707, + "ts": 6197199479650.609, "dur": 0.499, + "args": { + "External id": 34787,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2338707, + "ts": 6197199479655.716, "dur": 0.480, + "args": { + "External id": 34788,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2338707, + "ts": 6197199479657.797, "dur": 0.376, + "args": { + "External id": 34789,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2338707, + "ts": 6197199479675.556, "dur": 54.972, + "args": { + "External id": 34790,"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": 2338707, "tid": 2338707, + "ts": 6197199479806.567, "dur": 475.989, + "args": { + "External id": 34791,"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": 2338707, "tid": 2338707, + "ts": 6197199479842.932, "dur": 432.280, + "args": { + "External id": 34792,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2338707, + "ts": 6197199479854.860, "dur": 412.662, + "args": { + "External id": 34793,"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": 2338707, "tid": 2338707, + "ts": 6197199480315.101, "dur": 3.585, + "args": { + "External id": 34794,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.18)", "pid": 2338707, "tid": 2338707, + "ts": 6197199480433.428, "dur": 30103.439, + "args": { + "External id": 34795,"Record function id": 0, "Ev Idx": 17967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6197199480554.287, "dur": 8.020, + "args": { + "External id": 34796,"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": 2338707, "tid": 2338707, + "ts": 6197199480566.210, "dur": 1.528, + "args": { + "External id": 34797,"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": 2338707, "tid": 2338707, + "ts": 6197199480569.973, "dur": 3.738, + "args": { + "External id": 34798,"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": 2338707, "tid": 2338707, + "ts": 6197199480575.768, "dur": 1.184, + "args": { + "External id": 34799,"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": 2338707, "tid": 2338707, + "ts": 6197199480578.504, "dur": 0.891, + "args": { + "External id": 34800,"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": 2338707, "tid": 2338707, + "ts": 6197199480580.971, "dur": 1.223, + "args": { + "External id": 34801,"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": 2338707, "tid": 2338707, + "ts": 6197199480584.529, "dur": 1.250, + "args": { + "External id": 34802,"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": 2338707, "tid": 2338707, + "ts": 6197199480587.491, "dur": 2.576, + "args": { + "External id": 34803,"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": 2338707, "tid": 2338707, + "ts": 6197199480591.802, "dur": 0.918, + "args": { + "External id": 34804,"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": 2338707, "tid": 2338707, + "ts": 6197199480596.536, "dur": 0.815, + "args": { + "External id": 34805,"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": 2338707, "tid": 2338707, + "ts": 6197199480617.351, "dur": 29865.255, + "args": { + "External id": 34806,"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": 2338707, "tid": 2338707, + "ts": 6197199480636.346, "dur": 29836.718, + "args": { + "External id": 34807,"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": 2338707, "tid": 2338707, + "ts": 6197199480654.704, "dur": 20.468, + "args": { + "External id": 34808,"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": 2338707, "tid": 2338707, + "ts": 6197199480679.374, "dur": 29748.471, + "args": { + "External id": 34809,"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": 2338707, "tid": 2338707, + "ts": 6197199480682.606, "dur": 29744.590, + "args": { + "External id": 34810,"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": 2338707, "tid": 2338707, + "ts": 6197199480690.578, "dur": 6.670, + "args": { + "External id": 34811,"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": 2338707, "tid": 2338707, + "ts": 6197199480699.517, "dur": 29723.832, + "args": { + "External id": 34812,"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": 2338707, "tid": 2338707, + "ts": 6197199510719.634, "dur": 41.007, + "args": { + "External id": 34813,"Sequence number": 480032, "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": 2338707, "tid": 2338707, "ts": 6197199510719.634, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6197199510744.041, "dur": 10.657, + "args": { + "External id": 34814,"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": 2338707, "tid": 2338707, + "ts": 6197199510748.487, "dur": 5.807, + "args": { + "External id": 34815,"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": 2338707, "tid": 2338707, + "ts": 6197199510842.675, "dur": 86.200, + "args": { + "External id": 34816,"Record function id": 0, "Ev Idx": 17988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6197199510968.415, "dur": 1351.461, + "args": { + "External id": 34817,"Record function id": 0, "Ev Idx": 17989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197199511014.836, "dur": 1288.067, + "args": { + "External id": 34818,"Sequence number": 480033, "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": 2338707, "tid": 2338707, "ts": 6197199511014.836, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6197199511137.452, "dur": 62.858, + "args": { + "External id": 34819,"kernel_hash": "cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/du/cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs.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": 2338707, "tid": 2338707, + "ts": 6197199511215.744, "dur": 121.480, + "args": { + "External id": 34820,"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": 2338707, "tid": 2338707, + "ts": 6197199511353.881, "dur": 43.449, + "args": { + "External id": 34821,"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": 2338707, "tid": 2338707, + "ts": 6197199511405.198, "dur": 32.570, + "args": { + "External id": 34822,"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": 2338707, "tid": 2338707, + "ts": 6197199511470.386, "dur": 33.986, + "args": { + "External id": 34823,"kernel_hash": "cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5", "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/jw/cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5.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": 2338707, "tid": 2338707, + "ts": 6197199511528.351, "dur": 20.556, + "args": { + "External id": 34824,"kernel_hash": "cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi", "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/xw/cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi.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": 2338707, "tid": 2338707, + "ts": 6197199511576.869, "dur": 169.963, + "args": { + "External id": 34825,"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": 2338707, "tid": 2338707, + "ts": 6197199511635.570, "dur": 13.502, + "args": { + "External id": 34826,"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": 2338707, "tid": 2338707, + "ts": 6197199511641.945, "dur": 6.294, + "args": { + "External id": 34827,"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": 2338707, "tid": 2338707, + "ts": 6197199511652.604, "dur": 5.028, + "args": { + "External id": 34828,"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": 2338707, "tid": 2338707, + "ts": 6197199511659.298, "dur": 1.737, + "args": { + "External id": 34829,"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": 2338707, "tid": 2338707, + "ts": 6197199511665.991, "dur": 5.941, + "args": { + "External id": 34830,"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": 2338707, "tid": 2338707, + "ts": 6197199511761.202, "dur": 66.033, + "args": { + "External id": 34831,"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": 2338707, "tid": 2338707, + "ts": 6197199511864.123, "dur": 39.349, + "args": { + "External id": 34832,"kernel_hash": "cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/dm/cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43.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": 2338707, "tid": 2338707, + "ts": 6197199511915.252, "dur": 49.675, + "args": { + "External id": 34833,"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": 2338707, "tid": 2338707, + "ts": 6197199511975.572, "dur": 39.262, + "args": { + "External id": 34834,"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": 2338707, "tid": 2338707, + "ts": 6197199512039.566, "dur": 75.149, + "args": { + "External id": 34835,"kernel_hash": "cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/b7/cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu.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": 2338707, "tid": 2338707, + "ts": 6197199512124.075, "dur": 48.811, + "args": { + "External id": 34836,"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": 2338707, "tid": 2338707, + "ts": 6197199512198.433, "dur": 23.486, + "args": { + "External id": 34837,"kernel_hash": "cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/gi/cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb.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": 2338707, "tid": 2338707, + "ts": 6197199512397.658, "dur": 95.377, + "args": { + "External id": 34838,"Record function id": 0, "Ev Idx": 18010 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6197199512582.291, "dur": 54.721, + "args": { + "External id": 34839,"Record function id": 0, "Ev Idx": 18011 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.19)", "pid": 2338707, "tid": 2338707, + "ts": 6197199512648.203, "dur": 31148.773, + "args": { + "External id": 34840,"Record function id": 0, "Ev Idx": 18012 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.19)", "pid": 2338707, "tid": 2338707, + "ts": 6197199512657.558, "dur": 1145.789, + "args": { + "External id": 34841,"Record function id": 0, "Ev Idx": 18013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6197199512781.465, "dur": 11.029, + "args": { + "External id": 34842,"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": 2338707, "tid": 2338707, + "ts": 6197199512809.506, "dur": 45.729, + "args": { + "External id": 34843,"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": 2338707, "tid": 2338707, + "ts": 6197199512816.972, "dur": 2.846, + "args": { + "External id": 34844,"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": 2338707, "tid": 2338707, + "ts": 6197199512824.870, "dur": 0.693, + "args": { + "External id": 34845,"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": 2338707, "tid": 2338707, + "ts": 6197199512827.248, "dur": 0.818, + "args": { + "External id": 34846,"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": 2338707, "tid": 2338707, + "ts": 6197199512829.409, "dur": 0.525, + "args": { + "External id": 34847,"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": 2338707, "tid": 2338707, + "ts": 6197199512833.965, "dur": 0.622, + "args": { + "External id": 34848,"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": 2338707, "tid": 2338707, + "ts": 6197199512835.815, "dur": 0.669, + "args": { + "External id": 34849,"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": 2338707, "tid": 2338707, + "ts": 6197199512837.927, "dur": 5.306, + "args": { + "External id": 34850,"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": 2338707, "tid": 2338707, + "ts": 6197199512844.865, "dur": 0.566, + "args": { + "External id": 34851,"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": 2338707, "tid": 2338707, + "ts": 6197199512847.641, "dur": 0.509, + "args": { + "External id": 34852,"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": 2338707, "tid": 2338707, + "ts": 6197199512869.057, "dur": 65.480, + "args": { + "External id": 34853,"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": 2338707, "tid": 2338707, + "ts": 6197199512973.682, "dur": 207.366, + "args": { + "External id": 34854,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2338707, + "ts": 6197199512986.393, "dur": 4.312, + "args": { + "External id": 34855,"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": 2338707, "tid": 2338707, + "ts": 6197199513004.450, "dur": 13.024, + "args": { + "External id": 34856,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2338707, + "ts": 6197199513010.196, "dur": 6.771, + "args": { + "External id": 34857,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2338707, + "ts": 6197199513014.989, "dur": 0.561, + "args": { + "External id": 34858,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197199513024.946, "dur": 78.225, + "args": { + "External id": 34859,"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": 2338707, "tid": 2338707, + "ts": 6197199513027.314, "dur": 2.663, + "args": { + "External id": 34860,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197199513031.638, "dur": 0.642, + "args": { + "External id": 34861,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2338707, + "ts": 6197199513033.696, "dur": 0.597, + "args": { + "External id": 34862,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2338707, + "ts": 6197199513038.634, "dur": 2.979, + "args": { + "External id": 34863,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2338707, + "ts": 6197199513043.247, "dur": 0.392, + "args": { + "External id": 34864,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2338707, + "ts": 6197199513045.360, "dur": 0.420, + "args": { + "External id": 34865,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2338707, + "ts": 6197199513049.593, "dur": 0.574, + "args": { + "External id": 34866,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2338707, + "ts": 6197199513092.230, "dur": 0.836, + "args": { + "External id": 34867,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2338707, + "ts": 6197199513095.664, "dur": 2.353, + "args": { + "External id": 34868,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2338707, + "ts": 6197199513124.826, "dur": 45.870, + "args": { + "External id": 34869,"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": 2338707, "tid": 2338707, + "ts": 6197199513245.681, "dur": 419.705, + "args": { + "External id": 34870,"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": 2338707, "tid": 2338707, + "ts": 6197199513281.069, "dur": 378.551, + "args": { + "External id": 34871,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2338707, + "ts": 6197199513295.661, "dur": 357.774, + "args": { + "External id": 34872,"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": 2338707, "tid": 2338707, + "ts": 6197199513693.487, "dur": 2.758, + "args": { + "External id": 34873,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.19)", "pid": 2338707, "tid": 2338707, + "ts": 6197199513829.812, "dur": 29714.780, + "args": { + "External id": 34874,"Record function id": 0, "Ev Idx": 18046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6197199513950.550, "dur": 11.229, + "args": { + "External id": 34875,"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": 2338707, "tid": 2338707, + "ts": 6197199513965.885, "dur": 1.686, + "args": { + "External id": 34876,"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": 2338707, "tid": 2338707, + "ts": 6197199513969.797, "dur": 3.955, + "args": { + "External id": 34877,"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": 2338707, "tid": 2338707, + "ts": 6197199513975.778, "dur": 0.889, + "args": { + "External id": 34878,"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": 2338707, "tid": 2338707, + "ts": 6197199513978.273, "dur": 0.805, + "args": { + "External id": 34879,"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": 2338707, "tid": 2338707, + "ts": 6197199513980.625, "dur": 1.006, + "args": { + "External id": 34880,"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": 2338707, "tid": 2338707, + "ts": 6197199513983.723, "dur": 0.994, + "args": { + "External id": 34881,"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": 2338707, "tid": 2338707, + "ts": 6197199513986.786, "dur": 2.351, + "args": { + "External id": 34882,"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": 2338707, "tid": 2338707, + "ts": 6197199513990.645, "dur": 0.947, + "args": { + "External id": 34883,"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": 2338707, "tid": 2338707, + "ts": 6197199513995.248, "dur": 0.956, + "args": { + "External id": 34884,"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": 2338707, "tid": 2338707, + "ts": 6197199514020.132, "dur": 29473.671, + "args": { + "External id": 34885,"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": 2338707, "tid": 2338707, + "ts": 6197199514038.755, "dur": 29445.463, + "args": { + "External id": 34886,"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": 2338707, "tid": 2338707, + "ts": 6197199514099.473, "dur": 22.367, + "args": { + "External id": 34887,"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": 2338707, "tid": 2338707, + "ts": 6197199514126.455, "dur": 29312.704, + "args": { + "External id": 34888,"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": 2338707, "tid": 2338707, + "ts": 6197199514129.580, "dur": 29309.031, + "args": { + "External id": 34889,"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": 2338707, "tid": 2338707, + "ts": 6197199514136.614, "dur": 7.204, + "args": { + "External id": 34890,"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": 2338707, "tid": 2338707, + "ts": 6197199514145.826, "dur": 29288.851, + "args": { + "External id": 34891,"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": 2338707, "tid": 2338707, + "ts": 6197199543721.665, "dur": 44.450, + "args": { + "External id": 34892,"Sequence number": 480034, "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": 2338707, "tid": 2338707, "ts": 6197199543721.665, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6197199543746.525, "dur": 13.982, + "args": { + "External id": 34893,"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": 2338707, "tid": 2338707, + "ts": 6197199543754.140, "dur": 5.799, + "args": { + "External id": 34894,"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": 2338707, "tid": 2338707, + "ts": 6197199543847.128, "dur": 85.590, + "args": { + "External id": 34895,"Record function id": 0, "Ev Idx": 18067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6197199543934.015, "dur": 1349.721, + "args": { + "External id": 34896,"Record function id": 0, "Ev Idx": 18068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197199543978.735, "dur": 1289.112, + "args": { + "External id": 34897,"Sequence number": 480035, "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": 2338707, "tid": 2338707, "ts": 6197199543978.735, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6197199544093.018, "dur": 66.715, + "args": { + "External id": 34898,"kernel_hash": "cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/du/cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs.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": 2338707, "tid": 2338707, + "ts": 6197199544178.168, "dur": 121.946, + "args": { + "External id": 34899,"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": 2338707, "tid": 2338707, + "ts": 6197199544314.937, "dur": 41.945, + "args": { + "External id": 34900,"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": 2338707, "tid": 2338707, + "ts": 6197199544368.115, "dur": 33.638, + "args": { + "External id": 34901,"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": 2338707, "tid": 2338707, + "ts": 6197199544434.021, "dur": 32.077, + "args": { + "External id": 34902,"kernel_hash": "cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5", "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/jw/cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5.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": 2338707, "tid": 2338707, + "ts": 6197199544489.519, "dur": 19.227, + "args": { + "External id": 34903,"kernel_hash": "cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi", "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/xw/cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi.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": 2338707, "tid": 2338707, + "ts": 6197199544536.033, "dur": 154.848, + "args": { + "External id": 34904,"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": 2338707, "tid": 2338707, + "ts": 6197199544598.166, "dur": 13.171, + "args": { + "External id": 34905,"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": 2338707, "tid": 2338707, + "ts": 6197199544604.659, "dur": 5.726, + "args": { + "External id": 34906,"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": 2338707, "tid": 2338707, + "ts": 6197199544614.578, "dur": 4.899, + "args": { + "External id": 34907,"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": 2338707, "tid": 2338707, + "ts": 6197199544620.975, "dur": 1.462, + "args": { + "External id": 34908,"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": 2338707, "tid": 2338707, + "ts": 6197199544625.800, "dur": 6.104, + "args": { + "External id": 34909,"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": 2338707, "tid": 2338707, + "ts": 6197199544722.722, "dur": 65.866, + "args": { + "External id": 34910,"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": 2338707, "tid": 2338707, + "ts": 6197199544826.398, "dur": 36.122, + "args": { + "External id": 34911,"kernel_hash": "cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/dm/cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43.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": 2338707, "tid": 2338707, + "ts": 6197199544873.738, "dur": 48.888, + "args": { + "External id": 34912,"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": 2338707, "tid": 2338707, + "ts": 6197199544936.339, "dur": 39.435, + "args": { + "External id": 34913,"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": 2338707, "tid": 2338707, + "ts": 6197199545004.206, "dur": 31.768, + "args": { + "External id": 34914,"kernel_hash": "cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/b7/cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu.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": 2338707, "tid": 2338707, + "ts": 6197199545045.225, "dur": 87.455, + "args": { + "External id": 34915,"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": 2338707, "tid": 2338707, + "ts": 6197199545160.231, "dur": 24.543, + "args": { + "External id": 34916,"kernel_hash": "cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/gi/cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb.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": 2338707, "tid": 2338707, + "ts": 6197199545359.245, "dur": 96.634, + "args": { + "External id": 34917,"Record function id": 0, "Ev Idx": 18089 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6197199545548.251, "dur": 57.245, + "args": { + "External id": 34918,"Record function id": 0, "Ev Idx": 18090 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.20)", "pid": 2338707, "tid": 2338707, + "ts": 6197199545616.332, "dur": 32700.074, + "args": { + "External id": 34919,"Record function id": 0, "Ev Idx": 18091 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.20)", "pid": 2338707, "tid": 2338707, + "ts": 6197199545625.365, "dur": 1181.234, + "args": { + "External id": 34920,"Record function id": 0, "Ev Idx": 18092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6197199545747.425, "dur": 11.749, + "args": { + "External id": 34921,"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": 2338707, "tid": 2338707, + "ts": 6197199545776.197, "dur": 43.007, + "args": { + "External id": 34922,"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": 2338707, "tid": 2338707, + "ts": 6197199545783.432, "dur": 2.798, + "args": { + "External id": 34923,"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": 2338707, "tid": 2338707, + "ts": 6197199545791.358, "dur": 0.380, + "args": { + "External id": 34924,"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": 2338707, "tid": 2338707, + "ts": 6197199545793.486, "dur": 0.568, + "args": { + "External id": 34925,"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": 2338707, "tid": 2338707, + "ts": 6197199545795.321, "dur": 0.614, + "args": { + "External id": 34926,"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": 2338707, "tid": 2338707, + "ts": 6197199545800.232, "dur": 0.404, + "args": { + "External id": 34927,"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": 2338707, "tid": 2338707, + "ts": 6197199545801.723, "dur": 0.466, + "args": { + "External id": 34928,"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": 2338707, "tid": 2338707, + "ts": 6197199545803.807, "dur": 5.074, + "args": { + "External id": 34929,"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": 2338707, "tid": 2338707, + "ts": 6197199545810.078, "dur": 0.330, + "args": { + "External id": 34930,"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": 2338707, "tid": 2338707, + "ts": 6197199545812.150, "dur": 0.349, + "args": { + "External id": 34931,"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": 2338707, "tid": 2338707, + "ts": 6197199545833.909, "dur": 64.236, + "args": { + "External id": 34932,"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": 2338707, "tid": 2338707, + "ts": 6197199545938.256, "dur": 187.411, + "args": { + "External id": 34933,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2338707, + "ts": 6197199545951.210, "dur": 4.634, + "args": { + "External id": 34934,"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": 2338707, "tid": 2338707, + "ts": 6197199545961.667, "dur": 15.090, + "args": { + "External id": 34935,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2338707, + "ts": 6197199545967.194, "dur": 9.019, + "args": { + "External id": 34936,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2338707, + "ts": 6197199545973.808, "dur": 0.710, + "args": { + "External id": 34937,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197199545984.654, "dur": 34.347, + "args": { + "External id": 34938,"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": 2338707, "tid": 2338707, + "ts": 6197199545986.493, "dur": 2.630, + "args": { + "External id": 34939,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197199545991.116, "dur": 0.760, + "args": { + "External id": 34940,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2338707, + "ts": 6197199545993.238, "dur": 0.468, + "args": { + "External id": 34941,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2338707, + "ts": 6197199545997.664, "dur": 2.801, + "args": { + "External id": 34942,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2338707, + "ts": 6197199546001.965, "dur": 0.400, + "args": { + "External id": 34943,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2338707, + "ts": 6197199546003.867, "dur": 0.434, + "args": { + "External id": 34944,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2338707, + "ts": 6197199546008.059, "dur": 0.511, + "args": { + "External id": 34945,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2338707, + "ts": 6197199546010.167, "dur": 0.344, + "args": { + "External id": 34946,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2338707, + "ts": 6197199546011.974, "dur": 2.647, + "args": { + "External id": 34947,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2338707, + "ts": 6197199546032.751, "dur": 80.987, + "args": { + "External id": 34948,"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": 2338707, "tid": 2338707, + "ts": 6197199546195.196, "dur": 472.950, + "args": { + "External id": 34949,"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": 2338707, "tid": 2338707, + "ts": 6197199546233.086, "dur": 429.103, + "args": { + "External id": 34950,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2338707, + "ts": 6197199546245.161, "dur": 410.878, + "args": { + "External id": 34951,"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": 2338707, "tid": 2338707, + "ts": 6197199546697.413, "dur": 18.816, + "args": { + "External id": 34952,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.20)", "pid": 2338707, "tid": 2338707, + "ts": 6197199546833.373, "dur": 31215.332, + "args": { + "External id": 34953,"Record function id": 0, "Ev Idx": 18125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6197199546954.583, "dur": 8.500, + "args": { + "External id": 34954,"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": 2338707, "tid": 2338707, + "ts": 6197199546967.331, "dur": 1.142, + "args": { + "External id": 34955,"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": 2338707, "tid": 2338707, + "ts": 6197199546970.280, "dur": 3.965, + "args": { + "External id": 34956,"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": 2338707, "tid": 2338707, + "ts": 6197199546976.392, "dur": 0.976, + "args": { + "External id": 34957,"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": 2338707, "tid": 2338707, + "ts": 6197199546978.913, "dur": 0.976, + "args": { + "External id": 34958,"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": 2338707, "tid": 2338707, + "ts": 6197199546981.434, "dur": 0.820, + "args": { + "External id": 34959,"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": 2338707, "tid": 2338707, + "ts": 6197199546984.230, "dur": 0.905, + "args": { + "External id": 34960,"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": 2338707, "tid": 2338707, + "ts": 6197199546987.123, "dur": 2.100, + "args": { + "External id": 34961,"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": 2338707, "tid": 2338707, + "ts": 6197199546991.053, "dur": 0.971, + "args": { + "External id": 34962,"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": 2338707, "tid": 2338707, + "ts": 6197199546995.715, "dur": 0.852, + "args": { + "External id": 34963,"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": 2338707, "tid": 2338707, + "ts": 6197199547017.479, "dur": 30978.030, + "args": { + "External id": 34964,"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": 2338707, "tid": 2338707, + "ts": 6197199547036.110, "dur": 30949.940, + "args": { + "External id": 34965,"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": 2338707, "tid": 2338707, + "ts": 6197199547093.247, "dur": 23.921, + "args": { + "External id": 34966,"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": 2338707, "tid": 2338707, + "ts": 6197199547122.253, "dur": 30817.925, + "args": { + "External id": 34967,"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": 2338707, "tid": 2338707, + "ts": 6197199547125.327, "dur": 30814.055, + "args": { + "External id": 34968,"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": 2338707, "tid": 2338707, + "ts": 6197199547133.798, "dur": 7.980, + "args": { + "External id": 34969,"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": 2338707, "tid": 2338707, + "ts": 6197199547143.764, "dur": 30792.217, + "args": { + "External id": 34970,"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": 2338707, "tid": 2338707, + "ts": 6197199578245.402, "dur": 37.190, + "args": { + "External id": 34971,"Sequence number": 480036, "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": 2338707, "tid": 2338707, "ts": 6197199578245.402, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6197199578265.762, "dur": 10.883, + "args": { + "External id": 34972,"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": 2338707, "tid": 2338707, + "ts": 6197199578270.354, "dur": 5.938, + "args": { + "External id": 34973,"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": 2338707, "tid": 2338707, + "ts": 6197199578363.956, "dur": 88.017, + "args": { + "External id": 34974,"Record function id": 0, "Ev Idx": 18146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6197199578453.568, "dur": 1306.028, + "args": { + "External id": 34975,"Record function id": 0, "Ev Idx": 18147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197199578498.729, "dur": 1243.494, + "args": { + "External id": 34976,"Sequence number": 480037, "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": 2338707, "tid": 2338707, "ts": 6197199578498.729, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6197199578578.072, "dur": 59.302, + "args": { + "External id": 34977,"kernel_hash": "cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/du/cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs.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": 2338707, "tid": 2338707, + "ts": 6197199578652.688, "dur": 132.160, + "args": { + "External id": 34978,"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": 2338707, "tid": 2338707, + "ts": 6197199578802.858, "dur": 45.293, + "args": { + "External id": 34979,"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": 2338707, "tid": 2338707, + "ts": 6197199578859.875, "dur": 34.978, + "args": { + "External id": 34980,"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": 2338707, "tid": 2338707, + "ts": 6197199578927.113, "dur": 32.157, + "args": { + "External id": 34981,"kernel_hash": "cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5", "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/jw/cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5.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": 2338707, "tid": 2338707, + "ts": 6197199578984.777, "dur": 20.778, + "args": { + "External id": 34982,"kernel_hash": "cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi", "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/xw/cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi.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": 2338707, "tid": 2338707, + "ts": 6197199579032.201, "dur": 198.813, + "args": { + "External id": 34983,"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": 2338707, "tid": 2338707, + "ts": 6197199579131.447, "dur": 15.133, + "args": { + "External id": 34984,"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": 2338707, "tid": 2338707, + "ts": 6197199579137.581, "dur": 7.834, + "args": { + "External id": 34985,"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": 2338707, "tid": 2338707, + "ts": 6197199579149.866, "dur": 4.974, + "args": { + "External id": 34986,"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": 2338707, "tid": 2338707, + "ts": 6197199579156.733, "dur": 1.575, + "args": { + "External id": 34987,"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": 2338707, "tid": 2338707, + "ts": 6197199579161.126, "dur": 6.156, + "args": { + "External id": 34988,"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": 2338707, "tid": 2338707, + "ts": 6197199579245.106, "dur": 65.891, + "args": { + "External id": 34989,"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": 2338707, "tid": 2338707, + "ts": 6197199579347.971, "dur": 37.113, + "args": { + "External id": 34990,"kernel_hash": "cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/dm/cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43.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": 2338707, "tid": 2338707, + "ts": 6197199579396.657, "dur": 49.846, + "args": { + "External id": 34991,"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": 2338707, "tid": 2338707, + "ts": 6197199579459.758, "dur": 39.906, + "args": { + "External id": 34992,"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": 2338707, "tid": 2338707, + "ts": 6197199579524.432, "dur": 30.449, + "args": { + "External id": 34993,"kernel_hash": "cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/b7/cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu.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": 2338707, "tid": 2338707, + "ts": 6197199579564.115, "dur": 40.527, + "args": { + "External id": 34994,"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": 2338707, "tid": 2338707, + "ts": 6197199579626.794, "dur": 21.988, + "args": { + "External id": 34995,"kernel_hash": "cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/gi/cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb.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": 2338707, "tid": 2338707, + "ts": 6197199579839.043, "dur": 92.975, + "args": { + "External id": 34996,"Record function id": 0, "Ev Idx": 18168 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6197199580021.717, "dur": 98.842, + "args": { + "External id": 34997,"Record function id": 0, "Ev Idx": 18169 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.21)", "pid": 2338707, "tid": 2338707, + "ts": 6197199580133.103, "dur": 31142.055, + "args": { + "External id": 34998,"Record function id": 0, "Ev Idx": 18170 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.21)", "pid": 2338707, "tid": 2338707, + "ts": 6197199580144.466, "dur": 1092.037, + "args": { + "External id": 34999,"Record function id": 0, "Ev Idx": 18171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6197199580248.376, "dur": 11.174, + "args": { + "External id": 35000,"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": 2338707, "tid": 2338707, + "ts": 6197199580275.499, "dur": 41.078, + "args": { + "External id": 35001,"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": 2338707, "tid": 2338707, + "ts": 6197199580282.042, "dur": 2.859, + "args": { + "External id": 35002,"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": 2338707, "tid": 2338707, + "ts": 6197199580290.450, "dur": 0.478, + "args": { + "External id": 35003,"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": 2338707, "tid": 2338707, + "ts": 6197199580292.518, "dur": 0.679, + "args": { + "External id": 35004,"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": 2338707, "tid": 2338707, + "ts": 6197199580294.403, "dur": 0.566, + "args": { + "External id": 35005,"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": 2338707, "tid": 2338707, + "ts": 6197199580297.399, "dur": 0.614, + "args": { + "External id": 35006,"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": 2338707, "tid": 2338707, + "ts": 6197199580299.628, "dur": 0.462, + "args": { + "External id": 35007,"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": 2338707, "tid": 2338707, + "ts": 6197199580301.376, "dur": 4.836, + "args": { + "External id": 35008,"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": 2338707, "tid": 2338707, + "ts": 6197199580307.518, "dur": 0.491, + "args": { + "External id": 35009,"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": 2338707, "tid": 2338707, + "ts": 6197199580308.935, "dur": 0.431, + "args": { + "External id": 35010,"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": 2338707, "tid": 2338707, + "ts": 6197199580330.242, "dur": 66.688, + "args": { + "External id": 35011,"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": 2338707, "tid": 2338707, + "ts": 6197199580435.597, "dur": 134.234, + "args": { + "External id": 35012,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2338707, + "ts": 6197199580448.775, "dur": 3.698, + "args": { + "External id": 35013,"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": 2338707, "tid": 2338707, + "ts": 6197199580460.669, "dur": 12.363, + "args": { + "External id": 35014,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2338707, + "ts": 6197199580466.007, "dur": 6.524, + "args": { + "External id": 35015,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2338707, + "ts": 6197199580470.177, "dur": 0.757, + "args": { + "External id": 35016,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197199580480.823, "dur": 27.722, + "args": { + "External id": 35017,"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": 2338707, "tid": 2338707, + "ts": 6197199580482.264, "dur": 1.759, + "args": { + "External id": 35018,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197199580485.325, "dur": 0.399, + "args": { + "External id": 35019,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2338707, + "ts": 6197199580486.501, "dur": 0.462, + "args": { + "External id": 35020,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2338707, + "ts": 6197199580490.180, "dur": 3.081, + "args": { + "External id": 35021,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2338707, + "ts": 6197199580494.547, "dur": 0.409, + "args": { + "External id": 35022,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2338707, + "ts": 6197199580496.064, "dur": 0.560, + "args": { + "External id": 35023,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2338707, + "ts": 6197199580499.129, "dur": 0.514, + "args": { + "External id": 35024,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2338707, + "ts": 6197199580500.790, "dur": 0.552, + "args": { + "External id": 35025,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2338707, + "ts": 6197199580502.311, "dur": 2.101, + "args": { + "External id": 35026,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2338707, + "ts": 6197199580520.536, "dur": 40.182, + "args": { + "External id": 35027,"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": 2338707, "tid": 2338707, + "ts": 6197199580631.195, "dur": 477.229, + "args": { + "External id": 35028,"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": 2338707, "tid": 2338707, + "ts": 6197199580665.339, "dur": 435.396, + "args": { + "External id": 35029,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2338707, + "ts": 6197199580676.909, "dur": 377.857, + "args": { + "External id": 35030,"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": 2338707, "tid": 2338707, + "ts": 6197199581141.508, "dur": 3.700, + "args": { + "External id": 35031,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.21)", "pid": 2338707, "tid": 2338707, + "ts": 6197199581262.423, "dur": 29749.519, + "args": { + "External id": 35032,"Record function id": 0, "Ev Idx": 18204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6197199581386.442, "dur": 8.100, + "args": { + "External id": 35033,"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": 2338707, "tid": 2338707, + "ts": 6197199581398.337, "dur": 1.070, + "args": { + "External id": 35034,"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": 2338707, "tid": 2338707, + "ts": 6197199581401.399, "dur": 3.925, + "args": { + "External id": 35035,"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": 2338707, "tid": 2338707, + "ts": 6197199581407.509, "dur": 0.880, + "args": { + "External id": 35036,"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": 2338707, "tid": 2338707, + "ts": 6197199581409.787, "dur": 1.034, + "args": { + "External id": 35037,"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": 2338707, "tid": 2338707, + "ts": 6197199581412.273, "dur": 0.879, + "args": { + "External id": 35038,"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": 2338707, "tid": 2338707, + "ts": 6197199581414.994, "dur": 0.801, + "args": { + "External id": 35039,"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": 2338707, "tid": 2338707, + "ts": 6197199581417.480, "dur": 2.116, + "args": { + "External id": 35040,"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": 2338707, "tid": 2338707, + "ts": 6197199581421.348, "dur": 1.128, + "args": { + "External id": 35041,"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": 2338707, "tid": 2338707, + "ts": 6197199581426.635, "dur": 0.988, + "args": { + "External id": 35042,"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": 2338707, "tid": 2338707, + "ts": 6197199581448.607, "dur": 29514.532, + "args": { + "External id": 35043,"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": 2338707, "tid": 2338707, + "ts": 6197199581467.070, "dur": 29486.387, + "args": { + "External id": 35044,"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": 2338707, "tid": 2338707, + "ts": 6197199581490.544, "dur": 20.465, + "args": { + "External id": 35045,"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": 2338707, "tid": 2338707, + "ts": 6197199581515.320, "dur": 29391.476, + "args": { + "External id": 35046,"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": 2338707, "tid": 2338707, + "ts": 6197199581518.491, "dur": 29387.618, + "args": { + "External id": 35047,"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": 2338707, "tid": 2338707, + "ts": 6197199581525.518, "dur": 6.886, + "args": { + "External id": 35048,"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": 2338707, "tid": 2338707, + "ts": 6197199581534.407, "dur": 29367.840, + "args": { + "External id": 35049,"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": 2338707, "tid": 2338707, + "ts": 6197199611206.954, "dur": 37.517, + "args": { + "External id": 35050,"Sequence number": 480038, "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": 2338707, "tid": 2338707, "ts": 6197199611206.954, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6197199611227.815, "dur": 10.886, + "args": { + "External id": 35051,"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": 2338707, "tid": 2338707, + "ts": 6197199611232.484, "dur": 5.807, + "args": { + "External id": 35052,"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": 2338707, "tid": 2338707, + "ts": 6197199611327.017, "dur": 88.584, + "args": { + "External id": 35053,"Record function id": 0, "Ev Idx": 18225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6197199611417.183, "dur": 1329.457, + "args": { + "External id": 35054,"Record function id": 0, "Ev Idx": 18226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197199611462.486, "dur": 1266.165, + "args": { + "External id": 35055,"Sequence number": 480039, "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": 2338707, "tid": 2338707, "ts": 6197199611462.486, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6197199611540.645, "dur": 59.362, + "args": { + "External id": 35056,"kernel_hash": "cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/du/cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs.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": 2338707, "tid": 2338707, + "ts": 6197199611615.958, "dur": 131.763, + "args": { + "External id": 35057,"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": 2338707, "tid": 2338707, + "ts": 6197199611764.962, "dur": 48.659, + "args": { + "External id": 35058,"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": 2338707, "tid": 2338707, + "ts": 6197199611823.622, "dur": 37.280, + "args": { + "External id": 35059,"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": 2338707, "tid": 2338707, + "ts": 6197199611889.922, "dur": 38.498, + "args": { + "External id": 35060,"kernel_hash": "cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5", "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/jw/cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5.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": 2338707, "tid": 2338707, + "ts": 6197199611954.276, "dur": 20.111, + "args": { + "External id": 35061,"kernel_hash": "cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi", "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/xw/cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi.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": 2338707, "tid": 2338707, + "ts": 6197199612001.332, "dur": 201.790, + "args": { + "External id": 35062,"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": 2338707, "tid": 2338707, + "ts": 6197199612102.101, "dur": 15.020, + "args": { + "External id": 35063,"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": 2338707, "tid": 2338707, + "ts": 6197199612108.746, "dur": 7.227, + "args": { + "External id": 35064,"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": 2338707, "tid": 2338707, + "ts": 6197199612120.038, "dur": 5.095, + "args": { + "External id": 35065,"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": 2338707, "tid": 2338707, + "ts": 6197199612126.500, "dur": 1.352, + "args": { + "External id": 35066,"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": 2338707, "tid": 2338707, + "ts": 6197199612130.556, "dur": 6.831, + "args": { + "External id": 35067,"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": 2338707, "tid": 2338707, + "ts": 6197199612217.224, "dur": 68.340, + "args": { + "External id": 35068,"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": 2338707, "tid": 2338707, + "ts": 6197199612325.134, "dur": 37.794, + "args": { + "External id": 35069,"kernel_hash": "cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/dm/cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43.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": 2338707, "tid": 2338707, + "ts": 6197199612375.313, "dur": 50.209, + "args": { + "External id": 35070,"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": 2338707, "tid": 2338707, + "ts": 6197199612436.192, "dur": 41.218, + "args": { + "External id": 35071,"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": 2338707, "tid": 2338707, + "ts": 6197199612503.024, "dur": 31.853, + "args": { + "External id": 35072,"kernel_hash": "cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/b7/cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu.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": 2338707, "tid": 2338707, + "ts": 6197199612543.601, "dur": 44.019, + "args": { + "External id": 35073,"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": 2338707, "tid": 2338707, + "ts": 6197199612611.135, "dur": 22.136, + "args": { + "External id": 35074,"kernel_hash": "cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/gi/cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb.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": 2338707, "tid": 2338707, + "ts": 6197199612825.003, "dur": 97.000, + "args": { + "External id": 35075,"Record function id": 0, "Ev Idx": 18247 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6197199613010.890, "dur": 101.470, + "args": { + "External id": 35076,"Record function id": 0, "Ev Idx": 18248 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.22)", "pid": 2338707, "tid": 2338707, + "ts": 6197199613125.803, "dur": 33226.332, + "args": { + "External id": 35077,"Record function id": 0, "Ev Idx": 18249 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.22)", "pid": 2338707, "tid": 2338707, + "ts": 6197199613137.480, "dur": 1094.345, + "args": { + "External id": 35078,"Record function id": 0, "Ev Idx": 18250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6197199613241.897, "dur": 11.105, + "args": { + "External id": 35079,"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": 2338707, "tid": 2338707, + "ts": 6197199613269.699, "dur": 40.536, + "args": { + "External id": 35080,"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": 2338707, "tid": 2338707, + "ts": 6197199613276.001, "dur": 2.779, + "args": { + "External id": 35081,"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": 2338707, "tid": 2338707, + "ts": 6197199613283.623, "dur": 0.312, + "args": { + "External id": 35082,"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": 2338707, "tid": 2338707, + "ts": 6197199613285.097, "dur": 0.551, + "args": { + "External id": 35083,"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": 2338707, "tid": 2338707, + "ts": 6197199613287.088, "dur": 0.649, + "args": { + "External id": 35084,"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": 2338707, "tid": 2338707, + "ts": 6197199613291.552, "dur": 0.704, + "args": { + "External id": 35085,"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": 2338707, "tid": 2338707, + "ts": 6197199613293.772, "dur": 0.581, + "args": { + "External id": 35086,"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": 2338707, "tid": 2338707, + "ts": 6197199613295.356, "dur": 4.859, + "args": { + "External id": 35087,"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": 2338707, "tid": 2338707, + "ts": 6197199613301.319, "dur": 0.414, + "args": { + "External id": 35088,"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": 2338707, "tid": 2338707, + "ts": 6197199613302.659, "dur": 0.459, + "args": { + "External id": 35089,"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": 2338707, "tid": 2338707, + "ts": 6197199613324.535, "dur": 68.882, + "args": { + "External id": 35090,"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": 2338707, "tid": 2338707, + "ts": 6197199613432.774, "dur": 135.372, + "args": { + "External id": 35091,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2338707, + "ts": 6197199613445.759, "dur": 4.489, + "args": { + "External id": 35092,"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": 2338707, "tid": 2338707, + "ts": 6197199613456.135, "dur": 12.173, + "args": { + "External id": 35093,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2338707, + "ts": 6197199613461.847, "dur": 5.976, + "args": { + "External id": 35094,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2338707, + "ts": 6197199613465.603, "dur": 0.743, + "args": { + "External id": 35095,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197199613476.094, "dur": 32.794, + "args": { + "External id": 35096,"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": 2338707, "tid": 2338707, + "ts": 6197199613477.724, "dur": 2.161, + "args": { + "External id": 35097,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197199613481.659, "dur": 0.461, + "args": { + "External id": 35098,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2338707, + "ts": 6197199613483.810, "dur": 0.554, + "args": { + "External id": 35099,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2338707, + "ts": 6197199613487.271, "dur": 2.911, + "args": { + "External id": 35100,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2338707, + "ts": 6197199613493.587, "dur": 0.532, + "args": { + "External id": 35101,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2338707, + "ts": 6197199613495.346, "dur": 0.436, + "args": { + "External id": 35102,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2338707, + "ts": 6197199613499.030, "dur": 0.386, + "args": { + "External id": 35103,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2338707, + "ts": 6197199613500.769, "dur": 0.444, + "args": { + "External id": 35104,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2338707, + "ts": 6197199613502.133, "dur": 2.524, + "args": { + "External id": 35105,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2338707, + "ts": 6197199613521.250, "dur": 37.287, + "args": { + "External id": 35106,"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": 2338707, "tid": 2338707, + "ts": 6197199613629.802, "dur": 478.577, + "args": { + "External id": 35107,"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": 2338707, "tid": 2338707, + "ts": 6197199613665.386, "dur": 436.273, + "args": { + "External id": 35108,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2338707, + "ts": 6197199613677.295, "dur": 377.981, + "args": { + "External id": 35109,"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": 2338707, "tid": 2338707, + "ts": 6197199614140.799, "dur": 3.102, + "args": { + "External id": 35110,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.22)", "pid": 2338707, "tid": 2338707, + "ts": 6197199614256.613, "dur": 31851.738, + "args": { + "External id": 35111,"Record function id": 0, "Ev Idx": 18283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6197199614378.441, "dur": 8.177, + "args": { + "External id": 35112,"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": 2338707, "tid": 2338707, + "ts": 6197199614390.584, "dur": 1.253, + "args": { + "External id": 35113,"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": 2338707, "tid": 2338707, + "ts": 6197199614394.087, "dur": 3.235, + "args": { + "External id": 35114,"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": 2338707, "tid": 2338707, + "ts": 6197199614399.248, "dur": 1.040, + "args": { + "External id": 35115,"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": 2338707, "tid": 2338707, + "ts": 6197199614401.900, "dur": 0.926, + "args": { + "External id": 35116,"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": 2338707, "tid": 2338707, + "ts": 6197199614404.347, "dur": 0.776, + "args": { + "External id": 35117,"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": 2338707, "tid": 2338707, + "ts": 6197199614406.934, "dur": 0.984, + "args": { + "External id": 35118,"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": 2338707, "tid": 2338707, + "ts": 6197199614409.554, "dur": 2.494, + "args": { + "External id": 35119,"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": 2338707, "tid": 2338707, + "ts": 6197199614413.787, "dur": 0.901, + "args": { + "External id": 35120,"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": 2338707, "tid": 2338707, + "ts": 6197199614418.883, "dur": 0.744, + "args": { + "External id": 35121,"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": 2338707, "tid": 2338707, + "ts": 6197199614439.769, "dur": 31582.643, + "args": { + "External id": 35122,"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": 2338707, "tid": 2338707, + "ts": 6197199614457.900, "dur": 31554.452, + "args": { + "External id": 35123,"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": 2338707, "tid": 2338707, + "ts": 6197199614477.000, "dur": 19.653, + "args": { + "External id": 35124,"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": 2338707, "tid": 2338707, + "ts": 6197199614500.717, "dur": 31466.342, + "args": { + "External id": 35125,"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": 2338707, "tid": 2338707, + "ts": 6197199614503.654, "dur": 31462.599, + "args": { + "External id": 35126,"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": 2338707, "tid": 2338707, + "ts": 6197199614510.412, "dur": 8.202, + "args": { + "External id": 35127,"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": 2338707, "tid": 2338707, + "ts": 6197199614520.834, "dur": 31440.703, + "args": { + "External id": 35128,"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": 2338707, "tid": 2338707, + "ts": 6197199646282.662, "dur": 41.610, + "args": { + "External id": 35129,"Sequence number": 480040, "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": 2338707, "tid": 2338707, "ts": 6197199646282.662, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6197199646308.141, "dur": 10.311, + "args": { + "External id": 35130,"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": 2338707, "tid": 2338707, + "ts": 6197199646312.580, "dur": 5.666, + "args": { + "External id": 35131,"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": 2338707, "tid": 2338707, + "ts": 6197199646398.603, "dur": 86.849, + "args": { + "External id": 35132,"Record function id": 0, "Ev Idx": 18304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6197199646487.328, "dur": 1314.765, + "args": { + "External id": 35133,"Record function id": 0, "Ev Idx": 18305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197199646531.034, "dur": 1253.467, + "args": { + "External id": 35134,"Sequence number": 480041, "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": 2338707, "tid": 2338707, "ts": 6197199646531.034, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6197199646614.597, "dur": 61.355, + "args": { + "External id": 35135,"kernel_hash": "cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/du/cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs.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": 2338707, "tid": 2338707, + "ts": 6197199646691.522, "dur": 132.052, + "args": { + "External id": 35136,"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": 2338707, "tid": 2338707, + "ts": 6197199646842.155, "dur": 43.703, + "args": { + "External id": 35137,"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": 2338707, "tid": 2338707, + "ts": 6197199646896.709, "dur": 33.067, + "args": { + "External id": 35138,"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": 2338707, "tid": 2338707, + "ts": 6197199646963.149, "dur": 33.811, + "args": { + "External id": 35139,"kernel_hash": "cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5", "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/jw/cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5.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": 2338707, "tid": 2338707, + "ts": 6197199647020.276, "dur": 19.875, + "args": { + "External id": 35140,"kernel_hash": "cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi", "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/xw/cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi.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": 2338707, "tid": 2338707, + "ts": 6197199647105.108, "dur": 159.604, + "args": { + "External id": 35141,"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": 2338707, "tid": 2338707, + "ts": 6197199647166.759, "dur": 14.602, + "args": { + "External id": 35142,"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": 2338707, "tid": 2338707, + "ts": 6197199647172.867, "dur": 7.419, + "args": { + "External id": 35143,"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": 2338707, "tid": 2338707, + "ts": 6197199647184.624, "dur": 5.408, + "args": { + "External id": 35144,"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": 2338707, "tid": 2338707, + "ts": 6197199647191.495, "dur": 1.182, + "args": { + "External id": 35145,"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": 2338707, "tid": 2338707, + "ts": 6197199647195.785, "dur": 5.983, + "args": { + "External id": 35146,"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": 2338707, "tid": 2338707, + "ts": 6197199647278.811, "dur": 66.261, + "args": { + "External id": 35147,"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": 2338707, "tid": 2338707, + "ts": 6197199647385.363, "dur": 37.401, + "args": { + "External id": 35148,"kernel_hash": "cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/dm/cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43.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": 2338707, "tid": 2338707, + "ts": 6197199647434.088, "dur": 50.861, + "args": { + "External id": 35149,"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": 2338707, "tid": 2338707, + "ts": 6197199647495.233, "dur": 40.149, + "args": { + "External id": 35150,"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": 2338707, "tid": 2338707, + "ts": 6197199647562.196, "dur": 34.728, + "args": { + "External id": 35151,"kernel_hash": "cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/b7/cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu.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": 2338707, "tid": 2338707, + "ts": 6197199647606.023, "dur": 41.125, + "args": { + "External id": 35152,"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": 2338707, "tid": 2338707, + "ts": 6197199647669.455, "dur": 20.019, + "args": { + "External id": 35153,"kernel_hash": "cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/gi/cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb.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": 2338707, "tid": 2338707, + "ts": 6197199647879.898, "dur": 99.007, + "args": { + "External id": 35154,"Record function id": 0, "Ev Idx": 18326 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6197199648112.107, "dur": 60.414, + "args": { + "External id": 35155,"Record function id": 0, "Ev Idx": 18327 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.23)", "pid": 2338707, "tid": 2338707, + "ts": 6197199648184.213, "dur": 33091.511, + "args": { + "External id": 35156,"Record function id": 0, "Ev Idx": 18328 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.23)", "pid": 2338707, "tid": 2338707, + "ts": 6197199648194.509, "dur": 1115.410, + "args": { + "External id": 35157,"Record function id": 0, "Ev Idx": 18329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6197199648297.425, "dur": 14.126, + "args": { + "External id": 35158,"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": 2338707, "tid": 2338707, + "ts": 6197199648327.900, "dur": 41.830, + "args": { + "External id": 35159,"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": 2338707, "tid": 2338707, + "ts": 6197199648334.407, "dur": 2.617, + "args": { + "External id": 35160,"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": 2338707, "tid": 2338707, + "ts": 6197199648341.454, "dur": 0.305, + "args": { + "External id": 35161,"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": 2338707, "tid": 2338707, + "ts": 6197199648343.081, "dur": 0.357, + "args": { + "External id": 35162,"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": 2338707, "tid": 2338707, + "ts": 6197199648344.544, "dur": 0.653, + "args": { + "External id": 35163,"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": 2338707, "tid": 2338707, + "ts": 6197199648347.984, "dur": 0.498, + "args": { + "External id": 35164,"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": 2338707, "tid": 2338707, + "ts": 6197199648349.964, "dur": 0.560, + "args": { + "External id": 35165,"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": 2338707, "tid": 2338707, + "ts": 6197199648354.441, "dur": 2.466, + "args": { + "External id": 35166,"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": 2338707, "tid": 2338707, + "ts": 6197199648358.787, "dur": 2.297, + "args": { + "External id": 35167,"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": 2338707, "tid": 2338707, + "ts": 6197199648362.770, "dur": 0.301, + "args": { + "External id": 35168,"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": 2338707, "tid": 2338707, + "ts": 6197199648383.229, "dur": 66.940, + "args": { + "External id": 35169,"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": 2338707, "tid": 2338707, + "ts": 6197199648488.286, "dur": 137.047, + "args": { + "External id": 35170,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2338707, + "ts": 6197199648500.625, "dur": 5.073, + "args": { + "External id": 35171,"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": 2338707, "tid": 2338707, + "ts": 6197199648512.035, "dur": 11.980, + "args": { + "External id": 35172,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2338707, + "ts": 6197199648517.303, "dur": 6.251, + "args": { + "External id": 35173,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2338707, + "ts": 6197199648521.560, "dur": 0.547, + "args": { + "External id": 35174,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197199648531.397, "dur": 31.716, + "args": { + "External id": 35175,"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": 2338707, "tid": 2338707, + "ts": 6197199648533.304, "dur": 2.258, + "args": { + "External id": 35176,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197199648537.155, "dur": 0.648, + "args": { + "External id": 35177,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2338707, + "ts": 6197199648538.693, "dur": 0.529, + "args": { + "External id": 35178,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2338707, + "ts": 6197199648542.546, "dur": 0.361, + "args": { + "External id": 35179,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2338707, + "ts": 6197199648544.214, "dur": 2.709, + "args": { + "External id": 35180,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2338707, + "ts": 6197199648548.456, "dur": 0.524, + "args": { + "External id": 35181,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2338707, + "ts": 6197199648552.374, "dur": 0.601, + "args": { + "External id": 35182,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2338707, + "ts": 6197199648554.125, "dur": 0.396, + "args": { + "External id": 35183,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2338707, + "ts": 6197199648555.918, "dur": 2.287, + "args": { + "External id": 35184,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2338707, + "ts": 6197199648576.483, "dur": 39.330, + "args": { + "External id": 35185,"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": 2338707, "tid": 2338707, + "ts": 6197199648688.375, "dur": 490.887, + "args": { + "External id": 35186,"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": 2338707, "tid": 2338707, + "ts": 6197199648741.959, "dur": 430.324, + "args": { + "External id": 35187,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2338707, + "ts": 6197199648755.472, "dur": 406.836, + "args": { + "External id": 35188,"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": 2338707, "tid": 2338707, + "ts": 6197199649215.249, "dur": 3.176, + "args": { + "External id": 35189,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.23)", "pid": 2338707, "tid": 2338707, + "ts": 6197199649334.826, "dur": 31680.832, + "args": { + "External id": 35190,"Record function id": 0, "Ev Idx": 18362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6197199649455.549, "dur": 7.883, + "args": { + "External id": 35191,"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": 2338707, "tid": 2338707, + "ts": 6197199649467.377, "dur": 1.197, + "args": { + "External id": 35192,"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": 2338707, "tid": 2338707, + "ts": 6197199649470.683, "dur": 1.044, + "args": { + "External id": 35193,"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": 2338707, "tid": 2338707, + "ts": 6197199649473.672, "dur": 3.167, + "args": { + "External id": 35194,"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": 2338707, "tid": 2338707, + "ts": 6197199649478.908, "dur": 1.012, + "args": { + "External id": 35195,"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": 2338707, "tid": 2338707, + "ts": 6197199649481.497, "dur": 0.700, + "args": { + "External id": 35196,"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": 2338707, "tid": 2338707, + "ts": 6197199649484.055, "dur": 0.982, + "args": { + "External id": 35197,"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": 2338707, "tid": 2338707, + "ts": 6197199649487.453, "dur": 2.341, + "args": { + "External id": 35198,"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": 2338707, "tid": 2338707, + "ts": 6197199649491.391, "dur": 0.719, + "args": { + "External id": 35199,"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": 2338707, "tid": 2338707, + "ts": 6197199649495.930, "dur": 0.699, + "args": { + "External id": 35200,"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": 2338707, "tid": 2338707, + "ts": 6197199649518.570, "dur": 31448.171, + "args": { + "External id": 35201,"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": 2338707, "tid": 2338707, + "ts": 6197199649536.073, "dur": 31421.297, + "args": { + "External id": 35202,"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": 2338707, "tid": 2338707, + "ts": 6197199649554.720, "dur": 18.100, + "args": { + "External id": 35203,"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": 2338707, "tid": 2338707, + "ts": 6197199649577.155, "dur": 31338.338, + "args": { + "External id": 35204,"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": 2338707, "tid": 2338707, + "ts": 6197199649580.524, "dur": 31334.369, + "args": { + "External id": 35205,"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": 2338707, "tid": 2338707, + "ts": 6197199649586.951, "dur": 10.043, + "args": { + "External id": 35206,"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": 2338707, "tid": 2338707, + "ts": 6197199649599.008, "dur": 31312.374, + "args": { + "External id": 35207,"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": 2338707, "tid": 2338707, + "ts": 6197199681210.373, "dur": 35.828, + "args": { + "External id": 35208,"Sequence number": 480042, "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": 2338707, "tid": 2338707, "ts": 6197199681210.373, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6197199681230.162, "dur": 10.411, + "args": { + "External id": 35209,"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": 2338707, "tid": 2338707, + "ts": 6197199681234.708, "dur": 5.474, + "args": { + "External id": 35210,"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": 2338707, "tid": 2338707, + "ts": 6197199681325.518, "dur": 84.416, + "args": { + "External id": 35211,"Record function id": 0, "Ev Idx": 18383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6197199681411.479, "dur": 1284.398, + "args": { + "External id": 35212,"Record function id": 0, "Ev Idx": 18384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197199681455.310, "dur": 1223.226, + "args": { + "External id": 35213,"Sequence number": 480043, "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": 2338707, "tid": 2338707, "ts": 6197199681455.310, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6197199681533.872, "dur": 56.251, + "args": { + "External id": 35214,"kernel_hash": "cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/du/cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs.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": 2338707, "tid": 2338707, + "ts": 6197199681603.691, "dur": 130.971, + "args": { + "External id": 35215,"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": 2338707, "tid": 2338707, + "ts": 6197199681753.528, "dur": 49.633, + "args": { + "External id": 35216,"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": 2338707, "tid": 2338707, + "ts": 6197199681814.835, "dur": 33.742, + "args": { + "External id": 35217,"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": 2338707, "tid": 2338707, + "ts": 6197199681877.738, "dur": 32.266, + "args": { + "External id": 35218,"kernel_hash": "cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5", "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/jw/cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5.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": 2338707, "tid": 2338707, + "ts": 6197199681936.058, "dur": 19.625, + "args": { + "External id": 35219,"kernel_hash": "cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi", "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/xw/cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi.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": 2338707, "tid": 2338707, + "ts": 6197199681980.213, "dur": 203.734, + "args": { + "External id": 35220,"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": 2338707, "tid": 2338707, + "ts": 6197199682044.413, "dur": 53.761, + "args": { + "External id": 35221,"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": 2338707, "tid": 2338707, + "ts": 6197199682050.372, "dur": 46.503, + "args": { + "External id": 35222,"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": 2338707, "tid": 2338707, + "ts": 6197199682102.323, "dur": 5.578, + "args": { + "External id": 35223,"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": 2338707, "tid": 2338707, + "ts": 6197199682109.358, "dur": 1.021, + "args": { + "External id": 35224,"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": 2338707, "tid": 2338707, + "ts": 6197199682113.400, "dur": 4.905, + "args": { + "External id": 35225,"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": 2338707, "tid": 2338707, + "ts": 6197199682198.322, "dur": 63.852, + "args": { + "External id": 35226,"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": 2338707, "tid": 2338707, + "ts": 6197199682300.364, "dur": 36.355, + "args": { + "External id": 35227,"kernel_hash": "cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/dm/cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43.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": 2338707, "tid": 2338707, + "ts": 6197199682348.986, "dur": 48.793, + "args": { + "External id": 35228,"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": 2338707, "tid": 2338707, + "ts": 6197199682408.729, "dur": 39.390, + "args": { + "External id": 35229,"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": 2338707, "tid": 2338707, + "ts": 6197199682474.763, "dur": 31.532, + "args": { + "External id": 35230,"kernel_hash": "cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/b7/cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu.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": 2338707, "tid": 2338707, + "ts": 6197199682515.307, "dur": 39.476, + "args": { + "External id": 35231,"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": 2338707, "tid": 2338707, + "ts": 6197199682578.729, "dur": 20.935, + "args": { + "External id": 35232,"kernel_hash": "cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/gi/cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb.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": 2338707, "tid": 2338707, + "ts": 6197199682793.212, "dur": 93.677, + "args": { + "External id": 35233,"Record function id": 0, "Ev Idx": 18405 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6197199682980.858, "dur": 60.355, + "args": { + "External id": 35234,"Record function id": 0, "Ev Idx": 18406 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.24)", "pid": 2338707, "tid": 2338707, + "ts": 6197199683051.373, "dur": 32065.311, + "args": { + "External id": 35235,"Record function id": 0, "Ev Idx": 18407 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.24)", "pid": 2338707, "tid": 2338707, + "ts": 6197199683103.081, "dur": 1121.373, + "args": { + "External id": 35236,"Record function id": 0, "Ev Idx": 18408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6197199683207.001, "dur": 11.257, + "args": { + "External id": 35237,"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": 2338707, "tid": 2338707, + "ts": 6197199683234.386, "dur": 40.931, + "args": { + "External id": 35238,"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": 2338707, "tid": 2338707, + "ts": 6197199683241.236, "dur": 2.771, + "args": { + "External id": 35239,"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": 2338707, "tid": 2338707, + "ts": 6197199683248.506, "dur": 0.468, + "args": { + "External id": 35240,"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": 2338707, "tid": 2338707, + "ts": 6197199683249.766, "dur": 0.418, + "args": { + "External id": 35241,"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": 2338707, "tid": 2338707, + "ts": 6197199683251.392, "dur": 0.552, + "args": { + "External id": 35242,"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": 2338707, "tid": 2338707, + "ts": 6197199683255.779, "dur": 0.677, + "args": { + "External id": 35243,"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": 2338707, "tid": 2338707, + "ts": 6197199683257.849, "dur": 0.537, + "args": { + "External id": 35244,"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": 2338707, "tid": 2338707, + "ts": 6197199683259.721, "dur": 4.768, + "args": { + "External id": 35245,"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": 2338707, "tid": 2338707, + "ts": 6197199683265.681, "dur": 0.528, + "args": { + "External id": 35246,"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": 2338707, "tid": 2338707, + "ts": 6197199683267.651, "dur": 0.533, + "args": { + "External id": 35247,"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": 2338707, "tid": 2338707, + "ts": 6197199683290.553, "dur": 65.749, + "args": { + "External id": 35248,"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": 2338707, "tid": 2338707, + "ts": 6197199683394.075, "dur": 145.235, + "args": { + "External id": 35249,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2338707, + "ts": 6197199683407.595, "dur": 5.454, + "args": { + "External id": 35250,"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": 2338707, "tid": 2338707, + "ts": 6197199683419.147, "dur": 12.095, + "args": { + "External id": 35251,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2338707, + "ts": 6197199683424.774, "dur": 5.972, + "args": { + "External id": 35252,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2338707, + "ts": 6197199683428.553, "dur": 0.794, + "args": { + "External id": 35253,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197199683438.973, "dur": 31.306, + "args": { + "External id": 35254,"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": 2338707, "tid": 2338707, + "ts": 6197199683441.289, "dur": 2.271, + "args": { + "External id": 35255,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197199683445.302, "dur": 0.374, + "args": { + "External id": 35256,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2338707, + "ts": 6197199683446.692, "dur": 0.425, + "args": { + "External id": 35257,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2338707, + "ts": 6197199683450.468, "dur": 2.941, + "args": { + "External id": 35258,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2338707, + "ts": 6197199683454.819, "dur": 0.675, + "args": { + "External id": 35259,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2338707, + "ts": 6197199683456.604, "dur": 0.285, + "args": { + "External id": 35260,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2338707, + "ts": 6197199683460.363, "dur": 0.327, + "args": { + "External id": 35261,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2338707, + "ts": 6197199683462.420, "dur": 0.364, + "args": { + "External id": 35262,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2338707, + "ts": 6197199683464.153, "dur": 2.067, + "args": { + "External id": 35263,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2338707, + "ts": 6197199683487.539, "dur": 38.304, + "args": { + "External id": 35264,"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": 2338707, "tid": 2338707, + "ts": 6197199683606.583, "dur": 490.248, + "args": { + "External id": 35265,"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": 2338707, "tid": 2338707, + "ts": 6197199683641.533, "dur": 409.737, + "args": { + "External id": 35266,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2338707, + "ts": 6197199683658.785, "dur": 385.387, + "args": { + "External id": 35267,"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": 2338707, "tid": 2338707, + "ts": 6197199684132.453, "dur": 4.100, + "args": { + "External id": 35268,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.24)", "pid": 2338707, "tid": 2338707, + "ts": 6197199684249.715, "dur": 30604.428, + "args": { + "External id": 35269,"Record function id": 0, "Ev Idx": 18441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6197199684370.628, "dur": 7.831, + "args": { + "External id": 35270,"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": 2338707, "tid": 2338707, + "ts": 6197199684382.471, "dur": 0.991, + "args": { + "External id": 35271,"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": 2338707, "tid": 2338707, + "ts": 6197199684385.706, "dur": 3.599, + "args": { + "External id": 35272,"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": 2338707, "tid": 2338707, + "ts": 6197199684391.229, "dur": 1.161, + "args": { + "External id": 35273,"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": 2338707, "tid": 2338707, + "ts": 6197199684393.985, "dur": 1.087, + "args": { + "External id": 35274,"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": 2338707, "tid": 2338707, + "ts": 6197199684396.758, "dur": 1.040, + "args": { + "External id": 35275,"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": 2338707, "tid": 2338707, + "ts": 6197199684399.555, "dur": 0.876, + "args": { + "External id": 35276,"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": 2338707, "tid": 2338707, + "ts": 6197199684402.052, "dur": 2.066, + "args": { + "External id": 35277,"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": 2338707, "tid": 2338707, + "ts": 6197199684406.573, "dur": 0.982, + "args": { + "External id": 35278,"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": 2338707, "tid": 2338707, + "ts": 6197199684411.860, "dur": 0.732, + "args": { + "External id": 35279,"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": 2338707, "tid": 2338707, + "ts": 6197199684433.059, "dur": 30369.482, + "args": { + "External id": 35280,"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": 2338707, "tid": 2338707, + "ts": 6197199684451.279, "dur": 30341.993, + "args": { + "External id": 35281,"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": 2338707, "tid": 2338707, + "ts": 6197199684471.476, "dur": 20.129, + "args": { + "External id": 35282,"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": 2338707, "tid": 2338707, + "ts": 6197199684496.125, "dur": 30254.457, + "args": { + "External id": 35283,"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": 2338707, "tid": 2338707, + "ts": 6197199684499.196, "dur": 30250.746, + "args": { + "External id": 35284,"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": 2338707, "tid": 2338707, + "ts": 6197199684505.264, "dur": 8.228, + "args": { + "External id": 35285,"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": 2338707, "tid": 2338707, + "ts": 6197199684515.854, "dur": 30230.284, + "args": { + "External id": 35286,"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": 2338707, "tid": 2338707, + "ts": 6197199715018.092, "dur": 65.657, + "args": { + "External id": 35287,"Sequence number": 480044, "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": 2338707, "tid": 2338707, "ts": 6197199715018.092, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6197199715039.075, "dur": 9.507, + "args": { + "External id": 35288,"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": 2338707, "tid": 2338707, + "ts": 6197199715043.108, "dur": 5.283, + "args": { + "External id": 35289,"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": 2338707, "tid": 2338707, + "ts": 6197199715167.008, "dur": 84.053, + "args": { + "External id": 35290,"Record function id": 0, "Ev Idx": 18462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6197199715252.671, "dur": 1308.161, + "args": { + "External id": 35291,"Record function id": 0, "Ev Idx": 18463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197199715297.807, "dur": 1246.781, + "args": { + "External id": 35292,"Sequence number": 480045, "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": 2338707, "tid": 2338707, "ts": 6197199715297.807, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6197199715376.575, "dur": 58.098, + "args": { + "External id": 35293,"kernel_hash": "cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/du/cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs.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": 2338707, "tid": 2338707, + "ts": 6197199715451.962, "dur": 121.994, + "args": { + "External id": 35294,"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": 2338707, "tid": 2338707, + "ts": 6197199715588.864, "dur": 41.943, + "args": { + "External id": 35295,"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": 2338707, "tid": 2338707, + "ts": 6197199715642.309, "dur": 33.979, + "args": { + "External id": 35296,"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": 2338707, "tid": 2338707, + "ts": 6197199715720.932, "dur": 37.297, + "args": { + "External id": 35297,"kernel_hash": "cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5", "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/jw/cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5.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": 2338707, "tid": 2338707, + "ts": 6197199715786.418, "dur": 22.296, + "args": { + "External id": 35298,"kernel_hash": "cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi", "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/xw/cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi.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": 2338707, "tid": 2338707, + "ts": 6197199715832.934, "dur": 154.591, + "args": { + "External id": 35299,"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": 2338707, "tid": 2338707, + "ts": 6197199715896.058, "dur": 14.023, + "args": { + "External id": 35300,"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": 2338707, "tid": 2338707, + "ts": 6197199715902.158, "dur": 7.079, + "args": { + "External id": 35301,"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": 2338707, "tid": 2338707, + "ts": 6197199715913.109, "dur": 4.902, + "args": { + "External id": 35302,"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": 2338707, "tid": 2338707, + "ts": 6197199715919.636, "dur": 1.320, + "args": { + "External id": 35303,"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": 2338707, "tid": 2338707, + "ts": 6197199715923.935, "dur": 4.190, + "args": { + "External id": 35304,"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": 2338707, "tid": 2338707, + "ts": 6197199715999.881, "dur": 101.828, + "args": { + "External id": 35305,"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": 2338707, "tid": 2338707, + "ts": 6197199716145.331, "dur": 37.206, + "args": { + "External id": 35306,"kernel_hash": "cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/dm/cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43.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": 2338707, "tid": 2338707, + "ts": 6197199716194.294, "dur": 56.434, + "args": { + "External id": 35307,"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": 2338707, "tid": 2338707, + "ts": 6197199716267.399, "dur": 40.247, + "args": { + "External id": 35308,"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": 2338707, "tid": 2338707, + "ts": 6197199716337.835, "dur": 35.357, + "args": { + "External id": 35309,"kernel_hash": "cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/b7/cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu.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": 2338707, "tid": 2338707, + "ts": 6197199716382.528, "dur": 41.967, + "args": { + "External id": 35310,"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": 2338707, "tid": 2338707, + "ts": 6197199716444.868, "dur": 22.350, + "args": { + "External id": 35311,"kernel_hash": "cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/gi/cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb.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": 2338707, "tid": 2338707, + "ts": 6197199716637.056, "dur": 113.086, + "args": { + "External id": 35312,"Record function id": 0, "Ev Idx": 18484 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6197199716847.327, "dur": 58.225, + "args": { + "External id": 35313,"Record function id": 0, "Ev Idx": 18485 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.25)", "pid": 2338707, "tid": 2338707, + "ts": 6197199716916.786, "dur": 30106.145, + "args": { + "External id": 35314,"Record function id": 0, "Ev Idx": 18486 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.25)", "pid": 2338707, "tid": 2338707, + "ts": 6197199716927.832, "dur": 1237.383, + "args": { + "External id": 35315,"Record function id": 0, "Ev Idx": 18487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6197199717027.989, "dur": 10.543, + "args": { + "External id": 35316,"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": 2338707, "tid": 2338707, + "ts": 6197199717054.050, "dur": 83.598, + "args": { + "External id": 35317,"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": 2338707, "tid": 2338707, + "ts": 6197199717100.538, "dur": 3.060, + "args": { + "External id": 35318,"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": 2338707, "tid": 2338707, + "ts": 6197199717108.478, "dur": 0.568, + "args": { + "External id": 35319,"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": 2338707, "tid": 2338707, + "ts": 6197199717110.176, "dur": 0.583, + "args": { + "External id": 35320,"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": 2338707, "tid": 2338707, + "ts": 6197199717112.782, "dur": 0.511, + "args": { + "External id": 35321,"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": 2338707, "tid": 2338707, + "ts": 6197199717117.263, "dur": 0.681, + "args": { + "External id": 35322,"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": 2338707, "tid": 2338707, + "ts": 6197199717118.922, "dur": 0.342, + "args": { + "External id": 35323,"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": 2338707, "tid": 2338707, + "ts": 6197199717120.913, "dur": 4.950, + "args": { + "External id": 35324,"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": 2338707, "tid": 2338707, + "ts": 6197199717127.583, "dur": 0.705, + "args": { + "External id": 35325,"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": 2338707, "tid": 2338707, + "ts": 6197199717129.656, "dur": 0.592, + "args": { + "External id": 35326,"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": 2338707, "tid": 2338707, + "ts": 6197199717153.119, "dur": 66.985, + "args": { + "External id": 35327,"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": 2338707, "tid": 2338707, + "ts": 6197199717259.897, "dur": 183.413, + "args": { + "External id": 35328,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "27264000", "8", "1", "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": 2338707, "tid": 2338707, + "ts": 6197199717307.456, "dur": 8.414, + "args": { + "External id": 35329,"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": 2338707, "tid": 2338707, + "ts": 6197199717322.796, "dur": 11.814, + "args": { + "External id": 35330,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "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": 2338707, "tid": 2338707, + "ts": 6197199717328.123, "dur": 5.762, + "args": { + "External id": 35331,"Record function id": 0, "Concrete Inputs": ["", "0", "27264000", "54528000", "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": 2338707, "tid": 2338707, + "ts": 6197199717331.664, "dur": 0.610, + "args": { + "External id": 35332,"Record function id": 0, "Concrete Inputs": ["", "[27264000]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197199717343.913, "dur": 33.575, + "args": { + "External id": 35333,"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": 2338707, "tid": 2338707, + "ts": 6197199717352.180, "dur": 0.417, + "args": { + "External id": 35334,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "27264000"], "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": 2338707, "tid": 2338707, + "ts": 6197199717355.528, "dur": 0.396, + "args": { + "External id": 35335,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "27264512"], "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": 2338707, "tid": 2338707, + "ts": 6197199717356.922, "dur": 0.414, + "args": { + "External id": 35336,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29361664"], "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": 2338707, "tid": 2338707, + "ts": 6197199717358.401, "dur": 4.773, + "args": { + "External id": 35337,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29885952"], "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": 2338707, "tid": 2338707, + "ts": 6197199717364.574, "dur": 0.343, + "args": { + "External id": 35338,"Record function id": 0, "Concrete Inputs": ["", "[2097152]", "[1]", "30410240"], "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": 2338707, "tid": 2338707, + "ts": 6197199717365.823, "dur": 0.283, + "args": { + "External id": 35339,"Record function id": 0, "Concrete Inputs": ["", "[512]", "[1]", "32507392"], "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": 2338707, "tid": 2338707, + "ts": 6197199717369.829, "dur": 0.342, + "args": { + "External id": 35340,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "32507904"], "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": 2338707, "tid": 2338707, + "ts": 6197199717371.477, "dur": 0.179, + "args": { + "External id": 35341,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "39847936"], "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": 2338707, "tid": 2338707, + "ts": 6197199717372.623, "dur": 0.355, + "args": { + "External id": 35342,"Record function id": 0, "Concrete Inputs": ["", "[7340032]", "[1]", "47187968"], "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": 2338707, "tid": 2338707, + "ts": 6197199717391.264, "dur": 42.526, + "args": { + "External id": 35343,"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": 2338707, "tid": 2338707, + "ts": 6197199717508.699, "dur": 488.630, + "args": { + "External id": 35344,"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": 2338707, "tid": 2338707, + "ts": 6197199717544.110, "dur": 446.304, + "args": { + "External id": 35345,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 1, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2338707, + "ts": 6197199717556.444, "dur": 426.408, + "args": { + "External id": 35346,"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": 2338707, "tid": 2338707, + "ts": 6197199718032.025, "dur": 3.365, + "args": { + "External id": 35347,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.25)", "pid": 2338707, "tid": 2338707, + "ts": 6197199718194.881, "dur": 28591.102, + "args": { + "External id": 35348,"Record function id": 0, "Ev Idx": 18520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6197199718319.102, "dur": 7.972, + "args": { + "External id": 35349,"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": 2338707, "tid": 2338707, + "ts": 6197199718331.086, "dur": 0.999, + "args": { + "External id": 35350,"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": 2338707, "tid": 2338707, + "ts": 6197199718334.351, "dur": 1.269, + "args": { + "External id": 35351,"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": 2338707, "tid": 2338707, + "ts": 6197199718337.749, "dur": 3.459, + "args": { + "External id": 35352,"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": 2338707, "tid": 2338707, + "ts": 6197199718342.644, "dur": 1.061, + "args": { + "External id": 35353,"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": 2338707, "tid": 2338707, + "ts": 6197199718345.204, "dur": 1.434, + "args": { + "External id": 35354,"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": 2338707, "tid": 2338707, + "ts": 6197199718348.337, "dur": 0.965, + "args": { + "External id": 35355,"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": 2338707, "tid": 2338707, + "ts": 6197199718351.560, "dur": 2.646, + "args": { + "External id": 35356,"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": 2338707, "tid": 2338707, + "ts": 6197199718355.882, "dur": 0.988, + "args": { + "External id": 35357,"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": 2338707, "tid": 2338707, + "ts": 6197199718360.831, "dur": 0.743, + "args": { + "External id": 35358,"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": 2338707, "tid": 2338707, + "ts": 6197199718382.551, "dur": 28349.178, + "args": { + "External id": 35359,"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": 2338707, "tid": 2338707, + "ts": 6197199718401.455, "dur": 28319.244, + "args": { + "External id": 35360,"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": 2338707, "tid": 2338707, + "ts": 6197199718421.094, "dur": 18.087, + "args": { + "External id": 35361,"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": 2338707, "tid": 2338707, + "ts": 6197199718443.131, "dur": 28221.264, + "args": { + "External id": 35362,"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": 2338707, "tid": 2338707, + "ts": 6197199718446.414, "dur": 28217.281, + "args": { + "External id": 35363,"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": 2338707, "tid": 2338707, + "ts": 6197199718453.475, "dur": 10.336, + "args": { + "External id": 35364,"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": 2338707, "tid": 2338707, + "ts": 6197199718466.152, "dur": 28193.884, + "args": { + "External id": 35365,"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": 2338707, "tid": 2338707, + "ts": 6197199746956.069, "dur": 38.260, + "args": { + "External id": 35366,"Sequence number": 480046, "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": 2338707, "tid": 2338707, "ts": 6197199746956.069, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6197199746977.847, "dur": 10.718, + "args": { + "External id": 35367,"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": 2338707, "tid": 2338707, + "ts": 6197199746982.570, "dur": 5.736, + "args": { + "External id": 35368,"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": 2338707, "tid": 2338707, + "ts": 6197199747102.481, "dur": 85.748, + "args": { + "External id": 35369,"Record function id": 0, "Ev Idx": 18541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6197199747190.277, "dur": 1324.498, + "args": { + "External id": 35370,"Record function id": 0, "Ev Idx": 18542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197199747236.770, "dur": 1261.807, + "args": { + "External id": 35371,"Sequence number": 480047, "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": 2338707, "tid": 2338707, "ts": 6197199747236.770, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6197199747318.084, "dur": 63.216, + "args": { + "External id": 35372,"kernel_hash": "cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/du/cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs.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": 2338707, "tid": 2338707, + "ts": 6197199747398.065, "dur": 121.569, + "args": { + "External id": 35373,"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": 2338707, "tid": 2338707, + "ts": 6197199747533.692, "dur": 43.886, + "args": { + "External id": 35374,"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": 2338707, "tid": 2338707, + "ts": 6197199747588.863, "dur": 34.323, + "args": { + "External id": 35375,"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": 2338707, "tid": 2338707, + "ts": 6197199747651.339, "dur": 31.319, + "args": { + "External id": 35376,"kernel_hash": "cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5", "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/jw/cjwvznu7opd4dgjdmuzqwvdt6lhviut6sieddl3tkktzzxofvzt5.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": 2338707, "tid": 2338707, + "ts": 6197199747725.406, "dur": 24.717, + "args": { + "External id": 35377,"kernel_hash": "cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi", "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/xw/cxwsdhjjh6geaxjsibzwiye546vfxkikrsjksa55ws62s4qjbrgi.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": 2338707, "tid": 2338707, + "ts": 6197199747780.106, "dur": 152.590, + "args": { + "External id": 35378,"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": 2338707, "tid": 2338707, + "ts": 6197199747841.261, "dur": 14.635, + "args": { + "External id": 35379,"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": 2338707, "tid": 2338707, + "ts": 6197199747847.441, "dur": 7.586, + "args": { + "External id": 35380,"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": 2338707, "tid": 2338707, + "ts": 6197199747858.887, "dur": 5.099, + "args": { + "External id": 35381,"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": 2338707, "tid": 2338707, + "ts": 6197199747865.709, "dur": 1.053, + "args": { + "External id": 35382,"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": 2338707, "tid": 2338707, + "ts": 6197199747869.751, "dur": 4.256, + "args": { + "External id": 35383,"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": 2338707, "tid": 2338707, + "ts": 6197199747944.997, "dur": 62.064, + "args": { + "External id": 35384,"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": 2338707, "tid": 2338707, + "ts": 6197199748047.477, "dur": 85.577, + "args": { + "External id": 35385,"kernel_hash": "cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/dm/cdmhy2hmlhgvjhiufswlbupaei6azjf5dk6opbfvxrcm5fprtg43.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": 2338707, "tid": 2338707, + "ts": 6197199748147.557, "dur": 57.752, + "args": { + "External id": 35386,"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": 2338707, "tid": 2338707, + "ts": 6197199748216.798, "dur": 40.588, + "args": { + "External id": 35387,"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": 2338707, "tid": 2338707, + "ts": 6197199748285.855, "dur": 32.396, + "args": { + "External id": 35388,"kernel_hash": "cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu", "grid": "grid(469762048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "469762048"], "kernel_file": "/tmp/torchinductor_cvm/b7/cb7afso2qkvt3i6pzg4vijqlu6jjlgwbjzzyh4oznhdt75ykajyu.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": 2338707, "tid": 2338707, + "ts": 6197199748326.967, "dur": 43.043, + "args": { + "External id": 35389,"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": 2338707, "tid": 2338707, + "ts": 6197199748393.273, "dur": 23.682, + "args": { + "External id": 35390,"kernel_hash": "cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/gi/cgik4ktlpri5iod5s5ynrzau3qlffebgfpe6sdr2lepxbydsdryb.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": 2338707, "tid": 2338707, + "ts": 6197199748593.634, "dur": 41.639, + "args": { + "External id": 35391,"Record function id": 0, "Ev Idx": 18563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197199748821.185, "dur": 416.497, + "args": { + "External id": 35392,"Sequence number": 480048, "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": 2338707, "tid": 2338707, "ts": 6197199748821.185, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6197199748862.112, "dur": 10.578, + "args": { + "External id": 35393,"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": 2338707, "tid": 2338707, + "ts": 6197199748864.860, "dur": 7.344, + "args": { + "External id": 35394,"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": 2338707, "tid": 2338707, + "ts": 6197199748885.700, "dur": 15.855, + "args": { + "External id": 35395,"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": 2338707, "tid": 2338707, + "ts": 6197199748889.583, "dur": 11.353, + "args": { + "External id": 35396,"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": 2338707, "tid": 2338707, + "ts": 6197199748913.225, "dur": 5.961, + "args": { + "External id": 35397,"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": 2338707, "tid": 2338707, + "ts": 6197199749209.038, "dur": 9.919, + "args": { + "External id": 35398,"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": 2338707, "tid": 2338707, + "ts": 6197199749213.232, "dur": 5.378, + "args": { + "External id": 35399,"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": 2338707, "tid": 2338707, + "ts": 6197199749271.939, "dur": 167.433, + "args": { + "External id": 35400,"Sequence number": 480049, "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": 2338707, "tid": 2338707, + "ts": 6197199749274.915, "dur": 17.747, + "args": { + "External id": 35401,"Sequence number": 480049, "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": 2338707, "tid": 2338707, "ts": 6197199749274.915, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6197199749280.522, "dur": 9.810, + "args": { + "External id": 35402,"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": 2338707, "tid": 2338707, + "ts": 6197199749287.504, "dur": 2.455, + "args": { + "External id": 35403,"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": 2338707, "tid": 2338707, + "ts": 6197199749295.699, "dur": 143.294, + "args": { + "External id": 35404,"Sequence number": 480050, "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": 2338707, "tid": 2338707, + "ts": 6197199749299.455, "dur": 5.671, + "args": { + "External id": 35405,"Sequence number": 480050, "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": 2338707, "tid": 2338707, + "ts": 6197199749300.242, "dur": 4.710, + "args": { + "External id": 35406,"Sequence number": 480050, "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": 2338707, "tid": 2338707, "ts": 6197199749300.242, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6197199749309.235, "dur": 117.188, + "args": { + "External id": 35407,"Sequence number": 480051, "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": 2338707, "tid": 2338707, "ts": 6197199749309.235, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6197199749429.770, "dur": 7.333, + "args": { + "External id": 35408,"Sequence number": 480052, "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": 2338707, "tid": 2338707, "ts": 6197199749429.770, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338707, "tid": 2338707, + "ts": 6197199749451.775, "dur": 82.870, + "args": { + "External id": 35409,"Sequence number": 480053, "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": 2338707, "tid": 2338707, + "ts": 6197199749453.070, "dur": 9.954, + "args": { + "External id": 35410,"Sequence number": 480053, "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": 2338707, "tid": 2338707, "ts": 6197199749453.070, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6197199749455.287, "dur": 6.315, + "args": { + "External id": 35411,"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": 2338707, "tid": 2338707, + "ts": 6197199749460.324, "dur": 1.063, + "args": { + "External id": 35412,"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": 2338707, "tid": 2338707, + "ts": 6197199749463.974, "dur": 70.281, + "args": { + "External id": 35413,"Sequence number": 480054, "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": 2338707, "tid": 2338707, + "ts": 6197199749465.090, "dur": 6.244, + "args": { + "External id": 35414,"Sequence number": 480054, "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": 2338707, "tid": 2338707, + "ts": 6197199749466.067, "dur": 5.096, + "args": { + "External id": 35415,"Sequence number": 480054, "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": 2338707, "tid": 2338707, "ts": 6197199749466.067, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6197199749472.408, "dur": 54.096, + "args": { + "External id": 35416,"Sequence number": 480055, "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": 2338707, "tid": 2338707, "ts": 6197199749472.408, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6197199749528.598, "dur": 5.159, + "args": { + "External id": 35417,"Sequence number": 480056, "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": 2338707, "tid": 2338707, "ts": 6197199749528.598, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338707, "tid": 2338707, + "ts": 6197199749544.144, "dur": 69.157, + "args": { + "External id": 35418,"Sequence number": 480057, "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": 2338707, "tid": 2338707, + "ts": 6197199749544.843, "dur": 6.283, + "args": { + "External id": 35419,"Sequence number": 480057, "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": 2338707, "tid": 2338707, "ts": 6197199749544.843, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6197199749546.950, "dur": 2.686, + "args": { + "External id": 35420,"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": 2338707, "tid": 2338707, + "ts": 6197199749548.906, "dur": 0.537, + "args": { + "External id": 35421,"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": 2338707, "tid": 2338707, + "ts": 6197199749554.481, "dur": 58.559, + "args": { + "External id": 35422,"Sequence number": 480058, "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": 2338707, "tid": 2338707, + "ts": 6197199749555.745, "dur": 4.775, + "args": { + "External id": 35423,"Sequence number": 480058, "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": 2338707, "tid": 2338707, + "ts": 6197199749556.406, "dur": 3.917, + "args": { + "External id": 35424,"Sequence number": 480058, "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": 2338707, "tid": 2338707, "ts": 6197199749556.406, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6197199749561.530, "dur": 45.014, + "args": { + "External id": 35425,"Sequence number": 480059, "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": 2338707, "tid": 2338707, "ts": 6197199749561.530, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6197199749608.464, "dur": 4.192, + "args": { + "External id": 35426,"Sequence number": 480060, "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": 2338707, "tid": 2338707, "ts": 6197199749608.464, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6197199749644.276, "dur": 4.768, + "args": { + "External id": 35427,"Sequence number": 480061, "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": 2338707, "tid": 2338707, + "ts": 6197199749645.538, "dur": 3.365, + "args": { + "External id": 35428,"Sequence number": 480061, "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": 2338707, "tid": 2338707, "ts": 6197199749645.538, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6197199749658.517, "dur": 8.424, + "args": { + "External id": 35429,"Sequence number": 480062, "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": 2338707, "tid": 2338707, + "ts": 6197199749659.917, "dur": 6.877, + "args": { + "External id": 35430,"Sequence number": 480062, "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": 2338707, "tid": 2338707, "ts": 6197199749659.917, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6197199749673.643, "dur": 5.522, + "args": { + "External id": 35431,"Sequence number": 480063, "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": 2338707, "tid": 2338707, + "ts": 6197199749674.947, "dur": 4.049, + "args": { + "External id": 35432,"Sequence number": 480063, "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": 2338707, "tid": 2338707, "ts": 6197199749674.947, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197199749744.427, "dur": 222.047, + "args": { + "External id": 35433,"Sequence number": 480064, "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": 2338707, "tid": 2338707, "ts": 6197199749744.427, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338707, "tid": 2338707, + "ts": 6197199749772.403, "dur": 13.348, + "args": { + "External id": 35434,"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": 2338707, "tid": 2338707, + "ts": 6197199749776.633, "dur": 8.291, + "args": { + "External id": 35435,"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": 2338707, "tid": 2338707, + "ts": 6197199749982.020, "dur": 182.127, + "args": { + "External id": 35436,"Sequence number": 480065, "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": 2338707, "tid": 2338707, "ts": 6197199749982.020, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338707, "tid": 2338707, + "ts": 6197199749998.854, "dur": 7.873, + "args": { + "External id": 35437,"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": 2338707, "tid": 2338707, + "ts": 6197199750001.275, "dur": 4.898, + "args": { + "External id": 35438,"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": 2338707, "tid": 2338707, + "ts": 6197199750201.263, "dur": 226.113, + "args": { + "External id": 35439,"Sequence number": 480066, "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": 2338707, "tid": 2338707, "ts": 6197199750201.263, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338707, "tid": 2338707, + "ts": 6197199750238.556, "dur": 154.108, + "args": { + "External id": 35440,"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": 2338707, "tid": 2338707, + "ts": 6197199750296.326, "dur": 12.000, + "args": { + "External id": 35441,"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": 2338707, "tid": 2338707, + "ts": 6197199750299.428, "dur": 8.415, + "args": { + "External id": 35442,"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": 2338707, "tid": 2338707, + "ts": 6197199750311.376, "dur": 5.317, + "args": { + "External id": 35443,"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": 2338707, "tid": 2338707, + "ts": 6197199750318.093, "dur": 1.498, + "args": { + "External id": 35444,"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": 2338707, "tid": 2338707, + "ts": 6197199750322.199, "dur": 6.274, + "args": { + "External id": 35445,"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": 2338707, "tid": 2338707, + "ts": 6197199750409.769, "dur": 6.559, + "args": { + "External id": 35446,"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": 2338707, "tid": 2338707, + "ts": 6197199750433.930, "dur": 7.250, + "args": { + "External id": 35447,"Sequence number": 480067, "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": 2338707, "tid": 2338707, + "ts": 6197199750435.448, "dur": 5.494, + "args": { + "External id": 35448,"Sequence number": 480067, "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": 2338707, "tid": 2338707, "ts": 6197199750435.448, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338707, "tid": 2338707, + "ts": 6197199750456.937, "dur": 140.298, + "args": { + "External id": 35449,"Sequence number": 480068, "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": 2338707, "tid": 2338707, + "ts": 6197199750461.049, "dur": 10.467, + "args": { + "External id": 35450,"Sequence number": 480068, "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": 2338707, "tid": 2338707, "ts": 6197199750461.049, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6197199750464.534, "dur": 5.675, + "args": { + "External id": 35451,"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": 2338707, "tid": 2338707, + "ts": 6197199750467.808, "dur": 2.106, + "args": { + "External id": 35452,"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": 2338707, "tid": 2338707, + "ts": 6197199750473.206, "dur": 123.574, + "args": { + "External id": 35453,"Sequence number": 480069, "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": 2338707, "tid": 2338707, + "ts": 6197199750475.119, "dur": 6.648, + "args": { + "External id": 35454,"Sequence number": 480069, "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": 2338707, "tid": 2338707, + "ts": 6197199750478.622, "dur": 3.000, + "args": { + "External id": 35455,"Sequence number": 480069, "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": 2338707, "tid": 2338707, "ts": 6197199750478.622, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6197199750482.874, "dur": 105.060, + "args": { + "External id": 35456,"Sequence number": 480070, "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": 2338707, "tid": 2338707, "ts": 6197199750482.874, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6197199750591.273, "dur": 4.670, + "args": { + "External id": 35457,"Sequence number": 480071, "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": 2338707, "tid": 2338707, "ts": 6197199750591.273, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197199750639.146, "dur": 314.522, + "args": { + "External id": 35458,"Sequence number": 480072, "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": 2338707, "tid": 2338707, "ts": 6197199750639.146, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6197199750669.590, "dur": 5.385, + "args": { + "External id": 35459,"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": 2338707, "tid": 2338707, + "ts": 6197199750670.784, "dur": 4.006, + "args": { + "External id": 35460,"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": 2338707, "tid": 2338707, + "ts": 6197199750681.133, "dur": 4.112, + "args": { + "External id": 35461,"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": 2338707, "tid": 2338707, + "ts": 6197199750682.213, "dur": 2.895, + "args": { + "External id": 35462,"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": 2338707, "tid": 2338707, + "ts": 6197199750683.461, "dur": 1.536, + "args": { + "External id": 35463,"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": 2338707, "tid": 2338707, + "ts": 6197199750694.000, "dur": 31.607, + "args": { + "External id": 35464,"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": 2338707, "tid": 2338707, + "ts": 6197199750698.334, "dur": 26.502, + "args": { + "External id": 35465,"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": 2338707, "tid": 2338707, + "ts": 6197199750735.071, "dur": 6.149, + "args": { + "External id": 35466,"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": 2338707, "tid": 2338707, + "ts": 6197199750745.241, "dur": 3.747, + "args": { + "External id": 35467,"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": 2338707, "tid": 2338707, + "ts": 6197199750922.785, "dur": 5.210, + "args": { + "External id": 35468,"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": 2338707, "tid": 2338707, + "ts": 6197199750923.824, "dur": 3.922, + "args": { + "External id": 35469,"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": 2338707, "tid": 2338707, + "ts": 6197199750931.074, "dur": 5.203, + "args": { + "External id": 35470,"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": 2338707, "tid": 2338707, + "ts": 6197199750934.888, "dur": 1.271, + "args": { + "External id": 35471,"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": 2338707, "tid": 2338707, + "ts": 6197199750979.822, "dur": 175.555, + "args": { + "External id": 35472,"Sequence number": 480073, "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": 2338707, "tid": 2338707, + "ts": 6197199750981.356, "dur": 10.523, + "args": { + "External id": 35473,"Sequence number": 480073, "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": 2338707, "tid": 2338707, "ts": 6197199750981.356, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6197199750984.839, "dur": 5.323, + "args": { + "External id": 35474,"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": 2338707, "tid": 2338707, + "ts": 6197199750987.342, "dur": 2.473, + "args": { + "External id": 35475,"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": 2338707, "tid": 2338707, + "ts": 6197199750993.409, "dur": 161.498, + "args": { + "External id": 35476,"Sequence number": 480074, "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": 2338707, "tid": 2338707, + "ts": 6197199750998.058, "dur": 4.360, + "args": { + "External id": 35477,"Sequence number": 480074, "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": 2338707, "tid": 2338707, + "ts": 6197199750998.711, "dur": 3.560, + "args": { + "External id": 35478,"Sequence number": 480074, "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": 2338707, "tid": 2338707, "ts": 6197199750998.711, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6197199751003.711, "dur": 141.428, + "args": { + "External id": 35479,"Sequence number": 480075, "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": 2338707, "tid": 2338707, "ts": 6197199751003.711, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6197199751150.133, "dur": 3.815, + "args": { + "External id": 35480,"Sequence number": 480076, "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": 2338707, "tid": 2338707, "ts": 6197199751150.133, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338707, "tid": 2338707, + "ts": 6197199751172.108, "dur": 93.838, + "args": { + "External id": 35481,"Sequence number": 480077, "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": 2338707, "tid": 2338707, + "ts": 6197199751173.238, "dur": 8.185, + "args": { + "External id": 35482,"Sequence number": 480077, "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": 2338707, "tid": 2338707, "ts": 6197199751173.238, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6197199751175.535, "dur": 4.134, + "args": { + "External id": 35483,"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": 2338707, "tid": 2338707, + "ts": 6197199751177.728, "dur": 1.611, + "args": { + "External id": 35484,"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": 2338707, "tid": 2338707, + "ts": 6197199751182.424, "dur": 83.140, + "args": { + "External id": 35485,"Sequence number": 480078, "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": 2338707, "tid": 2338707, + "ts": 6197199751186.923, "dur": 5.709, + "args": { + "External id": 35486,"Sequence number": 480078, "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": 2338707, "tid": 2338707, + "ts": 6197199751187.896, "dur": 4.597, + "args": { + "External id": 35487,"Sequence number": 480078, "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": 2338707, "tid": 2338707, "ts": 6197199751187.896, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6197199751193.533, "dur": 65.003, + "args": { + "External id": 35488,"Sequence number": 480079, "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": 2338707, "tid": 2338707, "ts": 6197199751193.533, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6197199751260.705, "dur": 3.733, + "args": { + "External id": 35489,"Sequence number": 480080, "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": 2338707, "tid": 2338707, "ts": 6197199751260.705, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197199751297.110, "dur": 201.724, + "args": { + "External id": 35490,"Sequence number": 480081, "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": 2338707, "tid": 2338707, "ts": 6197199751297.110, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6197199751353.107, "dur": 5.903, + "args": { + "External id": 35491,"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": 2338707, "tid": 2338707, + "ts": 6197199751401.955, "dur": 78.479, + "args": { + "External id": 35492,"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": 2338707, "tid": 2338707, + "ts": 6197199751403.048, "dur": 8.493, + "args": { + "External id": 35493,"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": 2338707, "tid": 2338707, + "ts": 6197199751407.307, "dur": 3.099, + "args": { + "External id": 35494,"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": 2338707, "tid": 2338707, + "ts": 6197199751408.922, "dur": 1.200, + "args": { + "External id": 35495,"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": 2338707, "tid": 2338707, + "ts": 6197199751413.045, "dur": 67.028, + "args": { + "External id": 35496,"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": 2338707, "tid": 2338707, + "ts": 6197199751417.455, "dur": 3.059, + "args": { + "External id": 35497,"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": 2338707, "tid": 2338707, + "ts": 6197199751419.045, "dur": 1.214, + "args": { + "External id": 35498,"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": 2338707, "tid": 2338707, + "ts": 6197199751421.366, "dur": 54.020, + "args": { + "External id": 35499,"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": 2338707, "tid": 2338707, + "ts": 6197199751478.277, "dur": 0.957, + "args": { + "External id": 35500,"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": 2338707, "tid": 2338707, + "ts": 6197199751510.250, "dur": 31.921, + "args": { + "External id": 35501,"Sequence number": 480082, "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": 2338707, "tid": 2338707, "ts": 6197199751510.250, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197199751585.609, "dur": 257.353, + "args": { + "External id": 35502,"Sequence number": 480083, "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": 2338707, "tid": 2338707, "ts": 6197199751585.609, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6197199751611.099, "dur": 3.648, + "args": { + "External id": 35503,"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": 2338707, "tid": 2338707, + "ts": 6197199751612.512, "dur": 2.113, + "args": { + "External id": 35504,"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": 2338707, "tid": 2338707, + "ts": 6197199751624.804, "dur": 8.650, + "args": { + "External id": 35505,"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": 2338707, "tid": 2338707, + "ts": 6197199751628.268, "dur": 4.705, + "args": { + "External id": 35506,"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": 2338707, "tid": 2338707, + "ts": 6197199751640.908, "dur": 4.818, + "args": { + "External id": 35507,"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": 2338707, "tid": 2338707, + "ts": 6197199751821.061, "dur": 6.788, + "args": { + "External id": 35508,"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": 2338707, "tid": 2338707, + "ts": 6197199751822.625, "dur": 4.791, + "args": { + "External id": 35509,"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": 2338707, "tid": 2338707, + "ts": 6197199751865.430, "dur": 114.085, + "args": { + "External id": 35510,"Sequence number": 480084, "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": 2338707, "tid": 2338707, + "ts": 6197199751868.441, "dur": 9.770, + "args": { + "External id": 35511,"Sequence number": 480084, "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": 2338707, "tid": 2338707, "ts": 6197199751868.441, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6197199751872.375, "dur": 4.375, + "args": { + "External id": 35512,"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": 2338707, "tid": 2338707, + "ts": 6197199751874.705, "dur": 1.803, + "args": { + "External id": 35513,"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": 2338707, "tid": 2338707, + "ts": 6197199751879.703, "dur": 99.431, + "args": { + "External id": 35514,"Sequence number": 480085, "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": 2338707, "tid": 2338707, + "ts": 6197199751881.289, "dur": 7.249, + "args": { + "External id": 35515,"Sequence number": 480085, "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": 2338707, "tid": 2338707, + "ts": 6197199751885.010, "dur": 3.391, + "args": { + "External id": 35516,"Sequence number": 480085, "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": 2338707, "tid": 2338707, "ts": 6197199751885.010, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6197199751889.629, "dur": 77.815, + "args": { + "External id": 35517,"Sequence number": 480086, "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": 2338707, "tid": 2338707, "ts": 6197199751889.629, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6197199751969.840, "dur": 8.400, + "args": { + "External id": 35518,"Sequence number": 480087, "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": 2338707, "tid": 2338707, "ts": 6197199751969.840, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338707, "tid": 2338707, + "ts": 6197199751990.578, "dur": 120.926, + "args": { + "External id": 35519,"Sequence number": 480088, "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": 2338707, "tid": 2338707, + "ts": 6197199751991.476, "dur": 10.194, + "args": { + "External id": 35520,"Sequence number": 480088, "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": 2338707, "tid": 2338707, "ts": 6197199751991.476, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6197199751997.351, "dur": 3.192, + "args": { + "External id": 35521,"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": 2338707, "tid": 2338707, + "ts": 6197199751999.477, "dur": 0.842, + "args": { + "External id": 35522,"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": 2338707, "tid": 2338707, + "ts": 6197199752002.534, "dur": 108.670, + "args": { + "External id": 35523,"Sequence number": 480089, "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": 2338707, "tid": 2338707, + "ts": 6197199752003.670, "dur": 6.143, + "args": { + "External id": 35524,"Sequence number": 480089, "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": 2338707, "tid": 2338707, + "ts": 6197199752006.999, "dur": 2.647, + "args": { + "External id": 35525,"Sequence number": 480089, "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": 2338707, "tid": 2338707, "ts": 6197199752006.999, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6197199752010.614, "dur": 93.159, + "args": { + "External id": 35526,"Sequence number": 480090, "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": 2338707, "tid": 2338707, "ts": 6197199752010.614, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6197199752107.765, "dur": 2.856, + "args": { + "External id": 35527,"Sequence number": 480091, "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": 2338707, "tid": 2338707, "ts": 6197199752107.765, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338707, "tid": 2338707, + "ts": 6197199752123.212, "dur": 79.911, + "args": { + "External id": 35528,"Sequence number": 480092, "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": 2338707, "tid": 2338707, + "ts": 6197199752124.153, "dur": 9.833, + "args": { + "External id": 35529,"Sequence number": 480092, "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": 2338707, "tid": 2338707, "ts": 6197199752124.153, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6197199752127.006, "dur": 5.541, + "args": { + "External id": 35530,"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": 2338707, "tid": 2338707, + "ts": 6197199752131.137, "dur": 1.232, + "args": { + "External id": 35531,"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": 2338707, "tid": 2338707, + "ts": 6197199752134.905, "dur": 67.893, + "args": { + "External id": 35532,"Sequence number": 480093, "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": 2338707, "tid": 2338707, + "ts": 6197199752135.745, "dur": 8.973, + "args": { + "External id": 35533,"Sequence number": 480093, "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": 2338707, "tid": 2338707, + "ts": 6197199752137.216, "dur": 7.298, + "args": { + "External id": 35534,"Sequence number": 480093, "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": 2338707, "tid": 2338707, "ts": 6197199752137.216, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6197199752147.774, "dur": 49.485, + "args": { + "External id": 35535,"Sequence number": 480094, "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": 2338707, "tid": 2338707, "ts": 6197199752147.774, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6197199752199.349, "dur": 3.045, + "args": { + "External id": 35536,"Sequence number": 480095, "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": 2338707, "tid": 2338707, "ts": 6197199752199.349, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6197199752224.538, "dur": 6.501, + "args": { + "External id": 35537,"Sequence number": 480096, "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": 2338707, "tid": 2338707, + "ts": 6197199752225.695, "dur": 5.159, + "args": { + "External id": 35538,"Sequence number": 480096, "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": 2338707, "tid": 2338707, "ts": 6197199752225.695, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6197199752239.816, "dur": 6.281, + "args": { + "External id": 35539,"Sequence number": 480097, "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": 2338707, "tid": 2338707, + "ts": 6197199752243.744, "dur": 2.092, + "args": { + "External id": 35540,"Sequence number": 480097, "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": 2338707, "tid": 2338707, "ts": 6197199752243.744, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6197199752250.825, "dur": 3.604, + "args": { + "External id": 35541,"Sequence number": 480098, "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": 2338707, "tid": 2338707, + "ts": 6197199752252.045, "dur": 2.240, + "args": { + "External id": 35542,"Sequence number": 480098, "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": 2338707, "tid": 2338707, "ts": 6197199752252.045, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197199752288.317, "dur": 200.371, + "args": { + "External id": 35543,"Sequence number": 480099, "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": 2338707, "tid": 2338707, "ts": 6197199752288.317, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338707, "tid": 2338707, + "ts": 6197199752314.967, "dur": 16.176, + "args": { + "External id": 35544,"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": 2338707, "tid": 2338707, + "ts": 6197199752323.464, "dur": 7.233, + "args": { + "External id": 35545,"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": 2338707, "tid": 2338707, + "ts": 6197199752505.761, "dur": 126.868, + "args": { + "External id": 35546,"Sequence number": 480100, "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": 2338707, "tid": 2338707, "ts": 6197199752505.761, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338707, "tid": 2338707, + "ts": 6197199752523.474, "dur": 8.913, + "args": { + "External id": 35547,"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": 2338707, "tid": 2338707, + "ts": 6197199752526.236, "dur": 5.717, + "args": { + "External id": 35548,"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": 2338707, "tid": 2338707, + "ts": 6197199752664.191, "dur": 236.588, + "args": { + "External id": 35549,"Sequence number": 480101, "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": 2338707, "tid": 2338707, "ts": 6197199752664.191, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338707, "tid": 2338707, + "ts": 6197199752698.881, "dur": 170.248, + "args": { + "External id": 35550,"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": 2338707, "tid": 2338707, + "ts": 6197199752774.140, "dur": 11.446, + "args": { + "External id": 35551,"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": 2338707, "tid": 2338707, + "ts": 6197199752779.041, "dur": 5.836, + "args": { + "External id": 35552,"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": 2338707, "tid": 2338707, + "ts": 6197199752788.960, "dur": 4.695, + "args": { + "External id": 35553,"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": 2338707, "tid": 2338707, + "ts": 6197199752795.287, "dur": 1.669, + "args": { + "External id": 35554,"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": 2338707, "tid": 2338707, + "ts": 6197199752799.887, "dur": 4.666, + "args": { + "External id": 35555,"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": 2338707, "tid": 2338707, + "ts": 6197199752881.982, "dur": 6.182, + "args": { + "External id": 35556,"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": 2338707, "tid": 2338707, + "ts": 6197199752906.959, "dur": 9.230, + "args": { + "External id": 35557,"Sequence number": 480102, "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": 2338707, "tid": 2338707, + "ts": 6197199752909.008, "dur": 6.966, + "args": { + "External id": 35558,"Sequence number": 480102, "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": 2338707, "tid": 2338707, "ts": 6197199752909.008, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338707, "tid": 2338707, + "ts": 6197199752930.415, "dur": 172.457, + "args": { + "External id": 35559,"Sequence number": 480103, "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": 2338707, "tid": 2338707, + "ts": 6197199752931.606, "dur": 10.344, + "args": { + "External id": 35560,"Sequence number": 480103, "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": 2338707, "tid": 2338707, "ts": 6197199752931.606, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6197199752935.009, "dur": 5.448, + "args": { + "External id": 35561,"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": 2338707, "tid": 2338707, + "ts": 6197199752938.020, "dur": 2.141, + "args": { + "External id": 35562,"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": 2338707, "tid": 2338707, + "ts": 6197199752943.517, "dur": 158.846, + "args": { + "External id": 35563,"Sequence number": 480104, "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": 2338707, "tid": 2338707, + "ts": 6197199752947.795, "dur": 4.284, + "args": { + "External id": 35564,"Sequence number": 480104, "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": 2338707, "tid": 2338707, + "ts": 6197199752948.956, "dur": 2.959, + "args": { + "External id": 35565,"Sequence number": 480104, "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": 2338707, "tid": 2338707, "ts": 6197199752948.956, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6197199752953.332, "dur": 98.098, + "args": { + "External id": 35566,"Sequence number": 480105, "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": 2338707, "tid": 2338707, "ts": 6197199752953.332, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6197199753054.603, "dur": 46.487, + "args": { + "External id": 35567,"Sequence number": 480106, "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": 2338707, "tid": 2338707, "ts": 6197199753054.603, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197199753151.768, "dur": 282.274, + "args": { + "External id": 35568,"Sequence number": 480107, "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": 2338707, "tid": 2338707, "ts": 6197199753151.768, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6197199753176.690, "dur": 6.686, + "args": { + "External id": 35569,"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": 2338707, "tid": 2338707, + "ts": 6197199753180.670, "dur": 2.532, + "args": { + "External id": 35570,"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": 2338707, "tid": 2338707, + "ts": 6197199753188.546, "dur": 6.811, + "args": { + "External id": 35571,"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": 2338707, "tid": 2338707, + "ts": 6197199753189.990, "dur": 5.251, + "args": { + "External id": 35572,"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": 2338707, "tid": 2338707, + "ts": 6197199753193.727, "dur": 1.190, + "args": { + "External id": 35573,"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": 2338707, "tid": 2338707, + "ts": 6197199753205.011, "dur": 10.847, + "args": { + "External id": 35574,"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": 2338707, "tid": 2338707, + "ts": 6197199753207.750, "dur": 7.687, + "args": { + "External id": 35575,"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": 2338707, "tid": 2338707, + "ts": 6197199753223.183, "dur": 4.422, + "args": { + "External id": 35576,"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": 2338707, "tid": 2338707, + "ts": 6197199753231.694, "dur": 4.546, + "args": { + "External id": 35577,"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": 2338707, "tid": 2338707, + "ts": 6197199753406.098, "dur": 4.547, + "args": { + "External id": 35578,"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": 2338707, "tid": 2338707, + "ts": 6197199753407.554, "dur": 2.716, + "args": { + "External id": 35579,"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": 2338707, "tid": 2338707, + "ts": 6197199753414.125, "dur": 2.504, + "args": { + "External id": 35580,"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": 2338707, "tid": 2338707, + "ts": 6197199753415.224, "dur": 1.261, + "args": { + "External id": 35581,"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": 2338707, "tid": 2338707, + "ts": 6197199753458.190, "dur": 131.824, + "args": { + "External id": 35582,"Sequence number": 480108, "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": 2338707, "tid": 2338707, + "ts": 6197199753459.369, "dur": 12.903, + "args": { + "External id": 35583,"Sequence number": 480108, "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": 2338707, "tid": 2338707, "ts": 6197199753459.369, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6197199753462.745, "dur": 8.157, + "args": { + "External id": 35584,"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": 2338707, "tid": 2338707, + "ts": 6197199753467.803, "dur": 2.560, + "args": { + "External id": 35585,"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": 2338707, "tid": 2338707, + "ts": 6197199753473.700, "dur": 115.946, + "args": { + "External id": 35586,"Sequence number": 480109, "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": 2338707, "tid": 2338707, + "ts": 6197199753475.761, "dur": 4.761, + "args": { + "External id": 35587,"Sequence number": 480109, "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": 2338707, "tid": 2338707, + "ts": 6197199753476.794, "dur": 3.565, + "args": { + "External id": 35588,"Sequence number": 480109, "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": 2338707, "tid": 2338707, "ts": 6197199753476.794, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6197199753481.492, "dur": 97.211, + "args": { + "External id": 35589,"Sequence number": 480110, "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": 2338707, "tid": 2338707, "ts": 6197199753481.492, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6197199753581.858, "dur": 7.145, + "args": { + "External id": 35590,"Sequence number": 480111, "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": 2338707, "tid": 2338707, "ts": 6197199753581.858, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338707, "tid": 2338707, + "ts": 6197199753601.096, "dur": 83.995, + "args": { + "External id": 35591,"Sequence number": 480112, "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": 2338707, "tid": 2338707, + "ts": 6197199753601.982, "dur": 7.084, + "args": { + "External id": 35592,"Sequence number": 480112, "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": 2338707, "tid": 2338707, "ts": 6197199753601.982, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6197199753604.053, "dur": 3.550, + "args": { + "External id": 35593,"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": 2338707, "tid": 2338707, + "ts": 6197199753606.316, "dur": 1.103, + "args": { + "External id": 35594,"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": 2338707, "tid": 2338707, + "ts": 6197199753612.204, "dur": 72.652, + "args": { + "External id": 35595,"Sequence number": 480113, "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": 2338707, "tid": 2338707, + "ts": 6197199753613.475, "dur": 7.382, + "args": { + "External id": 35596,"Sequence number": 480113, "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": 2338707, "tid": 2338707, + "ts": 6197199753614.428, "dur": 6.257, + "args": { + "External id": 35597,"Sequence number": 480113, "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": 2338707, "tid": 2338707, "ts": 6197199753614.428, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6197199753621.732, "dur": 54.863, + "args": { + "External id": 35598,"Sequence number": 480114, "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": 2338707, "tid": 2338707, "ts": 6197199753621.732, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6197199753678.521, "dur": 5.819, + "args": { + "External id": 35599,"Sequence number": 480115, "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": 2338707, "tid": 2338707, "ts": 6197199753678.521, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197199753731.018, "dur": 190.454, + "args": { + "External id": 35600,"Sequence number": 480116, "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": 2338707, "tid": 2338707, "ts": 6197199753731.018, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6197199753777.449, "dur": 7.136, + "args": { + "External id": 35601,"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": 2338707, "tid": 2338707, + "ts": 6197199753828.807, "dur": 75.669, + "args": { + "External id": 35602,"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": 2338707, "tid": 2338707, + "ts": 6197199753829.764, "dur": 8.488, + "args": { + "External id": 35603,"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": 2338707, "tid": 2338707, + "ts": 6197199753831.542, "dur": 5.530, + "args": { + "External id": 35604,"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": 2338707, "tid": 2338707, + "ts": 6197199753835.489, "dur": 1.327, + "args": { + "External id": 35605,"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": 2338707, "tid": 2338707, + "ts": 6197199753839.271, "dur": 64.756, + "args": { + "External id": 35606,"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": 2338707, "tid": 2338707, + "ts": 6197199753841.059, "dur": 3.562, + "args": { + "External id": 35607,"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": 2338707, "tid": 2338707, + "ts": 6197199753842.526, "dur": 1.905, + "args": { + "External id": 35608,"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": 2338707, "tid": 2338707, + "ts": 6197199753845.449, "dur": 53.585, + "args": { + "External id": 35609,"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": 2338707, "tid": 2338707, + "ts": 6197199753901.601, "dur": 1.488, + "args": { + "External id": 35610,"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": 2338707, "tid": 2338707, + "ts": 6197199753931.792, "dur": 35.889, + "args": { + "External id": 35611,"Sequence number": 480117, "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": 2338707, "tid": 2338707, "ts": 6197199753931.792, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197199754012.010, "dur": 278.311, + "args": { + "External id": 35612,"Sequence number": 480118, "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": 2338707, "tid": 2338707, "ts": 6197199754012.010, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6197199754033.948, "dur": 3.530, + "args": { + "External id": 35613,"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": 2338707, "tid": 2338707, + "ts": 6197199754035.103, "dur": 2.160, + "args": { + "External id": 35614,"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": 2338707, "tid": 2338707, + "ts": 6197199754046.916, "dur": 8.183, + "args": { + "External id": 35615,"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": 2338707, "tid": 2338707, + "ts": 6197199754050.052, "dur": 4.642, + "args": { + "External id": 35616,"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": 2338707, "tid": 2338707, + "ts": 6197199754108.166, "dur": 5.956, + "args": { + "External id": 35617,"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": 2338707, "tid": 2338707, + "ts": 6197199754270.386, "dur": 5.265, + "args": { + "External id": 35618,"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": 2338707, "tid": 2338707, + "ts": 6197199754272.052, "dur": 3.350, + "args": { + "External id": 35619,"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": 2338707, "tid": 2338707, + "ts": 6197199754313.049, "dur": 113.254, + "args": { + "External id": 35620,"Sequence number": 480119, "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": 2338707, "tid": 2338707, + "ts": 6197199754314.438, "dur": 9.844, + "args": { + "External id": 35621,"Sequence number": 480119, "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": 2338707, "tid": 2338707, "ts": 6197199754314.438, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6197199754317.650, "dur": 4.928, + "args": { + "External id": 35622,"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": 2338707, "tid": 2338707, + "ts": 6197199754320.562, "dur": 1.777, + "args": { + "External id": 35623,"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": 2338707, "tid": 2338707, + "ts": 6197199754325.576, "dur": 100.409, + "args": { + "External id": 35624,"Sequence number": 480120, "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": 2338707, "tid": 2338707, + "ts": 6197199754330.090, "dur": 5.070, + "args": { + "External id": 35625,"Sequence number": 480120, "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": 2338707, "tid": 2338707, + "ts": 6197199754331.206, "dur": 3.818, + "args": { + "External id": 35626,"Sequence number": 480120, "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": 2338707, "tid": 2338707, "ts": 6197199754331.206, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6197199754336.282, "dur": 80.719, + "args": { + "External id": 35627,"Sequence number": 480121, "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": 2338707, "tid": 2338707, "ts": 6197199754336.282, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6197199754419.633, "dur": 5.491, + "args": { + "External id": 35628,"Sequence number": 480122, "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": 2338707, "tid": 2338707, "ts": 6197199754419.633, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338707, "tid": 2338707, + "ts": 6197199754442.733, "dur": 73.411, + "args": { + "External id": 35629,"Sequence number": 480123, "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": 2338707, "tid": 2338707, + "ts": 6197199754443.525, "dur": 6.516, + "args": { + "External id": 35630,"Sequence number": 480123, "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": 2338707, "tid": 2338707, "ts": 6197199754443.525, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6197199754445.340, "dur": 3.593, + "args": { + "External id": 35631,"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": 2338707, "tid": 2338707, + "ts": 6197199754447.364, "dur": 1.402, + "args": { + "External id": 35632,"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": 2338707, "tid": 2338707, + "ts": 6197199754450.784, "dur": 65.106, + "args": { + "External id": 35633,"Sequence number": 480124, "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": 2338707, "tid": 2338707, + "ts": 6197199754454.724, "dur": 6.084, + "args": { + "External id": 35634,"Sequence number": 480124, "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": 2338707, "tid": 2338707, + "ts": 6197199754455.637, "dur": 4.999, + "args": { + "External id": 35635,"Sequence number": 480124, "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": 2338707, "tid": 2338707, "ts": 6197199754455.637, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6197199754461.656, "dur": 45.322, + "args": { + "External id": 35636,"Sequence number": 480125, "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": 2338707, "tid": 2338707, "ts": 6197199754461.656, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6197199754509.109, "dur": 6.364, + "args": { + "External id": 35637,"Sequence number": 480126, "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": 2338707, "tid": 2338707, "ts": 6197199754509.109, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338707, "tid": 2338707, + "ts": 6197199754525.641, "dur": 69.605, + "args": { + "External id": 35638,"Sequence number": 480127, "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": 2338707, "tid": 2338707, + "ts": 6197199754526.496, "dur": 10.757, + "args": { + "External id": 35639,"Sequence number": 480127, "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": 2338707, "tid": 2338707, "ts": 6197199754526.496, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6197199754530.625, "dur": 5.033, + "args": { + "External id": 35640,"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": 2338707, "tid": 2338707, + "ts": 6197199754534.746, "dur": 0.770, + "args": { + "External id": 35641,"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": 2338707, "tid": 2338707, + "ts": 6197199754538.198, "dur": 56.754, + "args": { + "External id": 35642,"Sequence number": 480128, "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": 2338707, "tid": 2338707, + "ts": 6197199754539.707, "dur": 7.463, + "args": { + "External id": 35643,"Sequence number": 480128, "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": 2338707, "tid": 2338707, + "ts": 6197199754542.823, "dur": 3.918, + "args": { + "External id": 35644,"Sequence number": 480128, "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": 2338707, "tid": 2338707, "ts": 6197199754542.823, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6197199754547.891, "dur": 40.431, + "args": { + "External id": 35645,"Sequence number": 480129, "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": 2338707, "tid": 2338707, "ts": 6197199754547.891, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6197199754590.202, "dur": 4.325, + "args": { + "External id": 35646,"Sequence number": 480130, "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": 2338707, "tid": 2338707, "ts": 6197199754590.202, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6197199754613.962, "dur": 6.536, + "args": { + "External id": 35647,"Sequence number": 480131, "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": 2338707, "tid": 2338707, + "ts": 6197199754615.091, "dur": 5.257, + "args": { + "External id": 35648,"Sequence number": 480131, "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": 2338707, "tid": 2338707, "ts": 6197199754615.091, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6197199754629.004, "dur": 4.033, + "args": { + "External id": 35649,"Sequence number": 480132, "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": 2338707, "tid": 2338707, + "ts": 6197199754630.112, "dur": 2.776, + "args": { + "External id": 35650,"Sequence number": 480132, "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": 2338707, "tid": 2338707, "ts": 6197199754630.112, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6197199754637.640, "dur": 4.012, + "args": { + "External id": 35651,"Sequence number": 480133, "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": 2338707, "tid": 2338707, + "ts": 6197199754639.158, "dur": 2.347, + "args": { + "External id": 35652,"Sequence number": 480133, "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": 2338707, "tid": 2338707, "ts": 6197199754639.158, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197199754676.870, "dur": 213.088, + "args": { + "External id": 35653,"Sequence number": 480134, "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": 2338707, "tid": 2338707, "ts": 6197199754676.870, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338707, "tid": 2338707, + "ts": 6197199754699.519, "dur": 29.253, + "args": { + "External id": 35654,"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": 2338707, "tid": 2338707, + "ts": 6197199754720.388, "dur": 7.705, + "args": { + "External id": 35655,"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": 2338707, "tid": 2338707, + "ts": 6197199754905.075, "dur": 126.819, + "args": { + "External id": 35656,"Sequence number": 480135, "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": 2338707, "tid": 2338707, "ts": 6197199754905.075, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338707, "tid": 2338707, + "ts": 6197199754922.091, "dur": 8.143, + "args": { + "External id": 35657,"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": 2338707, "tid": 2338707, + "ts": 6197199754924.960, "dur": 4.898, + "args": { + "External id": 35658,"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": 2338707, "tid": 2338707, + "ts": 6197199755107.263, "dur": 221.426, + "args": { + "External id": 35659,"Sequence number": 480136, "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": 2338707, "tid": 2338707, "ts": 6197199755107.263, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338707, "tid": 2338707, + "ts": 6197199755144.042, "dur": 152.475, + "args": { + "External id": 35660,"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": 2338707, "tid": 2338707, + "ts": 6197199755200.444, "dur": 9.723, + "args": { + "External id": 35661,"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": 2338707, "tid": 2338707, + "ts": 6197199755203.218, "dur": 6.259, + "args": { + "External id": 35662,"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": 2338707, "tid": 2338707, + "ts": 6197199755213.020, "dur": 4.915, + "args": { + "External id": 35663,"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": 2338707, "tid": 2338707, + "ts": 6197199755219.982, "dur": 1.606, + "args": { + "External id": 35664,"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": 2338707, "tid": 2338707, + "ts": 6197199755224.469, "dur": 7.213, + "args": { + "External id": 35665,"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": 2338707, "tid": 2338707, + "ts": 6197199755310.694, "dur": 6.179, + "args": { + "External id": 35666,"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": 2338707, "tid": 2338707, + "ts": 6197199755334.976, "dur": 7.133, + "args": { + "External id": 35667,"Sequence number": 480137, "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": 2338707, "tid": 2338707, + "ts": 6197199755337.242, "dur": 4.675, + "args": { + "External id": 35668,"Sequence number": 480137, "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": 2338707, "tid": 2338707, "ts": 6197199755337.242, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338707, "tid": 2338707, + "ts": 6197199755357.153, "dur": 141.222, + "args": { + "External id": 35669,"Sequence number": 480138, "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": 2338707, "tid": 2338707, + "ts": 6197199755358.624, "dur": 15.792, + "args": { + "External id": 35670,"Sequence number": 480138, "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": 2338707, "tid": 2338707, "ts": 6197199755358.624, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6197199755365.616, "dur": 7.675, + "args": { + "External id": 35671,"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": 2338707, "tid": 2338707, + "ts": 6197199755370.843, "dur": 2.193, + "args": { + "External id": 35672,"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": 2338707, "tid": 2338707, + "ts": 6197199755376.458, "dur": 121.433, + "args": { + "External id": 35673,"Sequence number": 480139, "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": 2338707, "tid": 2338707, + "ts": 6197199755378.686, "dur": 3.823, + "args": { + "External id": 35674,"Sequence number": 480139, "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": 2338707, "tid": 2338707, + "ts": 6197199755380.006, "dur": 2.325, + "args": { + "External id": 35675,"Sequence number": 480139, "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": 2338707, "tid": 2338707, "ts": 6197199755380.006, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6197199755383.765, "dur": 106.341, + "args": { + "External id": 35676,"Sequence number": 480140, "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": 2338707, "tid": 2338707, "ts": 6197199755383.765, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6197199755493.381, "dur": 3.776, + "args": { + "External id": 35677,"Sequence number": 480141, "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": 2338707, "tid": 2338707, "ts": 6197199755493.381, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197199755538.187, "dur": 292.693, + "args": { + "External id": 35678,"Sequence number": 480142, "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": 2338707, "tid": 2338707, "ts": 6197199755538.187, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6197199755560.624, "dur": 2.767, + "args": { + "External id": 35679,"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": 2338707, "tid": 2338707, + "ts": 6197199755561.571, "dur": 1.615, + "args": { + "External id": 35680,"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": 2338707, "tid": 2338707, + "ts": 6197199755567.857, "dur": 9.204, + "args": { + "External id": 35681,"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": 2338707, "tid": 2338707, + "ts": 6197199755574.268, "dur": 2.663, + "args": { + "External id": 35682,"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": 2338707, "tid": 2338707, + "ts": 6197199755575.407, "dur": 1.400, + "args": { + "External id": 35683,"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": 2338707, "tid": 2338707, + "ts": 6197199755585.441, "dur": 9.372, + "args": { + "External id": 35684,"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": 2338707, "tid": 2338707, + "ts": 6197199755588.215, "dur": 6.092, + "args": { + "External id": 35685,"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": 2338707, "tid": 2338707, + "ts": 6197199755601.719, "dur": 3.849, + "args": { + "External id": 35686,"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": 2338707, "tid": 2338707, + "ts": 6197199755611.970, "dur": 6.081, + "args": { + "External id": 35687,"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": 2338707, "tid": 2338707, + "ts": 6197199755803.525, "dur": 4.988, + "args": { + "External id": 35688,"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": 2338707, "tid": 2338707, + "ts": 6197199755804.956, "dur": 3.109, + "args": { + "External id": 35689,"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": 2338707, "tid": 2338707, + "ts": 6197199755811.858, "dur": 3.425, + "args": { + "External id": 35690,"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": 2338707, "tid": 2338707, + "ts": 6197199755813.767, "dur": 1.379, + "args": { + "External id": 35691,"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": 2338707, "tid": 2338707, + "ts": 6197199755854.383, "dur": 127.492, + "args": { + "External id": 35692,"Sequence number": 480143, "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": 2338707, "tid": 2338707, + "ts": 6197199755856.004, "dur": 14.903, + "args": { + "External id": 35693,"Sequence number": 480143, "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": 2338707, "tid": 2338707, "ts": 6197199755856.004, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6197199755862.013, "dur": 7.163, + "args": { + "External id": 35694,"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": 2338707, "tid": 2338707, + "ts": 6197199755864.842, "dur": 4.004, + "args": { + "External id": 35695,"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": 2338707, "tid": 2338707, + "ts": 6197199755872.111, "dur": 109.381, + "args": { + "External id": 35696,"Sequence number": 480144, "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": 2338707, "tid": 2338707, + "ts": 6197199755873.763, "dur": 6.588, + "args": { + "External id": 35697,"Sequence number": 480144, "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": 2338707, "tid": 2338707, + "ts": 6197199755875.071, "dur": 5.117, + "args": { + "External id": 35698,"Sequence number": 480144, "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": 2338707, "tid": 2338707, "ts": 6197199755875.071, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6197199755881.458, "dur": 91.181, + "args": { + "External id": 35699,"Sequence number": 480145, "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": 2338707, "tid": 2338707, "ts": 6197199755881.458, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6197199755975.446, "dur": 5.487, + "args": { + "External id": 35700,"Sequence number": 480146, "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": 2338707, "tid": 2338707, "ts": 6197199755975.446, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338707, "tid": 2338707, + "ts": 6197199755992.572, "dur": 127.657, + "args": { + "External id": 35701,"Sequence number": 480147, "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": 2338707, "tid": 2338707, + "ts": 6197199755993.268, "dur": 9.477, + "args": { + "External id": 35702,"Sequence number": 480147, "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": 2338707, "tid": 2338707, "ts": 6197199755993.268, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6197199755995.345, "dur": 5.872, + "args": { + "External id": 35703,"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": 2338707, "tid": 2338707, + "ts": 6197199755999.926, "dur": 1.084, + "args": { + "External id": 35704,"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": 2338707, "tid": 2338707, + "ts": 6197199756003.991, "dur": 115.976, + "args": { + "External id": 35705,"Sequence number": 480148, "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": 2338707, "tid": 2338707, + "ts": 6197199756005.183, "dur": 5.302, + "args": { + "External id": 35706,"Sequence number": 480148, "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": 2338707, "tid": 2338707, + "ts": 6197199756005.737, "dur": 4.583, + "args": { + "External id": 35707,"Sequence number": 480148, "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": 2338707, "tid": 2338707, "ts": 6197199756005.737, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6197199756013.257, "dur": 95.959, + "args": { + "External id": 35708,"Sequence number": 480149, "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": 2338707, "tid": 2338707, "ts": 6197199756013.257, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6197199756113.087, "dur": 6.261, + "args": { + "External id": 35709,"Sequence number": 480150, "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": 2338707, "tid": 2338707, "ts": 6197199756113.087, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197199756149.551, "dur": 190.500, + "args": { + "External id": 35710,"Sequence number": 480151, "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": 2338707, "tid": 2338707, "ts": 6197199756149.551, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6197199756197.144, "dur": 6.789, + "args": { + "External id": 35711,"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": 2338707, "tid": 2338707, + "ts": 6197199756243.699, "dur": 80.248, + "args": { + "External id": 35712,"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": 2338707, "tid": 2338707, + "ts": 6197199756244.911, "dur": 9.367, + "args": { + "External id": 35713,"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": 2338707, "tid": 2338707, + "ts": 6197199756246.837, "dur": 6.180, + "args": { + "External id": 35714,"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": 2338707, "tid": 2338707, + "ts": 6197199756249.614, "dur": 3.180, + "args": { + "External id": 35715,"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": 2338707, "tid": 2338707, + "ts": 6197199756255.395, "dur": 68.030, + "args": { + "External id": 35716,"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": 2338707, "tid": 2338707, + "ts": 6197199756256.867, "dur": 3.194, + "args": { + "External id": 35717,"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": 2338707, "tid": 2338707, + "ts": 6197199756258.068, "dur": 1.656, + "args": { + "External id": 35718,"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": 2338707, "tid": 2338707, + "ts": 6197199756263.094, "dur": 55.556, + "args": { + "External id": 35719,"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": 2338707, "tid": 2338707, + "ts": 6197199756321.090, "dur": 1.593, + "args": { + "External id": 35720,"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": 2338707, "tid": 2338707, + "ts": 6197199756350.572, "dur": 31.091, + "args": { + "External id": 35721,"Sequence number": 480152, "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": 2338707, "tid": 2338707, "ts": 6197199756350.572, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197199756424.417, "dur": 218.420, + "args": { + "External id": 35722,"Sequence number": 480153, "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": 2338707, "tid": 2338707, "ts": 6197199756424.417, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6197199756446.409, "dur": 6.138, + "args": { + "External id": 35723,"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": 2338707, "tid": 2338707, + "ts": 6197199756448.049, "dur": 4.319, + "args": { + "External id": 35724,"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": 2338707, "tid": 2338707, + "ts": 6197199756462.158, "dur": 10.926, + "args": { + "External id": 35725,"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": 2338707, "tid": 2338707, + "ts": 6197199756467.903, "dur": 4.739, + "args": { + "External id": 35726,"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": 2338707, "tid": 2338707, + "ts": 6197199756480.524, "dur": 5.017, + "args": { + "External id": 35727,"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": 2338707, "tid": 2338707, + "ts": 6197199756628.721, "dur": 3.251, + "args": { + "External id": 35728,"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": 2338707, "tid": 2338707, + "ts": 6197199756629.908, "dur": 1.791, + "args": { + "External id": 35729,"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": 2338707, "tid": 2338707, + "ts": 6197199756664.181, "dur": 130.130, + "args": { + "External id": 35730,"Sequence number": 480154, "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": 2338707, "tid": 2338707, + "ts": 6197199756665.261, "dur": 10.180, + "args": { + "External id": 35731,"Sequence number": 480154, "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": 2338707, "tid": 2338707, "ts": 6197199756665.261, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6197199756667.857, "dur": 6.295, + "args": { + "External id": 35732,"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": 2338707, "tid": 2338707, + "ts": 6197199756672.389, "dur": 1.546, + "args": { + "External id": 35733,"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": 2338707, "tid": 2338707, + "ts": 6197199756676.472, "dur": 117.381, + "args": { + "External id": 35734,"Sequence number": 480155, "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": 2338707, "tid": 2338707, + "ts": 6197199756678.302, "dur": 5.938, + "args": { + "External id": 35735,"Sequence number": 480155, "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": 2338707, "tid": 2338707, + "ts": 6197199756679.112, "dur": 4.938, + "args": { + "External id": 35736,"Sequence number": 480155, "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": 2338707, "tid": 2338707, "ts": 6197199756679.112, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6197199756685.168, "dur": 100.178, + "args": { + "External id": 35737,"Sequence number": 480156, "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": 2338707, "tid": 2338707, "ts": 6197199756685.168, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6197199756789.442, "dur": 3.652, + "args": { + "External id": 35738,"Sequence number": 480157, "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": 2338707, "tid": 2338707, "ts": 6197199756789.442, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338707, "tid": 2338707, + "ts": 6197199756805.783, "dur": 72.953, + "args": { + "External id": 35739,"Sequence number": 480158, "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": 2338707, "tid": 2338707, + "ts": 6197199756807.101, "dur": 8.167, + "args": { + "External id": 35740,"Sequence number": 480158, "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": 2338707, "tid": 2338707, "ts": 6197199756807.101, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6197199756809.072, "dur": 4.819, + "args": { + "External id": 35741,"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": 2338707, "tid": 2338707, + "ts": 6197199756812.616, "dur": 1.083, + "args": { + "External id": 35742,"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": 2338707, "tid": 2338707, + "ts": 6197199756818.784, "dur": 59.567, + "args": { + "External id": 35743,"Sequence number": 480159, "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": 2338707, "tid": 2338707, + "ts": 6197199756820.557, "dur": 4.059, + "args": { + "External id": 35744,"Sequence number": 480159, "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": 2338707, "tid": 2338707, + "ts": 6197199756821.209, "dur": 3.231, + "args": { + "External id": 35745,"Sequence number": 480159, "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": 2338707, "tid": 2338707, "ts": 6197199756821.209, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6197199756825.609, "dur": 46.907, + "args": { + "External id": 35746,"Sequence number": 480160, "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": 2338707, "tid": 2338707, "ts": 6197199756825.609, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6197199756874.251, "dur": 3.710, + "args": { + "External id": 35747,"Sequence number": 480161, "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": 2338707, "tid": 2338707, "ts": 6197199756874.251, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338707, "tid": 2338707, + "ts": 6197199756889.412, "dur": 66.926, + "args": { + "External id": 35748,"Sequence number": 480162, "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": 2338707, "tid": 2338707, + "ts": 6197199756890.183, "dur": 5.651, + "args": { + "External id": 35749,"Sequence number": 480162, "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": 2338707, "tid": 2338707, "ts": 6197199756890.183, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6197199756891.303, "dur": 3.265, + "args": { + "External id": 35750,"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": 2338707, "tid": 2338707, + "ts": 6197199756893.259, "dur": 1.176, + "args": { + "External id": 35751,"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": 2338707, "tid": 2338707, + "ts": 6197199756896.452, "dur": 59.606, + "args": { + "External id": 35752,"Sequence number": 480163, "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": 2338707, "tid": 2338707, + "ts": 6197199756900.271, "dur": 5.181, + "args": { + "External id": 35753,"Sequence number": 480163, "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": 2338707, "tid": 2338707, + "ts": 6197199756901.316, "dur": 3.986, + "args": { + "External id": 35754,"Sequence number": 480163, "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": 2338707, "tid": 2338707, "ts": 6197199756901.316, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6197199756906.024, "dur": 41.780, + "args": { + "External id": 35755,"Sequence number": 480164, "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": 2338707, "tid": 2338707, "ts": 6197199756906.024, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6197199756949.891, "dur": 5.798, + "args": { + "External id": 35756,"Sequence number": 480165, "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": 2338707, "tid": 2338707, "ts": 6197199756949.891, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6197199756978.692, "dur": 4.526, + "args": { + "External id": 35757,"Sequence number": 480166, "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": 2338707, "tid": 2338707, + "ts": 6197199756979.974, "dur": 3.093, + "args": { + "External id": 35758,"Sequence number": 480166, "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": 2338707, "tid": 2338707, "ts": 6197199756979.974, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6197199756991.160, "dur": 5.270, + "args": { + "External id": 35759,"Sequence number": 480167, "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": 2338707, "tid": 2338707, + "ts": 6197199756992.379, "dur": 3.879, + "args": { + "External id": 35760,"Sequence number": 480167, "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": 2338707, "tid": 2338707, "ts": 6197199756992.379, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6197199757001.423, "dur": 5.173, + "args": { + "External id": 35761,"Sequence number": 480168, "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": 2338707, "tid": 2338707, + "ts": 6197199757002.442, "dur": 3.997, + "args": { + "External id": 35762,"Sequence number": 480168, "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": 2338707, "tid": 2338707, "ts": 6197199757002.442, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197199757040.247, "dur": 233.571, + "args": { + "External id": 35763,"Sequence number": 480169, "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": 2338707, "tid": 2338707, "ts": 6197199757040.247, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338707, "tid": 2338707, + "ts": 6197199757104.176, "dur": 11.708, + "args": { + "External id": 35764,"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": 2338707, "tid": 2338707, + "ts": 6197199757107.606, "dur": 7.443, + "args": { + "External id": 35765,"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": 2338707, "tid": 2338707, + "ts": 6197199757289.685, "dur": 123.656, + "args": { + "External id": 35766,"Sequence number": 480170, "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": 2338707, "tid": 2338707, "ts": 6197199757289.685, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338707, "tid": 2338707, + "ts": 6197199757306.967, "dur": 7.980, + "args": { + "External id": 35767,"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": 2338707, "tid": 2338707, + "ts": 6197199757309.503, "dur": 5.031, + "args": { + "External id": 35768,"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": 2338707, "tid": 2338707, + "ts": 6197199757447.294, "dur": 205.616, + "args": { + "External id": 35769,"Sequence number": 480171, "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": 2338707, "tid": 2338707, "ts": 6197199757447.294, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338707, "tid": 2338707, + "ts": 6197199757477.271, "dur": 143.169, + "args": { + "External id": 35770,"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": 2338707, "tid": 2338707, + "ts": 6197199757533.620, "dur": 7.308, + "args": { + "External id": 35771,"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": 2338707, "tid": 2338707, + "ts": 6197199757535.995, "dur": 4.489, + "args": { + "External id": 35772,"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": 2338707, "tid": 2338707, + "ts": 6197199757544.106, "dur": 3.957, + "args": { + "External id": 35773,"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": 2338707, "tid": 2338707, + "ts": 6197199757553.961, "dur": 1.663, + "args": { + "External id": 35774,"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": 2338707, "tid": 2338707, + "ts": 6197199757558.775, "dur": 3.582, + "args": { + "External id": 35775,"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": 2338707, "tid": 2338707, + "ts": 6197199757633.783, "dur": 5.912, + "args": { + "External id": 35776,"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": 2338707, "tid": 2338707, + "ts": 6197199757658.913, "dur": 7.196, + "args": { + "External id": 35777,"Sequence number": 480172, "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": 2338707, "tid": 2338707, + "ts": 6197199757660.798, "dur": 5.067, + "args": { + "External id": 35778,"Sequence number": 480172, "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": 2338707, "tid": 2338707, "ts": 6197199757660.798, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338707, "tid": 2338707, + "ts": 6197199757679.436, "dur": 155.120, + "args": { + "External id": 35779,"Sequence number": 480173, "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": 2338707, "tid": 2338707, + "ts": 6197199757680.729, "dur": 13.007, + "args": { + "External id": 35780,"Sequence number": 480173, "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": 2338707, "tid": 2338707, "ts": 6197199757680.729, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6197199757683.918, "dur": 8.341, + "args": { + "External id": 35781,"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": 2338707, "tid": 2338707, + "ts": 6197199757689.811, "dur": 2.172, + "args": { + "External id": 35782,"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": 2338707, "tid": 2338707, + "ts": 6197199757695.472, "dur": 138.678, + "args": { + "External id": 35783,"Sequence number": 480174, "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": 2338707, "tid": 2338707, + "ts": 6197199757697.515, "dur": 25.769, + "args": { + "External id": 35784,"Sequence number": 480174, "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": 2338707, "tid": 2338707, + "ts": 6197199757698.377, "dur": 24.279, + "args": { + "External id": 35785,"Sequence number": 480174, "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": 2338707, "tid": 2338707, "ts": 6197199757698.377, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6197199757727.383, "dur": 99.158, + "args": { + "External id": 35786,"Sequence number": 480175, "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": 2338707, "tid": 2338707, "ts": 6197199757727.383, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6197199757829.496, "dur": 3.837, + "args": { + "External id": 35787,"Sequence number": 480176, "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": 2338707, "tid": 2338707, "ts": 6197199757829.496, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197199757879.961, "dur": 295.229, + "args": { + "External id": 35788,"Sequence number": 480177, "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": 2338707, "tid": 2338707, "ts": 6197199757879.961, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6197199757901.823, "dur": 5.951, + "args": { + "External id": 35789,"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": 2338707, "tid": 2338707, + "ts": 6197199757905.502, "dur": 2.108, + "args": { + "External id": 35790,"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": 2338707, "tid": 2338707, + "ts": 6197199757912.309, "dur": 4.050, + "args": { + "External id": 35791,"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": 2338707, "tid": 2338707, + "ts": 6197199757913.489, "dur": 2.741, + "args": { + "External id": 35792,"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": 2338707, "tid": 2338707, + "ts": 6197199757914.788, "dur": 1.309, + "args": { + "External id": 35793,"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": 2338707, "tid": 2338707, + "ts": 6197199757925.066, "dur": 8.231, + "args": { + "External id": 35794,"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": 2338707, "tid": 2338707, + "ts": 6197199757927.577, "dur": 5.258, + "args": { + "External id": 35795,"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": 2338707, "tid": 2338707, + "ts": 6197199757943.024, "dur": 3.959, + "args": { + "External id": 35796,"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": 2338707, "tid": 2338707, + "ts": 6197199757953.308, "dur": 3.922, + "args": { + "External id": 35797,"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": 2338707, "tid": 2338707, + "ts": 6197199758146.135, "dur": 5.170, + "args": { + "External id": 35798,"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": 2338707, "tid": 2338707, + "ts": 6197199758147.657, "dur": 3.108, + "args": { + "External id": 35799,"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": 2338707, "tid": 2338707, + "ts": 6197199758154.771, "dur": 3.138, + "args": { + "External id": 35800,"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": 2338707, "tid": 2338707, + "ts": 6197199758156.310, "dur": 1.483, + "args": { + "External id": 35801,"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": 2338707, "tid": 2338707, + "ts": 6197199758198.278, "dur": 116.668, + "args": { + "External id": 35802,"Sequence number": 480178, "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": 2338707, "tid": 2338707, + "ts": 6197199758199.591, "dur": 10.928, + "args": { + "External id": 35803,"Sequence number": 480178, "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": 2338707, "tid": 2338707, "ts": 6197199758199.591, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6197199758204.553, "dur": 4.518, + "args": { + "External id": 35804,"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": 2338707, "tid": 2338707, + "ts": 6197199758206.924, "dur": 1.850, + "args": { + "External id": 35805,"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": 2338707, "tid": 2338707, + "ts": 6197199758211.820, "dur": 102.755, + "args": { + "External id": 35806,"Sequence number": 480179, "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": 2338707, "tid": 2338707, + "ts": 6197199758213.899, "dur": 6.674, + "args": { + "External id": 35807,"Sequence number": 480179, "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": 2338707, "tid": 2338707, + "ts": 6197199758217.053, "dur": 3.376, + "args": { + "External id": 35808,"Sequence number": 480179, "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": 2338707, "tid": 2338707, "ts": 6197199758217.053, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6197199758221.625, "dur": 85.688, + "args": { + "External id": 35809,"Sequence number": 480180, "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": 2338707, "tid": 2338707, "ts": 6197199758221.625, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6197199758309.562, "dur": 4.437, + "args": { + "External id": 35810,"Sequence number": 480181, "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": 2338707, "tid": 2338707, "ts": 6197199758309.562, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338707, "tid": 2338707, + "ts": 6197199758325.951, "dur": 90.362, + "args": { + "External id": 35811,"Sequence number": 480182, "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": 2338707, "tid": 2338707, + "ts": 6197199758326.820, "dur": 11.526, + "args": { + "External id": 35812,"Sequence number": 480182, "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": 2338707, "tid": 2338707, "ts": 6197199758326.820, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6197199758333.784, "dur": 3.061, + "args": { + "External id": 35813,"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": 2338707, "tid": 2338707, + "ts": 6197199758335.407, "dur": 1.267, + "args": { + "External id": 35814,"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": 2338707, "tid": 2338707, + "ts": 6197199758338.884, "dur": 77.109, + "args": { + "External id": 35815,"Sequence number": 480183, "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": 2338707, "tid": 2338707, + "ts": 6197199758340.154, "dur": 7.233, + "args": { + "External id": 35816,"Sequence number": 480183, "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": 2338707, "tid": 2338707, + "ts": 6197199758341.385, "dur": 5.851, + "args": { + "External id": 35817,"Sequence number": 480183, "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": 2338707, "tid": 2338707, "ts": 6197199758341.385, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6197199758348.095, "dur": 63.017, + "args": { + "External id": 35818,"Sequence number": 480184, "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": 2338707, "tid": 2338707, "ts": 6197199758348.095, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6197199758413.279, "dur": 2.389, + "args": { + "External id": 35819,"Sequence number": 480185, "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": 2338707, "tid": 2338707, "ts": 6197199758413.279, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197199758441.288, "dur": 174.183, + "args": { + "External id": 35820,"Sequence number": 480186, "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": 2338707, "tid": 2338707, "ts": 6197199758441.288, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6197199758488.956, "dur": 5.214, + "args": { + "External id": 35821,"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": 2338707, "tid": 2338707, + "ts": 6197199758532.022, "dur": 69.387, + "args": { + "External id": 35822,"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": 2338707, "tid": 2338707, + "ts": 6197199758533.014, "dur": 6.909, + "args": { + "External id": 35823,"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": 2338707, "tid": 2338707, + "ts": 6197199758534.455, "dur": 4.460, + "args": { + "External id": 35824,"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": 2338707, "tid": 2338707, + "ts": 6197199758538.013, "dur": 0.711, + "args": { + "External id": 35825,"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": 2338707, "tid": 2338707, + "ts": 6197199758540.927, "dur": 60.042, + "args": { + "External id": 35826,"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": 2338707, "tid": 2338707, + "ts": 6197199758542.307, "dur": 4.824, + "args": { + "External id": 35827,"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": 2338707, "tid": 2338707, + "ts": 6197199758545.513, "dur": 1.443, + "args": { + "External id": 35828,"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": 2338707, "tid": 2338707, + "ts": 6197199758548.074, "dur": 48.467, + "args": { + "External id": 35829,"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": 2338707, "tid": 2338707, + "ts": 6197199758599.181, "dur": 1.117, + "args": { + "External id": 35830,"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": 2338707, "tid": 2338707, + "ts": 6197199758624.963, "dur": 29.784, + "args": { + "External id": 35831,"Sequence number": 480187, "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": 2338707, "tid": 2338707, "ts": 6197199758624.963, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::stack", "pid": 2338707, "tid": 2338707, + "ts": 6197199758676.771, "dur": 77.093, + "args": { + "External id": 35832,"Sequence number": 480188, "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": 2338707, "tid": 2338707, "ts": 6197199758676.771, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::cat", "pid": 2338707, "tid": 2338707, + "ts": 6197199758686.809, "dur": 59.222, + "args": { + "External id": 35833,"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": 2338707, "tid": 2338707, + "ts": 6197199758749.275, "dur": 1.824, + "args": { + "External id": 35834,"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": 2338707, "tid": 2338707, + "ts": 6197199758799.106, "dur": 56.999, + "args": { + "External id": 35835,"Record function id": 0, "Ev Idx": 19007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 2/0", "pid": 2338707, "tid": 2338707, + "ts": 6197199758857.965, "dur": 283.076, + "args": { + "External id": 35836,"Record function id": 0, "Ev Idx": 19008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6197199758902.049, "dur": 227.172, + "args": { + "External id": 35837,"Sequence number": 480189, "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": 2338707, "tid": 2338707, "ts": 6197199758902.049, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6197199758989.653, "dur": 46.981, + "args": { + "External id": 35838,"kernel_hash": "cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "4096", "1", "9.9999999999999995e-07", "True", "4096", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/du/cdud5dksr72gsdwqcwxmxkrfjwvdpdc72uaztxrtc3aq46xq4xfs.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": 2338707, "tid": 2338707, + "ts": 6197199759250.109, "dur": 84.296, + "args": { + "External id": 35839,"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": 2338707, "tid": 2338707, + "ts": 6197199759253.707, "dur": 7.551, + "args": { + "External id": 35840,"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": 2338707, "tid": 2338707, + "ts": 6197199759295.407, "dur": 38.592, + "args": { + "External id": 35841,"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": 2338707, "tid": 2338707, + "ts": 6197199759298.911, "dur": 34.476, + "args": { + "External id": 35842,"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": 2338707, "tid": 2338707, + "ts": 6197199759341.190, "dur": 22.185, + "args": { + "External id": 35843,"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": 2338707, "tid": 2338707, + "ts": 6197199759342.603, "dur": 2.685, + "args": { + "External id": 35844,"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": 2338707, "tid": 2338707, + "ts": 6197199759346.054, "dur": 17.029, + "args": { + "External id": 35845,"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": 2338707, "tid": 2338707, + "ts": 6197199759349.250, "dur": 13.320, + "args": { + "External id": 35846,"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": 2338707, "tid": 2338707, + "ts": 6197199759366.645, "dur": 17.920, + "args": { + "External id": 35847,"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": 2338707, "tid": 2338707, + "ts": 6197199759367.629, "dur": 2.672, + "args": { + "External id": 35848,"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": 2338707, "tid": 2338707, + "ts": 6197199759370.912, "dur": 13.366, + "args": { + "External id": 35849,"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": 2338707, "tid": 2338707, + "ts": 6197199759371.379, "dur": 12.457, + "args": { + "External id": 35850,"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": 2338707, "tid": 2338707, + "ts": 6197199759396.612, "dur": 0.843, + "args": { + "External id": 35851,"Sequence number": 480190, "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": 2338707, "tid": 2338707, + "ts": 6197199759408.698, "dur": 13.534, + "args": { + "External id": 35852,"Sequence number": 480190, "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": 2338707, "tid": 2338707, + "ts": 6197199759417.569, "dur": 2.367, + "args": { + "External id": 35853,"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": 2338707, "tid": 2338707, + "ts": 6197199759429.589, "dur": 8.036, + "args": { + "External id": 35854,"Sequence number": 480190, "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": 2338707, "tid": 2338707, + "ts": 6197199759434.192, "dur": 1.313, + "args": { + "External id": 35855,"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": 2338707, "tid": 2338707, + "ts": 6197199759438.961, "dur": 4.403, + "args": { + "External id": 35856,"Sequence number": 480190, "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": 2338707, "tid": 2338707, + "ts": 6197199759441.757, "dur": 0.755, + "args": { + "External id": 35857,"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": 2338707, "tid": 2338707, + "ts": 6197199759444.879, "dur": 3.406, + "args": { + "External id": 35858,"Sequence number": 480190, "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": 2338707, "tid": 2338707, + "ts": 6197199759446.788, "dur": 0.816, + "args": { + "External id": 35859,"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": 2338707, "tid": 2338707, + "ts": 6197199759451.854, "dur": 2.995, + "args": { + "External id": 35860,"Sequence number": 480190, "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": 2338707, "tid": 2338707, + "ts": 6197199759453.497, "dur": 0.687, + "args": { + "External id": 35861,"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": 2338707, "tid": 2338707, + "ts": 6197199759456.117, "dur": 3.762, + "args": { + "External id": 35862,"Sequence number": 480190, "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": 2338707, "tid": 2338707, + "ts": 6197199759458.279, "dur": 0.774, + "args": { + "External id": 35863,"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": 2338707, "tid": 2338707, + "ts": 6197199759461.171, "dur": 3.334, + "args": { + "External id": 35864,"Sequence number": 480190, "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": 2338707, "tid": 2338707, + "ts": 6197199759463.035, "dur": 0.843, + "args": { + "External id": 35865,"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": 2338707, "tid": 2338707, + "ts": 6197199759469.310, "dur": 5.722, + "args": { + "External id": 35866,"Sequence number": 480190, "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": 2338707, "tid": 2338707, + "ts": 6197199759473.074, "dur": 1.026, + "args": { + "External id": 35867,"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": 2338707, "tid": 2338707, + "ts": 6197199759479.832, "dur": 3.612, + "args": { + "External id": 35868,"Sequence number": 480190, "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": 2338707, "tid": 2338707, + "ts": 6197199759482.201, "dur": 0.595, + "args": { + "External id": 35869,"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": 2338707, "tid": 2338707, + "ts": 6197199759486.887, "dur": 10.174, + "args": { + "External id": 35870,"Sequence number": 480190, "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": 2338707, "tid": 2338707, + "ts": 6197199759494.905, "dur": 0.933, + "args": { + "External id": 35871,"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": 2338707, "tid": 2338707, + "ts": 6197199759498.594, "dur": 3.226, + "args": { + "External id": 35872,"Sequence number": 480190, "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": 2338707, "tid": 2338707, + "ts": 6197199759500.324, "dur": 0.825, + "args": { + "External id": 35873,"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": 2338707, "tid": 2338707, + "ts": 6197199759504.828, "dur": 6.663, + "args": { + "External id": 35874,"Sequence number": 480190, "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": 2338707, "tid": 2338707, "ts": 6197199759504.828, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2338707, + "ts": 6197199759508.792, "dur": 0.942, + "args": { + "External id": 35875,"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": 2338707, "tid": 2338707, + "ts": 6197199759515.373, "dur": 5.674, + "args": { + "External id": 35876,"Sequence number": 480191, "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": 2338707, "tid": 2338707, "ts": 6197199759515.373, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2338707, + "ts": 6197199759519.442, "dur": 0.748, + "args": { + "External id": 35877,"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": 2338707, "tid": 2338707, + "ts": 6197199759522.174, "dur": 4.963, + "args": { + "External id": 35878,"Sequence number": 480192, "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": 2338707, "tid": 2338707, "ts": 6197199759522.174, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2338707, + "ts": 6197199759525.435, "dur": 0.723, + "args": { + "External id": 35879,"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": 2338707, "tid": 2338707, + "ts": 6197199759528.312, "dur": 7.014, + "args": { + "External id": 35880,"Sequence number": 480193, "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": 2338707, "tid": 2338707, "ts": 6197199759528.312, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2338707, + "ts": 6197199759533.654, "dur": 0.760, + "args": { + "External id": 35881,"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": 2338707, "tid": 2338707, + "ts": 6197199759540.351, "dur": 47.269, + "args": { + "External id": 35882,"Sequence number": 480194, "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": 2338707, "tid": 2338707, + "ts": 6197199759544.651, "dur": 42.616, + "args": { + "External id": 35883,"Sequence number": 480194, "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": 2338707, "tid": 2338707, + "ts": 6197199759548.105, "dur": 8.145, + "args": { + "External id": 35884,"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": 2338707, "tid": 2338707, + "ts": 6197199759550.159, "dur": 5.357, + "args": { + "External id": 35885,"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": 2338707, "tid": 2338707, + "ts": 6197199759557.889, "dur": 28.837, + "args": { + "External id": 35886,"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": 2338707, "tid": 2338707, + "ts": 6197199759620.039, "dur": 5.174, + "args": { + "External id": 35887,"Sequence number": 480194, "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": 2338707, "tid": 2338707, "ts": 6197199759620.039, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6197199759628.069, "dur": 1.135, + "args": { + "External id": 35888,"Sequence number": 480195, "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": 2338707, "tid": 2338707, + "ts": 6197199759664.214, "dur": 136020.400, + "args": { + "External id": 35889,"Sequence number": 480195, "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": 2338707, "tid": 2338707, "ts": 6197199759664.214, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338707, "tid": 2338707, + "ts": 6197199759681.516, "dur": 50.791, + "args": { + "External id": 35890,"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": 2338707, "tid": 2338707, + "ts": 6197199759682.040, "dur": 49.892, + "args": { + "External id": 35891,"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": 2338707, "tid": 2338707, + "ts": 6197199759683.576, "dur": 7.866, + "args": { + "External id": 35892,"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": 2338707, "tid": 2338707, + "ts": 6197199759687.110, "dur": 3.930, + "args": { + "External id": 35893,"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": 2338707, "tid": 2338707, + "ts": 6197199759692.336, "dur": 38.733, + "args": { + "External id": 35894,"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": 2338707, "tid": 2338707, + "ts": 6197199759756.661, "dur": 29.366, + "args": { + "External id": 35895,"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": 2338707, "tid": 2338707, + "ts": 6197199759757.982, "dur": 8.600, + "args": { + "External id": 35896,"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": 2338707, "tid": 2338707, + "ts": 6197199759760.765, "dur": 5.455, + "args": { + "External id": 35897,"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": 2338707, "tid": 2338707, + "ts": 6197199759767.819, "dur": 17.981, + "args": { + "External id": 35898,"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": 2338707, "tid": 2338707, + "ts": 6197199759769.021, "dur": 16.233, + "args": { + "External id": 35899,"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": 2338707, "tid": 2338707, + "ts": 6197199759790.856, "dur": 21.129, + "args": { + "External id": 35900,"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": 2338707, "tid": 2338707, + "ts": 6197199759791.646, "dur": 7.424, + "args": { + "External id": 35901,"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": 2338707, "tid": 2338707, + "ts": 6197199759794.925, "dur": 3.829, + "args": { + "External id": 35902,"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": 2338707, "tid": 2338707, + "ts": 6197199759799.612, "dur": 12.153, + "args": { + "External id": 35903,"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": 2338707, "tid": 2338707, + "ts": 6197199759800.062, "dur": 11.339, + "args": { + "External id": 35904,"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": 2338707, "tid": 2338707, + "ts": 6197199759817.580, "dur": 18.146, + "args": { + "External id": 35905,"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": 2338707, "tid": 2338707, + "ts": 6197199759818.730, "dur": 4.130, + "args": { + "External id": 35906,"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": 2338707, "tid": 2338707, + "ts": 6197199759823.788, "dur": 11.627, + "args": { + "External id": 35907,"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": 2338707, "tid": 2338707, + "ts": 6197199759824.441, "dur": 10.569, + "args": { + "External id": 35908,"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": 2338707, "tid": 2338707, + "ts": 6197199759845.242, "dur": 31.813, + "args": { + "External id": 35909,"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": 2338707, "tid": 2338707, + "ts": 6197199759881.840, "dur": 68.252, + "args": { + "External id": 35910,"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": 2338707, "tid": 2338707, + "ts": 6197199759884.879, "dur": 64.721, + "args": { + "External id": 35911,"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": 2338707, "tid": 2338707, + "ts": 6197199759893.204, "dur": 1.076, + "args": { + "External id": 35912,"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": 2338707, "tid": 2338707, + "ts": 6197199759898.554, "dur": 29.532, + "args": { + "External id": 35913,"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": 2338707, "tid": 2338707, + "ts": 6197199759900.410, "dur": 27.171, + "args": { + "External id": 35914,"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": 2338707, "tid": 2338707, + "ts": 6197199759903.236, "dur": 2.972, + "args": { + "External id": 35915,"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": 2338707, "tid": 2338707, + "ts": 6197199759907.435, "dur": 19.531, + "args": { + "External id": 35916,"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": 2338707, "tid": 2338707, + "ts": 6197199759958.665, "dur": 128624.905, + "args": { + "External id": 35917,"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": 2338707, "tid": 2338707, + "ts": 6197199759960.828, "dur": 128615.753, + "args": { + "External id": 35918,"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": 2338707, "tid": 2338707, + "ts": 6197199888634.261, "dur": 22.311, + "args": { + "External id": 35919,"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": 2338707, "tid": 2338707, + "ts": 6197199888648.763, "dur": 3.807, + "args": { + "External id": 35920,"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": 2338707, "tid": 2338707, + "ts": 6197199888666.777, "dur": 212.054, + "args": { + "External id": 35921,"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": 2338707, "tid": 2338707, + "ts": 6197199888669.230, "dur": 10.939, + "args": { + "External id": 35922,"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": 2338707, "tid": 2338707, + "ts": 6197199888674.009, "dur": 4.973, + "args": { + "External id": 35923,"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": 2338707, "tid": 2338707, + "ts": 6197199888677.050, "dur": 1.612, + "args": { + "External id": 35924,"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": 2338707, "tid": 2338707, + "ts": 6197199888685.713, "dur": 191.978, + "args": { + "External id": 35925,"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": 2338707, "tid": 2338707, + "ts": 6197199888688.797, "dur": 186.501, + "args": { + "External id": 35926,"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": 2338707, "tid": 2338707, + "ts": 6197199888887.696, "dur": 8.530, + "args": { + "External id": 35927,"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": 2338707, "tid": 2338707, + "ts": 6197199888892.210, "dur": 1.300, + "args": { + "External id": 35928,"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": 2338707, "tid": 2338707, + "ts": 6197199888913.624, "dur": 7.495, + "args": { + "External id": 35929,"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": 2338707, "tid": 2338707, + "ts": 6197199888941.004, "dur": 15.349, + "args": { + "External id": 35930,"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": 2338707, "tid": 2338707, + "ts": 6197199888948.031, "dur": 8.043, + "args": { + "External id": 35931,"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": 2338707, "tid": 2338707, + "ts": 6197199889203.683, "dur": 291.359, + "args": { + "External id": 35932,"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": 2338707, "tid": 2338707, + "ts": 6197199889210.502, "dur": 4.136, + "args": { + "External id": 35933,"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": 2338707, "tid": 2338707, + "ts": 6197199889217.771, "dur": 276.425, + "args": { + "External id": 35934,"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": 2338707, "tid": 2338707, + "ts": 6197199889221.278, "dur": 0.894, + "args": { + "External id": 35935,"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": 2338707, "tid": 2338707, + "ts": 6197199889225.697, "dur": 43.375, + "args": { + "External id": 35936,"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": 2338707, "tid": 2338707, + "ts": 6197199889272.279, "dur": 5.545, + "args": { + "External id": 35937,"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": 2338707, "tid": 2338707, + "ts": 6197199889275.853, "dur": 1.325, + "args": { + "External id": 35938,"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": 2338707, "tid": 2338707, + "ts": 6197199889280.619, "dur": 42.826, + "args": { + "External id": 35939,"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": 2338707, "tid": 2338707, + "ts": 6197199889285.344, "dur": 1.676, + "args": { + "External id": 35940,"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": 2338707, "tid": 2338707, + "ts": 6197199889290.149, "dur": 32.846, + "args": { + "External id": 35941,"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": 2338707, "tid": 2338707, + "ts": 6197199889299.613, "dur": 5.347, + "args": { + "External id": 35942,"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": 2338707, "tid": 2338707, + "ts": 6197199889326.782, "dur": 32.260, + "args": { + "External id": 35943,"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": 2338707, "tid": 2338707, + "ts": 6197199889361.941, "dur": 18.801, + "args": { + "External id": 35944,"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": 2338707, "tid": 2338707, + "ts": 6197199889385.650, "dur": 18.491, + "args": { + "External id": 35945,"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": 2338707, "tid": 2338707, + "ts": 6197199889407.722, "dur": 18.941, + "args": { + "External id": 35946,"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": 2338707, "tid": 2338707, + "ts": 6197199889429.156, "dur": 27.149, + "args": { + "External id": 35947,"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": 2338707, "tid": 2338707, + "ts": 6197199889431.915, "dur": 1.548, + "args": { + "External id": 35948,"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": 2338707, "tid": 2338707, + "ts": 6197199889438.086, "dur": 1.488, + "args": { + "External id": 35949,"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": 2338707, "tid": 2338707, + "ts": 6197199889459.065, "dur": 18.443, + "args": { + "External id": 35950,"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": 2338707, "tid": 2338707, + "ts": 6197199889479.177, "dur": 13.947, + "args": { + "External id": 35951,"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": 2338707, "tid": 2338707, + "ts": 6197199889504.900, "dur": 3.569, + "args": { + "External id": 35952,"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": 2338707, "tid": 2338707, + "ts": 6197199889519.578, "dur": 5.642, + "args": { + "External id": 35953,"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": 2338707, "tid": 2338707, + "ts": 6197199889523.071, "dur": 0.805, + "args": { + "External id": 35954,"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": 2338707, "tid": 2338707, + "ts": 6197199889629.667, "dur": 120.240, + "args": { + "External id": 35955,"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": 2338707, "tid": 2338707, + "ts": 6197199889765.721, "dur": 9.779, + "args": { + "External id": 35956,"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": 2338707, "tid": 2338707, + "ts": 6197199889770.794, "dur": 2.239, + "args": { + "External id": 35957,"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": 2338707, "tid": 2338707, + "ts": 6197199889778.566, "dur": 38.298, + "args": { + "External id": 35958,"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": 2338707, "tid": 2338707, + "ts": 6197199889826.191, "dur": 7.798, + "args": { + "External id": 35959,"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": 2338707, "tid": 2338707, + "ts": 6197199889829.007, "dur": 4.162, + "args": { + "External id": 35960,"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": 2338707, "tid": 2338707, + "ts": 6197199889831.730, "dur": 1.168, + "args": { + "External id": 35961,"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": 2338707, "tid": 2338707, + "ts": 6197199889843.194, "dur": 65.430, + "args": { + "External id": 35962,"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": 2338707, "tid": 2338707, + "ts": 6197199889844.876, "dur": 62.793, + "args": { + "External id": 35963,"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": 2338707, "tid": 2338707, + "ts": 6197199889915.571, "dur": 19.470, + "args": { + "External id": 35964,"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": 2338707, "tid": 2338707, + "ts": 6197199889943.969, "dur": 4.863, + "args": { + "External id": 35965,"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": 2338707, "tid": 2338707, + "ts": 6197199889946.901, "dur": 0.675, + "args": { + "External id": 35966,"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": 2338707, "tid": 2338707, + "ts": 6197199889954.349, "dur": 55.643, + "args": { + "External id": 35967,"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": 2338707, "tid": 2338707, + "ts": 6197199889955.811, "dur": 9.818, + "args": { + "External id": 35968,"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": 2338707, "tid": 2338707, + "ts": 6197199889959.333, "dur": 5.403, + "args": { + "External id": 35969,"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": 2338707, "tid": 2338707, + "ts": 6197199889961.291, "dur": 3.191, + "args": { + "External id": 35970,"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": 2338707, "tid": 2338707, + "ts": 6197199889966.269, "dur": 43.105, + "args": { + "External id": 35971,"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": 2338707, "tid": 2338707, + "ts": 6197199889967.225, "dur": 41.462, + "args": { + "External id": 35972,"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": 2338707, "tid": 2338707, + "ts": 6197199890015.489, "dur": 4.561, + "args": { + "External id": 35973,"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": 2338707, "tid": 2338707, + "ts": 6197199890017.908, "dur": 0.721, + "args": { + "External id": 35974,"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": 2338707, "tid": 2338707, + "ts": 6197199890027.936, "dur": 2.531, + "args": { + "External id": 35975,"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": 2338707, "tid": 2338707, + "ts": 6197199890043.935, "dur": 7.785, + "args": { + "External id": 35976,"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": 2338707, "tid": 2338707, + "ts": 6197199890046.911, "dur": 4.538, + "args": { + "External id": 35977,"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": 2338707, "tid": 2338707, + "ts": 6197199890223.126, "dur": 209.052, + "args": { + "External id": 35978,"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": 2338707, "tid": 2338707, + "ts": 6197199890226.119, "dur": 3.134, + "args": { + "External id": 35979,"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": 2338707, "tid": 2338707, + "ts": 6197199890232.245, "dur": 199.333, + "args": { + "External id": 35980,"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": 2338707, "tid": 2338707, + "ts": 6197199890234.231, "dur": 0.389, + "args": { + "External id": 35981,"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": 2338707, "tid": 2338707, + "ts": 6197199890241.447, "dur": 26.649, + "args": { + "External id": 35982,"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": 2338707, "tid": 2338707, + "ts": 6197199890270.320, "dur": 4.580, + "args": { + "External id": 35983,"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": 2338707, "tid": 2338707, + "ts": 6197199890273.189, "dur": 1.368, + "args": { + "External id": 35984,"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": 2338707, "tid": 2338707, + "ts": 6197199890276.178, "dur": 27.305, + "args": { + "External id": 35985,"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": 2338707, "tid": 2338707, + "ts": 6197199890277.537, "dur": 4.246, + "args": { + "External id": 35986,"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": 2338707, "tid": 2338707, + "ts": 6197199890283.712, "dur": 19.309, + "args": { + "External id": 35987,"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": 2338707, "tid": 2338707, + "ts": 6197199890287.745, "dur": 2.790, + "args": { + "External id": 35988,"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": 2338707, "tid": 2338707, + "ts": 6197199890305.317, "dur": 24.408, + "args": { + "External id": 35989,"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": 2338707, "tid": 2338707, + "ts": 6197199890331.725, "dur": 14.218, + "args": { + "External id": 35990,"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": 2338707, "tid": 2338707, + "ts": 6197199890349.513, "dur": 14.074, + "args": { + "External id": 35991,"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": 2338707, "tid": 2338707, + "ts": 6197199890365.643, "dur": 12.486, + "args": { + "External id": 35992,"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": 2338707, "tid": 2338707, + "ts": 6197199890383.244, "dur": 22.182, + "args": { + "External id": 35993,"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": 2338707, "tid": 2338707, + "ts": 6197199890385.836, "dur": 3.027, + "args": { + "External id": 35994,"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": 2338707, "tid": 2338707, + "ts": 6197199890391.152, "dur": 0.988, + "args": { + "External id": 35995,"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": 2338707, "tid": 2338707, + "ts": 6197199890407.185, "dur": 11.727, + "args": { + "External id": 35996,"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": 2338707, "tid": 2338707, + "ts": 6197199890420.111, "dur": 10.464, + "args": { + "External id": 35997,"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": 2338707, "tid": 2338707, + "ts": 6197199890440.744, "dur": 2.972, + "args": { + "External id": 35998,"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": 2338707, "tid": 2338707, + "ts": 6197199890454.761, "dur": 4.595, + "args": { + "External id": 35999,"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": 2338707, "tid": 2338707, + "ts": 6197199890457.832, "dur": 0.574, + "args": { + "External id": 36000,"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": 2338707, "tid": 2338707, + "ts": 6197199890539.101, "dur": 67.664, + "args": { + "External id": 36001,"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": 2338707, "tid": 2338707, + "ts": 6197199890612.707, "dur": 5.803, + "args": { + "External id": 36002,"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": 2338707, "tid": 2338707, + "ts": 6197199890615.983, "dur": 1.236, + "args": { + "External id": 36003,"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": 2338707, "tid": 2338707, + "ts": 6197199890620.326, "dur": 27.137, + "args": { + "External id": 36004,"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": 2338707, "tid": 2338707, + "ts": 6197199890652.811, "dur": 11.863, + "args": { + "External id": 36005,"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": 2338707, "tid": 2338707, + "ts": 6197199890654.872, "dur": 8.981, + "args": { + "External id": 36006,"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": 2338707, "tid": 2338707, + "ts": 6197199890659.554, "dur": 4.090, + "args": { + "External id": 36007,"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": 2338707, "tid": 2338707, + "ts": 6197199890668.050, "dur": 67.724, + "args": { + "External id": 36008,"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": 2338707, "tid": 2338707, + "ts": 6197199890669.646, "dur": 64.767, + "args": { + "External id": 36009,"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": 2338707, "tid": 2338707, + "ts": 6197199890743.827, "dur": 28.249, + "args": { + "External id": 36010,"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": 2338707, "tid": 2338707, + "ts": 6197199890781.901, "dur": 12.902, + "args": { + "External id": 36011,"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": 2338707, "tid": 2338707, + "ts": 6197199890791.866, "dur": 1.189, + "args": { + "External id": 36012,"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": 2338707, "tid": 2338707, + "ts": 6197199890801.447, "dur": 84.322, + "args": { + "External id": 36013,"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": 2338707, "tid": 2338707, + "ts": 6197199890805.567, "dur": 6.853, + "args": { + "External id": 36014,"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": 2338707, "tid": 2338707, + "ts": 6197199890807.514, "dur": 4.016, + "args": { + "External id": 36015,"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": 2338707, "tid": 2338707, + "ts": 6197199890809.552, "dur": 1.765, + "args": { + "External id": 36016,"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": 2338707, "tid": 2338707, + "ts": 6197199890813.340, "dur": 71.655, + "args": { + "External id": 36017,"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": 2338707, "tid": 2338707, + "ts": 6197199890814.372, "dur": 69.144, + "args": { + "External id": 36018,"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": 2338707, "tid": 2338707, + "ts": 6197199890893.628, "dur": 7.110, + "args": { + "External id": 36019,"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": 2338707, "tid": 2338707, + "ts": 6197199890897.399, "dur": 1.226, + "args": { + "External id": 36020,"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": 2338707, "tid": 2338707, + "ts": 6197199890913.754, "dur": 2.927, + "args": { + "External id": 36021,"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": 2338707, "tid": 2338707, + "ts": 6197199890929.649, "dur": 10.215, + "args": { + "External id": 36022,"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": 2338707, "tid": 2338707, + "ts": 6197199890932.539, "dur": 7.051, + "args": { + "External id": 36023,"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": 2338707, "tid": 2338707, + "ts": 6197199891098.128, "dur": 214.050, + "args": { + "External id": 36024,"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": 2338707, "tid": 2338707, + "ts": 6197199891101.389, "dur": 3.646, + "args": { + "External id": 36025,"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": 2338707, "tid": 2338707, + "ts": 6197199891107.379, "dur": 204.284, + "args": { + "External id": 36026,"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": 2338707, "tid": 2338707, + "ts": 6197199891112.163, "dur": 0.426, + "args": { + "External id": 36027,"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": 2338707, "tid": 2338707, + "ts": 6197199891114.254, "dur": 32.003, + "args": { + "External id": 36028,"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": 2338707, "tid": 2338707, + "ts": 6197199891148.382, "dur": 4.794, + "args": { + "External id": 36029,"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": 2338707, "tid": 2338707, + "ts": 6197199891151.356, "dur": 1.301, + "args": { + "External id": 36030,"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": 2338707, "tid": 2338707, + "ts": 6197199891154.327, "dur": 26.616, + "args": { + "External id": 36031,"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": 2338707, "tid": 2338707, + "ts": 6197199891155.846, "dur": 1.388, + "args": { + "External id": 36032,"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": 2338707, "tid": 2338707, + "ts": 6197199891158.963, "dur": 21.683, + "args": { + "External id": 36033,"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": 2338707, "tid": 2338707, + "ts": 6197199891165.623, "dur": 2.941, + "args": { + "External id": 36034,"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": 2338707, "tid": 2338707, + "ts": 6197199891182.569, "dur": 25.144, + "args": { + "External id": 36035,"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": 2338707, "tid": 2338707, + "ts": 6197199891209.689, "dur": 13.199, + "args": { + "External id": 36036,"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": 2338707, "tid": 2338707, + "ts": 6197199891228.592, "dur": 14.592, + "args": { + "External id": 36037,"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": 2338707, "tid": 2338707, + "ts": 6197199891245.059, "dur": 13.705, + "args": { + "External id": 36038,"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": 2338707, "tid": 2338707, + "ts": 6197199891261.103, "dur": 21.266, + "args": { + "External id": 36039,"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": 2338707, "tid": 2338707, + "ts": 6197199891263.716, "dur": 1.454, + "args": { + "External id": 36040,"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": 2338707, "tid": 2338707, + "ts": 6197199891267.650, "dur": 1.158, + "args": { + "External id": 36041,"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": 2338707, "tid": 2338707, + "ts": 6197199891284.251, "dur": 12.245, + "args": { + "External id": 36042,"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": 2338707, "tid": 2338707, + "ts": 6197199891300.470, "dur": 10.260, + "args": { + "External id": 36043,"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": 2338707, "tid": 2338707, + "ts": 6197199891321.792, "dur": 2.831, + "args": { + "External id": 36044,"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": 2338707, "tid": 2338707, + "ts": 6197199891336.823, "dur": 4.575, + "args": { + "External id": 36045,"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": 2338707, "tid": 2338707, + "ts": 6197199891339.719, "dur": 0.600, + "args": { + "External id": 36046,"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": 2338707, "tid": 2338707, + "ts": 6197199891419.671, "dur": 70.878, + "args": { + "External id": 36047,"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": 2338707, "tid": 2338707, + "ts": 6197199891496.135, "dur": 5.224, + "args": { + "External id": 36048,"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": 2338707, "tid": 2338707, + "ts": 6197199891499.292, "dur": 0.759, + "args": { + "External id": 36049,"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": 2338707, "tid": 2338707, + "ts": 6197199891503.064, "dur": 29.078, + "args": { + "External id": 36050,"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": 2338707, "tid": 2338707, + "ts": 6197199891541.194, "dur": 7.073, + "args": { + "External id": 36051,"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": 2338707, "tid": 2338707, + "ts": 6197199891543.279, "dur": 4.223, + "args": { + "External id": 36052,"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": 2338707, "tid": 2338707, + "ts": 6197199891545.750, "dur": 1.575, + "args": { + "External id": 36053,"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": 2338707, "tid": 2338707, + "ts": 6197199891551.528, "dur": 44.597, + "args": { + "External id": 36054,"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": 2338707, "tid": 2338707, + "ts": 6197199891552.997, "dur": 42.389, + "args": { + "External id": 36055,"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": 2338707, "tid": 2338707, + "ts": 6197199891600.357, "dur": 16.611, + "args": { + "External id": 36056,"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": 2338707, "tid": 2338707, + "ts": 6197199891623.389, "dur": 6.286, + "args": { + "External id": 36057,"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": 2338707, "tid": 2338707, + "ts": 6197199891627.697, "dur": 0.993, + "args": { + "External id": 36058,"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": 2338707, "tid": 2338707, + "ts": 6197199891634.353, "dur": 49.666, + "args": { + "External id": 36059,"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": 2338707, "tid": 2338707, + "ts": 6197199891635.499, "dur": 6.560, + "args": { + "External id": 36060,"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": 2338707, "tid": 2338707, + "ts": 6197199891636.381, "dur": 5.064, + "args": { + "External id": 36061,"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": 2338707, "tid": 2338707, + "ts": 6197199891638.018, "dur": 3.264, + "args": { + "External id": 36062,"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": 2338707, "tid": 2338707, + "ts": 6197199891642.735, "dur": 40.743, + "args": { + "External id": 36063,"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": 2338707, "tid": 2338707, + "ts": 6197199891645.878, "dur": 36.973, + "args": { + "External id": 36064,"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": 2338707, "tid": 2338707, + "ts": 6197199891688.274, "dur": 4.691, + "args": { + "External id": 36065,"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": 2338707, "tid": 2338707, + "ts": 6197199891690.418, "dur": 1.168, + "args": { + "External id": 36066,"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": 2338707, "tid": 2338707, + "ts": 6197199891699.091, "dur": 19.264, + "args": { + "External id": 36067,"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": 2338707, "tid": 2338707, + "ts": 6197199891733.446, "dur": 10.296, + "args": { + "External id": 36068,"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": 2338707, "tid": 2338707, + "ts": 6197199891736.933, "dur": 6.385, + "args": { + "External id": 36069,"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": 2338707, "tid": 2338707, + "ts": 6197199891870.417, "dur": 259.286, + "args": { + "External id": 36070,"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": 2338707, "tid": 2338707, + "ts": 6197199891874.540, "dur": 2.709, + "args": { + "External id": 36071,"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": 2338707, "tid": 2338707, + "ts": 6197199891880.516, "dur": 248.502, + "args": { + "External id": 36072,"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": 2338707, "tid": 2338707, + "ts": 6197199891882.742, "dur": 0.579, + "args": { + "External id": 36073,"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": 2338707, "tid": 2338707, + "ts": 6197199891888.402, "dur": 30.462, + "args": { + "External id": 36074,"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": 2338707, "tid": 2338707, + "ts": 6197199891921.031, "dur": 5.056, + "args": { + "External id": 36075,"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": 2338707, "tid": 2338707, + "ts": 6197199891924.265, "dur": 1.403, + "args": { + "External id": 36076,"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": 2338707, "tid": 2338707, + "ts": 6197199891927.721, "dur": 34.210, + "args": { + "External id": 36077,"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": 2338707, "tid": 2338707, + "ts": 6197199891929.899, "dur": 4.432, + "args": { + "External id": 36078,"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": 2338707, "tid": 2338707, + "ts": 6197199891939.012, "dur": 22.632, + "args": { + "External id": 36079,"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": 2338707, "tid": 2338707, + "ts": 6197199891943.433, "dur": 3.255, + "args": { + "External id": 36080,"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": 2338707, "tid": 2338707, + "ts": 6197199891963.481, "dur": 24.769, + "args": { + "External id": 36081,"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": 2338707, "tid": 2338707, + "ts": 6197199891989.950, "dur": 14.890, + "args": { + "External id": 36082,"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": 2338707, "tid": 2338707, + "ts": 6197199892007.862, "dur": 12.885, + "args": { + "External id": 36083,"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": 2338707, "tid": 2338707, + "ts": 6197199892022.408, "dur": 12.083, + "args": { + "External id": 36084,"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": 2338707, "tid": 2338707, + "ts": 6197199892036.573, "dur": 61.033, + "args": { + "External id": 36085,"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": 2338707, "tid": 2338707, + "ts": 6197199892039.581, "dur": 1.751, + "args": { + "External id": 36086,"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": 2338707, "tid": 2338707, + "ts": 6197199892043.791, "dur": 1.026, + "args": { + "External id": 36087,"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": 2338707, "tid": 2338707, + "ts": 6197199892103.175, "dur": 12.867, + "args": { + "External id": 36088,"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": 2338707, "tid": 2338707, + "ts": 6197199892117.320, "dur": 10.533, + "args": { + "External id": 36089,"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": 2338707, "tid": 2338707, + "ts": 6197199892141.047, "dur": 3.452, + "args": { + "External id": 36090,"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": 2338707, "tid": 2338707, + "ts": 6197199892157.185, "dur": 5.300, + "args": { + "External id": 36091,"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": 2338707, "tid": 2338707, + "ts": 6197199892160.728, "dur": 0.656, + "args": { + "External id": 36092,"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": 2338707, "tid": 2338707, + "ts": 6197199892243.851, "dur": 71.849, + "args": { + "External id": 36093,"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": 2338707, "tid": 2338707, + "ts": 6197199892321.549, "dur": 6.935, + "args": { + "External id": 36094,"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": 2338707, "tid": 2338707, + "ts": 6197199892326.007, "dur": 1.086, + "args": { + "External id": 36095,"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": 2338707, "tid": 2338707, + "ts": 6197199892333.091, "dur": 26.414, + "args": { + "External id": 36096,"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": 2338707, "tid": 2338707, + "ts": 6197199892364.807, "dur": 6.987, + "args": { + "External id": 36097,"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": 2338707, "tid": 2338707, + "ts": 6197199892366.755, "dur": 4.201, + "args": { + "External id": 36098,"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": 2338707, "tid": 2338707, + "ts": 6197199892369.447, "dur": 1.257, + "args": { + "External id": 36099,"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": 2338707, "tid": 2338707, + "ts": 6197199892375.049, "dur": 43.874, + "args": { + "External id": 36100,"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": 2338707, "tid": 2338707, + "ts": 6197199892376.729, "dur": 41.462, + "args": { + "External id": 36101,"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": 2338707, "tid": 2338707, + "ts": 6197199892423.392, "dur": 15.159, + "args": { + "External id": 36102,"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": 2338707, "tid": 2338707, + "ts": 6197199892447.720, "dur": 4.198, + "args": { + "External id": 36103,"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": 2338707, "tid": 2338707, + "ts": 6197199892450.131, "dur": 0.792, + "args": { + "External id": 36104,"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": 2338707, "tid": 2338707, + "ts": 6197199892457.270, "dur": 52.230, + "args": { + "External id": 36105,"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": 2338707, "tid": 2338707, + "ts": 6197199892458.485, "dur": 7.594, + "args": { + "External id": 36106,"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": 2338707, "tid": 2338707, + "ts": 6197199892459.592, "dur": 5.854, + "args": { + "External id": 36107,"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": 2338707, "tid": 2338707, + "ts": 6197199892464.373, "dur": 0.923, + "args": { + "External id": 36108,"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": 2338707, "tid": 2338707, + "ts": 6197199892469.333, "dur": 39.638, + "args": { + "External id": 36109,"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": 2338707, "tid": 2338707, + "ts": 6197199892470.423, "dur": 37.824, + "args": { + "External id": 36110,"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": 2338707, "tid": 2338707, + "ts": 6197199892514.157, "dur": 4.483, + "args": { + "External id": 36111,"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": 2338707, "tid": 2338707, + "ts": 6197199892516.432, "dur": 0.874, + "args": { + "External id": 36112,"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": 2338707, "tid": 2338707, + "ts": 6197199892525.739, "dur": 1.572, + "args": { + "External id": 36113,"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": 2338707, "tid": 2338707, + "ts": 6197199892537.600, "dur": 9.237, + "args": { + "External id": 36114,"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": 2338707, "tid": 2338707, + "ts": 6197199892542.996, "dur": 3.589, + "args": { + "External id": 36115,"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": 2338707, "tid": 2338707, + "ts": 6197199892640.295, "dur": 270.284, + "args": { + "External id": 36116,"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": 2338707, "tid": 2338707, + "ts": 6197199892643.300, "dur": 1.565, + "args": { + "External id": 36117,"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": 2338707, "tid": 2338707, + "ts": 6197199892647.018, "dur": 262.915, + "args": { + "External id": 36118,"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": 2338707, "tid": 2338707, + "ts": 6197199892651.111, "dur": 0.324, + "args": { + "External id": 36119,"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": 2338707, "tid": 2338707, + "ts": 6197199892652.677, "dur": 24.006, + "args": { + "External id": 36120,"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": 2338707, "tid": 2338707, + "ts": 6197199892678.445, "dur": 3.769, + "args": { + "External id": 36121,"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": 2338707, "tid": 2338707, + "ts": 6197199892681.069, "dur": 0.844, + "args": { + "External id": 36122,"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": 2338707, "tid": 2338707, + "ts": 6197199892683.301, "dur": 50.912, + "args": { + "External id": 36123,"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": 2338707, "tid": 2338707, + "ts": 6197199892689.884, "dur": 1.195, + "args": { + "External id": 36124,"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": 2338707, "tid": 2338707, + "ts": 6197199892692.613, "dur": 40.615, + "args": { + "External id": 36125,"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": 2338707, "tid": 2338707, + "ts": 6197199892695.338, "dur": 2.893, + "args": { + "External id": 36126,"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": 2338707, "tid": 2338707, + "ts": 6197199892737.066, "dur": 32.634, + "args": { + "External id": 36127,"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": 2338707, "tid": 2338707, + "ts": 6197199892771.938, "dur": 18.458, + "args": { + "External id": 36128,"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": 2338707, "tid": 2338707, + "ts": 6197199892794.189, "dur": 19.923, + "args": { + "External id": 36129,"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": 2338707, "tid": 2338707, + "ts": 6197199892816.469, "dur": 18.362, + "args": { + "External id": 36130,"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": 2338707, "tid": 2338707, + "ts": 6197199892837.869, "dur": 33.099, + "args": { + "External id": 36131,"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": 2338707, "tid": 2338707, + "ts": 6197199892841.607, "dur": 1.933, + "args": { + "External id": 36132,"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": 2338707, "tid": 2338707, + "ts": 6197199892849.340, "dur": 1.112, + "args": { + "External id": 36133,"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": 2338707, "tid": 2338707, + "ts": 6197199892872.834, "dur": 18.878, + "args": { + "External id": 36134,"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": 2338707, "tid": 2338707, + "ts": 6197199892893.152, "dur": 15.289, + "args": { + "External id": 36135,"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": 2338707, "tid": 2338707, + "ts": 6197199892920.898, "dur": 3.550, + "args": { + "External id": 36136,"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": 2338707, "tid": 2338707, + "ts": 6197199892936.952, "dur": 4.977, + "args": { + "External id": 36137,"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": 2338707, "tid": 2338707, + "ts": 6197199892940.186, "dur": 0.553, + "args": { + "External id": 36138,"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": 2338707, "tid": 2338707, + "ts": 6197199893022.972, "dur": 107.620, + "args": { + "External id": 36139,"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": 2338707, "tid": 2338707, + "ts": 6197199893154.400, "dur": 13.928, + "args": { + "External id": 36140,"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": 2338707, "tid": 2338707, + "ts": 6197199893161.373, "dur": 4.568, + "args": { + "External id": 36141,"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": 2338707, "tid": 2338707, + "ts": 6197199893170.578, "dur": 41.910, + "args": { + "External id": 36142,"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": 2338707, "tid": 2338707, + "ts": 6197199893220.080, "dur": 7.137, + "args": { + "External id": 36143,"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": 2338707, "tid": 2338707, + "ts": 6197199893222.268, "dur": 4.106, + "args": { + "External id": 36144,"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": 2338707, "tid": 2338707, + "ts": 6197199893224.674, "dur": 1.459, + "args": { + "External id": 36145,"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": 2338707, "tid": 2338707, + "ts": 6197199893235.267, "dur": 52.131, + "args": { + "External id": 36146,"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": 2338707, "tid": 2338707, + "ts": 6197199893237.156, "dur": 49.572, + "args": { + "External id": 36147,"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": 2338707, "tid": 2338707, + "ts": 6197199893292.299, "dur": 16.663, + "args": { + "External id": 36148,"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": 2338707, "tid": 2338707, + "ts": 6197199893316.403, "dur": 4.463, + "args": { + "External id": 36149,"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": 2338707, "tid": 2338707, + "ts": 6197199893318.583, "dur": 1.153, + "args": { + "External id": 36150,"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": 2338707, "tid": 2338707, + "ts": 6197199893325.994, "dur": 53.321, + "args": { + "External id": 36151,"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": 2338707, "tid": 2338707, + "ts": 6197199893327.268, "dur": 6.741, + "args": { + "External id": 36152,"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": 2338707, "tid": 2338707, + "ts": 6197199893330.637, "dur": 2.745, + "args": { + "External id": 36153,"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": 2338707, "tid": 2338707, + "ts": 6197199893332.126, "dur": 1.116, + "args": { + "External id": 36154,"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": 2338707, "tid": 2338707, + "ts": 6197199893334.652, "dur": 44.144, + "args": { + "External id": 36155,"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": 2338707, "tid": 2338707, + "ts": 6197199893339.627, "dur": 38.631, + "args": { + "External id": 36156,"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": 2338707, "tid": 2338707, + "ts": 6197199893383.920, "dur": 4.696, + "args": { + "External id": 36157,"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": 2338707, "tid": 2338707, + "ts": 6197199893386.229, "dur": 1.009, + "args": { + "External id": 36158,"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": 2338707, "tid": 2338707, + "ts": 6197199893396.093, "dur": 2.420, + "args": { + "External id": 36159,"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": 2338707, "tid": 2338707, + "ts": 6197199893410.343, "dur": 9.834, + "args": { + "External id": 36160,"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": 2338707, "tid": 2338707, + "ts": 6197199893413.465, "dur": 6.377, + "args": { + "External id": 36161,"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": 2338707, "tid": 2338707, + "ts": 6197199893527.971, "dur": 235.123, + "args": { + "External id": 36162,"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": 2338707, "tid": 2338707, + "ts": 6197199893530.434, "dur": 2.486, + "args": { + "External id": 36163,"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": 2338707, "tid": 2338707, + "ts": 6197199893534.778, "dur": 227.524, + "args": { + "External id": 36164,"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": 2338707, "tid": 2338707, + "ts": 6197199893536.608, "dur": 0.475, + "args": { + "External id": 36165,"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": 2338707, "tid": 2338707, + "ts": 6197199893540.574, "dur": 25.538, + "args": { + "External id": 36166,"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": 2338707, "tid": 2338707, + "ts": 6197199893568.115, "dur": 3.932, + "args": { + "External id": 36167,"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": 2338707, "tid": 2338707, + "ts": 6197199893570.594, "dur": 1.135, + "args": { + "External id": 36168,"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": 2338707, "tid": 2338707, + "ts": 6197199893573.313, "dur": 25.159, + "args": { + "External id": 36169,"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": 2338707, "tid": 2338707, + "ts": 6197199893574.874, "dur": 1.715, + "args": { + "External id": 36170,"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": 2338707, "tid": 2338707, + "ts": 6197199893577.988, "dur": 20.141, + "args": { + "External id": 36171,"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": 2338707, "tid": 2338707, + "ts": 6197199893583.647, "dur": 2.705, + "args": { + "External id": 36172,"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": 2338707, "tid": 2338707, + "ts": 6197199893599.869, "dur": 20.994, + "args": { + "External id": 36173,"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": 2338707, "tid": 2338707, + "ts": 6197199893622.722, "dur": 16.114, + "args": { + "External id": 36174,"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": 2338707, "tid": 2338707, + "ts": 6197199893641.903, "dur": 13.995, + "args": { + "External id": 36175,"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": 2338707, "tid": 2338707, + "ts": 6197199893657.690, "dur": 14.601, + "args": { + "External id": 36176,"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": 2338707, "tid": 2338707, + "ts": 6197199893676.999, "dur": 40.351, + "args": { + "External id": 36177,"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": 2338707, "tid": 2338707, + "ts": 6197199893679.443, "dur": 1.577, + "args": { + "External id": 36178,"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": 2338707, "tid": 2338707, + "ts": 6197199893683.505, "dur": 0.780, + "args": { + "External id": 36179,"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": 2338707, "tid": 2338707, + "ts": 6197199893721.526, "dur": 21.234, + "args": { + "External id": 36180,"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": 2338707, "tid": 2338707, + "ts": 6197199893744.893, "dur": 15.877, + "args": { + "External id": 36181,"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": 2338707, "tid": 2338707, + "ts": 6197199893774.370, "dur": 3.121, + "args": { + "External id": 36182,"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": 2338707, "tid": 2338707, + "ts": 6197199893791.106, "dur": 5.458, + "args": { + "External id": 36183,"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": 2338707, "tid": 2338707, + "ts": 6197199893794.856, "dur": 0.684, + "args": { + "External id": 36184,"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": 2338707, "tid": 2338707, + "ts": 6197199893884.904, "dur": 64.270, + "args": { + "External id": 36185,"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": 2338707, "tid": 2338707, + "ts": 6197199893955.192, "dur": 6.025, + "args": { + "External id": 36186,"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": 2338707, "tid": 2338707, + "ts": 6197199893958.655, "dur": 1.489, + "args": { + "External id": 36187,"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": 2338707, "tid": 2338707, + "ts": 6197199893963.100, "dur": 28.781, + "args": { + "External id": 36188,"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": 2338707, "tid": 2338707, + "ts": 6197199893996.576, "dur": 15.983, + "args": { + "External id": 36189,"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": 2338707, "tid": 2338707, + "ts": 6197199893998.426, "dur": 13.362, + "args": { + "External id": 36190,"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": 2338707, "tid": 2338707, + "ts": 6197199894010.151, "dur": 1.470, + "args": { + "External id": 36191,"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": 2338707, "tid": 2338707, + "ts": 6197199894015.768, "dur": 84.736, + "args": { + "External id": 36192,"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": 2338707, "tid": 2338707, + "ts": 6197199894017.225, "dur": 82.147, + "args": { + "External id": 36193,"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": 2338707, "tid": 2338707, + "ts": 6197199894107.384, "dur": 19.418, + "args": { + "External id": 36194,"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": 2338707, "tid": 2338707, + "ts": 6197199894134.070, "dur": 5.038, + "args": { + "External id": 36195,"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": 2338707, "tid": 2338707, + "ts": 6197199894136.772, "dur": 1.223, + "args": { + "External id": 36196,"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": 2338707, "tid": 2338707, + "ts": 6197199894144.584, "dur": 55.964, + "args": { + "External id": 36197,"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": 2338707, "tid": 2338707, + "ts": 6197199894148.582, "dur": 6.852, + "args": { + "External id": 36198,"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": 2338707, "tid": 2338707, + "ts": 6197199894149.959, "dur": 4.902, + "args": { + "External id": 36199,"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": 2338707, "tid": 2338707, + "ts": 6197199894151.350, "dur": 3.350, + "args": { + "External id": 36200,"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": 2338707, "tid": 2338707, + "ts": 6197199894156.091, "dur": 43.866, + "args": { + "External id": 36201,"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": 2338707, "tid": 2338707, + "ts": 6197199894157.353, "dur": 42.037, + "args": { + "External id": 36202,"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": 2338707, "tid": 2338707, + "ts": 6197199894204.474, "dur": 4.180, + "args": { + "External id": 36203,"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": 2338707, "tid": 2338707, + "ts": 6197199894206.491, "dur": 0.752, + "args": { + "External id": 36204,"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": 2338707, "tid": 2338707, + "ts": 6197199894219.132, "dur": 2.042, + "args": { + "External id": 36205,"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": 2338707, "tid": 2338707, + "ts": 6197199894230.171, "dur": 7.217, + "args": { + "External id": 36206,"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": 2338707, "tid": 2338707, + "ts": 6197199894232.668, "dur": 4.445, + "args": { + "External id": 36207,"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": 2338707, "tid": 2338707, + "ts": 6197199894338.775, "dur": 188.966, + "args": { + "External id": 36208,"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": 2338707, "tid": 2338707, + "ts": 6197199894341.895, "dur": 1.927, + "args": { + "External id": 36209,"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": 2338707, "tid": 2338707, + "ts": 6197199894345.581, "dur": 181.745, + "args": { + "External id": 36210,"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": 2338707, "tid": 2338707, + "ts": 6197199894348.992, "dur": 0.468, + "args": { + "External id": 36211,"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": 2338707, "tid": 2338707, + "ts": 6197199894353.537, "dur": 21.317, + "args": { + "External id": 36212,"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": 2338707, "tid": 2338707, + "ts": 6197199894376.553, "dur": 3.942, + "args": { + "External id": 36213,"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": 2338707, "tid": 2338707, + "ts": 6197199894378.876, "dur": 1.327, + "args": { + "External id": 36214,"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": 2338707, "tid": 2338707, + "ts": 6197199894381.425, "dur": 25.096, + "args": { + "External id": 36215,"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": 2338707, "tid": 2338707, + "ts": 6197199894383.474, "dur": 3.413, + "args": { + "External id": 36216,"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": 2338707, "tid": 2338707, + "ts": 6197199894388.266, "dur": 17.863, + "args": { + "External id": 36217,"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": 2338707, "tid": 2338707, + "ts": 6197199894391.446, "dur": 2.795, + "args": { + "External id": 36218,"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": 2338707, "tid": 2338707, + "ts": 6197199894408.159, "dur": 22.030, + "args": { + "External id": 36219,"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": 2338707, "tid": 2338707, + "ts": 6197199894431.874, "dur": 12.523, + "args": { + "External id": 36220,"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": 2338707, "tid": 2338707, + "ts": 6197199894450.235, "dur": 13.386, + "args": { + "External id": 36221,"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": 2338707, "tid": 2338707, + "ts": 6197199894465.520, "dur": 11.854, + "args": { + "External id": 36222,"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": 2338707, "tid": 2338707, + "ts": 6197199894479.254, "dur": 20.387, + "args": { + "External id": 36223,"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": 2338707, "tid": 2338707, + "ts": 6197199894481.739, "dur": 1.609, + "args": { + "External id": 36224,"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": 2338707, "tid": 2338707, + "ts": 6197199894485.604, "dur": 1.052, + "args": { + "External id": 36225,"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": 2338707, "tid": 2338707, + "ts": 6197199894500.979, "dur": 11.696, + "args": { + "External id": 36226,"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": 2338707, "tid": 2338707, + "ts": 6197199894516.208, "dur": 10.223, + "args": { + "External id": 36227,"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": 2338707, "tid": 2338707, + "ts": 6197199894534.350, "dur": 1.833, + "args": { + "External id": 36228,"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": 2338707, "tid": 2338707, + "ts": 6197199894544.936, "dur": 3.821, + "args": { + "External id": 36229,"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": 2338707, "tid": 2338707, + "ts": 6197199894547.288, "dur": 0.593, + "args": { + "External id": 36230,"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": 2338707, "tid": 2338707, + "ts": 6197199894614.135, "dur": 52.249, + "args": { + "External id": 36231,"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": 2338707, "tid": 2338707, + "ts": 6197199894671.799, "dur": 5.634, + "args": { + "External id": 36232,"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": 2338707, "tid": 2338707, + "ts": 6197199894675.030, "dur": 1.260, + "args": { + "External id": 36233,"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": 2338707, "tid": 2338707, + "ts": 6197199894679.273, "dur": 44.451, + "args": { + "External id": 36234,"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": 2338707, "tid": 2338707, + "ts": 6197199894735.528, "dur": 10.013, + "args": { + "External id": 36235,"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": 2338707, "tid": 2338707, + "ts": 6197199894737.606, "dur": 6.861, + "args": { + "External id": 36236,"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": 2338707, "tid": 2338707, + "ts": 6197199894740.501, "dur": 3.678, + "args": { + "External id": 36237,"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": 2338707, "tid": 2338707, + "ts": 6197199894750.087, "dur": 59.332, + "args": { + "External id": 36238,"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": 2338707, "tid": 2338707, + "ts": 6197199894751.911, "dur": 56.666, + "args": { + "External id": 36239,"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": 2338707, "tid": 2338707, + "ts": 6197199894814.269, "dur": 16.961, + "args": { + "External id": 36240,"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": 2338707, "tid": 2338707, + "ts": 6197199894837.582, "dur": 7.904, + "args": { + "External id": 36241,"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": 2338707, "tid": 2338707, + "ts": 6197199894843.142, "dur": 1.135, + "args": { + "External id": 36242,"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": 2338707, "tid": 2338707, + "ts": 6197199894850.413, "dur": 50.064, + "args": { + "External id": 36243,"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": 2338707, "tid": 2338707, + "ts": 6197199894851.565, "dur": 4.979, + "args": { + "External id": 36244,"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": 2338707, "tid": 2338707, + "ts": 6197199894852.830, "dur": 3.024, + "args": { + "External id": 36245,"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": 2338707, "tid": 2338707, + "ts": 6197199894854.765, "dur": 0.973, + "args": { + "External id": 36246,"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": 2338707, "tid": 2338707, + "ts": 6197199894857.183, "dur": 42.926, + "args": { + "External id": 36247,"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": 2338707, "tid": 2338707, + "ts": 6197199894860.830, "dur": 38.621, + "args": { + "External id": 36248,"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": 2338707, "tid": 2338707, + "ts": 6197199894904.630, "dur": 4.731, + "args": { + "External id": 36249,"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": 2338707, "tid": 2338707, + "ts": 6197199894907.070, "dur": 0.923, + "args": { + "External id": 36250,"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": 2338707, "tid": 2338707, + "ts": 6197199894915.591, "dur": 1.805, + "args": { + "External id": 36251,"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": 2338707, "tid": 2338707, + "ts": 6197199894926.419, "dur": 7.356, + "args": { + "External id": 36252,"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": 2338707, "tid": 2338707, + "ts": 6197199894928.884, "dur": 4.617, + "args": { + "External id": 36253,"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": 2338707, "tid": 2338707, + "ts": 6197199895030.517, "dur": 251.144, + "args": { + "External id": 36254,"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": 2338707, "tid": 2338707, + "ts": 6197199895032.912, "dur": 2.637, + "args": { + "External id": 36255,"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": 2338707, "tid": 2338707, + "ts": 6197199895040.339, "dur": 240.954, + "args": { + "External id": 36256,"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": 2338707, "tid": 2338707, + "ts": 6197199895041.971, "dur": 0.410, + "args": { + "External id": 36257,"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": 2338707, "tid": 2338707, + "ts": 6197199895044.262, "dur": 62.960, + "args": { + "External id": 36258,"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": 2338707, "tid": 2338707, + "ts": 6197199895109.998, "dur": 11.391, + "args": { + "External id": 36259,"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": 2338707, "tid": 2338707, + "ts": 6197199895117.431, "dur": 3.589, + "args": { + "External id": 36260,"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": 2338707, "tid": 2338707, + "ts": 6197199895122.412, "dur": 27.549, + "args": { + "External id": 36261,"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": 2338707, "tid": 2338707, + "ts": 6197199895126.219, "dur": 1.853, + "args": { + "External id": 36262,"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": 2338707, "tid": 2338707, + "ts": 6197199895129.454, "dur": 20.264, + "args": { + "External id": 36263,"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": 2338707, "tid": 2338707, + "ts": 6197199895132.662, "dur": 2.960, + "args": { + "External id": 36264,"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": 2338707, "tid": 2338707, + "ts": 6197199895151.480, "dur": 22.434, + "args": { + "External id": 36265,"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": 2338707, "tid": 2338707, + "ts": 6197199895175.682, "dur": 14.046, + "args": { + "External id": 36266,"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": 2338707, "tid": 2338707, + "ts": 6197199895192.485, "dur": 12.950, + "args": { + "External id": 36267,"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": 2338707, "tid": 2338707, + "ts": 6197199895206.801, "dur": 12.418, + "args": { + "External id": 36268,"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": 2338707, "tid": 2338707, + "ts": 6197199895221.005, "dur": 26.033, + "args": { + "External id": 36269,"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": 2338707, "tid": 2338707, + "ts": 6197199895223.752, "dur": 1.413, + "args": { + "External id": 36270,"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": 2338707, "tid": 2338707, + "ts": 6197199895229.783, "dur": 3.782, + "args": { + "External id": 36271,"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": 2338707, "tid": 2338707, + "ts": 6197199895248.208, "dur": 14.851, + "args": { + "External id": 36272,"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": 2338707, "tid": 2338707, + "ts": 6197199895268.875, "dur": 11.101, + "args": { + "External id": 36273,"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": 2338707, "tid": 2338707, + "ts": 6197199895290.859, "dur": 2.700, + "args": { + "External id": 36274,"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": 2338707, "tid": 2338707, + "ts": 6197199895304.243, "dur": 4.295, + "args": { + "External id": 36275,"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": 2338707, "tid": 2338707, + "ts": 6197199895307.286, "dur": 0.358, + "args": { + "External id": 36276,"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": 2338707, "tid": 2338707, + "ts": 6197199895383.699, "dur": 61.321, + "args": { + "External id": 36277,"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": 2338707, "tid": 2338707, + "ts": 6197199895450.240, "dur": 7.195, + "args": { + "External id": 36278,"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": 2338707, "tid": 2338707, + "ts": 6197199895455.281, "dur": 1.047, + "args": { + "External id": 36279,"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": 2338707, "tid": 2338707, + "ts": 6197199895459.020, "dur": 25.153, + "args": { + "External id": 36280,"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": 2338707, "tid": 2338707, + "ts": 6197199895488.436, "dur": 6.784, + "args": { + "External id": 36281,"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": 2338707, "tid": 2338707, + "ts": 6197199895490.108, "dur": 4.198, + "args": { + "External id": 36282,"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": 2338707, "tid": 2338707, + "ts": 6197199895492.309, "dur": 1.813, + "args": { + "External id": 36283,"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": 2338707, "tid": 2338707, + "ts": 6197199895497.933, "dur": 43.125, + "args": { + "External id": 36284,"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": 2338707, "tid": 2338707, + "ts": 6197199895499.127, "dur": 41.042, + "args": { + "External id": 36285,"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": 2338707, "tid": 2338707, + "ts": 6197199895546.649, "dur": 15.289, + "args": { + "External id": 36286,"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": 2338707, "tid": 2338707, + "ts": 6197199895567.694, "dur": 25.006, + "args": { + "External id": 36287,"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": 2338707, "tid": 2338707, + "ts": 6197199895570.400, "dur": 21.928, + "args": { + "External id": 36288,"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": 2338707, "tid": 2338707, + "ts": 6197199895575.362, "dur": 1.037, + "args": { + "External id": 36289,"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": 2338707, "tid": 2338707, + "ts": 6197199895598.547, "dur": 27.497, + "args": { + "External id": 36290,"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": 2338707, "tid": 2338707, + "ts": 6197199895600.553, "dur": 25.252, + "args": { + "External id": 36291,"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": 2338707, "tid": 2338707, + "ts": 6197199895606.020, "dur": 3.879, + "args": { + "External id": 36292,"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": 2338707, "tid": 2338707, + "ts": 6197199895611.255, "dur": 14.067, + "args": { + "External id": 36293,"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": 2338707, "tid": 2338707, + "ts": 6197199895644.455, "dur": 5.540, + "args": { + "External id": 36294,"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": 2338707, "tid": 2338707, + "ts": 6197199895646.571, "dur": 3.109, + "args": { + "External id": 36295,"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": 2338707, "tid": 2338707, + "ts": 6197199895651.278, "dur": 1.532, + "args": { + "External id": 36296,"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": 2338707, "tid": 2338707, + "ts": 6197199895652.102, "dur": 0.629, + "args": { + "External id": 36297,"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": 2338707, "tid": 2338707, + "ts": 6197199895738.101, "dur": 34.093, + "args": { + "External id": 36298,"Sequence number": 480196, "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": 2338707, "tid": 2338707, "ts": 6197199895738.101, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338707, "tid": 2338707, + "ts": 6197199895779.970, "dur": 8.808, + "args": { + "External id": 36299,"Sequence number": 480197, "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": 2338707, "tid": 2338707, + "ts": 6197199895784.939, "dur": 1.661, + "args": { + "External id": 36300,"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": 2338707, "tid": 2338707, + "ts": 6197199895794.714, "dur": 7.806, + "args": { + "External id": 36301,"Sequence number": 480197, "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": 2338707, "tid": 2338707, + "ts": 6197199895800.345, "dur": 0.957, + "args": { + "External id": 36302,"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": 2338707, "tid": 2338707, + "ts": 6197199895803.840, "dur": 3.016, + "args": { + "External id": 36303,"Sequence number": 480197, "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": 2338707, "tid": 2338707, + "ts": 6197199895805.451, "dur": 0.852, + "args": { + "External id": 36304,"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": 2338707, "tid": 2338707, + "ts": 6197199895811.125, "dur": 8.937, + "args": { + "External id": 36305,"Sequence number": 480197, "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": 2338707, "tid": 2338707, "ts": 6197199895811.125, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2338707, + "ts": 6197199895817.362, "dur": 1.116, + "args": { + "External id": 36306,"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": 2338707, "tid": 2338707, + "ts": 6197199895821.524, "dur": 5.363, + "args": { + "External id": 36307,"Sequence number": 480198, "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": 2338707, "tid": 2338707, "ts": 6197199895821.524, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2338707, + "ts": 6197199895825.179, "dur": 0.956, + "args": { + "External id": 36308,"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": 2338707, "tid": 2338707, + "ts": 6197199895828.274, "dur": 9.510, + "args": { + "External id": 36309,"Sequence number": 480199, "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": 2338707, "tid": 2338707, "ts": 6197199895828.274, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2338707, + "ts": 6197199895835.960, "dur": 0.834, + "args": { + "External id": 36310,"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": 2338707, "tid": 2338707, + "ts": 6197199895839.117, "dur": 5.963, + "args": { + "External id": 36311,"Sequence number": 480200, "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": 2338707, "tid": 2338707, "ts": 6197199895839.117, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2338707, + "ts": 6197199895843.179, "dur": 1.210, + "args": { + "External id": 36312,"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": 2338707, "tid": 2338707, + "ts": 6197199895850.063, "dur": 35.226, + "args": { + "External id": 36313,"Sequence number": 480201, "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": 2338707, "tid": 2338707, + "ts": 6197199895851.940, "dur": 33.081, + "args": { + "External id": 36314,"Sequence number": 480201, "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": 2338707, "tid": 2338707, + "ts": 6197199895854.761, "dur": 7.900, + "args": { + "External id": 36315,"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": 2338707, "tid": 2338707, + "ts": 6197199895857.682, "dur": 4.275, + "args": { + "External id": 36316,"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": 2338707, "tid": 2338707, + "ts": 6197199895863.771, "dur": 20.749, + "args": { + "External id": 36317,"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": 2338707, "tid": 2338707, + "ts": 6197199895926.538, "dur": 7.381, + "args": { + "External id": 36318,"Sequence number": 480201, "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": 2338707, "tid": 2338707, "ts": 6197199895926.538, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6197199895939.071, "dur": 1.407, + "args": { + "External id": 36319,"Sequence number": 480202, "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": 2338707, "tid": 2338707, + "ts": 6197199895981.183, "dur": 46376.506, + "args": { + "External id": 36320,"Sequence number": 480202, "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": 2338707, "tid": 2338707, "ts": 6197199895981.183, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338707, "tid": 2338707, + "ts": 6197199896001.302, "dur": 27.964, + "args": { + "External id": 36321,"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": 2338707, "tid": 2338707, + "ts": 6197199896002.428, "dur": 26.642, + "args": { + "External id": 36322,"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": 2338707, "tid": 2338707, + "ts": 6197199896004.276, "dur": 6.283, + "args": { + "External id": 36323,"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": 2338707, "tid": 2338707, + "ts": 6197199896006.029, "dur": 4.092, + "args": { + "External id": 36324,"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": 2338707, "tid": 2338707, + "ts": 6197199896011.458, "dur": 17.212, + "args": { + "External id": 36325,"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": 2338707, "tid": 2338707, + "ts": 6197199896050.403, "dur": 71.194, + "args": { + "External id": 36326,"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": 2338707, "tid": 2338707, + "ts": 6197199896051.661, "dur": 45.206, + "args": { + "External id": 36327,"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": 2338707, "tid": 2338707, + "ts": 6197199896054.171, "dur": 41.934, + "args": { + "External id": 36328,"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": 2338707, "tid": 2338707, + "ts": 6197199896099.155, "dur": 22.229, + "args": { + "External id": 36329,"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": 2338707, "tid": 2338707, + "ts": 6197199896104.274, "dur": 16.600, + "args": { + "External id": 36330,"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": 2338707, "tid": 2338707, + "ts": 6197199896127.266, "dur": 23.031, + "args": { + "External id": 36331,"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": 2338707, "tid": 2338707, + "ts": 6197199896128.530, "dur": 5.588, + "args": { + "External id": 36332,"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": 2338707, "tid": 2338707, + "ts": 6197199896130.243, "dur": 3.647, + "args": { + "External id": 36333,"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": 2338707, "tid": 2338707, + "ts": 6197199896134.708, "dur": 15.396, + "args": { + "External id": 36334,"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": 2338707, "tid": 2338707, + "ts": 6197199896135.506, "dur": 14.298, + "args": { + "External id": 36335,"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": 2338707, "tid": 2338707, + "ts": 6197199896159.448, "dur": 22.076, + "args": { + "External id": 36336,"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": 2338707, "tid": 2338707, + "ts": 6197199896164.495, "dur": 3.132, + "args": { + "External id": 36337,"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": 2338707, "tid": 2338707, + "ts": 6197199896168.316, "dur": 12.948, + "args": { + "External id": 36338,"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": 2338707, "tid": 2338707, + "ts": 6197199896172.231, "dur": 8.583, + "args": { + "External id": 36339,"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": 2338707, "tid": 2338707, + "ts": 6197199896189.458, "dur": 27.044, + "args": { + "External id": 36340,"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": 2338707, "tid": 2338707, + "ts": 6197199896219.817, "dur": 61.153, + "args": { + "External id": 36341,"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": 2338707, "tid": 2338707, + "ts": 6197199896222.628, "dur": 57.897, + "args": { + "External id": 36342,"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": 2338707, "tid": 2338707, + "ts": 6197199896227.696, "dur": 1.453, + "args": { + "External id": 36343,"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": 2338707, "tid": 2338707, + "ts": 6197199896231.214, "dur": 29.479, + "args": { + "External id": 36344,"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": 2338707, "tid": 2338707, + "ts": 6197199896233.333, "dur": 27.118, + "args": { + "External id": 36345,"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": 2338707, "tid": 2338707, + "ts": 6197199896238.284, "dur": 3.459, + "args": { + "External id": 36346,"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": 2338707, "tid": 2338707, + "ts": 6197199896242.608, "dur": 17.277, + "args": { + "External id": 36347,"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": 2338707, "tid": 2338707, + "ts": 6197199896285.558, "dur": 39683.495, + "args": { + "External id": 36348,"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": 2338707, "tid": 2338707, + "ts": 6197199896287.687, "dur": 39679.865, + "args": { + "External id": 36349,"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": 2338707, "tid": 2338707, + "ts": 6197199935986.765, "dur": 8.586, + "args": { + "External id": 36350,"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": 2338707, "tid": 2338707, + "ts": 6197199935991.529, "dur": 1.484, + "args": { + "External id": 36351,"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": 2338707, "tid": 2338707, + "ts": 6197199936001.423, "dur": 185.362, + "args": { + "External id": 36352,"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": 2338707, "tid": 2338707, + "ts": 6197199936039.855, "dur": 8.220, + "args": { + "External id": 36353,"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": 2338707, "tid": 2338707, + "ts": 6197199936042.839, "dur": 4.320, + "args": { + "External id": 36354,"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": 2338707, "tid": 2338707, + "ts": 6197199936045.705, "dur": 1.175, + "args": { + "External id": 36355,"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": 2338707, "tid": 2338707, + "ts": 6197199936074.344, "dur": 111.418, + "args": { + "External id": 36356,"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": 2338707, "tid": 2338707, + "ts": 6197199936076.783, "dur": 107.833, + "args": { + "External id": 36357,"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": 2338707, "tid": 2338707, + "ts": 6197199936193.099, "dur": 5.223, + "args": { + "External id": 36358,"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": 2338707, "tid": 2338707, + "ts": 6197199936195.697, "dur": 0.817, + "args": { + "External id": 36359,"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": 2338707, "tid": 2338707, + "ts": 6197199936208.816, "dur": 3.155, + "args": { + "External id": 36360,"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": 2338707, "tid": 2338707, + "ts": 6197199936225.302, "dur": 9.953, + "args": { + "External id": 36361,"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": 2338707, "tid": 2338707, + "ts": 6197199936230.271, "dur": 4.696, + "args": { + "External id": 36362,"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": 2338707, "tid": 2338707, + "ts": 6197199936390.752, "dur": 225.398, + "args": { + "External id": 36363,"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": 2338707, "tid": 2338707, + "ts": 6197199936396.265, "dur": 2.200, + "args": { + "External id": 36364,"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": 2338707, "tid": 2338707, + "ts": 6197199936400.526, "dur": 214.991, + "args": { + "External id": 36365,"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": 2338707, "tid": 2338707, + "ts": 6197199936402.272, "dur": 0.460, + "args": { + "External id": 36366,"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": 2338707, "tid": 2338707, + "ts": 6197199936404.310, "dur": 30.680, + "args": { + "External id": 36367,"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": 2338707, "tid": 2338707, + "ts": 6197199936436.732, "dur": 6.464, + "args": { + "External id": 36368,"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": 2338707, "tid": 2338707, + "ts": 6197199936441.823, "dur": 0.949, + "args": { + "External id": 36369,"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": 2338707, "tid": 2338707, + "ts": 6197199936444.522, "dur": 28.929, + "args": { + "External id": 36370,"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": 2338707, "tid": 2338707, + "ts": 6197199936447.947, "dur": 1.132, + "args": { + "External id": 36371,"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": 2338707, "tid": 2338707, + "ts": 6197199936450.612, "dur": 22.497, + "args": { + "External id": 36372,"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": 2338707, "tid": 2338707, + "ts": 6197199936454.287, "dur": 4.146, + "args": { + "External id": 36373,"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": 2338707, "tid": 2338707, + "ts": 6197199936475.241, "dur": 28.823, + "args": { + "External id": 36374,"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": 2338707, "tid": 2338707, + "ts": 6197199936506.369, "dur": 15.806, + "args": { + "External id": 36375,"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": 2338707, "tid": 2338707, + "ts": 6197199936525.189, "dur": 16.687, + "args": { + "External id": 36376,"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": 2338707, "tid": 2338707, + "ts": 6197199936543.697, "dur": 14.686, + "args": { + "External id": 36377,"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": 2338707, "tid": 2338707, + "ts": 6197199936560.189, "dur": 24.343, + "args": { + "External id": 36378,"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": 2338707, "tid": 2338707, + "ts": 6197199936562.543, "dur": 1.203, + "args": { + "External id": 36379,"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": 2338707, "tid": 2338707, + "ts": 6197199936568.096, "dur": 1.074, + "args": { + "External id": 36380,"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": 2338707, "tid": 2338707, + "ts": 6197199936586.059, "dur": 13.822, + "args": { + "External id": 36381,"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": 2338707, "tid": 2338707, + "ts": 6197199936601.203, "dur": 13.251, + "args": { + "External id": 36382,"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": 2338707, "tid": 2338707, + "ts": 6197199936623.797, "dur": 2.086, + "args": { + "External id": 36383,"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": 2338707, "tid": 2338707, + "ts": 6197199936633.645, "dur": 4.824, + "args": { + "External id": 36384,"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": 2338707, "tid": 2338707, + "ts": 6197199936636.337, "dur": 1.044, + "args": { + "External id": 36385,"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": 2338707, "tid": 2338707, + "ts": 6197199936740.643, "dur": 92.200, + "args": { + "External id": 36386,"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": 2338707, "tid": 2338707, + "ts": 6197199936843.307, "dur": 9.688, + "args": { + "External id": 36387,"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": 2338707, "tid": 2338707, + "ts": 6197199936847.200, "dur": 1.431, + "args": { + "External id": 36388,"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": 2338707, "tid": 2338707, + "ts": 6197199936854.800, "dur": 39.678, + "args": { + "External id": 36389,"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": 2338707, "tid": 2338707, + "ts": 6197199936903.912, "dur": 9.525, + "args": { + "External id": 36390,"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": 2338707, "tid": 2338707, + "ts": 6197199936905.908, "dur": 6.561, + "args": { + "External id": 36391,"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": 2338707, "tid": 2338707, + "ts": 6197199936908.320, "dur": 3.915, + "args": { + "External id": 36392,"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": 2338707, "tid": 2338707, + "ts": 6197199936919.546, "dur": 47.540, + "args": { + "External id": 36393,"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": 2338707, "tid": 2338707, + "ts": 6197199936920.869, "dur": 45.573, + "args": { + "External id": 36394,"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": 2338707, "tid": 2338707, + "ts": 6197199936971.788, "dur": 17.982, + "args": { + "External id": 36395,"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": 2338707, "tid": 2338707, + "ts": 6197199936996.996, "dur": 4.170, + "args": { + "External id": 36396,"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": 2338707, "tid": 2338707, + "ts": 6197199936999.392, "dur": 0.900, + "args": { + "External id": 36397,"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": 2338707, "tid": 2338707, + "ts": 6197199937006.413, "dur": 93.538, + "args": { + "External id": 36398,"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": 2338707, "tid": 2338707, + "ts": 6197199937007.330, "dur": 7.743, + "args": { + "External id": 36399,"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": 2338707, "tid": 2338707, + "ts": 6197199937011.134, "dur": 3.312, + "args": { + "External id": 36400,"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": 2338707, "tid": 2338707, + "ts": 6197199937013.344, "dur": 0.967, + "args": { + "External id": 36401,"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": 2338707, "tid": 2338707, + "ts": 6197199937015.779, "dur": 83.595, + "args": { + "External id": 36402,"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": 2338707, "tid": 2338707, + "ts": 6197199937016.237, "dur": 81.731, + "args": { + "External id": 36403,"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": 2338707, "tid": 2338707, + "ts": 6197199937107.391, "dur": 5.942, + "args": { + "External id": 36404,"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": 2338707, "tid": 2338707, + "ts": 6197199937110.369, "dur": 1.159, + "args": { + "External id": 36405,"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": 2338707, "tid": 2338707, + "ts": 6197199937121.955, "dur": 2.125, + "args": { + "External id": 36406,"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": 2338707, "tid": 2338707, + "ts": 6197199937136.535, "dur": 8.742, + "args": { + "External id": 36407,"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": 2338707, "tid": 2338707, + "ts": 6197199937139.601, "dur": 5.441, + "args": { + "External id": 36408,"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": 2338707, "tid": 2338707, + "ts": 6197199937265.653, "dur": 204.745, + "args": { + "External id": 36409,"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": 2338707, "tid": 2338707, + "ts": 6197199937268.100, "dur": 2.060, + "args": { + "External id": 36410,"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": 2338707, "tid": 2338707, + "ts": 6197199937274.127, "dur": 195.895, + "args": { + "External id": 36411,"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": 2338707, "tid": 2338707, + "ts": 6197199937275.661, "dur": 0.754, + "args": { + "External id": 36412,"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": 2338707, "tid": 2338707, + "ts": 6197199937280.498, "dur": 25.809, + "args": { + "External id": 36413,"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": 2338707, "tid": 2338707, + "ts": 6197199937308.048, "dur": 5.705, + "args": { + "External id": 36414,"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": 2338707, "tid": 2338707, + "ts": 6197199937310.629, "dur": 2.808, + "args": { + "External id": 36415,"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": 2338707, "tid": 2338707, + "ts": 6197199937314.940, "dur": 23.307, + "args": { + "External id": 36416,"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": 2338707, "tid": 2338707, + "ts": 6197199937316.335, "dur": 1.071, + "args": { + "External id": 36417,"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": 2338707, "tid": 2338707, + "ts": 6197199937318.676, "dur": 19.318, + "args": { + "External id": 36418,"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": 2338707, "tid": 2338707, + "ts": 6197199937322.040, "dur": 2.524, + "args": { + "External id": 36419,"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": 2338707, "tid": 2338707, + "ts": 6197199937340.229, "dur": 25.395, + "args": { + "External id": 36420,"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": 2338707, "tid": 2338707, + "ts": 6197199937367.226, "dur": 15.550, + "args": { + "External id": 36421,"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": 2338707, "tid": 2338707, + "ts": 6197199937385.355, "dur": 14.783, + "args": { + "External id": 36422,"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": 2338707, "tid": 2338707, + "ts": 6197199937401.605, "dur": 13.808, + "args": { + "External id": 36423,"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": 2338707, "tid": 2338707, + "ts": 6197199937419.980, "dur": 22.088, + "args": { + "External id": 36424,"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": 2338707, "tid": 2338707, + "ts": 6197199937422.501, "dur": 2.034, + "args": { + "External id": 36425,"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": 2338707, "tid": 2338707, + "ts": 6197199937426.576, "dur": 0.894, + "args": { + "External id": 36426,"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": 2338707, "tid": 2338707, + "ts": 6197199937443.921, "dur": 12.855, + "args": { + "External id": 36427,"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": 2338707, "tid": 2338707, + "ts": 6197199937457.841, "dur": 11.020, + "args": { + "External id": 36428,"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": 2338707, "tid": 2338707, + "ts": 6197199937477.528, "dur": 2.009, + "args": { + "External id": 36429,"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": 2338707, "tid": 2338707, + "ts": 6197199937488.877, "dur": 4.093, + "args": { + "External id": 36430,"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": 2338707, "tid": 2338707, + "ts": 6197199937491.646, "dur": 0.499, + "args": { + "External id": 36431,"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": 2338707, "tid": 2338707, + "ts": 6197199937570.801, "dur": 61.824, + "args": { + "External id": 36432,"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": 2338707, "tid": 2338707, + "ts": 6197199937638.525, "dur": 6.747, + "args": { + "External id": 36433,"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": 2338707, "tid": 2338707, + "ts": 6197199937641.130, "dur": 3.020, + "args": { + "External id": 36434,"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": 2338707, "tid": 2338707, + "ts": 6197199937646.829, "dur": 26.508, + "args": { + "External id": 36435,"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": 2338707, "tid": 2338707, + "ts": 6197199937678.160, "dur": 8.856, + "args": { + "External id": 36436,"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": 2338707, "tid": 2338707, + "ts": 6197199937679.696, "dur": 6.529, + "args": { + "External id": 36437,"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": 2338707, "tid": 2338707, + "ts": 6197199937684.743, "dur": 1.202, + "args": { + "External id": 36438,"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": 2338707, "tid": 2338707, + "ts": 6197199937689.699, "dur": 78.699, + "args": { + "External id": 36439,"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": 2338707, "tid": 2338707, + "ts": 6197199937690.728, "dur": 75.918, + "args": { + "External id": 36440,"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": 2338707, "tid": 2338707, + "ts": 6197199937774.730, "dur": 19.535, + "args": { + "External id": 36441,"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": 2338707, "tid": 2338707, + "ts": 6197199937802.102, "dur": 5.375, + "args": { + "External id": 36442,"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": 2338707, "tid": 2338707, + "ts": 6197199937805.190, "dur": 1.173, + "args": { + "External id": 36443,"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": 2338707, "tid": 2338707, + "ts": 6197199937812.040, "dur": 51.449, + "args": { + "External id": 36444,"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": 2338707, "tid": 2338707, + "ts": 6197199937815.530, "dur": 4.441, + "args": { + "External id": 36445,"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": 2338707, "tid": 2338707, + "ts": 6197199937816.640, "dur": 2.658, + "args": { + "External id": 36446,"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": 2338707, "tid": 2338707, + "ts": 6197199937818.326, "dur": 0.834, + "args": { + "External id": 36447,"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": 2338707, "tid": 2338707, + "ts": 6197199937820.862, "dur": 42.167, + "args": { + "External id": 36448,"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": 2338707, "tid": 2338707, + "ts": 6197199937821.592, "dur": 40.762, + "args": { + "External id": 36449,"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": 2338707, "tid": 2338707, + "ts": 6197199937868.729, "dur": 3.695, + "args": { + "External id": 36450,"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": 2338707, "tid": 2338707, + "ts": 6197199937870.601, "dur": 0.495, + "args": { + "External id": 36451,"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": 2338707, "tid": 2338707, + "ts": 6197199937882.644, "dur": 1.800, + "args": { + "External id": 36452,"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": 2338707, "tid": 2338707, + "ts": 6197199937893.550, "dur": 7.101, + "args": { + "External id": 36453,"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": 2338707, "tid": 2338707, + "ts": 6197199937895.764, "dur": 4.588, + "args": { + "External id": 36454,"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": 2338707, "tid": 2338707, + "ts": 6197199938003.086, "dur": 306.207, + "args": { + "External id": 36455,"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": 2338707, "tid": 2338707, + "ts": 6197199938005.182, "dur": 4.349, + "args": { + "External id": 36456,"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": 2338707, "tid": 2338707, + "ts": 6197199938011.419, "dur": 297.104, + "args": { + "External id": 36457,"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": 2338707, "tid": 2338707, + "ts": 6197199938015.058, "dur": 0.373, + "args": { + "External id": 36458,"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": 2338707, "tid": 2338707, + "ts": 6197199938016.678, "dur": 26.340, + "args": { + "External id": 36459,"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": 2338707, "tid": 2338707, + "ts": 6197199938045.162, "dur": 5.509, + "args": { + "External id": 36460,"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": 2338707, "tid": 2338707, + "ts": 6197199938049.725, "dur": 0.691, + "args": { + "External id": 36461,"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": 2338707, "tid": 2338707, + "ts": 6197199938051.660, "dur": 62.961, + "args": { + "External id": 36462,"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": 2338707, "tid": 2338707, + "ts": 6197199938088.063, "dur": 2.250, + "args": { + "External id": 36463,"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": 2338707, "tid": 2338707, + "ts": 6197199938092.125, "dur": 22.097, + "args": { + "External id": 36464,"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": 2338707, "tid": 2338707, + "ts": 6197199938095.967, "dur": 3.015, + "args": { + "External id": 36465,"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": 2338707, "tid": 2338707, + "ts": 6197199938116.325, "dur": 24.860, + "args": { + "External id": 36466,"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": 2338707, "tid": 2338707, + "ts": 6197199938142.744, "dur": 14.110, + "args": { + "External id": 36467,"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": 2338707, "tid": 2338707, + "ts": 6197199938162.683, "dur": 13.859, + "args": { + "External id": 36468,"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": 2338707, "tid": 2338707, + "ts": 6197199938178.149, "dur": 31.431, + "args": { + "External id": 36469,"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": 2338707, "tid": 2338707, + "ts": 6197199938211.631, "dur": 38.385, + "args": { + "External id": 36470,"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": 2338707, "tid": 2338707, + "ts": 6197199938214.076, "dur": 1.289, + "args": { + "External id": 36471,"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": 2338707, "tid": 2338707, + "ts": 6197199938217.378, "dur": 3.178, + "args": { + "External id": 36472,"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": 2338707, "tid": 2338707, + "ts": 6197199938251.507, "dur": 39.969, + "args": { + "External id": 36473,"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": 2338707, "tid": 2338707, + "ts": 6197199938294.453, "dur": 13.143, + "args": { + "External id": 36474,"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": 2338707, "tid": 2338707, + "ts": 6197199938318.246, "dur": 2.475, + "args": { + "External id": 36475,"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": 2338707, "tid": 2338707, + "ts": 6197199938331.636, "dur": 3.560, + "args": { + "External id": 36476,"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": 2338707, "tid": 2338707, + "ts": 6197199938333.873, "dur": 0.523, + "args": { + "External id": 36477,"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": 2338707, "tid": 2338707, + "ts": 6197199938410.740, "dur": 63.425, + "args": { + "External id": 36478,"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": 2338707, "tid": 2338707, + "ts": 6197199938479.525, "dur": 5.194, + "args": { + "External id": 36479,"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": 2338707, "tid": 2338707, + "ts": 6197199938482.602, "dur": 0.954, + "args": { + "External id": 36480,"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": 2338707, "tid": 2338707, + "ts": 6197199938486.214, "dur": 27.221, + "args": { + "External id": 36481,"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": 2338707, "tid": 2338707, + "ts": 6197199938520.867, "dur": 6.435, + "args": { + "External id": 36482,"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": 2338707, "tid": 2338707, + "ts": 6197199938522.461, "dur": 3.918, + "args": { + "External id": 36483,"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": 2338707, "tid": 2338707, + "ts": 6197199938524.475, "dur": 1.692, + "args": { + "External id": 36484,"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": 2338707, "tid": 2338707, + "ts": 6197199938530.117, "dur": 42.721, + "args": { + "External id": 36485,"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": 2338707, "tid": 2338707, + "ts": 6197199938531.329, "dur": 40.876, + "args": { + "External id": 36486,"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": 2338707, "tid": 2338707, + "ts": 6197199938576.696, "dur": 14.040, + "args": { + "External id": 36487,"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": 2338707, "tid": 2338707, + "ts": 6197199938597.113, "dur": 5.318, + "args": { + "External id": 36488,"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": 2338707, "tid": 2338707, + "ts": 6197199938600.861, "dur": 0.677, + "args": { + "External id": 36489,"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": 2338707, "tid": 2338707, + "ts": 6197199938606.798, "dur": 46.630, + "args": { + "External id": 36490,"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": 2338707, "tid": 2338707, + "ts": 6197199938607.841, "dur": 3.214, + "args": { + "External id": 36491,"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": 2338707, "tid": 2338707, + "ts": 6197199938608.639, "dur": 1.815, + "args": { + "External id": 36492,"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": 2338707, "tid": 2338707, + "ts": 6197199938609.785, "dur": 0.524, + "args": { + "External id": 36493,"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": 2338707, "tid": 2338707, + "ts": 6197199938612.071, "dur": 40.984, + "args": { + "External id": 36494,"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": 2338707, "tid": 2338707, + "ts": 6197199938615.366, "dur": 37.000, + "args": { + "External id": 36495,"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": 2338707, "tid": 2338707, + "ts": 6197199938658.378, "dur": 3.650, + "args": { + "External id": 36496,"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": 2338707, "tid": 2338707, + "ts": 6197199938660.387, "dur": 0.535, + "args": { + "External id": 36497,"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": 2338707, "tid": 2338707, + "ts": 6197199938668.010, "dur": 1.614, + "args": { + "External id": 36498,"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": 2338707, "tid": 2338707, + "ts": 6197199938678.163, "dur": 6.212, + "args": { + "External id": 36499,"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": 2338707, "tid": 2338707, + "ts": 6197199938680.312, "dur": 3.803, + "args": { + "External id": 36500,"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": 2338707, "tid": 2338707, + "ts": 6197199938825.402, "dur": 198.677, + "args": { + "External id": 36501,"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": 2338707, "tid": 2338707, + "ts": 6197199938830.890, "dur": 2.977, + "args": { + "External id": 36502,"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": 2338707, "tid": 2338707, + "ts": 6197199938835.971, "dur": 187.573, + "args": { + "External id": 36503,"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": 2338707, "tid": 2338707, + "ts": 6197199938837.683, "dur": 0.413, + "args": { + "External id": 36504,"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": 2338707, "tid": 2338707, + "ts": 6197199938839.648, "dur": 26.081, + "args": { + "External id": 36505,"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": 2338707, "tid": 2338707, + "ts": 6197199938867.402, "dur": 6.509, + "args": { + "External id": 36506,"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": 2338707, "tid": 2338707, + "ts": 6197199938871.978, "dur": 1.650, + "args": { + "External id": 36507,"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": 2338707, "tid": 2338707, + "ts": 6197199938875.131, "dur": 25.178, + "args": { + "External id": 36508,"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": 2338707, "tid": 2338707, + "ts": 6197199938876.136, "dur": 1.073, + "args": { + "External id": 36509,"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": 2338707, "tid": 2338707, + "ts": 6197199938881.056, "dur": 18.994, + "args": { + "External id": 36510,"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": 2338707, "tid": 2338707, + "ts": 6197199938884.848, "dur": 2.513, + "args": { + "External id": 36511,"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": 2338707, "tid": 2338707, + "ts": 6197199938901.880, "dur": 21.510, + "args": { + "External id": 36512,"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": 2338707, "tid": 2338707, + "ts": 6197199938925.571, "dur": 13.140, + "args": { + "External id": 36513,"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": 2338707, "tid": 2338707, + "ts": 6197199938941.398, "dur": 12.966, + "args": { + "External id": 36514,"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": 2338707, "tid": 2338707, + "ts": 6197199938958.946, "dur": 11.995, + "args": { + "External id": 36515,"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": 2338707, "tid": 2338707, + "ts": 6197199938972.922, "dur": 22.748, + "args": { + "External id": 36516,"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": 2338707, "tid": 2338707, + "ts": 6197199938977.643, "dur": 1.767, + "args": { + "External id": 36517,"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": 2338707, "tid": 2338707, + "ts": 6197199938981.322, "dur": 0.871, + "args": { + "External id": 36518,"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": 2338707, "tid": 2338707, + "ts": 6197199938999.430, "dur": 11.660, + "args": { + "External id": 36519,"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": 2338707, "tid": 2338707, + "ts": 6197199939012.130, "dur": 10.304, + "args": { + "External id": 36520,"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": 2338707, "tid": 2338707, + "ts": 6197199939031.644, "dur": 2.381, + "args": { + "External id": 36521,"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": 2338707, "tid": 2338707, + "ts": 6197199939044.036, "dur": 3.975, + "args": { + "External id": 36522,"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": 2338707, "tid": 2338707, + "ts": 6197199939046.557, "dur": 0.448, + "args": { + "External id": 36523,"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": 2338707, "tid": 2338707, + "ts": 6197199939165.370, "dur": 69.426, + "args": { + "External id": 36524,"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": 2338707, "tid": 2338707, + "ts": 6197199939241.025, "dur": 7.030, + "args": { + "External id": 36525,"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": 2338707, "tid": 2338707, + "ts": 6197199939244.822, "dur": 1.408, + "args": { + "External id": 36526,"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": 2338707, "tid": 2338707, + "ts": 6197199939252.089, "dur": 26.271, + "args": { + "External id": 36527,"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": 2338707, "tid": 2338707, + "ts": 6197199939283.772, "dur": 7.062, + "args": { + "External id": 36528,"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": 2338707, "tid": 2338707, + "ts": 6197199939285.461, "dur": 4.473, + "args": { + "External id": 36529,"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": 2338707, "tid": 2338707, + "ts": 6197199939287.551, "dur": 2.105, + "args": { + "External id": 36530,"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": 2338707, "tid": 2338707, + "ts": 6197199939293.727, "dur": 43.670, + "args": { + "External id": 36531,"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": 2338707, "tid": 2338707, + "ts": 6197199939295.208, "dur": 41.533, + "args": { + "External id": 36532,"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": 2338707, "tid": 2338707, + "ts": 6197199939341.510, "dur": 17.288, + "args": { + "External id": 36533,"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": 2338707, "tid": 2338707, + "ts": 6197199939368.033, "dur": 3.537, + "args": { + "External id": 36534,"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": 2338707, "tid": 2338707, + "ts": 6197199939370.017, "dur": 0.654, + "args": { + "External id": 36535,"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": 2338707, "tid": 2338707, + "ts": 6197199939376.226, "dur": 47.079, + "args": { + "External id": 36536,"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": 2338707, "tid": 2338707, + "ts": 6197199939377.045, "dur": 4.088, + "args": { + "External id": 36537,"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": 2338707, "tid": 2338707, + "ts": 6197199939377.693, "dur": 2.779, + "args": { + "External id": 36538,"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": 2338707, "tid": 2338707, + "ts": 6197199939379.721, "dur": 0.613, + "args": { + "External id": 36539,"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": 2338707, "tid": 2338707, + "ts": 6197199939384.037, "dur": 38.862, + "args": { + "External id": 36540,"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": 2338707, "tid": 2338707, + "ts": 6197199939384.989, "dur": 37.248, + "args": { + "External id": 36541,"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": 2338707, "tid": 2338707, + "ts": 6197199939427.967, "dur": 4.216, + "args": { + "External id": 36542,"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": 2338707, "tid": 2338707, + "ts": 6197199939430.184, "dur": 0.729, + "args": { + "External id": 36543,"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": 2338707, "tid": 2338707, + "ts": 6197199939438.243, "dur": 1.944, + "args": { + "External id": 36544,"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": 2338707, "tid": 2338707, + "ts": 6197199939448.628, "dur": 9.031, + "args": { + "External id": 36545,"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": 2338707, "tid": 2338707, + "ts": 6197199939453.387, "dur": 4.011, + "args": { + "External id": 36546,"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": 2338707, "tid": 2338707, + "ts": 6197199939547.992, "dur": 218.009, + "args": { + "External id": 36547,"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": 2338707, "tid": 2338707, + "ts": 6197199939552.897, "dur": 2.100, + "args": { + "External id": 36548,"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": 2338707, "tid": 2338707, + "ts": 6197199939556.872, "dur": 208.594, + "args": { + "External id": 36549,"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": 2338707, "tid": 2338707, + "ts": 6197199939558.331, "dur": 0.789, + "args": { + "External id": 36550,"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": 2338707, "tid": 2338707, + "ts": 6197199939560.090, "dur": 21.064, + "args": { + "External id": 36551,"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": 2338707, "tid": 2338707, + "ts": 6197199939582.506, "dur": 5.424, + "args": { + "External id": 36552,"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": 2338707, "tid": 2338707, + "ts": 6197199939586.752, "dur": 0.784, + "args": { + "External id": 36553,"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": 2338707, "tid": 2338707, + "ts": 6197199939588.918, "dur": 23.261, + "args": { + "External id": 36554,"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": 2338707, "tid": 2338707, + "ts": 6197199939593.003, "dur": 1.120, + "args": { + "External id": 36555,"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": 2338707, "tid": 2338707, + "ts": 6197199939595.427, "dur": 16.517, + "args": { + "External id": 36556,"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": 2338707, "tid": 2338707, + "ts": 6197199939598.436, "dur": 2.847, + "args": { + "External id": 36557,"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": 2338707, "tid": 2338707, + "ts": 6197199939613.494, "dur": 23.063, + "args": { + "External id": 36558,"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": 2338707, "tid": 2338707, + "ts": 6197199939638.018, "dur": 15.809, + "args": { + "External id": 36559,"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": 2338707, "tid": 2338707, + "ts": 6197199939656.633, "dur": 14.314, + "args": { + "External id": 36560,"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": 2338707, "tid": 2338707, + "ts": 6197199939672.416, "dur": 11.360, + "args": { + "External id": 36561,"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": 2338707, "tid": 2338707, + "ts": 6197199939685.587, "dur": 43.962, + "args": { + "External id": 36562,"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": 2338707, "tid": 2338707, + "ts": 6197199939687.804, "dur": 1.072, + "args": { + "External id": 36563,"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": 2338707, "tid": 2338707, + "ts": 6197199939693.026, "dur": 0.751, + "args": { + "External id": 36564,"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": 2338707, "tid": 2338707, + "ts": 6197199939732.781, "dur": 17.222, + "args": { + "External id": 36565,"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": 2338707, "tid": 2338707, + "ts": 6197199939751.194, "dur": 13.020, + "args": { + "External id": 36566,"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": 2338707, "tid": 2338707, + "ts": 6197199939775.889, "dur": 3.064, + "args": { + "External id": 36567,"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": 2338707, "tid": 2338707, + "ts": 6197199939788.925, "dur": 4.084, + "args": { + "External id": 36568,"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": 2338707, "tid": 2338707, + "ts": 6197199939791.606, "dur": 0.580, + "args": { + "External id": 36569,"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": 2338707, "tid": 2338707, + "ts": 6197199939867.335, "dur": 61.632, + "args": { + "External id": 36570,"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": 2338707, "tid": 2338707, + "ts": 6197199939936.900, "dur": 5.273, + "args": { + "External id": 36571,"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": 2338707, "tid": 2338707, + "ts": 6197199939940.215, "dur": 0.687, + "args": { + "External id": 36572,"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": 2338707, "tid": 2338707, + "ts": 6197199939943.771, "dur": 26.091, + "args": { + "External id": 36573,"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": 2338707, "tid": 2338707, + "ts": 6197199939974.580, "dur": 6.256, + "args": { + "External id": 36574,"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": 2338707, "tid": 2338707, + "ts": 6197199939976.162, "dur": 3.630, + "args": { + "External id": 36575,"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": 2338707, "tid": 2338707, + "ts": 6197199939978.092, "dur": 1.494, + "args": { + "External id": 36576,"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": 2338707, "tid": 2338707, + "ts": 6197199939985.459, "dur": 42.750, + "args": { + "External id": 36577,"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": 2338707, "tid": 2338707, + "ts": 6197199939986.509, "dur": 41.099, + "args": { + "External id": 36578,"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": 2338707, "tid": 2338707, + "ts": 6197199940031.990, "dur": 15.613, + "args": { + "External id": 36579,"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": 2338707, "tid": 2338707, + "ts": 6197199940092.497, "dur": 5.257, + "args": { + "External id": 36580,"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": 2338707, "tid": 2338707, + "ts": 6197199940095.189, "dur": 1.157, + "args": { + "External id": 36581,"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": 2338707, "tid": 2338707, + "ts": 6197199940103.601, "dur": 53.089, + "args": { + "External id": 36582,"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": 2338707, "tid": 2338707, + "ts": 6197199940104.379, "dur": 6.867, + "args": { + "External id": 36583,"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": 2338707, "tid": 2338707, + "ts": 6197199940108.000, "dur": 2.552, + "args": { + "External id": 36584,"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": 2338707, "tid": 2338707, + "ts": 6197199940109.830, "dur": 0.602, + "args": { + "External id": 36585,"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": 2338707, "tid": 2338707, + "ts": 6197199940111.775, "dur": 44.473, + "args": { + "External id": 36586,"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": 2338707, "tid": 2338707, + "ts": 6197199940112.447, "dur": 43.149, + "args": { + "External id": 36587,"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": 2338707, "tid": 2338707, + "ts": 6197199940161.554, "dur": 3.754, + "args": { + "External id": 36588,"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": 2338707, "tid": 2338707, + "ts": 6197199940163.528, "dur": 0.810, + "args": { + "External id": 36589,"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": 2338707, "tid": 2338707, + "ts": 6197199940172.168, "dur": 1.737, + "args": { + "External id": 36590,"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": 2338707, "tid": 2338707, + "ts": 6197199940184.549, "dur": 9.646, + "args": { + "External id": 36591,"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": 2338707, "tid": 2338707, + "ts": 6197199940186.732, "dur": 7.158, + "args": { + "External id": 36592,"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": 2338707, "tid": 2338707, + "ts": 6197199940286.587, "dur": 180.262, + "args": { + "External id": 36593,"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": 2338707, "tid": 2338707, + "ts": 6197199940288.590, "dur": 1.832, + "args": { + "External id": 36594,"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": 2338707, "tid": 2338707, + "ts": 6197199940292.011, "dur": 174.460, + "args": { + "External id": 36595,"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": 2338707, "tid": 2338707, + "ts": 6197199940293.459, "dur": 0.349, + "args": { + "External id": 36596,"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": 2338707, "tid": 2338707, + "ts": 6197199940297.513, "dur": 24.678, + "args": { + "External id": 36597,"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": 2338707, "tid": 2338707, + "ts": 6197199940323.998, "dur": 2.993, + "args": { + "External id": 36598,"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": 2338707, "tid": 2338707, + "ts": 6197199940326.034, "dur": 0.741, + "args": { + "External id": 36599,"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": 2338707, "tid": 2338707, + "ts": 6197199940327.888, "dur": 23.642, + "args": { + "External id": 36600,"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": 2338707, "tid": 2338707, + "ts": 6197199940329.103, "dur": 1.155, + "args": { + "External id": 36601,"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": 2338707, "tid": 2338707, + "ts": 6197199940331.364, "dur": 19.851, + "args": { + "External id": 36602,"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": 2338707, "tid": 2338707, + "ts": 6197199940337.044, "dur": 2.236, + "args": { + "External id": 36603,"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": 2338707, "tid": 2338707, + "ts": 6197199940353.228, "dur": 20.416, + "args": { + "External id": 36604,"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": 2338707, "tid": 2338707, + "ts": 6197199940375.306, "dur": 12.936, + "args": { + "External id": 36605,"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": 2338707, "tid": 2338707, + "ts": 6197199940390.655, "dur": 12.115, + "args": { + "External id": 36606,"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": 2338707, "tid": 2338707, + "ts": 6197199940404.184, "dur": 11.025, + "args": { + "External id": 36607,"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": 2338707, "tid": 2338707, + "ts": 6197199940418.971, "dur": 19.440, + "args": { + "External id": 36608,"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": 2338707, "tid": 2338707, + "ts": 6197199940421.205, "dur": 1.287, + "args": { + "External id": 36609,"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": 2338707, "tid": 2338707, + "ts": 6197199940424.706, "dur": 0.699, + "args": { + "External id": 36610,"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": 2338707, "tid": 2338707, + "ts": 6197199940439.825, "dur": 12.946, + "args": { + "External id": 36611,"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": 2338707, "tid": 2338707, + "ts": 6197199940453.671, "dur": 11.618, + "args": { + "External id": 36612,"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": 2338707, "tid": 2338707, + "ts": 6197199940473.595, "dur": 1.580, + "args": { + "External id": 36613,"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": 2338707, "tid": 2338707, + "ts": 6197199940484.124, "dur": 3.948, + "args": { + "External id": 36614,"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": 2338707, "tid": 2338707, + "ts": 6197199940486.626, "dur": 0.526, + "args": { + "External id": 36615,"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": 2338707, "tid": 2338707, + "ts": 6197199940555.059, "dur": 52.200, + "args": { + "External id": 36616,"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": 2338707, "tid": 2338707, + "ts": 6197199940612.326, "dur": 4.982, + "args": { + "External id": 36617,"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": 2338707, "tid": 2338707, + "ts": 6197199940615.332, "dur": 0.713, + "args": { + "External id": 36618,"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": 2338707, "tid": 2338707, + "ts": 6197199940618.652, "dur": 23.741, + "args": { + "External id": 36619,"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": 2338707, "tid": 2338707, + "ts": 6197199940646.775, "dur": 8.670, + "args": { + "External id": 36620,"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": 2338707, "tid": 2338707, + "ts": 6197199940648.388, "dur": 6.255, + "args": { + "External id": 36621,"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": 2338707, "tid": 2338707, + "ts": 6197199940652.888, "dur": 1.585, + "args": { + "External id": 36622,"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": 2338707, "tid": 2338707, + "ts": 6197199940657.899, "dur": 41.665, + "args": { + "External id": 36623,"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": 2338707, "tid": 2338707, + "ts": 6197199940658.959, "dur": 39.970, + "args": { + "External id": 36624,"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": 2338707, "tid": 2338707, + "ts": 6197199940724.522, "dur": 24.838, + "args": { + "External id": 36625,"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": 2338707, "tid": 2338707, + "ts": 6197199940757.900, "dur": 6.439, + "args": { + "External id": 36626,"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": 2338707, "tid": 2338707, + "ts": 6197199940761.526, "dur": 1.342, + "args": { + "External id": 36627,"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": 2338707, "tid": 2338707, + "ts": 6197199940769.735, "dur": 62.249, + "args": { + "External id": 36628,"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": 2338707, "tid": 2338707, + "ts": 6197199940773.691, "dur": 6.078, + "args": { + "External id": 36629,"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": 2338707, "tid": 2338707, + "ts": 6197199940775.107, "dur": 3.726, + "args": { + "External id": 36630,"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": 2338707, "tid": 2338707, + "ts": 6197199940777.338, "dur": 1.266, + "args": { + "External id": 36631,"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": 2338707, "tid": 2338707, + "ts": 6197199940780.987, "dur": 50.556, + "args": { + "External id": 36632,"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": 2338707, "tid": 2338707, + "ts": 6197199940782.087, "dur": 48.751, + "args": { + "External id": 36633,"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": 2338707, "tid": 2338707, + "ts": 6197199940837.257, "dur": 9.783, + "args": { + "External id": 36634,"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": 2338707, "tid": 2338707, + "ts": 6197199940842.720, "dur": 3.047, + "args": { + "External id": 36635,"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": 2338707, "tid": 2338707, + "ts": 6197199940856.953, "dur": 1.709, + "args": { + "External id": 36636,"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": 2338707, "tid": 2338707, + "ts": 6197199940867.336, "dur": 6.758, + "args": { + "External id": 36637,"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": 2338707, "tid": 2338707, + "ts": 6197199940869.316, "dur": 4.474, + "args": { + "External id": 36638,"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": 2338707, "tid": 2338707, + "ts": 6197199940976.165, "dur": 233.939, + "args": { + "External id": 36639,"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": 2338707, "tid": 2338707, + "ts": 6197199940978.414, "dur": 2.873, + "args": { + "External id": 36640,"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": 2338707, "tid": 2338707, + "ts": 6197199940983.480, "dur": 226.007, + "args": { + "External id": 36641,"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": 2338707, "tid": 2338707, + "ts": 6197199940987.452, "dur": 0.475, + "args": { + "External id": 36642,"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": 2338707, "tid": 2338707, + "ts": 6197199940988.870, "dur": 24.950, + "args": { + "External id": 36643,"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": 2338707, "tid": 2338707, + "ts": 6197199941015.503, "dur": 3.545, + "args": { + "External id": 36644,"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": 2338707, "tid": 2338707, + "ts": 6197199941017.888, "dur": 0.929, + "args": { + "External id": 36645,"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": 2338707, "tid": 2338707, + "ts": 6197199941020.026, "dur": 23.522, + "args": { + "External id": 36646,"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": 2338707, "tid": 2338707, + "ts": 6197199941021.356, "dur": 1.162, + "args": { + "External id": 36647,"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": 2338707, "tid": 2338707, + "ts": 6197199941023.884, "dur": 19.404, + "args": { + "External id": 36648,"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": 2338707, "tid": 2338707, + "ts": 6197199941029.000, "dur": 3.015, + "args": { + "External id": 36649,"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": 2338707, "tid": 2338707, + "ts": 6197199941044.981, "dur": 61.853, + "args": { + "External id": 36650,"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": 2338707, "tid": 2338707, + "ts": 6197199941109.656, "dur": 12.901, + "args": { + "External id": 36651,"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": 2338707, "tid": 2338707, + "ts": 6197199941128.461, "dur": 14.629, + "args": { + "External id": 36652,"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": 2338707, "tid": 2338707, + "ts": 6197199941144.807, "dur": 12.182, + "args": { + "External id": 36653,"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": 2338707, "tid": 2338707, + "ts": 6197199941158.976, "dur": 21.297, + "args": { + "External id": 36654,"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": 2338707, "tid": 2338707, + "ts": 6197199941161.202, "dur": 2.062, + "args": { + "External id": 36655,"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": 2338707, "tid": 2338707, + "ts": 6197199941165.549, "dur": 1.169, + "args": { + "External id": 36656,"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": 2338707, "tid": 2338707, + "ts": 6197199941181.751, "dur": 11.362, + "args": { + "External id": 36657,"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": 2338707, "tid": 2338707, + "ts": 6197199941197.431, "dur": 10.852, + "args": { + "External id": 36658,"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": 2338707, "tid": 2338707, + "ts": 6197199941219.015, "dur": 2.796, + "args": { + "External id": 36659,"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": 2338707, "tid": 2338707, + "ts": 6197199941232.451, "dur": 4.184, + "args": { + "External id": 36660,"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": 2338707, "tid": 2338707, + "ts": 6197199941235.023, "dur": 0.714, + "args": { + "External id": 36661,"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": 2338707, "tid": 2338707, + "ts": 6197199941312.098, "dur": 63.435, + "args": { + "External id": 36662,"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": 2338707, "tid": 2338707, + "ts": 6197199941380.987, "dur": 6.588, + "args": { + "External id": 36663,"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": 2338707, "tid": 2338707, + "ts": 6197199941384.363, "dur": 2.098, + "args": { + "External id": 36664,"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": 2338707, "tid": 2338707, + "ts": 6197199941389.520, "dur": 26.885, + "args": { + "External id": 36665,"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": 2338707, "tid": 2338707, + "ts": 6197199941423.627, "dur": 6.218, + "args": { + "External id": 36666,"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": 2338707, "tid": 2338707, + "ts": 6197199941425.401, "dur": 3.473, + "args": { + "External id": 36667,"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": 2338707, "tid": 2338707, + "ts": 6197199941427.502, "dur": 1.156, + "args": { + "External id": 36668,"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": 2338707, "tid": 2338707, + "ts": 6197199941433.023, "dur": 46.170, + "args": { + "External id": 36669,"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": 2338707, "tid": 2338707, + "ts": 6197199941434.173, "dur": 44.131, + "args": { + "External id": 36670,"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": 2338707, "tid": 2338707, + "ts": 6197199941483.325, "dur": 14.834, + "args": { + "External id": 36671,"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": 2338707, "tid": 2338707, + "ts": 6197199941504.140, "dur": 6.300, + "args": { + "External id": 36672,"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": 2338707, "tid": 2338707, + "ts": 6197199941509.131, "dur": 0.486, + "args": { + "External id": 36673,"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": 2338707, "tid": 2338707, + "ts": 6197199941514.869, "dur": 48.714, + "args": { + "External id": 36674,"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": 2338707, "tid": 2338707, + "ts": 6197199941515.935, "dur": 5.863, + "args": { + "External id": 36675,"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": 2338707, "tid": 2338707, + "ts": 6197199941516.656, "dur": 4.568, + "args": { + "External id": 36676,"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": 2338707, "tid": 2338707, + "ts": 6197199941520.307, "dur": 0.784, + "args": { + "External id": 36677,"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": 2338707, "tid": 2338707, + "ts": 6197199941522.387, "dur": 40.753, + "args": { + "External id": 36678,"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": 2338707, "tid": 2338707, + "ts": 6197199941525.468, "dur": 36.916, + "args": { + "External id": 36679,"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": 2338707, "tid": 2338707, + "ts": 6197199941568.154, "dur": 4.080, + "args": { + "External id": 36680,"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": 2338707, "tid": 2338707, + "ts": 6197199941570.287, "dur": 0.932, + "args": { + "External id": 36681,"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": 2338707, "tid": 2338707, + "ts": 6197199941577.791, "dur": 1.434, + "args": { + "External id": 36682,"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": 2338707, "tid": 2338707, + "ts": 6197199941587.554, "dur": 6.502, + "args": { + "External id": 36683,"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": 2338707, "tid": 2338707, + "ts": 6197199941589.733, "dur": 3.998, + "args": { + "External id": 36684,"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": 2338707, "tid": 2338707, + "ts": 6197199941681.643, "dur": 217.125, + "args": { + "External id": 36685,"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": 2338707, "tid": 2338707, + "ts": 6197199941684.080, "dur": 1.985, + "args": { + "External id": 36686,"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": 2338707, "tid": 2338707, + "ts": 6197199941687.430, "dur": 210.665, + "args": { + "External id": 36687,"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": 2338707, "tid": 2338707, + "ts": 6197199941691.152, "dur": 0.326, + "args": { + "External id": 36688,"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": 2338707, "tid": 2338707, + "ts": 6197199941693.152, "dur": 45.088, + "args": { + "External id": 36689,"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": 2338707, "tid": 2338707, + "ts": 6197199941742.220, "dur": 4.952, + "args": { + "External id": 36690,"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": 2338707, "tid": 2338707, + "ts": 6197199941745.235, "dur": 1.499, + "args": { + "External id": 36691,"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": 2338707, "tid": 2338707, + "ts": 6197199941748.397, "dur": 31.989, + "args": { + "External id": 36692,"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": 2338707, "tid": 2338707, + "ts": 6197199941752.549, "dur": 2.138, + "args": { + "External id": 36693,"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": 2338707, "tid": 2338707, + "ts": 6197199941759.537, "dur": 20.572, + "args": { + "External id": 36694,"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": 2338707, "tid": 2338707, + "ts": 6197199941763.619, "dur": 3.088, + "args": { + "External id": 36695,"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": 2338707, "tid": 2338707, + "ts": 6197199941781.865, "dur": 22.513, + "args": { + "External id": 36696,"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": 2338707, "tid": 2338707, + "ts": 6197199941806.066, "dur": 12.547, + "args": { + "External id": 36697,"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": 2338707, "tid": 2338707, + "ts": 6197199941820.997, "dur": 12.408, + "args": { + "External id": 36698,"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": 2338707, "tid": 2338707, + "ts": 6197199941834.947, "dur": 12.246, + "args": { + "External id": 36699,"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": 2338707, "tid": 2338707, + "ts": 6197199941849.091, "dur": 19.624, + "args": { + "External id": 36700,"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": 2338707, "tid": 2338707, + "ts": 6197199941851.953, "dur": 1.437, + "args": { + "External id": 36701,"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": 2338707, "tid": 2338707, + "ts": 6197199941855.087, "dur": 1.025, + "args": { + "External id": 36702,"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": 2338707, "tid": 2338707, + "ts": 6197199941872.980, "dur": 12.170, + "args": { + "External id": 36703,"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": 2338707, "tid": 2338707, + "ts": 6197199941886.325, "dur": 10.468, + "args": { + "External id": 36704,"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": 2338707, "tid": 2338707, + "ts": 6197199941907.976, "dur": 2.366, + "args": { + "External id": 36705,"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": 2338707, "tid": 2338707, + "ts": 6197199941920.761, "dur": 3.820, + "args": { + "External id": 36706,"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": 2338707, "tid": 2338707, + "ts": 6197199941923.213, "dur": 0.417, + "args": { + "External id": 36707,"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": 2338707, "tid": 2338707, + "ts": 6197199942001.831, "dur": 100.879, + "args": { + "External id": 36708,"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": 2338707, "tid": 2338707, + "ts": 6197199942111.068, "dur": 10.044, + "args": { + "External id": 36709,"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": 2338707, "tid": 2338707, + "ts": 6197199942115.554, "dur": 3.693, + "args": { + "External id": 36710,"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": 2338707, "tid": 2338707, + "ts": 6197199942125.531, "dur": 29.841, + "args": { + "External id": 36711,"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": 2338707, "tid": 2338707, + "ts": 6197199942161.474, "dur": 5.776, + "args": { + "External id": 36712,"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": 2338707, "tid": 2338707, + "ts": 6197199942163.071, "dur": 3.432, + "args": { + "External id": 36713,"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": 2338707, "tid": 2338707, + "ts": 6197199942165.044, "dur": 1.209, + "args": { + "External id": 36714,"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": 2338707, "tid": 2338707, + "ts": 6197199942170.860, "dur": 49.762, + "args": { + "External id": 36715,"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": 2338707, "tid": 2338707, + "ts": 6197199942172.089, "dur": 47.713, + "args": { + "External id": 36716,"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": 2338707, "tid": 2338707, + "ts": 6197199942224.618, "dur": 16.570, + "args": { + "External id": 36717,"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": 2338707, "tid": 2338707, + "ts": 6197199942248.821, "dur": 26.031, + "args": { + "External id": 36718,"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": 2338707, "tid": 2338707, + "ts": 6197199942251.454, "dur": 22.969, + "args": { + "External id": 36719,"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": 2338707, "tid": 2338707, + "ts": 6197199942256.635, "dur": 1.028, + "args": { + "External id": 36720,"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": 2338707, "tid": 2338707, + "ts": 6197199942280.615, "dur": 27.894, + "args": { + "External id": 36721,"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": 2338707, "tid": 2338707, + "ts": 6197199942282.335, "dur": 25.944, + "args": { + "External id": 36722,"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": 2338707, "tid": 2338707, + "ts": 6197199942287.442, "dur": 3.963, + "args": { + "External id": 36723,"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": 2338707, "tid": 2338707, + "ts": 6197199942292.637, "dur": 14.933, + "args": { + "External id": 36724,"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": 2338707, "tid": 2338707, + "ts": 6197199942321.862, "dur": 7.552, + "args": { + "External id": 36725,"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": 2338707, "tid": 2338707, + "ts": 6197199942326.437, "dur": 2.652, + "args": { + "External id": 36726,"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": 2338707, "tid": 2338707, + "ts": 6197199942330.633, "dur": 1.328, + "args": { + "External id": 36727,"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": 2338707, "tid": 2338707, + "ts": 6197199942331.362, "dur": 0.489, + "args": { + "External id": 36728,"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": 2338707, "tid": 2338707, + "ts": 6197199942377.182, "dur": 22.810, + "args": { + "External id": 36729,"Sequence number": 480203, "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": 2338707, "tid": 2338707, + "ts": 6197199942402.196, "dur": 14.690, + "args": { + "External id": 36730,"Sequence number": 480204, "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": 2338707, "tid": 2338707, "ts": 6197199942402.196, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338707, "tid": 2338707, + "ts": 6197199942422.900, "dur": 6.179, + "args": { + "External id": 36731,"Sequence number": 480205, "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": 2338707, "tid": 2338707, + "ts": 6197199942426.478, "dur": 1.101, + "args": { + "External id": 36732,"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": 2338707, "tid": 2338707, + "ts": 6197199942431.954, "dur": 9.347, + "args": { + "External id": 36733,"Sequence number": 480205, "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": 2338707, "tid": 2338707, + "ts": 6197199942438.846, "dur": 0.989, + "args": { + "External id": 36734,"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": 2338707, "tid": 2338707, + "ts": 6197199942442.623, "dur": 2.991, + "args": { + "External id": 36735,"Sequence number": 480205, "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": 2338707, "tid": 2338707, + "ts": 6197199942444.041, "dur": 0.988, + "args": { + "External id": 36736,"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": 2338707, "tid": 2338707, + "ts": 6197199942449.638, "dur": 5.878, + "args": { + "External id": 36737,"Sequence number": 480205, "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": 2338707, "tid": 2338707, "ts": 6197199942449.638, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2338707, + "ts": 6197199942453.118, "dur": 1.091, + "args": { + "External id": 36738,"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": 2338707, "tid": 2338707, + "ts": 6197199942459.101, "dur": 5.744, + "args": { + "External id": 36739,"Sequence number": 480206, "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": 2338707, "tid": 2338707, "ts": 6197199942459.101, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2338707, + "ts": 6197199942463.156, "dur": 0.935, + "args": { + "External id": 36740,"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": 2338707, "tid": 2338707, + "ts": 6197199942466.359, "dur": 5.862, + "args": { + "External id": 36741,"Sequence number": 480207, "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": 2338707, "tid": 2338707, "ts": 6197199942466.359, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2338707, + "ts": 6197199942470.454, "dur": 0.846, + "args": { + "External id": 36742,"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": 2338707, "tid": 2338707, + "ts": 6197199942473.270, "dur": 6.093, + "args": { + "External id": 36743,"Sequence number": 480208, "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": 2338707, "tid": 2338707, "ts": 6197199942473.270, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2338707, + "ts": 6197199942477.490, "dur": 1.126, + "args": { + "External id": 36744,"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": 2338707, "tid": 2338707, + "ts": 6197199942483.155, "dur": 33.299, + "args": { + "External id": 36745,"Sequence number": 480209, "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": 2338707, "tid": 2338707, + "ts": 6197199942487.416, "dur": 28.773, + "args": { + "External id": 36746,"Sequence number": 480209, "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": 2338707, "tid": 2338707, + "ts": 6197199942490.116, "dur": 6.049, + "args": { + "External id": 36747,"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": 2338707, "tid": 2338707, + "ts": 6197199942492.365, "dur": 3.227, + "args": { + "External id": 36748,"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": 2338707, "tid": 2338707, + "ts": 6197199942497.072, "dur": 18.498, + "args": { + "External id": 36749,"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": 2338707, "tid": 2338707, + "ts": 6197199942545.454, "dur": 4.857, + "args": { + "External id": 36750,"Sequence number": 480209, "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": 2338707, "tid": 2338707, "ts": 6197199942545.454, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6197199942553.319, "dur": 3.660, + "args": { + "External id": 36751,"Sequence number": 480210, "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": 2338707, "tid": 2338707, + "ts": 6197199942594.399, "dur": 46504.003, + "args": { + "External id": 36752,"Sequence number": 480210, "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": 2338707, "tid": 2338707, "ts": 6197199942594.399, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338707, "tid": 2338707, + "ts": 6197199942611.004, "dur": 31.843, + "args": { + "External id": 36753,"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": 2338707, "tid": 2338707, + "ts": 6197199942616.090, "dur": 26.588, + "args": { + "External id": 36754,"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": 2338707, "tid": 2338707, + "ts": 6197199942617.444, "dur": 5.273, + "args": { + "External id": 36755,"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": 2338707, "tid": 2338707, + "ts": 6197199942618.884, "dur": 3.337, + "args": { + "External id": 36756,"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": 2338707, "tid": 2338707, + "ts": 6197199942623.503, "dur": 18.721, + "args": { + "External id": 36757,"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": 2338707, "tid": 2338707, + "ts": 6197199942659.837, "dur": 31.214, + "args": { + "External id": 36758,"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": 2338707, "tid": 2338707, + "ts": 6197199942660.820, "dur": 5.677, + "args": { + "External id": 36759,"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": 2338707, "tid": 2338707, + "ts": 6197199942662.501, "dur": 3.642, + "args": { + "External id": 36760,"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": 2338707, "tid": 2338707, + "ts": 6197199942667.734, "dur": 23.081, + "args": { + "External id": 36761,"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": 2338707, "tid": 2338707, + "ts": 6197199942672.014, "dur": 18.399, + "args": { + "External id": 36762,"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": 2338707, "tid": 2338707, + "ts": 6197199942694.793, "dur": 46.035, + "args": { + "External id": 36763,"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": 2338707, "tid": 2338707, + "ts": 6197199942695.480, "dur": 3.864, + "args": { + "External id": 36764,"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": 2338707, "tid": 2338707, + "ts": 6197199942696.497, "dur": 2.636, + "args": { + "External id": 36765,"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": 2338707, "tid": 2338707, + "ts": 6197199942717.284, "dur": 23.310, + "args": { + "External id": 36766,"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": 2338707, "tid": 2338707, + "ts": 6197199942719.990, "dur": 19.652, + "args": { + "External id": 36767,"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": 2338707, "tid": 2338707, + "ts": 6197199942750.757, "dur": 23.617, + "args": { + "External id": 36768,"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": 2338707, "tid": 2338707, + "ts": 6197199942753.060, "dur": 4.224, + "args": { + "External id": 36769,"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": 2338707, "tid": 2338707, + "ts": 6197199942758.202, "dur": 15.895, + "args": { + "External id": 36770,"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": 2338707, "tid": 2338707, + "ts": 6197199942761.527, "dur": 12.221, + "args": { + "External id": 36771,"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": 2338707, "tid": 2338707, + "ts": 6197199942779.991, "dur": 23.903, + "args": { + "External id": 36772,"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": 2338707, "tid": 2338707, + "ts": 6197199942806.510, "dur": 50.098, + "args": { + "External id": 36773,"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": 2338707, "tid": 2338707, + "ts": 6197199942808.550, "dur": 47.655, + "args": { + "External id": 36774,"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": 2338707, "tid": 2338707, + "ts": 6197199942814.470, "dur": 3.489, + "args": { + "External id": 36775,"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": 2338707, "tid": 2338707, + "ts": 6197199942819.345, "dur": 22.047, + "args": { + "External id": 36776,"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": 2338707, "tid": 2338707, + "ts": 6197199942821.031, "dur": 20.162, + "args": { + "External id": 36777,"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": 2338707, "tid": 2338707, + "ts": 6197199942823.879, "dur": 2.791, + "args": { + "External id": 36778,"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": 2338707, "tid": 2338707, + "ts": 6197199942827.585, "dur": 13.007, + "args": { + "External id": 36779,"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": 2338707, "tid": 2338707, + "ts": 6197199942862.508, "dur": 39877.615, + "args": { + "External id": 36780,"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": 2338707, "tid": 2338707, + "ts": 6197199942863.797, "dur": 39874.131, + "args": { + "External id": 36781,"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": 2338707, "tid": 2338707, + "ts": 6197199982759.062, "dur": 9.371, + "args": { + "External id": 36782,"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": 2338707, "tid": 2338707, + "ts": 6197199982764.455, "dur": 1.478, + "args": { + "External id": 36783,"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": 2338707, "tid": 2338707, + "ts": 6197199982774.448, "dur": 123.081, + "args": { + "External id": 36784,"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": 2338707, "tid": 2338707, + "ts": 6197199982775.828, "dur": 7.509, + "args": { + "External id": 36785,"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": 2338707, "tid": 2338707, + "ts": 6197199982778.258, "dur": 4.093, + "args": { + "External id": 36786,"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": 2338707, "tid": 2338707, + "ts": 6197199982780.755, "dur": 1.298, + "args": { + "External id": 36787,"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": 2338707, "tid": 2338707, + "ts": 6197199982787.444, "dur": 109.046, + "args": { + "External id": 36788,"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": 2338707, "tid": 2338707, + "ts": 6197199982789.693, "dur": 105.627, + "args": { + "External id": 36789,"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": 2338707, "tid": 2338707, + "ts": 6197199982902.445, "dur": 4.851, + "args": { + "External id": 36790,"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": 2338707, "tid": 2338707, + "ts": 6197199982904.730, "dur": 0.673, + "args": { + "External id": 36791,"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": 2338707, "tid": 2338707, + "ts": 6197199982916.823, "dur": 2.861, + "args": { + "External id": 36792,"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": 2338707, "tid": 2338707, + "ts": 6197199982932.266, "dur": 9.768, + "args": { + "External id": 36793,"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": 2338707, "tid": 2338707, + "ts": 6197199982937.160, "dur": 4.537, + "args": { + "External id": 36794,"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": 2338707, "tid": 2338707, + "ts": 6197199983123.048, "dur": 220.887, + "args": { + "External id": 36795,"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": 2338707, "tid": 2338707, + "ts": 6197199983129.154, "dur": 3.350, + "args": { + "External id": 36796,"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": 2338707, "tid": 2338707, + "ts": 6197199983134.764, "dur": 208.529, + "args": { + "External id": 36797,"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": 2338707, "tid": 2338707, + "ts": 6197199983136.692, "dur": 0.515, + "args": { + "External id": 36798,"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": 2338707, "tid": 2338707, + "ts": 6197199983139.096, "dur": 28.312, + "args": { + "External id": 36799,"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": 2338707, "tid": 2338707, + "ts": 6197199983169.535, "dur": 6.836, + "args": { + "External id": 36800,"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": 2338707, "tid": 2338707, + "ts": 6197199983175.002, "dur": 0.942, + "args": { + "External id": 36801,"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": 2338707, "tid": 2338707, + "ts": 6197199983177.746, "dur": 31.830, + "args": { + "External id": 36802,"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": 2338707, "tid": 2338707, + "ts": 6197199983186.939, "dur": 1.416, + "args": { + "External id": 36803,"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": 2338707, "tid": 2338707, + "ts": 6197199983189.884, "dur": 19.440, + "args": { + "External id": 36804,"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": 2338707, "tid": 2338707, + "ts": 6197199983193.910, "dur": 2.901, + "args": { + "External id": 36805,"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": 2338707, "tid": 2338707, + "ts": 6197199983211.486, "dur": 24.524, + "args": { + "External id": 36806,"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": 2338707, "tid": 2338707, + "ts": 6197199983237.712, "dur": 15.009, + "args": { + "External id": 36807,"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": 2338707, "tid": 2338707, + "ts": 6197199983256.466, "dur": 14.516, + "args": { + "External id": 36808,"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": 2338707, "tid": 2338707, + "ts": 6197199983272.478, "dur": 15.476, + "args": { + "External id": 36809,"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": 2338707, "tid": 2338707, + "ts": 6197199983290.031, "dur": 26.296, + "args": { + "External id": 36810,"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": 2338707, "tid": 2338707, + "ts": 6197199983294.661, "dur": 1.254, + "args": { + "External id": 36811,"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": 2338707, "tid": 2338707, + "ts": 6197199983300.106, "dur": 1.005, + "args": { + "External id": 36812,"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": 2338707, "tid": 2338707, + "ts": 6197199983317.920, "dur": 12.566, + "args": { + "External id": 36813,"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": 2338707, "tid": 2338707, + "ts": 6197199983331.804, "dur": 10.514, + "args": { + "External id": 36814,"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": 2338707, "tid": 2338707, + "ts": 6197199983352.134, "dur": 2.584, + "args": { + "External id": 36815,"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": 2338707, "tid": 2338707, + "ts": 6197199983363.267, "dur": 4.849, + "args": { + "External id": 36816,"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": 2338707, "tid": 2338707, + "ts": 6197199983366.367, "dur": 0.602, + "args": { + "External id": 36817,"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": 2338707, "tid": 2338707, + "ts": 6197199983452.652, "dur": 78.767, + "args": { + "External id": 36818,"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": 2338707, "tid": 2338707, + "ts": 6197199983539.699, "dur": 7.579, + "args": { + "External id": 36819,"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": 2338707, "tid": 2338707, + "ts": 6197199983542.755, "dur": 0.899, + "args": { + "External id": 36820,"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": 2338707, "tid": 2338707, + "ts": 6197199983549.001, "dur": 29.917, + "args": { + "External id": 36821,"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": 2338707, "tid": 2338707, + "ts": 6197199983584.998, "dur": 6.985, + "args": { + "External id": 36822,"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": 2338707, "tid": 2338707, + "ts": 6197199983586.760, "dur": 4.275, + "args": { + "External id": 36823,"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": 2338707, "tid": 2338707, + "ts": 6197199983589.040, "dur": 1.751, + "args": { + "External id": 36824,"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": 2338707, "tid": 2338707, + "ts": 6197199983597.793, "dur": 45.844, + "args": { + "External id": 36825,"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": 2338707, "tid": 2338707, + "ts": 6197199983599.113, "dur": 43.934, + "args": { + "External id": 36826,"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": 2338707, "tid": 2338707, + "ts": 6197199983648.495, "dur": 15.098, + "args": { + "External id": 36827,"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": 2338707, "tid": 2338707, + "ts": 6197199983670.493, "dur": 3.610, + "args": { + "External id": 36828,"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": 2338707, "tid": 2338707, + "ts": 6197199983672.602, "dur": 0.613, + "args": { + "External id": 36829,"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": 2338707, "tid": 2338707, + "ts": 6197199983678.781, "dur": 77.140, + "args": { + "External id": 36830,"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": 2338707, "tid": 2338707, + "ts": 6197199983679.767, "dur": 5.987, + "args": { + "External id": 36831,"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": 2338707, "tid": 2338707, + "ts": 6197199983683.018, "dur": 2.140, + "args": { + "External id": 36832,"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": 2338707, "tid": 2338707, + "ts": 6197199983684.437, "dur": 0.591, + "args": { + "External id": 36833,"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": 2338707, "tid": 2338707, + "ts": 6197199983686.287, "dur": 69.056, + "args": { + "External id": 36834,"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": 2338707, "tid": 2338707, + "ts": 6197199983686.943, "dur": 66.818, + "args": { + "External id": 36835,"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": 2338707, "tid": 2338707, + "ts": 6197199983763.404, "dur": 4.999, + "args": { + "External id": 36836,"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": 2338707, "tid": 2338707, + "ts": 6197199983766.079, "dur": 0.643, + "args": { + "External id": 36837,"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": 2338707, "tid": 2338707, + "ts": 6197199983779.007, "dur": 2.112, + "args": { + "External id": 36838,"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": 2338707, "tid": 2338707, + "ts": 6197199983791.111, "dur": 7.388, + "args": { + "External id": 36839,"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": 2338707, "tid": 2338707, + "ts": 6197199983793.154, "dur": 5.004, + "args": { + "External id": 36840,"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": 2338707, "tid": 2338707, + "ts": 6197199983907.627, "dur": 236.048, + "args": { + "External id": 36841,"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": 2338707, "tid": 2338707, + "ts": 6197199983911.744, "dur": 2.615, + "args": { + "External id": 36842,"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": 2338707, "tid": 2338707, + "ts": 6197199983916.096, "dur": 226.701, + "args": { + "External id": 36843,"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": 2338707, "tid": 2338707, + "ts": 6197199983920.153, "dur": 0.494, + "args": { + "External id": 36844,"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": 2338707, "tid": 2338707, + "ts": 6197199983921.970, "dur": 24.456, + "args": { + "External id": 36845,"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": 2338707, "tid": 2338707, + "ts": 6197199983948.041, "dur": 5.656, + "args": { + "External id": 36846,"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": 2338707, "tid": 2338707, + "ts": 6197199983952.519, "dur": 0.943, + "args": { + "External id": 36847,"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": 2338707, "tid": 2338707, + "ts": 6197199983954.687, "dur": 22.045, + "args": { + "External id": 36848,"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": 2338707, "tid": 2338707, + "ts": 6197199983955.878, "dur": 1.154, + "args": { + "External id": 36849,"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": 2338707, "tid": 2338707, + "ts": 6197199983958.465, "dur": 17.987, + "args": { + "External id": 36850,"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": 2338707, "tid": 2338707, + "ts": 6197199983961.959, "dur": 2.721, + "args": { + "External id": 36851,"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": 2338707, "tid": 2338707, + "ts": 6197199983978.441, "dur": 25.144, + "args": { + "External id": 36852,"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": 2338707, "tid": 2338707, + "ts": 6197199984005.170, "dur": 12.876, + "args": { + "External id": 36853,"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": 2338707, "tid": 2338707, + "ts": 6197199984023.587, "dur": 13.324, + "args": { + "External id": 36854,"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": 2338707, "tid": 2338707, + "ts": 6197199984038.474, "dur": 12.171, + "args": { + "External id": 36855,"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": 2338707, "tid": 2338707, + "ts": 6197199984087.109, "dur": 25.687, + "args": { + "External id": 36856,"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": 2338707, "tid": 2338707, + "ts": 6197199984090.695, "dur": 2.696, + "args": { + "External id": 36857,"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": 2338707, "tid": 2338707, + "ts": 6197199984095.585, "dur": 0.843, + "args": { + "External id": 36858,"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": 2338707, "tid": 2338707, + "ts": 6197199984114.416, "dur": 12.660, + "args": { + "External id": 36859,"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": 2338707, "tid": 2338707, + "ts": 6197199984128.271, "dur": 13.119, + "args": { + "External id": 36860,"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": 2338707, "tid": 2338707, + "ts": 6197199984155.154, "dur": 2.433, + "args": { + "External id": 36861,"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": 2338707, "tid": 2338707, + "ts": 6197199984169.380, "dur": 3.771, + "args": { + "External id": 36862,"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": 2338707, "tid": 2338707, + "ts": 6197199984171.716, "dur": 0.555, + "args": { + "External id": 36863,"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": 2338707, "tid": 2338707, + "ts": 6197199984253.147, "dur": 69.566, + "args": { + "External id": 36864,"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": 2338707, "tid": 2338707, + "ts": 6197199984362.058, "dur": 16.347, + "args": { + "External id": 36865,"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": 2338707, "tid": 2338707, + "ts": 6197199984376.059, "dur": 0.827, + "args": { + "External id": 36866,"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": 2338707, "tid": 2338707, + "ts": 6197199984380.035, "dur": 29.446, + "args": { + "External id": 36867,"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": 2338707, "tid": 2338707, + "ts": 6197199984418.042, "dur": 9.587, + "args": { + "External id": 36868,"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": 2338707, "tid": 2338707, + "ts": 6197199984419.807, "dur": 6.947, + "args": { + "External id": 36869,"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": 2338707, "tid": 2338707, + "ts": 6197199984423.200, "dur": 3.304, + "args": { + "External id": 36870,"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": 2338707, "tid": 2338707, + "ts": 6197199984430.607, "dur": 46.086, + "args": { + "External id": 36871,"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": 2338707, "tid": 2338707, + "ts": 6197199984431.820, "dur": 44.220, + "args": { + "External id": 36872,"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": 2338707, "tid": 2338707, + "ts": 6197199984480.765, "dur": 14.860, + "args": { + "External id": 36873,"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": 2338707, "tid": 2338707, + "ts": 6197199984501.866, "dur": 6.268, + "args": { + "External id": 36874,"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": 2338707, "tid": 2338707, + "ts": 6197199984506.535, "dur": 0.653, + "args": { + "External id": 36875,"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": 2338707, "tid": 2338707, + "ts": 6197199984512.608, "dur": 45.624, + "args": { + "External id": 36876,"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": 2338707, "tid": 2338707, + "ts": 6197199984513.460, "dur": 3.485, + "args": { + "External id": 36877,"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": 2338707, "tid": 2338707, + "ts": 6197199984514.020, "dur": 2.296, + "args": { + "External id": 36878,"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": 2338707, "tid": 2338707, + "ts": 6197199984515.455, "dur": 0.712, + "args": { + "External id": 36879,"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": 2338707, "tid": 2338707, + "ts": 6197199984517.491, "dur": 40.336, + "args": { + "External id": 36880,"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": 2338707, "tid": 2338707, + "ts": 6197199984520.692, "dur": 36.573, + "args": { + "External id": 36881,"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": 2338707, "tid": 2338707, + "ts": 6197199984562.723, "dur": 3.300, + "args": { + "External id": 36882,"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": 2338707, "tid": 2338707, + "ts": 6197199984564.490, "dur": 0.382, + "args": { + "External id": 36883,"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": 2338707, "tid": 2338707, + "ts": 6197199984572.538, "dur": 1.483, + "args": { + "External id": 36884,"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": 2338707, "tid": 2338707, + "ts": 6197199984583.083, "dur": 6.733, + "args": { + "External id": 36885,"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": 2338707, "tid": 2338707, + "ts": 6197199984585.092, "dur": 4.457, + "args": { + "External id": 36886,"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": 2338707, "tid": 2338707, + "ts": 6197199984690.544, "dur": 311.377, + "args": { + "External id": 36887,"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": 2338707, "tid": 2338707, + "ts": 6197199984692.450, "dur": 1.936, + "args": { + "External id": 36888,"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": 2338707, "tid": 2338707, + "ts": 6197199984698.472, "dur": 302.734, + "args": { + "External id": 36889,"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": 2338707, "tid": 2338707, + "ts": 6197199984717.174, "dur": 0.833, + "args": { + "External id": 36890,"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": 2338707, "tid": 2338707, + "ts": 6197199984721.003, "dur": 34.543, + "args": { + "External id": 36891,"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": 2338707, "tid": 2338707, + "ts": 6197199984757.816, "dur": 6.706, + "args": { + "External id": 36892,"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": 2338707, "tid": 2338707, + "ts": 6197199984760.823, "dur": 3.196, + "args": { + "External id": 36893,"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": 2338707, "tid": 2338707, + "ts": 6197199984766.194, "dur": 31.803, + "args": { + "External id": 36894,"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": 2338707, "tid": 2338707, + "ts": 6197199984768.024, "dur": 1.868, + "args": { + "External id": 36895,"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": 2338707, "tid": 2338707, + "ts": 6197199984772.063, "dur": 25.563, + "args": { + "External id": 36896,"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": 2338707, "tid": 2338707, + "ts": 6197199984778.363, "dur": 3.009, + "args": { + "External id": 36897,"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": 2338707, "tid": 2338707, + "ts": 6197199984800.174, "dur": 29.355, + "args": { + "External id": 36898,"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": 2338707, "tid": 2338707, + "ts": 6197199984831.207, "dur": 18.588, + "args": { + "External id": 36899,"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": 2338707, "tid": 2338707, + "ts": 6197199984852.706, "dur": 33.379, + "args": { + "External id": 36900,"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": 2338707, "tid": 2338707, + "ts": 6197199984887.685, "dur": 43.731, + "args": { + "External id": 36901,"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": 2338707, "tid": 2338707, + "ts": 6197199984933.325, "dur": 32.631, + "args": { + "External id": 36902,"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": 2338707, "tid": 2338707, + "ts": 6197199984935.234, "dur": 1.226, + "args": { + "External id": 36903,"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": 2338707, "tid": 2338707, + "ts": 6197199984938.695, "dur": 3.066, + "args": { + "External id": 36904,"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": 2338707, "tid": 2338707, + "ts": 6197199984969.483, "dur": 14.031, + "args": { + "External id": 36905,"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": 2338707, "tid": 2338707, + "ts": 6197199984984.657, "dur": 15.610, + "args": { + "External id": 36906,"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": 2338707, "tid": 2338707, + "ts": 6197199985011.537, "dur": 2.940, + "args": { + "External id": 36907,"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": 2338707, "tid": 2338707, + "ts": 6197199985025.984, "dur": 4.083, + "args": { + "External id": 36908,"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": 2338707, "tid": 2338707, + "ts": 6197199985028.525, "dur": 0.372, + "args": { + "External id": 36909,"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": 2338707, "tid": 2338707, + "ts": 6197199985160.332, "dur": 72.706, + "args": { + "External id": 36910,"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": 2338707, "tid": 2338707, + "ts": 6197199985239.332, "dur": 9.570, + "args": { + "External id": 36911,"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": 2338707, "tid": 2338707, + "ts": 6197199985246.459, "dur": 0.873, + "args": { + "External id": 36912,"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": 2338707, "tid": 2338707, + "ts": 6197199985250.576, "dur": 28.438, + "args": { + "External id": 36913,"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": 2338707, "tid": 2338707, + "ts": 6197199985284.465, "dur": 7.256, + "args": { + "External id": 36914,"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": 2338707, "tid": 2338707, + "ts": 6197199985286.561, "dur": 4.551, + "args": { + "External id": 36915,"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": 2338707, "tid": 2338707, + "ts": 6197199985288.768, "dur": 2.115, + "args": { + "External id": 36916,"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": 2338707, "tid": 2338707, + "ts": 6197199985294.945, "dur": 44.171, + "args": { + "External id": 36917,"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": 2338707, "tid": 2338707, + "ts": 6197199985296.421, "dur": 41.989, + "args": { + "External id": 36918,"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": 2338707, "tid": 2338707, + "ts": 6197199985345.542, "dur": 20.883, + "args": { + "External id": 36919,"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": 2338707, "tid": 2338707, + "ts": 6197199985373.170, "dur": 4.254, + "args": { + "External id": 36920,"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": 2338707, "tid": 2338707, + "ts": 6197199985375.322, "dur": 1.027, + "args": { + "External id": 36921,"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": 2338707, "tid": 2338707, + "ts": 6197199985382.212, "dur": 47.628, + "args": { + "External id": 36922,"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": 2338707, "tid": 2338707, + "ts": 6197199985382.930, "dur": 6.604, + "args": { + "External id": 36923,"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": 2338707, "tid": 2338707, + "ts": 6197199985383.456, "dur": 5.484, + "args": { + "External id": 36924,"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": 2338707, "tid": 2338707, + "ts": 6197199985387.967, "dur": 0.841, + "args": { + "External id": 36925,"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": 2338707, "tid": 2338707, + "ts": 6197199985390.044, "dur": 39.345, + "args": { + "External id": 36926,"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": 2338707, "tid": 2338707, + "ts": 6197199985390.928, "dur": 37.717, + "args": { + "External id": 36927,"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": 2338707, "tid": 2338707, + "ts": 6197199985434.026, "dur": 4.152, + "args": { + "External id": 36928,"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": 2338707, "tid": 2338707, + "ts": 6197199985435.778, "dur": 1.160, + "args": { + "External id": 36929,"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": 2338707, "tid": 2338707, + "ts": 6197199985443.963, "dur": 1.634, + "args": { + "External id": 36930,"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": 2338707, "tid": 2338707, + "ts": 6197199985456.813, "dur": 6.290, + "args": { + "External id": 36931,"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": 2338707, "tid": 2338707, + "ts": 6197199985459.317, "dur": 3.531, + "args": { + "External id": 36932,"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": 2338707, "tid": 2338707, + "ts": 6197199985554.481, "dur": 217.110, + "args": { + "External id": 36933,"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": 2338707, "tid": 2338707, + "ts": 6197199985559.143, "dur": 2.208, + "args": { + "External id": 36934,"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": 2338707, "tid": 2338707, + "ts": 6197199985562.879, "dur": 207.908, + "args": { + "External id": 36935,"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": 2338707, "tid": 2338707, + "ts": 6197199985564.231, "dur": 0.511, + "args": { + "External id": 36936,"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": 2338707, "tid": 2338707, + "ts": 6197199985565.899, "dur": 20.167, + "args": { + "External id": 36937,"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": 2338707, "tid": 2338707, + "ts": 6197199985590.241, "dur": 5.119, + "args": { + "External id": 36938,"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": 2338707, "tid": 2338707, + "ts": 6197199985594.047, "dur": 1.070, + "args": { + "External id": 36939,"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": 2338707, "tid": 2338707, + "ts": 6197199985596.331, "dur": 20.283, + "args": { + "External id": 36940,"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": 2338707, "tid": 2338707, + "ts": 6197199985597.256, "dur": 1.250, + "args": { + "External id": 36941,"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": 2338707, "tid": 2338707, + "ts": 6197199985599.723, "dur": 16.629, + "args": { + "External id": 36942,"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": 2338707, "tid": 2338707, + "ts": 6197199985602.435, "dur": 2.646, + "args": { + "External id": 36943,"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": 2338707, "tid": 2338707, + "ts": 6197199985617.881, "dur": 20.513, + "args": { + "External id": 36944,"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": 2338707, "tid": 2338707, + "ts": 6197199985639.899, "dur": 14.142, + "args": { + "External id": 36945,"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": 2338707, "tid": 2338707, + "ts": 6197199985656.462, "dur": 15.383, + "args": { + "External id": 36946,"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": 2338707, "tid": 2338707, + "ts": 6197199985673.195, "dur": 12.885, + "args": { + "External id": 36947,"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": 2338707, "tid": 2338707, + "ts": 6197199985687.881, "dur": 47.025, + "args": { + "External id": 36948,"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": 2338707, "tid": 2338707, + "ts": 6197199985694.764, "dur": 1.401, + "args": { + "External id": 36949,"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": 2338707, "tid": 2338707, + "ts": 6197199985698.220, "dur": 0.740, + "args": { + "External id": 36950,"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": 2338707, "tid": 2338707, + "ts": 6197199985738.258, "dur": 16.443, + "args": { + "External id": 36951,"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": 2338707, "tid": 2338707, + "ts": 6197199985756.492, "dur": 12.585, + "args": { + "External id": 36952,"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": 2338707, "tid": 2338707, + "ts": 6197199985781.472, "dur": 2.828, + "args": { + "External id": 36953,"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": 2338707, "tid": 2338707, + "ts": 6197199985794.353, "dur": 3.773, + "args": { + "External id": 36954,"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": 2338707, "tid": 2338707, + "ts": 6197199985796.805, "dur": 0.517, + "args": { + "External id": 36955,"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": 2338707, "tid": 2338707, + "ts": 6197199985873.776, "dur": 61.001, + "args": { + "External id": 36956,"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": 2338707, "tid": 2338707, + "ts": 6197199985940.281, "dur": 4.934, + "args": { + "External id": 36957,"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": 2338707, "tid": 2338707, + "ts": 6197199985943.229, "dur": 1.005, + "args": { + "External id": 36958,"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": 2338707, "tid": 2338707, + "ts": 6197199985946.695, "dur": 25.372, + "args": { + "External id": 36959,"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": 2338707, "tid": 2338707, + "ts": 6197199985976.733, "dur": 8.920, + "args": { + "External id": 36960,"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": 2338707, "tid": 2338707, + "ts": 6197199985978.384, "dur": 6.269, + "args": { + "External id": 36961,"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": 2338707, "tid": 2338707, + "ts": 6197199985983.081, "dur": 1.368, + "args": { + "External id": 36962,"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": 2338707, "tid": 2338707, + "ts": 6197199985988.382, "dur": 42.462, + "args": { + "External id": 36963,"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": 2338707, "tid": 2338707, + "ts": 6197199985989.399, "dur": 40.727, + "args": { + "External id": 36964,"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": 2338707, "tid": 2338707, + "ts": 6197199986034.961, "dur": 15.009, + "args": { + "External id": 36965,"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": 2338707, "tid": 2338707, + "ts": 6197199986093.363, "dur": 5.347, + "args": { + "External id": 36966,"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": 2338707, "tid": 2338707, + "ts": 6197199986096.369, "dur": 0.993, + "args": { + "External id": 36967,"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": 2338707, "tid": 2338707, + "ts": 6197199986104.250, "dur": 53.929, + "args": { + "External id": 36968,"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": 2338707, "tid": 2338707, + "ts": 6197199986107.479, "dur": 4.144, + "args": { + "External id": 36969,"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": 2338707, "tid": 2338707, + "ts": 6197199986108.833, "dur": 2.271, + "args": { + "External id": 36970,"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": 2338707, "tid": 2338707, + "ts": 6197199986109.988, "dur": 0.996, + "args": { + "External id": 36971,"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": 2338707, "tid": 2338707, + "ts": 6197199986112.314, "dur": 45.488, + "args": { + "External id": 36972,"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": 2338707, "tid": 2338707, + "ts": 6197199986112.987, "dur": 44.092, + "args": { + "External id": 36973,"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": 2338707, "tid": 2338707, + "ts": 6197199986162.894, "dur": 3.408, + "args": { + "External id": 36974,"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": 2338707, "tid": 2338707, + "ts": 6197199986164.603, "dur": 0.451, + "args": { + "External id": 36975,"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": 2338707, "tid": 2338707, + "ts": 6197199986173.547, "dur": 1.875, + "args": { + "External id": 36976,"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": 2338707, "tid": 2338707, + "ts": 6197199986186.347, "dur": 6.641, + "args": { + "External id": 36977,"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": 2338707, "tid": 2338707, + "ts": 6197199986188.652, "dur": 4.062, + "args": { + "External id": 36978,"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": 2338707, "tid": 2338707, + "ts": 6197199986292.410, "dur": 211.159, + "args": { + "External id": 36979,"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": 2338707, "tid": 2338707, + "ts": 6197199986296.624, "dur": 2.070, + "args": { + "External id": 36980,"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": 2338707, "tid": 2338707, + "ts": 6197199986300.435, "dur": 202.556, + "args": { + "External id": 36981,"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": 2338707, "tid": 2338707, + "ts": 6197199986301.971, "dur": 0.737, + "args": { + "External id": 36982,"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": 2338707, "tid": 2338707, + "ts": 6197199986306.573, "dur": 25.011, + "args": { + "External id": 36983,"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": 2338707, "tid": 2338707, + "ts": 6197199986333.355, "dur": 5.746, + "args": { + "External id": 36984,"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": 2338707, "tid": 2338707, + "ts": 6197199986337.480, "dur": 1.315, + "args": { + "External id": 36985,"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": 2338707, "tid": 2338707, + "ts": 6197199986340.076, "dur": 21.721, + "args": { + "External id": 36986,"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": 2338707, "tid": 2338707, + "ts": 6197199986341.178, "dur": 1.166, + "args": { + "External id": 36987,"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": 2338707, "tid": 2338707, + "ts": 6197199986343.607, "dur": 17.938, + "args": { + "External id": 36988,"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": 2338707, "tid": 2338707, + "ts": 6197199986346.312, "dur": 3.063, + "args": { + "External id": 36989,"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": 2338707, "tid": 2338707, + "ts": 6197199986363.155, "dur": 20.528, + "args": { + "External id": 36990,"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": 2338707, "tid": 2338707, + "ts": 6197199986385.445, "dur": 15.302, + "args": { + "External id": 36991,"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": 2338707, "tid": 2338707, + "ts": 6197199986411.131, "dur": 13.806, + "args": { + "External id": 36992,"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": 2338707, "tid": 2338707, + "ts": 6197199986429.066, "dur": 12.226, + "args": { + "External id": 36993,"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": 2338707, "tid": 2338707, + "ts": 6197199986445.706, "dur": 20.782, + "args": { + "External id": 36994,"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": 2338707, "tid": 2338707, + "ts": 6197199986447.698, "dur": 1.130, + "args": { + "External id": 36995,"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": 2338707, "tid": 2338707, + "ts": 6197199986451.266, "dur": 1.291, + "args": { + "External id": 36996,"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": 2338707, "tid": 2338707, + "ts": 6197199986467.817, "dur": 15.987, + "args": { + "External id": 36997,"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": 2338707, "tid": 2338707, + "ts": 6197199986485.017, "dur": 16.932, + "args": { + "External id": 36998,"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": 2338707, "tid": 2338707, + "ts": 6197199986512.584, "dur": 1.711, + "args": { + "External id": 36999,"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": 2338707, "tid": 2338707, + "ts": 6197199986523.764, "dur": 3.950, + "args": { + "External id": 37000,"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": 2338707, "tid": 2338707, + "ts": 6197199986526.356, "dur": 0.553, + "args": { + "External id": 37001,"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": 2338707, "tid": 2338707, + "ts": 6197199986598.383, "dur": 58.549, + "args": { + "External id": 37002,"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": 2338707, "tid": 2338707, + "ts": 6197199986662.719, "dur": 5.735, + "args": { + "External id": 37003,"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": 2338707, "tid": 2338707, + "ts": 6197199986666.491, "dur": 0.721, + "args": { + "External id": 37004,"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": 2338707, "tid": 2338707, + "ts": 6197199986670.157, "dur": 25.503, + "args": { + "External id": 37005,"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": 2338707, "tid": 2338707, + "ts": 6197199986720.351, "dur": 14.618, + "args": { + "External id": 37006,"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": 2338707, "tid": 2338707, + "ts": 6197199986725.130, "dur": 8.453, + "args": { + "External id": 37007,"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": 2338707, "tid": 2338707, + "ts": 6197199986729.144, "dur": 3.960, + "args": { + "External id": 37008,"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": 2338707, "tid": 2338707, + "ts": 6197199986739.677, "dur": 58.613, + "args": { + "External id": 37009,"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": 2338707, "tid": 2338707, + "ts": 6197199986741.550, "dur": 55.698, + "args": { + "External id": 37010,"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": 2338707, "tid": 2338707, + "ts": 6197199986803.456, "dur": 17.141, + "args": { + "External id": 37011,"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": 2338707, "tid": 2338707, + "ts": 6197199986828.357, "dur": 6.512, + "args": { + "External id": 37012,"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": 2338707, "tid": 2338707, + "ts": 6197199986832.744, "dur": 1.033, + "args": { + "External id": 37013,"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": 2338707, "tid": 2338707, + "ts": 6197199986843.166, "dur": 48.106, + "args": { + "External id": 37014,"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": 2338707, "tid": 2338707, + "ts": 6197199986844.157, "dur": 3.868, + "args": { + "External id": 37015,"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": 2338707, "tid": 2338707, + "ts": 6197199986845.030, "dur": 2.324, + "args": { + "External id": 37016,"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": 2338707, "tid": 2338707, + "ts": 6197199986846.097, "dur": 1.127, + "args": { + "External id": 37017,"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": 2338707, "tid": 2338707, + "ts": 6197199986848.893, "dur": 42.050, + "args": { + "External id": 37018,"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": 2338707, "tid": 2338707, + "ts": 6197199986849.687, "dur": 40.491, + "args": { + "External id": 37019,"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": 2338707, "tid": 2338707, + "ts": 6197199986897.882, "dur": 3.953, + "args": { + "External id": 37020,"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": 2338707, "tid": 2338707, + "ts": 6197199986899.633, "dur": 0.939, + "args": { + "External id": 37021,"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": 2338707, "tid": 2338707, + "ts": 6197199986908.677, "dur": 1.839, + "args": { + "External id": 37022,"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": 2338707, "tid": 2338707, + "ts": 6197199986919.214, "dur": 9.198, + "args": { + "External id": 37023,"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": 2338707, "tid": 2338707, + "ts": 6197199986921.736, "dur": 6.360, + "args": { + "External id": 37024,"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": 2338707, "tid": 2338707, + "ts": 6197199987028.429, "dur": 238.523, + "args": { + "External id": 37025,"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": 2338707, "tid": 2338707, + "ts": 6197199987030.334, "dur": 2.488, + "args": { + "External id": 37026,"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": 2338707, "tid": 2338707, + "ts": 6197199987034.166, "dur": 232.161, + "args": { + "External id": 37027,"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": 2338707, "tid": 2338707, + "ts": 6197199987035.917, "dur": 0.349, + "args": { + "External id": 37028,"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": 2338707, "tid": 2338707, + "ts": 6197199987037.360, "dur": 63.675, + "args": { + "External id": 37029,"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": 2338707, "tid": 2338707, + "ts": 6197199987103.996, "dur": 4.310, + "args": { + "External id": 37030,"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": 2338707, "tid": 2338707, + "ts": 6197199987106.813, "dur": 1.093, + "args": { + "External id": 37031,"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": 2338707, "tid": 2338707, + "ts": 6197199987109.453, "dur": 28.442, + "args": { + "External id": 37032,"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": 2338707, "tid": 2338707, + "ts": 6197199987110.579, "dur": 1.868, + "args": { + "External id": 37033,"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": 2338707, "tid": 2338707, + "ts": 6197199987115.746, "dur": 21.780, + "args": { + "External id": 37034,"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": 2338707, "tid": 2338707, + "ts": 6197199987121.483, "dur": 2.875, + "args": { + "External id": 37035,"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": 2338707, "tid": 2338707, + "ts": 6197199987139.300, "dur": 24.590, + "args": { + "External id": 37036,"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": 2338707, "tid": 2338707, + "ts": 6197199987165.461, "dur": 13.884, + "args": { + "External id": 37037,"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": 2338707, "tid": 2338707, + "ts": 6197199987182.025, "dur": 15.013, + "args": { + "External id": 37038,"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": 2338707, "tid": 2338707, + "ts": 6197199987198.586, "dur": 13.019, + "args": { + "External id": 37039,"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": 2338707, "tid": 2338707, + "ts": 6197199987213.361, "dur": 20.145, + "args": { + "External id": 37040,"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": 2338707, "tid": 2338707, + "ts": 6197199987215.532, "dur": 1.413, + "args": { + "External id": 37041,"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": 2338707, "tid": 2338707, + "ts": 6197199987219.055, "dur": 0.835, + "args": { + "External id": 37042,"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": 2338707, "tid": 2338707, + "ts": 6197199987237.454, "dur": 14.055, + "args": { + "External id": 37043,"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": 2338707, "tid": 2338707, + "ts": 6197199987252.497, "dur": 12.480, + "args": { + "External id": 37044,"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": 2338707, "tid": 2338707, + "ts": 6197199987275.118, "dur": 2.441, + "args": { + "External id": 37045,"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": 2338707, "tid": 2338707, + "ts": 6197199987287.765, "dur": 3.850, + "args": { + "External id": 37046,"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": 2338707, "tid": 2338707, + "ts": 6197199987290.384, "dur": 0.414, + "args": { + "External id": 37047,"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": 2338707, "tid": 2338707, + "ts": 6197199987364.787, "dur": 61.383, + "args": { + "External id": 37048,"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": 2338707, "tid": 2338707, + "ts": 6197199987431.949, "dur": 6.423, + "args": { + "External id": 37049,"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": 2338707, "tid": 2338707, + "ts": 6197199987435.597, "dur": 1.496, + "args": { + "External id": 37050,"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": 2338707, "tid": 2338707, + "ts": 6197199987441.997, "dur": 25.944, + "args": { + "External id": 37051,"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": 2338707, "tid": 2338707, + "ts": 6197199987472.808, "dur": 5.182, + "args": { + "External id": 37052,"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": 2338707, "tid": 2338707, + "ts": 6197199987474.334, "dur": 2.974, + "args": { + "External id": 37053,"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": 2338707, "tid": 2338707, + "ts": 6197199987476.261, "dur": 0.878, + "args": { + "External id": 37054,"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": 2338707, "tid": 2338707, + "ts": 6197199987480.646, "dur": 42.532, + "args": { + "External id": 37055,"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": 2338707, "tid": 2338707, + "ts": 6197199987482.108, "dur": 40.375, + "args": { + "External id": 37056,"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": 2338707, "tid": 2338707, + "ts": 6197199987527.036, "dur": 13.779, + "args": { + "External id": 37057,"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": 2338707, "tid": 2338707, + "ts": 6197199987549.401, "dur": 3.666, + "args": { + "External id": 37058,"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": 2338707, "tid": 2338707, + "ts": 6197199987551.528, "dur": 0.634, + "args": { + "External id": 37059,"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": 2338707, "tid": 2338707, + "ts": 6197199987557.007, "dur": 48.409, + "args": { + "External id": 37060,"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": 2338707, "tid": 2338707, + "ts": 6197199987557.814, "dur": 6.242, + "args": { + "External id": 37061,"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": 2338707, "tid": 2338707, + "ts": 6197199987558.601, "dur": 4.832, + "args": { + "External id": 37062,"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": 2338707, "tid": 2338707, + "ts": 6197199987560.448, "dur": 2.820, + "args": { + "External id": 37063,"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": 2338707, "tid": 2338707, + "ts": 6197199987566.868, "dur": 37.939, + "args": { + "External id": 37064,"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": 2338707, "tid": 2338707, + "ts": 6197199987567.459, "dur": 36.755, + "args": { + "External id": 37065,"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": 2338707, "tid": 2338707, + "ts": 6197199987609.402, "dur": 4.234, + "args": { + "External id": 37066,"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": 2338707, "tid": 2338707, + "ts": 6197199987611.038, "dur": 1.392, + "args": { + "External id": 37067,"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": 2338707, "tid": 2338707, + "ts": 6197199987618.580, "dur": 1.509, + "args": { + "External id": 37068,"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": 2338707, "tid": 2338707, + "ts": 6197199987628.427, "dur": 5.947, + "args": { + "External id": 37069,"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": 2338707, "tid": 2338707, + "ts": 6197199987630.365, "dur": 3.720, + "args": { + "External id": 37070,"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": 2338707, "tid": 2338707, + "ts": 6197199987746.161, "dur": 183.169, + "args": { + "External id": 37071,"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": 2338707, "tid": 2338707, + "ts": 6197199987749.842, "dur": 3.694, + "args": { + "External id": 37072,"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": 2338707, "tid": 2338707, + "ts": 6197199987755.244, "dur": 173.648, + "args": { + "External id": 37073,"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": 2338707, "tid": 2338707, + "ts": 6197199987756.614, "dur": 0.469, + "args": { + "External id": 37074,"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": 2338707, "tid": 2338707, + "ts": 6197199987760.801, "dur": 23.499, + "args": { + "External id": 37075,"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": 2338707, "tid": 2338707, + "ts": 6197199987785.951, "dur": 3.460, + "args": { + "External id": 37076,"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": 2338707, "tid": 2338707, + "ts": 6197199987788.105, "dur": 1.056, + "args": { + "External id": 37077,"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": 2338707, "tid": 2338707, + "ts": 6197199987790.277, "dur": 25.640, + "args": { + "External id": 37078,"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": 2338707, "tid": 2338707, + "ts": 6197199987791.543, "dur": 3.245, + "args": { + "External id": 37079,"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": 2338707, "tid": 2338707, + "ts": 6197199987798.613, "dur": 17.063, + "args": { + "External id": 37080,"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": 2338707, "tid": 2338707, + "ts": 6197199987801.410, "dur": 2.741, + "args": { + "External id": 37081,"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": 2338707, "tid": 2338707, + "ts": 6197199987817.397, "dur": 20.813, + "args": { + "External id": 37082,"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": 2338707, "tid": 2338707, + "ts": 6197199987839.674, "dur": 12.998, + "args": { + "External id": 37083,"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": 2338707, "tid": 2338707, + "ts": 6197199987855.998, "dur": 12.259, + "args": { + "External id": 37084,"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": 2338707, "tid": 2338707, + "ts": 6197199987869.805, "dur": 11.865, + "args": { + "External id": 37085,"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": 2338707, "tid": 2338707, + "ts": 6197199987883.282, "dur": 20.968, + "args": { + "External id": 37086,"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": 2338707, "tid": 2338707, + "ts": 6197199987885.408, "dur": 1.215, + "args": { + "External id": 37087,"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": 2338707, "tid": 2338707, + "ts": 6197199987890.857, "dur": 0.770, + "args": { + "External id": 37088,"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": 2338707, "tid": 2338707, + "ts": 6197199987905.681, "dur": 11.137, + "args": { + "External id": 37089,"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": 2338707, "tid": 2338707, + "ts": 6197199987917.634, "dur": 10.460, + "args": { + "External id": 37090,"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": 2338707, "tid": 2338707, + "ts": 6197199987937.417, "dur": 2.148, + "args": { + "External id": 37091,"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": 2338707, "tid": 2338707, + "ts": 6197199987949.352, "dur": 3.733, + "args": { + "External id": 37092,"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": 2338707, "tid": 2338707, + "ts": 6197199987951.492, "dur": 0.672, + "args": { + "External id": 37093,"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": 2338707, "tid": 2338707, + "ts": 6197199988024.045, "dur": 101.666, + "args": { + "External id": 37094,"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": 2338707, "tid": 2338707, + "ts": 6197199988133.617, "dur": 9.988, + "args": { + "External id": 37095,"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": 2338707, "tid": 2338707, + "ts": 6197199988140.478, "dur": 1.404, + "args": { + "External id": 37096,"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": 2338707, "tid": 2338707, + "ts": 6197199988145.093, "dur": 28.360, + "args": { + "External id": 37097,"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": 2338707, "tid": 2338707, + "ts": 6197199988178.699, "dur": 5.467, + "args": { + "External id": 37098,"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": 2338707, "tid": 2338707, + "ts": 6197199988180.212, "dur": 3.158, + "args": { + "External id": 37099,"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": 2338707, "tid": 2338707, + "ts": 6197199988182.085, "dur": 1.096, + "args": { + "External id": 37100,"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": 2338707, "tid": 2338707, + "ts": 6197199988187.094, "dur": 50.276, + "args": { + "External id": 37101,"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": 2338707, "tid": 2338707, + "ts": 6197199988190.837, "dur": 46.035, + "args": { + "External id": 37102,"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": 2338707, "tid": 2338707, + "ts": 6197199988241.225, "dur": 17.093, + "args": { + "External id": 37103,"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": 2338707, "tid": 2338707, + "ts": 6197199988264.868, "dur": 3.491, + "args": { + "External id": 37104,"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": 2338707, "tid": 2338707, + "ts": 6197199988266.806, "dur": 0.688, + "args": { + "External id": 37105,"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": 2338707, "tid": 2338707, + "ts": 6197199988272.828, "dur": 49.060, + "args": { + "External id": 37106,"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": 2338707, "tid": 2338707, + "ts": 6197199988273.694, "dur": 8.032, + "args": { + "External id": 37107,"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": 2338707, "tid": 2338707, + "ts": 6197199988274.452, "dur": 6.613, + "args": { + "External id": 37108,"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": 2338707, "tid": 2338707, + "ts": 6197199988280.184, "dur": 0.743, + "args": { + "External id": 37109,"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": 2338707, "tid": 2338707, + "ts": 6197199988282.433, "dur": 38.943, + "args": { + "External id": 37110,"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": 2338707, "tid": 2338707, + "ts": 6197199988283.011, "dur": 37.583, + "args": { + "External id": 37111,"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": 2338707, "tid": 2338707, + "ts": 6197199988325.830, "dur": 3.518, + "args": { + "External id": 37112,"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": 2338707, "tid": 2338707, + "ts": 6197199988327.626, "dur": 0.493, + "args": { + "External id": 37113,"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": 2338707, "tid": 2338707, + "ts": 6197199988339.046, "dur": 1.869, + "args": { + "External id": 37114,"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": 2338707, "tid": 2338707, + "ts": 6197199988351.188, "dur": 6.560, + "args": { + "External id": 37115,"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": 2338707, "tid": 2338707, + "ts": 6197199988353.304, "dur": 4.186, + "args": { + "External id": 37116,"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": 2338707, "tid": 2338707, + "ts": 6197199988447.415, "dur": 181.360, + "args": { + "External id": 37117,"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": 2338707, "tid": 2338707, + "ts": 6197199988452.004, "dur": 2.203, + "args": { + "External id": 37118,"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": 2338707, "tid": 2338707, + "ts": 6197199988455.683, "dur": 172.438, + "args": { + "External id": 37119,"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": 2338707, "tid": 2338707, + "ts": 6197199988456.911, "dur": 0.352, + "args": { + "External id": 37120,"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": 2338707, "tid": 2338707, + "ts": 6197199988461.122, "dur": 21.324, + "args": { + "External id": 37121,"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": 2338707, "tid": 2338707, + "ts": 6197199988484.021, "dur": 5.088, + "args": { + "External id": 37122,"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": 2338707, "tid": 2338707, + "ts": 6197199988488.370, "dur": 0.540, + "args": { + "External id": 37123,"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": 2338707, "tid": 2338707, + "ts": 6197199988489.894, "dur": 21.012, + "args": { + "External id": 37124,"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": 2338707, "tid": 2338707, + "ts": 6197199988491.127, "dur": 1.026, + "args": { + "External id": 37125,"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": 2338707, "tid": 2338707, + "ts": 6197199988493.283, "dur": 17.299, + "args": { + "External id": 37126,"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": 2338707, "tid": 2338707, + "ts": 6197199988496.579, "dur": 2.242, + "args": { + "External id": 37127,"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": 2338707, "tid": 2338707, + "ts": 6197199988512.231, "dur": 20.752, + "args": { + "External id": 37128,"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": 2338707, "tid": 2338707, + "ts": 6197199988534.337, "dur": 11.625, + "args": { + "External id": 37129,"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": 2338707, "tid": 2338707, + "ts": 6197199988548.713, "dur": 13.188, + "args": { + "External id": 37130,"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": 2338707, "tid": 2338707, + "ts": 6197199988563.159, "dur": 11.035, + "args": { + "External id": 37131,"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": 2338707, "tid": 2338707, + "ts": 6197199988578.469, "dur": 21.646, + "args": { + "External id": 37132,"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": 2338707, "tid": 2338707, + "ts": 6197199988582.854, "dur": 1.392, + "args": { + "External id": 37133,"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": 2338707, "tid": 2338707, + "ts": 6197199988586.188, "dur": 0.722, + "args": { + "External id": 37134,"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": 2338707, "tid": 2338707, + "ts": 6197199988601.473, "dur": 13.152, + "args": { + "External id": 37135,"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": 2338707, "tid": 2338707, + "ts": 6197199988616.041, "dur": 11.141, + "args": { + "External id": 37136,"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": 2338707, "tid": 2338707, + "ts": 6197199988635.147, "dur": 1.612, + "args": { + "External id": 37137,"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": 2338707, "tid": 2338707, + "ts": 6197199988645.364, "dur": 3.473, + "args": { + "External id": 37138,"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": 2338707, "tid": 2338707, + "ts": 6197199988647.548, "dur": 0.385, + "args": { + "External id": 37139,"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": 2338707, "tid": 2338707, + "ts": 6197199988736.197, "dur": 73.517, + "args": { + "External id": 37140,"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": 2338707, "tid": 2338707, + "ts": 6197199988817.151, "dur": 7.958, + "args": { + "External id": 37141,"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": 2338707, "tid": 2338707, + "ts": 6197199988821.569, "dur": 1.797, + "args": { + "External id": 37142,"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": 2338707, "tid": 2338707, + "ts": 6197199988826.828, "dur": 28.671, + "args": { + "External id": 37143,"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": 2338707, "tid": 2338707, + "ts": 6197199988861.221, "dur": 9.088, + "args": { + "External id": 37144,"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": 2338707, "tid": 2338707, + "ts": 6197199988862.893, "dur": 6.684, + "args": { + "External id": 37145,"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": 2338707, "tid": 2338707, + "ts": 6197199988867.029, "dur": 2.344, + "args": { + "External id": 37146,"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": 2338707, "tid": 2338707, + "ts": 6197199988873.136, "dur": 43.187, + "args": { + "External id": 37147,"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": 2338707, "tid": 2338707, + "ts": 6197199988874.305, "dur": 41.418, + "args": { + "External id": 37148,"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": 2338707, "tid": 2338707, + "ts": 6197199988920.313, "dur": 15.581, + "args": { + "External id": 37149,"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": 2338707, "tid": 2338707, + "ts": 6197199988940.809, "dur": 24.300, + "args": { + "External id": 37150,"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": 2338707, "tid": 2338707, + "ts": 6197199988943.086, "dur": 21.627, + "args": { + "External id": 37151,"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": 2338707, "tid": 2338707, + "ts": 6197199988948.603, "dur": 1.007, + "args": { + "External id": 37152,"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": 2338707, "tid": 2338707, + "ts": 6197199988970.466, "dur": 39.561, + "args": { + "External id": 37153,"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": 2338707, "tid": 2338707, + "ts": 6197199988972.467, "dur": 37.312, + "args": { + "External id": 37154,"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": 2338707, "tid": 2338707, + "ts": 6197199988980.660, "dur": 3.901, + "args": { + "External id": 37155,"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": 2338707, "tid": 2338707, + "ts": 6197199988986.100, "dur": 23.188, + "args": { + "External id": 37156,"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": 2338707, "tid": 2338707, + "ts": 6197199989022.914, "dur": 5.214, + "args": { + "External id": 37157,"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": 2338707, "tid": 2338707, + "ts": 6197199989024.986, "dur": 2.846, + "args": { + "External id": 37158,"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": 2338707, "tid": 2338707, + "ts": 6197199989029.265, "dur": 1.350, + "args": { + "External id": 37159,"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": 2338707, "tid": 2338707, + "ts": 6197199989030.022, "dur": 0.515, + "args": { + "External id": 37160,"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": 2338707, "tid": 2338707, + "ts": 6197199989122.034, "dur": 28.468, + "args": { + "External id": 37161,"Sequence number": 480211, "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": 2338707, "tid": 2338707, + "ts": 6197199989152.519, "dur": 12.430, + "args": { + "External id": 37162,"Sequence number": 480212, "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": 2338707, "tid": 2338707, "ts": 6197199989152.519, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338707, "tid": 2338707, + "ts": 6197199989171.843, "dur": 7.339, + "args": { + "External id": 37163,"Sequence number": 480213, "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": 2338707, "tid": 2338707, + "ts": 6197199989175.689, "dur": 1.682, + "args": { + "External id": 37164,"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": 2338707, "tid": 2338707, + "ts": 6197199989181.895, "dur": 7.243, + "args": { + "External id": 37165,"Sequence number": 480213, "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": 2338707, "tid": 2338707, + "ts": 6197199989186.532, "dur": 1.132, + "args": { + "External id": 37166,"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": 2338707, "tid": 2338707, + "ts": 6197199989192.499, "dur": 2.651, + "args": { + "External id": 37167,"Sequence number": 480213, "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": 2338707, "tid": 2338707, + "ts": 6197199989193.893, "dur": 0.647, + "args": { + "External id": 37168,"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": 2338707, "tid": 2338707, + "ts": 6197199989199.144, "dur": 7.197, + "args": { + "External id": 37169,"Sequence number": 480213, "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": 2338707, "tid": 2338707, "ts": 6197199989199.144, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2338707, + "ts": 6197199989204.064, "dur": 0.934, + "args": { + "External id": 37170,"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": 2338707, "tid": 2338707, + "ts": 6197199989207.555, "dur": 8.032, + "args": { + "External id": 37171,"Sequence number": 480214, "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": 2338707, "tid": 2338707, "ts": 6197199989207.555, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2338707, + "ts": 6197199989213.884, "dur": 0.969, + "args": { + "External id": 37172,"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": 2338707, "tid": 2338707, + "ts": 6197199989216.914, "dur": 6.004, + "args": { + "External id": 37173,"Sequence number": 480215, "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": 2338707, "tid": 2338707, "ts": 6197199989216.914, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2338707, + "ts": 6197199989220.558, "dur": 1.244, + "args": { + "External id": 37174,"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": 2338707, "tid": 2338707, + "ts": 6197199989224.211, "dur": 4.015, + "args": { + "External id": 37175,"Sequence number": 480216, "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": 2338707, "tid": 2338707, "ts": 6197199989224.211, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2338707, + "ts": 6197199989226.588, "dur": 0.931, + "args": { + "External id": 37176,"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": 2338707, "tid": 2338707, + "ts": 6197199989232.026, "dur": 35.275, + "args": { + "External id": 37177,"Sequence number": 480217, "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": 2338707, "tid": 2338707, + "ts": 6197199989233.979, "dur": 33.069, + "args": { + "External id": 37178,"Sequence number": 480217, "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": 2338707, "tid": 2338707, + "ts": 6197199989236.393, "dur": 11.632, + "args": { + "External id": 37179,"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": 2338707, "tid": 2338707, + "ts": 6197199989241.196, "dur": 6.242, + "args": { + "External id": 37180,"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": 2338707, "tid": 2338707, + "ts": 6197199989249.047, "dur": 17.578, + "args": { + "External id": 37181,"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": 2338707, "tid": 2338707, + "ts": 6197199989296.405, "dur": 4.660, + "args": { + "External id": 37182,"Sequence number": 480217, "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": 2338707, "tid": 2338707, "ts": 6197199989296.405, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6197199989303.759, "dur": 1.219, + "args": { + "External id": 37183,"Sequence number": 480218, "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": 2338707, "tid": 2338707, + "ts": 6197199989339.872, "dur": 46321.066, + "args": { + "External id": 37184,"Sequence number": 480218, "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": 2338707, "tid": 2338707, "ts": 6197199989339.872, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338707, "tid": 2338707, + "ts": 6197199989361.073, "dur": 28.201, + "args": { + "External id": 37185,"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": 2338707, "tid": 2338707, + "ts": 6197199989364.488, "dur": 24.567, + "args": { + "External id": 37186,"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": 2338707, "tid": 2338707, + "ts": 6197199989366.225, "dur": 5.630, + "args": { + "External id": 37187,"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": 2338707, "tid": 2338707, + "ts": 6197199989367.592, "dur": 3.817, + "args": { + "External id": 37188,"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": 2338707, "tid": 2338707, + "ts": 6197199989372.635, "dur": 15.988, + "args": { + "External id": 37189,"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": 2338707, "tid": 2338707, + "ts": 6197199989406.668, "dur": 23.803, + "args": { + "External id": 37190,"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": 2338707, "tid": 2338707, + "ts": 6197199989407.822, "dur": 6.191, + "args": { + "External id": 37191,"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": 2338707, "tid": 2338707, + "ts": 6197199989409.944, "dur": 3.798, + "args": { + "External id": 37192,"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": 2338707, "tid": 2338707, + "ts": 6197199989415.204, "dur": 15.057, + "args": { + "External id": 37193,"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": 2338707, "tid": 2338707, + "ts": 6197199989417.172, "dur": 12.732, + "args": { + "External id": 37194,"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": 2338707, "tid": 2338707, + "ts": 6197199989434.315, "dur": 24.236, + "args": { + "External id": 37195,"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": 2338707, "tid": 2338707, + "ts": 6197199989435.189, "dur": 7.704, + "args": { + "External id": 37196,"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": 2338707, "tid": 2338707, + "ts": 6197199989439.155, "dur": 3.527, + "args": { + "External id": 37197,"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": 2338707, "tid": 2338707, + "ts": 6197199989443.368, "dur": 14.972, + "args": { + "External id": 37198,"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": 2338707, "tid": 2338707, + "ts": 6197199989444.389, "dur": 13.543, + "args": { + "External id": 37199,"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": 2338707, "tid": 2338707, + "ts": 6197199989464.306, "dur": 16.461, + "args": { + "External id": 37200,"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": 2338707, "tid": 2338707, + "ts": 6197199989466.002, "dur": 2.769, + "args": { + "External id": 37201,"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": 2338707, "tid": 2338707, + "ts": 6197199989469.788, "dur": 10.703, + "args": { + "External id": 37202,"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": 2338707, "tid": 2338707, + "ts": 6197199989470.458, "dur": 9.759, + "args": { + "External id": 37203,"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": 2338707, "tid": 2338707, + "ts": 6197199989485.699, "dur": 23.352, + "args": { + "External id": 37204,"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": 2338707, "tid": 2338707, + "ts": 6197199989514.324, "dur": 47.416, + "args": { + "External id": 37205,"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": 2338707, "tid": 2338707, + "ts": 6197199989516.157, "dur": 45.176, + "args": { + "External id": 37206,"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": 2338707, "tid": 2338707, + "ts": 6197199989520.242, "dur": 1.043, + "args": { + "External id": 37207,"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": 2338707, "tid": 2338707, + "ts": 6197199989522.793, "dur": 22.843, + "args": { + "External id": 37208,"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": 2338707, "tid": 2338707, + "ts": 6197199989527.102, "dur": 18.332, + "args": { + "External id": 37209,"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": 2338707, "tid": 2338707, + "ts": 6197199989529.446, "dur": 2.612, + "args": { + "External id": 37210,"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": 2338707, "tid": 2338707, + "ts": 6197199989532.951, "dur": 12.135, + "args": { + "External id": 37211,"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": 2338707, "tid": 2338707, + "ts": 6197199989565.968, "dur": 39735.714, + "args": { + "External id": 37212,"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": 2338707, "tid": 2338707, + "ts": 6197199989567.373, "dur": 39732.671, + "args": { + "External id": 37213,"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": 2338707, "tid": 2338707, + "ts": 6197200029316.981, "dur": 10.634, + "args": { + "External id": 37214,"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": 2338707, "tid": 2338707, + "ts": 6197200029324.400, "dur": 1.154, + "args": { + "External id": 37215,"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": 2338707, "tid": 2338707, + "ts": 6197200029333.336, "dur": 112.617, + "args": { + "External id": 37216,"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": 2338707, "tid": 2338707, + "ts": 6197200029334.916, "dur": 7.114, + "args": { + "External id": 37217,"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": 2338707, "tid": 2338707, + "ts": 6197200029337.416, "dur": 3.596, + "args": { + "External id": 37218,"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": 2338707, "tid": 2338707, + "ts": 6197200029339.745, "dur": 0.977, + "args": { + "External id": 37219,"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": 2338707, "tid": 2338707, + "ts": 6197200029343.306, "dur": 101.615, + "args": { + "External id": 37220,"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": 2338707, "tid": 2338707, + "ts": 6197200029345.147, "dur": 98.688, + "args": { + "External id": 37221,"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": 2338707, "tid": 2338707, + "ts": 6197200029452.391, "dur": 5.222, + "args": { + "External id": 37222,"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": 2338707, "tid": 2338707, + "ts": 6197200029455.089, "dur": 0.822, + "args": { + "External id": 37223,"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": 2338707, "tid": 2338707, + "ts": 6197200029466.296, "dur": 3.227, + "args": { + "External id": 37224,"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": 2338707, "tid": 2338707, + "ts": 6197200029481.371, "dur": 7.858, + "args": { + "External id": 37225,"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": 2338707, "tid": 2338707, + "ts": 6197200029483.943, "dur": 4.980, + "args": { + "External id": 37226,"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": 2338707, "tid": 2338707, + "ts": 6197200029637.017, "dur": 239.260, + "args": { + "External id": 37227,"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": 2338707, "tid": 2338707, + "ts": 6197200029640.147, "dur": 4.623, + "args": { + "External id": 37228,"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": 2338707, "tid": 2338707, + "ts": 6197200029646.560, "dur": 229.000, + "args": { + "External id": 37229,"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": 2338707, "tid": 2338707, + "ts": 6197200029648.425, "dur": 0.443, + "args": { + "External id": 37230,"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": 2338707, "tid": 2338707, + "ts": 6197200029650.542, "dur": 26.601, + "args": { + "External id": 37231,"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": 2338707, "tid": 2338707, + "ts": 6197200029678.907, "dur": 6.593, + "args": { + "External id": 37232,"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": 2338707, "tid": 2338707, + "ts": 6197200029684.302, "dur": 0.862, + "args": { + "External id": 37233,"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": 2338707, "tid": 2338707, + "ts": 6197200029686.804, "dur": 50.174, + "args": { + "External id": 37234,"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": 2338707, "tid": 2338707, + "ts": 6197200029687.811, "dur": 1.244, + "args": { + "External id": 37235,"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": 2338707, "tid": 2338707, + "ts": 6197200029690.545, "dur": 45.965, + "args": { + "External id": 37236,"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": 2338707, "tid": 2338707, + "ts": 6197200029696.948, "dur": 20.417, + "args": { + "External id": 37237,"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": 2338707, "tid": 2338707, + "ts": 6197200029740.084, "dur": 28.899, + "args": { + "External id": 37238,"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": 2338707, "tid": 2338707, + "ts": 6197200029771.309, "dur": 13.827, + "args": { + "External id": 37239,"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": 2338707, "tid": 2338707, + "ts": 6197200029788.878, "dur": 16.077, + "args": { + "External id": 37240,"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": 2338707, "tid": 2338707, + "ts": 6197200029806.592, "dur": 13.277, + "args": { + "External id": 37241,"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": 2338707, "tid": 2338707, + "ts": 6197200029822.272, "dur": 23.097, + "args": { + "External id": 37242,"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": 2338707, "tid": 2338707, + "ts": 6197200029824.911, "dur": 1.454, + "args": { + "External id": 37243,"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": 2338707, "tid": 2338707, + "ts": 6197200029828.512, "dur": 3.191, + "args": { + "External id": 37244,"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": 2338707, "tid": 2338707, + "ts": 6197200029849.431, "dur": 12.360, + "args": { + "External id": 37245,"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": 2338707, "tid": 2338707, + "ts": 6197200029863.050, "dur": 11.450, + "args": { + "External id": 37246,"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": 2338707, "tid": 2338707, + "ts": 6197200029886.256, "dur": 2.577, + "args": { + "External id": 37247,"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": 2338707, "tid": 2338707, + "ts": 6197200029896.537, "dur": 4.601, + "args": { + "External id": 37248,"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": 2338707, "tid": 2338707, + "ts": 6197200029899.222, "dur": 0.783, + "args": { + "External id": 37249,"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": 2338707, "tid": 2338707, + "ts": 6197200029987.157, "dur": 125.758, + "args": { + "External id": 37250,"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": 2338707, "tid": 2338707, + "ts": 6197200030122.232, "dur": 11.672, + "args": { + "External id": 37251,"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": 2338707, "tid": 2338707, + "ts": 6197200030128.566, "dur": 1.586, + "args": { + "External id": 37252,"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": 2338707, "tid": 2338707, + "ts": 6197200030135.478, "dur": 28.960, + "args": { + "External id": 37253,"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": 2338707, "tid": 2338707, + "ts": 6197200030172.021, "dur": 7.626, + "args": { + "External id": 37254,"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": 2338707, "tid": 2338707, + "ts": 6197200030174.059, "dur": 4.637, + "args": { + "External id": 37255,"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": 2338707, "tid": 2338707, + "ts": 6197200030176.419, "dur": 1.999, + "args": { + "External id": 37256,"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": 2338707, "tid": 2338707, + "ts": 6197200030183.335, "dur": 54.457, + "args": { + "External id": 37257,"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": 2338707, "tid": 2338707, + "ts": 6197200030184.821, "dur": 51.761, + "args": { + "External id": 37258,"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": 2338707, "tid": 2338707, + "ts": 6197200030244.804, "dur": 17.346, + "args": { + "External id": 37259,"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": 2338707, "tid": 2338707, + "ts": 6197200030269.486, "dur": 4.046, + "args": { + "External id": 37260,"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": 2338707, "tid": 2338707, + "ts": 6197200030271.448, "dur": 1.145, + "args": { + "External id": 37261,"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": 2338707, "tid": 2338707, + "ts": 6197200030278.354, "dur": 53.375, + "args": { + "External id": 37262,"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": 2338707, "tid": 2338707, + "ts": 6197200030279.539, "dur": 6.393, + "args": { + "External id": 37263,"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": 2338707, "tid": 2338707, + "ts": 6197200030280.408, "dur": 4.891, + "args": { + "External id": 37264,"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": 2338707, "tid": 2338707, + "ts": 6197200030284.469, "dur": 0.650, + "args": { + "External id": 37265,"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": 2338707, "tid": 2338707, + "ts": 6197200030290.000, "dur": 41.280, + "args": { + "External id": 37266,"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": 2338707, "tid": 2338707, + "ts": 6197200030290.887, "dur": 39.695, + "args": { + "External id": 37267,"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": 2338707, "tid": 2338707, + "ts": 6197200030335.876, "dur": 4.351, + "args": { + "External id": 37268,"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": 2338707, "tid": 2338707, + "ts": 6197200030337.672, "dur": 0.844, + "args": { + "External id": 37269,"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": 2338707, "tid": 2338707, + "ts": 6197200030347.728, "dur": 1.911, + "args": { + "External id": 37270,"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": 2338707, "tid": 2338707, + "ts": 6197200030361.894, "dur": 8.747, + "args": { + "External id": 37271,"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": 2338707, "tid": 2338707, + "ts": 6197200030363.987, "dur": 6.328, + "args": { + "External id": 37272,"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": 2338707, "tid": 2338707, + "ts": 6197200030482.335, "dur": 188.004, + "args": { + "External id": 37273,"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": 2338707, "tid": 2338707, + "ts": 6197200030484.870, "dur": 1.842, + "args": { + "External id": 37274,"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": 2338707, "tid": 2338707, + "ts": 6197200030488.428, "dur": 181.204, + "args": { + "External id": 37275,"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": 2338707, "tid": 2338707, + "ts": 6197200030490.252, "dur": 0.609, + "args": { + "External id": 37276,"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": 2338707, "tid": 2338707, + "ts": 6197200030492.285, "dur": 25.704, + "args": { + "External id": 37277,"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": 2338707, "tid": 2338707, + "ts": 6197200030522.368, "dur": 3.088, + "args": { + "External id": 37278,"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": 2338707, "tid": 2338707, + "ts": 6197200030524.501, "dur": 0.700, + "args": { + "External id": 37279,"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": 2338707, "tid": 2338707, + "ts": 6197200030526.765, "dur": 24.056, + "args": { + "External id": 37280,"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": 2338707, "tid": 2338707, + "ts": 6197200030527.813, "dur": 1.759, + "args": { + "External id": 37281,"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": 2338707, "tid": 2338707, + "ts": 6197200030531.078, "dur": 19.393, + "args": { + "External id": 37282,"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": 2338707, "tid": 2338707, + "ts": 6197200030536.402, "dur": 2.445, + "args": { + "External id": 37283,"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": 2338707, "tid": 2338707, + "ts": 6197200030552.636, "dur": 22.036, + "args": { + "External id": 37284,"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": 2338707, "tid": 2338707, + "ts": 6197200030576.252, "dur": 13.696, + "args": { + "External id": 37285,"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": 2338707, "tid": 2338707, + "ts": 6197200030592.696, "dur": 12.615, + "args": { + "External id": 37286,"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": 2338707, "tid": 2338707, + "ts": 6197200030606.842, "dur": 12.475, + "args": { + "External id": 37287,"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": 2338707, "tid": 2338707, + "ts": 6197200030621.112, "dur": 22.875, + "args": { + "External id": 37288,"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": 2338707, "tid": 2338707, + "ts": 6197200030625.988, "dur": 1.587, + "args": { + "External id": 37289,"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": 2338707, "tid": 2338707, + "ts": 6197200030630.236, "dur": 0.996, + "args": { + "External id": 37290,"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": 2338707, "tid": 2338707, + "ts": 6197200030645.456, "dur": 11.707, + "args": { + "External id": 37291,"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": 2338707, "tid": 2338707, + "ts": 6197200030658.496, "dur": 10.220, + "args": { + "External id": 37292,"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": 2338707, "tid": 2338707, + "ts": 6197200030677.033, "dur": 1.871, + "args": { + "External id": 37293,"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": 2338707, "tid": 2338707, + "ts": 6197200030687.801, "dur": 3.804, + "args": { + "External id": 37294,"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": 2338707, "tid": 2338707, + "ts": 6197200030690.363, "dur": 0.328, + "args": { + "External id": 37295,"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": 2338707, "tid": 2338707, + "ts": 6197200030799.080, "dur": 65.865, + "args": { + "External id": 37296,"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": 2338707, "tid": 2338707, + "ts": 6197200030873.604, "dur": 7.398, + "args": { + "External id": 37297,"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": 2338707, "tid": 2338707, + "ts": 6197200030878.311, "dur": 1.043, + "args": { + "External id": 37298,"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": 2338707, "tid": 2338707, + "ts": 6197200030882.724, "dur": 27.379, + "args": { + "External id": 37299,"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": 2338707, "tid": 2338707, + "ts": 6197200030915.072, "dur": 5.454, + "args": { + "External id": 37300,"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": 2338707, "tid": 2338707, + "ts": 6197200030916.658, "dur": 3.116, + "args": { + "External id": 37301,"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": 2338707, "tid": 2338707, + "ts": 6197200030918.317, "dur": 1.227, + "args": { + "External id": 37302,"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": 2338707, "tid": 2338707, + "ts": 6197200030925.928, "dur": 43.476, + "args": { + "External id": 37303,"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": 2338707, "tid": 2338707, + "ts": 6197200030927.098, "dur": 41.752, + "args": { + "External id": 37304,"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": 2338707, "tid": 2338707, + "ts": 6197200030973.298, "dur": 14.859, + "args": { + "External id": 37305,"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": 2338707, "tid": 2338707, + "ts": 6197200030994.229, "dur": 3.578, + "args": { + "External id": 37306,"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": 2338707, "tid": 2338707, + "ts": 6197200030996.363, "dur": 0.469, + "args": { + "External id": 37307,"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": 2338707, "tid": 2338707, + "ts": 6197200031002.385, "dur": 48.571, + "args": { + "External id": 37308,"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": 2338707, "tid": 2338707, + "ts": 6197200031003.561, "dur": 8.687, + "args": { + "External id": 37309,"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": 2338707, "tid": 2338707, + "ts": 6197200031007.037, "dur": 4.597, + "args": { + "External id": 37310,"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": 2338707, "tid": 2338707, + "ts": 6197200031008.767, "dur": 2.670, + "args": { + "External id": 37311,"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": 2338707, "tid": 2338707, + "ts": 6197200031013.284, "dur": 37.061, + "args": { + "External id": 37312,"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": 2338707, "tid": 2338707, + "ts": 6197200031014.165, "dur": 35.680, + "args": { + "External id": 37313,"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": 2338707, "tid": 2338707, + "ts": 6197200031095.470, "dur": 5.447, + "args": { + "External id": 37314,"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": 2338707, "tid": 2338707, + "ts": 6197200031097.878, "dur": 0.997, + "args": { + "External id": 37315,"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": 2338707, "tid": 2338707, + "ts": 6197200031108.698, "dur": 1.978, + "args": { + "External id": 37316,"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": 2338707, "tid": 2338707, + "ts": 6197200031122.186, "dur": 7.775, + "args": { + "External id": 37317,"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": 2338707, "tid": 2338707, + "ts": 6197200031124.763, "dur": 4.874, + "args": { + "External id": 37318,"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": 2338707, "tid": 2338707, + "ts": 6197200031237.806, "dur": 214.868, + "args": { + "External id": 37319,"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": 2338707, "tid": 2338707, + "ts": 6197200031240.457, "dur": 2.218, + "args": { + "External id": 37320,"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": 2338707, "tid": 2338707, + "ts": 6197200031244.207, "dur": 208.070, + "args": { + "External id": 37321,"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": 2338707, "tid": 2338707, + "ts": 6197200031246.334, "dur": 0.630, + "args": { + "External id": 37322,"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": 2338707, "tid": 2338707, + "ts": 6197200031251.092, "dur": 25.215, + "args": { + "External id": 37323,"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": 2338707, "tid": 2338707, + "ts": 6197200031280.617, "dur": 4.181, + "args": { + "External id": 37324,"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": 2338707, "tid": 2338707, + "ts": 6197200031283.763, "dur": 0.762, + "args": { + "External id": 37325,"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": 2338707, "tid": 2338707, + "ts": 6197200031285.957, "dur": 30.299, + "args": { + "External id": 37326,"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": 2338707, "tid": 2338707, + "ts": 6197200031287.043, "dur": 3.483, + "args": { + "External id": 37327,"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": 2338707, "tid": 2338707, + "ts": 6197200031292.378, "dur": 23.602, + "args": { + "External id": 37328,"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": 2338707, "tid": 2338707, + "ts": 6197200031295.677, "dur": 3.097, + "args": { + "External id": 37329,"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": 2338707, "tid": 2338707, + "ts": 6197200031318.268, "dur": 23.313, + "args": { + "External id": 37330,"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": 2338707, "tid": 2338707, + "ts": 6197200031343.139, "dur": 15.608, + "args": { + "External id": 37331,"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": 2338707, "tid": 2338707, + "ts": 6197200031362.014, "dur": 15.752, + "args": { + "External id": 37332,"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": 2338707, "tid": 2338707, + "ts": 6197200031379.730, "dur": 13.289, + "args": { + "External id": 37333,"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": 2338707, "tid": 2338707, + "ts": 6197200031396.901, "dur": 21.127, + "args": { + "External id": 37334,"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": 2338707, "tid": 2338707, + "ts": 6197200031398.874, "dur": 1.229, + "args": { + "External id": 37335,"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": 2338707, "tid": 2338707, + "ts": 6197200031402.249, "dur": 0.964, + "args": { + "External id": 37336,"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": 2338707, "tid": 2338707, + "ts": 6197200031419.304, "dur": 16.449, + "args": { + "External id": 37337,"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": 2338707, "tid": 2338707, + "ts": 6197200031437.117, "dur": 14.223, + "args": { + "External id": 37338,"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": 2338707, "tid": 2338707, + "ts": 6197200031459.893, "dur": 1.626, + "args": { + "External id": 37339,"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": 2338707, "tid": 2338707, + "ts": 6197200031473.822, "dur": 4.379, + "args": { + "External id": 37340,"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": 2338707, "tid": 2338707, + "ts": 6197200031476.621, "dur": 0.632, + "args": { + "External id": 37341,"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": 2338707, "tid": 2338707, + "ts": 6197200031551.089, "dur": 64.806, + "args": { + "External id": 37342,"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": 2338707, "tid": 2338707, + "ts": 6197200031621.472, "dur": 5.512, + "args": { + "External id": 37343,"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": 2338707, "tid": 2338707, + "ts": 6197200031624.783, "dur": 0.955, + "args": { + "External id": 37344,"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": 2338707, "tid": 2338707, + "ts": 6197200031628.515, "dur": 26.933, + "args": { + "External id": 37345,"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": 2338707, "tid": 2338707, + "ts": 6197200031660.815, "dur": 10.346, + "args": { + "External id": 37346,"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": 2338707, "tid": 2338707, + "ts": 6197200031662.473, "dur": 7.966, + "args": { + "External id": 37347,"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": 2338707, "tid": 2338707, + "ts": 6197200031667.429, "dur": 2.772, + "args": { + "External id": 37348,"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": 2338707, "tid": 2338707, + "ts": 6197200031676.506, "dur": 74.983, + "args": { + "External id": 37349,"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": 2338707, "tid": 2338707, + "ts": 6197200031677.938, "dur": 72.236, + "args": { + "External id": 37350,"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": 2338707, "tid": 2338707, + "ts": 6197200031758.205, "dur": 17.784, + "args": { + "External id": 37351,"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": 2338707, "tid": 2338707, + "ts": 6197200031783.898, "dur": 4.656, + "args": { + "External id": 37352,"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": 2338707, "tid": 2338707, + "ts": 6197200031786.315, "dur": 1.028, + "args": { + "External id": 37353,"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": 2338707, "tid": 2338707, + "ts": 6197200031796.739, "dur": 51.282, + "args": { + "External id": 37354,"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": 2338707, "tid": 2338707, + "ts": 6197200031797.922, "dur": 4.402, + "args": { + "External id": 37355,"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": 2338707, "tid": 2338707, + "ts": 6197200031798.935, "dur": 2.692, + "args": { + "External id": 37356,"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": 2338707, "tid": 2338707, + "ts": 6197200031800.449, "dur": 1.037, + "args": { + "External id": 37357,"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": 2338707, "tid": 2338707, + "ts": 6197200031802.976, "dur": 44.697, + "args": { + "External id": 37358,"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": 2338707, "tid": 2338707, + "ts": 6197200031803.831, "dur": 43.032, + "args": { + "External id": 37359,"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": 2338707, "tid": 2338707, + "ts": 6197200031855.072, "dur": 4.426, + "args": { + "External id": 37360,"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": 2338707, "tid": 2338707, + "ts": 6197200031856.930, "dur": 0.955, + "args": { + "External id": 37361,"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": 2338707, "tid": 2338707, + "ts": 6197200031866.444, "dur": 1.868, + "args": { + "External id": 37362,"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": 2338707, "tid": 2338707, + "ts": 6197200031877.703, "dur": 8.987, + "args": { + "External id": 37363,"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": 2338707, "tid": 2338707, + "ts": 6197200031879.933, "dur": 6.446, + "args": { + "External id": 37364,"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": 2338707, "tid": 2338707, + "ts": 6197200031988.770, "dur": 291.252, + "args": { + "External id": 37365,"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": 2338707, "tid": 2338707, + "ts": 6197200031991.386, "dur": 2.080, + "args": { + "External id": 37366,"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": 2338707, "tid": 2338707, + "ts": 6197200031994.926, "dur": 284.401, + "args": { + "External id": 37367,"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": 2338707, "tid": 2338707, + "ts": 6197200031996.489, "dur": 0.570, + "args": { + "External id": 37368,"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": 2338707, "tid": 2338707, + "ts": 6197200031998.493, "dur": 24.413, + "args": { + "External id": 37369,"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": 2338707, "tid": 2338707, + "ts": 6197200032025.051, "dur": 4.126, + "args": { + "External id": 37370,"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": 2338707, "tid": 2338707, + "ts": 6197200032027.402, "dur": 1.384, + "args": { + "External id": 37371,"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": 2338707, "tid": 2338707, + "ts": 6197200032030.265, "dur": 77.805, + "args": { + "External id": 37372,"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": 2338707, "tid": 2338707, + "ts": 6197200032031.319, "dur": 1.410, + "args": { + "External id": 37373,"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": 2338707, "tid": 2338707, + "ts": 6197200032034.148, "dur": 72.950, + "args": { + "External id": 37374,"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": 2338707, "tid": 2338707, + "ts": 6197200032041.642, "dur": 2.933, + "args": { + "External id": 37375,"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": 2338707, "tid": 2338707, + "ts": 6197200032110.358, "dur": 26.240, + "args": { + "External id": 37376,"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": 2338707, "tid": 2338707, + "ts": 6197200032180.156, "dur": 14.419, + "args": { + "External id": 37377,"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": 2338707, "tid": 2338707, + "ts": 6197200032197.899, "dur": 13.625, + "args": { + "External id": 37378,"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": 2338707, "tid": 2338707, + "ts": 6197200032213.075, "dur": 12.585, + "args": { + "External id": 37379,"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": 2338707, "tid": 2338707, + "ts": 6197200032228.135, "dur": 20.544, + "args": { + "External id": 37380,"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": 2338707, "tid": 2338707, + "ts": 6197200032230.368, "dur": 1.637, + "args": { + "External id": 37381,"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": 2338707, "tid": 2338707, + "ts": 6197200032233.863, "dur": 1.050, + "args": { + "External id": 37382,"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": 2338707, "tid": 2338707, + "ts": 6197200032252.087, "dur": 12.564, + "args": { + "External id": 37383,"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": 2338707, "tid": 2338707, + "ts": 6197200032265.713, "dur": 12.080, + "args": { + "External id": 37384,"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": 2338707, "tid": 2338707, + "ts": 6197200032290.145, "dur": 2.618, + "args": { + "External id": 37385,"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": 2338707, "tid": 2338707, + "ts": 6197200032303.705, "dur": 4.040, + "args": { + "External id": 37386,"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": 2338707, "tid": 2338707, + "ts": 6197200032306.394, "dur": 0.425, + "args": { + "External id": 37387,"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": 2338707, "tid": 2338707, + "ts": 6197200032387.712, "dur": 70.061, + "args": { + "External id": 37388,"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": 2338707, "tid": 2338707, + "ts": 6197200032463.451, "dur": 7.621, + "args": { + "External id": 37389,"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": 2338707, "tid": 2338707, + "ts": 6197200032466.620, "dur": 3.153, + "args": { + "External id": 37390,"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": 2338707, "tid": 2338707, + "ts": 6197200032474.782, "dur": 29.920, + "args": { + "External id": 37391,"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": 2338707, "tid": 2338707, + "ts": 6197200032509.858, "dur": 6.377, + "args": { + "External id": 37392,"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": 2338707, "tid": 2338707, + "ts": 6197200032511.495, "dur": 3.787, + "args": { + "External id": 37393,"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": 2338707, "tid": 2338707, + "ts": 6197200032513.611, "dur": 1.482, + "args": { + "External id": 37394,"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": 2338707, "tid": 2338707, + "ts": 6197200032518.858, "dur": 43.669, + "args": { + "External id": 37395,"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": 2338707, "tid": 2338707, + "ts": 6197200032520.069, "dur": 41.822, + "args": { + "External id": 37396,"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": 2338707, "tid": 2338707, + "ts": 6197200032566.576, "dur": 16.540, + "args": { + "External id": 37397,"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": 2338707, "tid": 2338707, + "ts": 6197200032591.002, "dur": 3.998, + "args": { + "External id": 37398,"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": 2338707, "tid": 2338707, + "ts": 6197200032592.814, "dur": 1.235, + "args": { + "External id": 37399,"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": 2338707, "tid": 2338707, + "ts": 6197200032599.674, "dur": 47.597, + "args": { + "External id": 37400,"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": 2338707, "tid": 2338707, + "ts": 6197200032600.558, "dur": 4.005, + "args": { + "External id": 37401,"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": 2338707, "tid": 2338707, + "ts": 6197200032601.380, "dur": 2.601, + "args": { + "External id": 37402,"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": 2338707, "tid": 2338707, + "ts": 6197200032603.020, "dur": 0.842, + "args": { + "External id": 37403,"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": 2338707, "tid": 2338707, + "ts": 6197200032607.602, "dur": 39.329, + "args": { + "External id": 37404,"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": 2338707, "tid": 2338707, + "ts": 6197200032608.200, "dur": 38.220, + "args": { + "External id": 37405,"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": 2338707, "tid": 2338707, + "ts": 6197200032652.018, "dur": 4.219, + "args": { + "External id": 37406,"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": 2338707, "tid": 2338707, + "ts": 6197200032653.640, "dur": 1.224, + "args": { + "External id": 37407,"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": 2338707, "tid": 2338707, + "ts": 6197200032661.747, "dur": 1.742, + "args": { + "External id": 37408,"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": 2338707, "tid": 2338707, + "ts": 6197200032671.647, "dur": 6.942, + "args": { + "External id": 37409,"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": 2338707, "tid": 2338707, + "ts": 6197200032674.410, "dur": 3.909, + "args": { + "External id": 37410,"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": 2338707, "tid": 2338707, + "ts": 6197200032820.574, "dur": 204.071, + "args": { + "External id": 37411,"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": 2338707, "tid": 2338707, + "ts": 6197200032823.694, "dur": 5.367, + "args": { + "External id": 37412,"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": 2338707, "tid": 2338707, + "ts": 6197200032830.922, "dur": 193.033, + "args": { + "External id": 37413,"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": 2338707, "tid": 2338707, + "ts": 6197200032832.722, "dur": 0.428, + "args": { + "External id": 37414,"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": 2338707, "tid": 2338707, + "ts": 6197200032834.485, "dur": 27.469, + "args": { + "External id": 37415,"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": 2338707, "tid": 2338707, + "ts": 6197200032863.541, "dur": 6.185, + "args": { + "External id": 37416,"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": 2338707, "tid": 2338707, + "ts": 6197200032868.361, "dur": 1.096, + "args": { + "External id": 37417,"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": 2338707, "tid": 2338707, + "ts": 6197200032870.607, "dur": 26.047, + "args": { + "External id": 37418,"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": 2338707, "tid": 2338707, + "ts": 6197200032871.812, "dur": 1.346, + "args": { + "External id": 37419,"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": 2338707, "tid": 2338707, + "ts": 6197200032876.795, "dur": 19.487, + "args": { + "External id": 37420,"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": 2338707, "tid": 2338707, + "ts": 6197200032879.779, "dur": 2.884, + "args": { + "External id": 37421,"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": 2338707, "tid": 2338707, + "ts": 6197200032898.103, "dur": 22.846, + "args": { + "External id": 37422,"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": 2338707, "tid": 2338707, + "ts": 6197200032922.476, "dur": 14.818, + "args": { + "External id": 37423,"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": 2338707, "tid": 2338707, + "ts": 6197200032940.439, "dur": 15.330, + "args": { + "External id": 37424,"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": 2338707, "tid": 2338707, + "ts": 6197200032957.311, "dur": 13.312, + "args": { + "External id": 37425,"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": 2338707, "tid": 2338707, + "ts": 6197200032972.314, "dur": 25.082, + "args": { + "External id": 37426,"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": 2338707, "tid": 2338707, + "ts": 6197200032974.432, "dur": 1.182, + "args": { + "External id": 37427,"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": 2338707, "tid": 2338707, + "ts": 6197200032980.160, "dur": 2.548, + "args": { + "External id": 37428,"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": 2338707, "tid": 2338707, + "ts": 6197200032998.969, "dur": 12.552, + "args": { + "External id": 37429,"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": 2338707, "tid": 2338707, + "ts": 6197200033012.837, "dur": 10.203, + "args": { + "External id": 37430,"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": 2338707, "tid": 2338707, + "ts": 6197200033032.506, "dur": 2.345, + "args": { + "External id": 37431,"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": 2338707, "tid": 2338707, + "ts": 6197200033045.868, "dur": 3.697, + "args": { + "External id": 37432,"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": 2338707, "tid": 2338707, + "ts": 6197200033048.245, "dur": 0.421, + "args": { + "External id": 37433,"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": 2338707, "tid": 2338707, + "ts": 6197200033184.720, "dur": 71.486, + "args": { + "External id": 37434,"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": 2338707, "tid": 2338707, + "ts": 6197200033262.678, "dur": 9.734, + "args": { + "External id": 37435,"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": 2338707, "tid": 2338707, + "ts": 6197200033269.555, "dur": 1.122, + "args": { + "External id": 37436,"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": 2338707, "tid": 2338707, + "ts": 6197200033274.010, "dur": 30.280, + "args": { + "External id": 37437,"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": 2338707, "tid": 2338707, + "ts": 6197200033309.651, "dur": 14.736, + "args": { + "External id": 37438,"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": 2338707, "tid": 2338707, + "ts": 6197200033317.790, "dur": 5.873, + "args": { + "External id": 37439,"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": 2338707, "tid": 2338707, + "ts": 6197200033319.936, "dur": 3.485, + "args": { + "External id": 37440,"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": 2338707, "tid": 2338707, + "ts": 6197200033327.698, "dur": 48.861, + "args": { + "External id": 37441,"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": 2338707, "tid": 2338707, + "ts": 6197200033331.182, "dur": 44.771, + "args": { + "External id": 37442,"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": 2338707, "tid": 2338707, + "ts": 6197200033380.978, "dur": 15.238, + "args": { + "External id": 37443,"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": 2338707, "tid": 2338707, + "ts": 6197200033402.245, "dur": 3.797, + "args": { + "External id": 37444,"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": 2338707, "tid": 2338707, + "ts": 6197200033404.120, "dur": 1.045, + "args": { + "External id": 37445,"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": 2338707, "tid": 2338707, + "ts": 6197200033410.736, "dur": 47.149, + "args": { + "External id": 37446,"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": 2338707, "tid": 2338707, + "ts": 6197200033411.485, "dur": 6.098, + "args": { + "External id": 37447,"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": 2338707, "tid": 2338707, + "ts": 6197200033412.434, "dur": 4.556, + "args": { + "External id": 37448,"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": 2338707, "tid": 2338707, + "ts": 6197200033416.381, "dur": 0.414, + "args": { + "External id": 37449,"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": 2338707, "tid": 2338707, + "ts": 6197200033418.467, "dur": 38.977, + "args": { + "External id": 37450,"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": 2338707, "tid": 2338707, + "ts": 6197200033419.148, "dur": 37.679, + "args": { + "External id": 37451,"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": 2338707, "tid": 2338707, + "ts": 6197200033461.930, "dur": 3.940, + "args": { + "External id": 37452,"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": 2338707, "tid": 2338707, + "ts": 6197200033463.737, "dur": 0.967, + "args": { + "External id": 37453,"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": 2338707, "tid": 2338707, + "ts": 6197200033472.159, "dur": 2.011, + "args": { + "External id": 37454,"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": 2338707, "tid": 2338707, + "ts": 6197200033484.723, "dur": 7.322, + "args": { + "External id": 37455,"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": 2338707, "tid": 2338707, + "ts": 6197200033487.105, "dur": 4.647, + "args": { + "External id": 37456,"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": 2338707, "tid": 2338707, + "ts": 6197200033579.666, "dur": 220.104, + "args": { + "External id": 37457,"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": 2338707, "tid": 2338707, + "ts": 6197200033582.098, "dur": 2.046, + "args": { + "External id": 37458,"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": 2338707, "tid": 2338707, + "ts": 6197200033588.176, "dur": 211.067, + "args": { + "External id": 37459,"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": 2338707, "tid": 2338707, + "ts": 6197200033589.759, "dur": 0.580, + "args": { + "External id": 37460,"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": 2338707, "tid": 2338707, + "ts": 6197200033593.468, "dur": 20.404, + "args": { + "External id": 37461,"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": 2338707, "tid": 2338707, + "ts": 6197200033615.681, "dur": 5.052, + "args": { + "External id": 37462,"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": 2338707, "tid": 2338707, + "ts": 6197200033617.727, "dur": 2.778, + "args": { + "External id": 37463,"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": 2338707, "tid": 2338707, + "ts": 6197200033621.834, "dur": 20.143, + "args": { + "External id": 37464,"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": 2338707, "tid": 2338707, + "ts": 6197200033623.224, "dur": 0.949, + "args": { + "External id": 37465,"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": 2338707, "tid": 2338707, + "ts": 6197200033625.460, "dur": 16.286, + "args": { + "External id": 37466,"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": 2338707, "tid": 2338707, + "ts": 6197200033628.045, "dur": 2.505, + "args": { + "External id": 37467,"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": 2338707, "tid": 2338707, + "ts": 6197200033643.351, "dur": 21.352, + "args": { + "External id": 37468,"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": 2338707, "tid": 2338707, + "ts": 6197200033665.973, "dur": 12.598, + "args": { + "External id": 37469,"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": 2338707, "tid": 2338707, + "ts": 6197200033681.099, "dur": 12.541, + "args": { + "External id": 37470,"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": 2338707, "tid": 2338707, + "ts": 6197200033695.044, "dur": 39.310, + "args": { + "External id": 37471,"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": 2338707, "tid": 2338707, + "ts": 6197200033740.874, "dur": 30.812, + "args": { + "External id": 37472,"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": 2338707, "tid": 2338707, + "ts": 6197200033744.014, "dur": 2.613, + "args": { + "External id": 37473,"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": 2338707, "tid": 2338707, + "ts": 6197200033749.599, "dur": 3.375, + "args": { + "External id": 37474,"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": 2338707, "tid": 2338707, + "ts": 6197200033773.682, "dur": 12.178, + "args": { + "External id": 37475,"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": 2338707, "tid": 2338707, + "ts": 6197200033786.879, "dur": 11.113, + "args": { + "External id": 37476,"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": 2338707, "tid": 2338707, + "ts": 6197200033809.123, "dur": 2.958, + "args": { + "External id": 37477,"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": 2338707, "tid": 2338707, + "ts": 6197200033822.761, "dur": 3.793, + "args": { + "External id": 37478,"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": 2338707, "tid": 2338707, + "ts": 6197200033825.119, "dur": 0.460, + "args": { + "External id": 37479,"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": 2338707, "tid": 2338707, + "ts": 6197200033903.814, "dur": 61.597, + "args": { + "External id": 37480,"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": 2338707, "tid": 2338707, + "ts": 6197200033971.047, "dur": 5.261, + "args": { + "External id": 37481,"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": 2338707, "tid": 2338707, + "ts": 6197200033974.000, "dur": 1.291, + "args": { + "External id": 37482,"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": 2338707, "tid": 2338707, + "ts": 6197200033977.956, "dur": 25.252, + "args": { + "External id": 37483,"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": 2338707, "tid": 2338707, + "ts": 6197200034007.930, "dur": 8.911, + "args": { + "External id": 37484,"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": 2338707, "tid": 2338707, + "ts": 6197200034009.751, "dur": 6.374, + "args": { + "External id": 37485,"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": 2338707, "tid": 2338707, + "ts": 6197200034014.050, "dur": 1.899, + "args": { + "External id": 37486,"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": 2338707, "tid": 2338707, + "ts": 6197200034019.848, "dur": 92.298, + "args": { + "External id": 37487,"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": 2338707, "tid": 2338707, + "ts": 6197200034021.122, "dur": 89.630, + "args": { + "External id": 37488,"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": 2338707, "tid": 2338707, + "ts": 6197200034118.813, "dur": 16.216, + "args": { + "External id": 37489,"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": 2338707, "tid": 2338707, + "ts": 6197200034142.102, "dur": 5.219, + "args": { + "External id": 37490,"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": 2338707, "tid": 2338707, + "ts": 6197200034145.197, "dur": 0.992, + "args": { + "External id": 37491,"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": 2338707, "tid": 2338707, + "ts": 6197200034152.222, "dur": 51.785, + "args": { + "External id": 37492,"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": 2338707, "tid": 2338707, + "ts": 6197200034155.650, "dur": 4.382, + "args": { + "External id": 37493,"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": 2338707, "tid": 2338707, + "ts": 6197200034156.779, "dur": 2.584, + "args": { + "External id": 37494,"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": 2338707, "tid": 2338707, + "ts": 6197200034158.176, "dur": 1.075, + "args": { + "External id": 37495,"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": 2338707, "tid": 2338707, + "ts": 6197200034160.849, "dur": 42.779, + "args": { + "External id": 37496,"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": 2338707, "tid": 2338707, + "ts": 6197200034161.456, "dur": 41.656, + "args": { + "External id": 37497,"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": 2338707, "tid": 2338707, + "ts": 6197200034208.934, "dur": 3.583, + "args": { + "External id": 37498,"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": 2338707, "tid": 2338707, + "ts": 6197200034210.669, "dur": 0.519, + "args": { + "External id": 37499,"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": 2338707, "tid": 2338707, + "ts": 6197200034219.495, "dur": 1.854, + "args": { + "External id": 37500,"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": 2338707, "tid": 2338707, + "ts": 6197200034232.589, "dur": 7.254, + "args": { + "External id": 37501,"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": 2338707, "tid": 2338707, + "ts": 6197200034234.640, "dur": 4.899, + "args": { + "External id": 37502,"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": 2338707, "tid": 2338707, + "ts": 6197200034329.672, "dur": 186.616, + "args": { + "External id": 37503,"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": 2338707, "tid": 2338707, + "ts": 6197200034334.162, "dur": 2.124, + "args": { + "External id": 37504,"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": 2338707, "tid": 2338707, + "ts": 6197200034337.665, "dur": 178.306, + "args": { + "External id": 37505,"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": 2338707, "tid": 2338707, + "ts": 6197200034338.958, "dur": 0.490, + "args": { + "External id": 37506,"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": 2338707, "tid": 2338707, + "ts": 6197200034343.713, "dur": 20.402, + "args": { + "External id": 37507,"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": 2338707, "tid": 2338707, + "ts": 6197200034365.939, "dur": 6.093, + "args": { + "External id": 37508,"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": 2338707, "tid": 2338707, + "ts": 6197200034370.570, "dur": 1.193, + "args": { + "External id": 37509,"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": 2338707, "tid": 2338707, + "ts": 6197200034373.061, "dur": 21.354, + "args": { + "External id": 37510,"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": 2338707, "tid": 2338707, + "ts": 6197200034374.088, "dur": 1.118, + "args": { + "External id": 37511,"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": 2338707, "tid": 2338707, + "ts": 6197200034376.408, "dur": 17.720, + "args": { + "External id": 37512,"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": 2338707, "tid": 2338707, + "ts": 6197200034379.053, "dur": 3.134, + "args": { + "External id": 37513,"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": 2338707, "tid": 2338707, + "ts": 6197200034395.949, "dur": 19.682, + "args": { + "External id": 37514,"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": 2338707, "tid": 2338707, + "ts": 6197200034417.064, "dur": 15.798, + "args": { + "External id": 37515,"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": 2338707, "tid": 2338707, + "ts": 6197200034435.861, "dur": 12.830, + "args": { + "External id": 37516,"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": 2338707, "tid": 2338707, + "ts": 6197200034457.265, "dur": 11.761, + "args": { + "External id": 37517,"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": 2338707, "tid": 2338707, + "ts": 6197200034470.959, "dur": 18.945, + "args": { + "External id": 37518,"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": 2338707, "tid": 2338707, + "ts": 6197200034472.712, "dur": 1.221, + "args": { + "External id": 37519,"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": 2338707, "tid": 2338707, + "ts": 6197200034475.941, "dur": 0.790, + "args": { + "External id": 37520,"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": 2338707, "tid": 2338707, + "ts": 6197200034490.975, "dur": 11.386, + "args": { + "External id": 37521,"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": 2338707, "tid": 2338707, + "ts": 6197200034503.558, "dur": 11.238, + "args": { + "External id": 37522,"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": 2338707, "tid": 2338707, + "ts": 6197200034525.187, "dur": 1.885, + "args": { + "External id": 37523,"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": 2338707, "tid": 2338707, + "ts": 6197200034535.344, "dur": 4.160, + "args": { + "External id": 37524,"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": 2338707, "tid": 2338707, + "ts": 6197200034538.040, "dur": 0.592, + "args": { + "External id": 37525,"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": 2338707, "tid": 2338707, + "ts": 6197200034606.099, "dur": 55.816, + "args": { + "External id": 37526,"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": 2338707, "tid": 2338707, + "ts": 6197200034667.328, "dur": 4.753, + "args": { + "External id": 37527,"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": 2338707, "tid": 2338707, + "ts": 6197200034670.211, "dur": 0.721, + "args": { + "External id": 37528,"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": 2338707, "tid": 2338707, + "ts": 6197200034673.575, "dur": 45.669, + "args": { + "External id": 37529,"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": 2338707, "tid": 2338707, + "ts": 6197200034727.930, "dur": 13.774, + "args": { + "External id": 37530,"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": 2338707, "tid": 2338707, + "ts": 6197200034732.754, "dur": 7.852, + "args": { + "External id": 37531,"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": 2338707, "tid": 2338707, + "ts": 6197200034736.068, "dur": 4.098, + "args": { + "External id": 37532,"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": 2338707, "tid": 2338707, + "ts": 6197200034745.832, "dur": 58.812, + "args": { + "External id": 37533,"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": 2338707, "tid": 2338707, + "ts": 6197200034747.536, "dur": 56.399, + "args": { + "External id": 37534,"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": 2338707, "tid": 2338707, + "ts": 6197200034809.205, "dur": 17.815, + "args": { + "External id": 37535,"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": 2338707, "tid": 2338707, + "ts": 6197200034833.663, "dur": 6.544, + "args": { + "External id": 37536,"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": 2338707, "tid": 2338707, + "ts": 6197200034838.378, "dur": 0.822, + "args": { + "External id": 37537,"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": 2338707, "tid": 2338707, + "ts": 6197200034844.786, "dur": 45.887, + "args": { + "External id": 37538,"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": 2338707, "tid": 2338707, + "ts": 6197200034845.740, "dur": 3.633, + "args": { + "External id": 37539,"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": 2338707, "tid": 2338707, + "ts": 6197200034846.568, "dur": 2.199, + "args": { + "External id": 37540,"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": 2338707, "tid": 2338707, + "ts": 6197200034847.900, "dur": 0.728, + "args": { + "External id": 37541,"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": 2338707, "tid": 2338707, + "ts": 6197200034850.206, "dur": 40.047, + "args": { + "External id": 37542,"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": 2338707, "tid": 2338707, + "ts": 6197200034850.893, "dur": 38.748, + "args": { + "External id": 37543,"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": 2338707, "tid": 2338707, + "ts": 6197200034897.267, "dur": 3.814, + "args": { + "External id": 37544,"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": 2338707, "tid": 2338707, + "ts": 6197200034899.136, "dur": 0.491, + "args": { + "External id": 37545,"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": 2338707, "tid": 2338707, + "ts": 6197200034908.013, "dur": 1.853, + "args": { + "External id": 37546,"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": 2338707, "tid": 2338707, + "ts": 6197200034918.891, "dur": 7.256, + "args": { + "External id": 37547,"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": 2338707, "tid": 2338707, + "ts": 6197200034921.447, "dur": 4.438, + "args": { + "External id": 37548,"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": 2338707, "tid": 2338707, + "ts": 6197200035027.235, "dur": 243.945, + "args": { + "External id": 37549,"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": 2338707, "tid": 2338707, + "ts": 6197200035029.324, "dur": 2.219, + "args": { + "External id": 37550,"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": 2338707, "tid": 2338707, + "ts": 6197200035035.473, "dur": 235.173, + "args": { + "External id": 37551,"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": 2338707, "tid": 2338707, + "ts": 6197200035036.727, "dur": 0.345, + "args": { + "External id": 37552,"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": 2338707, "tid": 2338707, + "ts": 6197200035038.175, "dur": 61.019, + "args": { + "External id": 37553,"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": 2338707, "tid": 2338707, + "ts": 6197200035102.335, "dur": 5.666, + "args": { + "External id": 37554,"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": 2338707, "tid": 2338707, + "ts": 6197200035104.837, "dur": 2.904, + "args": { + "External id": 37555,"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": 2338707, "tid": 2338707, + "ts": 6197200035109.328, "dur": 28.693, + "args": { + "External id": 37556,"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": 2338707, "tid": 2338707, + "ts": 6197200035110.457, "dur": 1.808, + "args": { + "External id": 37557,"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": 2338707, "tid": 2338707, + "ts": 6197200035115.794, "dur": 21.972, + "args": { + "External id": 37558,"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": 2338707, "tid": 2338707, + "ts": 6197200035119.155, "dur": 3.150, + "args": { + "External id": 37559,"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": 2338707, "tid": 2338707, + "ts": 6197200035139.797, "dur": 24.531, + "args": { + "External id": 37560,"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": 2338707, "tid": 2338707, + "ts": 6197200035165.897, "dur": 14.150, + "args": { + "External id": 37561,"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": 2338707, "tid": 2338707, + "ts": 6197200035182.662, "dur": 16.353, + "args": { + "External id": 37562,"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": 2338707, "tid": 2338707, + "ts": 6197200035200.807, "dur": 12.959, + "args": { + "External id": 37563,"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": 2338707, "tid": 2338707, + "ts": 6197200035215.431, "dur": 24.393, + "args": { + "External id": 37564,"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": 2338707, "tid": 2338707, + "ts": 6197200035217.628, "dur": 1.431, + "args": { + "External id": 37565,"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": 2338707, "tid": 2338707, + "ts": 6197200035221.250, "dur": 2.868, + "args": { + "External id": 37566,"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": 2338707, "tid": 2338707, + "ts": 6197200035243.632, "dur": 12.594, + "args": { + "External id": 37567,"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": 2338707, "tid": 2338707, + "ts": 6197200035257.282, "dur": 12.335, + "args": { + "External id": 37568,"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": 2338707, "tid": 2338707, + "ts": 6197200035280.073, "dur": 2.269, + "args": { + "External id": 37569,"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": 2338707, "tid": 2338707, + "ts": 6197200035292.291, "dur": 4.149, + "args": { + "External id": 37570,"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": 2338707, "tid": 2338707, + "ts": 6197200035295.057, "dur": 0.552, + "args": { + "External id": 37571,"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": 2338707, "tid": 2338707, + "ts": 6197200035370.574, "dur": 62.123, + "args": { + "External id": 37572,"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": 2338707, "tid": 2338707, + "ts": 6197200035438.052, "dur": 4.957, + "args": { + "External id": 37573,"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": 2338707, "tid": 2338707, + "ts": 6197200035440.772, "dur": 0.953, + "args": { + "External id": 37574,"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": 2338707, "tid": 2338707, + "ts": 6197200035447.422, "dur": 27.208, + "args": { + "External id": 37575,"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": 2338707, "tid": 2338707, + "ts": 6197200035479.387, "dur": 7.003, + "args": { + "External id": 37576,"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": 2338707, "tid": 2338707, + "ts": 6197200035481.162, "dur": 4.428, + "args": { + "External id": 37577,"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": 2338707, "tid": 2338707, + "ts": 6197200035483.092, "dur": 2.316, + "args": { + "External id": 37578,"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": 2338707, "tid": 2338707, + "ts": 6197200035489.454, "dur": 42.991, + "args": { + "External id": 37579,"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": 2338707, "tid": 2338707, + "ts": 6197200035490.524, "dur": 41.223, + "args": { + "External id": 37580,"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": 2338707, "tid": 2338707, + "ts": 6197200035536.431, "dur": 15.103, + "args": { + "External id": 37581,"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": 2338707, "tid": 2338707, + "ts": 6197200035558.560, "dur": 24.980, + "args": { + "External id": 37582,"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": 2338707, "tid": 2338707, + "ts": 6197200035560.867, "dur": 22.303, + "args": { + "External id": 37583,"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": 2338707, "tid": 2338707, + "ts": 6197200035566.346, "dur": 1.237, + "args": { + "External id": 37584,"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": 2338707, "tid": 2338707, + "ts": 6197200035588.789, "dur": 26.225, + "args": { + "External id": 37585,"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": 2338707, "tid": 2338707, + "ts": 6197200035590.779, "dur": 24.037, + "args": { + "External id": 37586,"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": 2338707, "tid": 2338707, + "ts": 6197200035595.527, "dur": 3.613, + "args": { + "External id": 37587,"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": 2338707, "tid": 2338707, + "ts": 6197200035600.431, "dur": 13.906, + "args": { + "External id": 37588,"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": 2338707, "tid": 2338707, + "ts": 6197200035626.661, "dur": 7.419, + "args": { + "External id": 37589,"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": 2338707, "tid": 2338707, + "ts": 6197200035631.067, "dur": 2.684, + "args": { + "External id": 37590,"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": 2338707, "tid": 2338707, + "ts": 6197200035635.137, "dur": 1.584, + "args": { + "External id": 37591,"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": 2338707, "tid": 2338707, + "ts": 6197200035636.056, "dur": 0.547, + "args": { + "External id": 37592,"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": 2338707, "tid": 2338707, + "ts": 6197200035682.869, "dur": 41.903, + "args": { + "External id": 37593,"Sequence number": 480219, "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": 2338707, "tid": 2338707, + "ts": 6197200035729.014, "dur": 20.841, + "args": { + "External id": 37594,"Sequence number": 480220, "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": 2338707, "tid": 2338707, "ts": 6197200035729.014, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward", "pid": 2338707, "tid": 2338707, + "ts": 6197200035918.672, "dur": 50.090, + "args": { + "External id": 37595,"Record function id": 0, "Ev Idx": 20767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::div", "pid": 2338707, "tid": 2338707, + "ts": 6197200036159.888, "dur": 45.246, + "args": { + "External id": 37596,"Sequence number": 480221, "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": 2338707, "tid": 2338707, "ts": 6197200036159.888, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ones_like", "pid": 2338707, "tid": 2338707, + "ts": 6197200036241.621, "dur": 29.103, + "args": { + "External id": 37597,"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": 2338707, "tid": 2338707, + "ts": 6197200036243.329, "dur": 10.459, + "args": { + "External id": 37598,"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": 2338707, "tid": 2338707, + "ts": 6197200036248.465, "dur": 4.550, + "args": { + "External id": 37599,"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": 2338707, "tid": 2338707, + "ts": 6197200036255.551, "dur": 14.882, + "args": { + "External id": 37600,"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": 2338707, "tid": 2338707, + "ts": 6197202106943.313, "dur": 203.273, + "args": { + "External id": 37601,"Sequence number": 480222, "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": 2338707, "tid": 2338707, + "ts": 6197202107163.398, "dur": 27.139, + "args": { + "External id": 37602,"Sequence number": 480223, "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": 2338707, "tid": 2338707, + "ts": 6197202107200.597, "dur": 24.778, + "args": { + "External id": 37603,"Sequence number": 480224, "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": 2338707, "tid": 2338707, + "ts": 6197202107229.025, "dur": 17.649, + "args": { + "External id": 37604,"Sequence number": 480225, "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": 2338707, "tid": 2338707, + "ts": 6197202108386.199, "dur": 54.947, + "args": { + "External id": 37605,"Sequence number": 480226, "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": 2338707, "tid": 2338707, + "ts": 6197202108445.434, "dur": 19.128, + "args": { + "External id": 37606,"Sequence number": 480227, "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": 2338707, "tid": 2338707, + "ts": 6197202108473.675, "dur": 17.722, + "args": { + "External id": 37607,"Sequence number": 480228, "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": 2338707, "tid": 2338707, + "ts": 6197202108493.222, "dur": 14.701, + "args": { + "External id": 37608,"Sequence number": 480229, "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": 2338707, "tid": 2338707, + "ts": 6197202110888.282, "dur": 3373.987, + "args": { + "External id": 37609,"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": 2338707, "tid": 2338707, + "ts": 6197202111539.223, "dur": 1220.091, + "args": { + "External id": 37610,"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": 2338707, "tid": 2338707, + "ts": 6197202111561.049, "dur": 84.042, + "args": { + "External id": 37611,"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": 2338707, "tid": 2338707, + "ts": 6197202111565.148, "dur": 17.658, + "args": { + "External id": 37612,"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": 2338707, "tid": 2338707, + "ts": 6197202111588.218, "dur": 56.582, + "args": { + "External id": 37613,"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": 2338707, "tid": 2338707, + "ts": 6197202111592.991, "dur": 51.189, + "args": { + "External id": 37614,"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": 2338707, "tid": 2338707, + "ts": 6197202114297.625, "dur": 4.101, + "args": { + "External id": 37615,"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": 2338707, "tid": 2338707, + "ts": 6197202114304.291, "dur": 0.473, + "args": { + "External id": 37616,"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": 2338707, "tid": 2338707, + "ts": 6197202114306.202, "dur": 0.239, + "args": { + "External id": 37617,"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": 2338707, "tid": 2338707, + "ts": 6197202114307.610, "dur": 0.255, + "args": { + "External id": 37618,"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": 2338707, "tid": 2338707, + "ts": 6197202114309.035, "dur": 0.386, + "args": { + "External id": 37619,"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": 2338707, "tid": 2338707, + "ts": 6197202114310.775, "dur": 0.392, + "args": { + "External id": 37620,"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": 2338707, "tid": 2338707, + "ts": 6197202114312.264, "dur": 0.462, + "args": { + "External id": 37621,"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": 2338707, "tid": 2338707, + "ts": 6197202114315.968, "dur": 0.451, + "args": { + "External id": 37622,"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": 2338707, "tid": 2338707, + "ts": 6197202114317.390, "dur": 0.396, + "args": { + "External id": 37623,"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": 2338707, "tid": 2338707, + "ts": 6197202114319.249, "dur": 0.364, + "args": { + "External id": 37624,"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": 2338707, "tid": 2338707, + "ts": 6197202114320.557, "dur": 0.209, + "args": { + "External id": 37625,"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": 2338707, "tid": 2338707, + "ts": 6197202114321.668, "dur": 0.209, + "args": { + "External id": 37626,"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": 2338707, "tid": 2338707, + "ts": 6197202114322.745, "dur": 0.205, + "args": { + "External id": 37627,"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": 2338707, "tid": 2338707, + "ts": 6197202114324.014, "dur": 0.213, + "args": { + "External id": 37628,"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": 2338707, "tid": 2338707, + "ts": 6197202114324.975, "dur": 0.214, + "args": { + "External id": 37629,"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": 2338707, "tid": 2338707, + "ts": 6197202114328.288, "dur": 0.237, + "args": { + "External id": 37630,"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": 2338707, "tid": 2338707, + "ts": 6197202114329.613, "dur": 0.222, + "args": { + "External id": 37631,"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": 2338707, "tid": 2338707, + "ts": 6197202114330.875, "dur": 0.373, + "args": { + "External id": 37632,"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": 2338707, "tid": 2338707, + "ts": 6197202114332.350, "dur": 0.180, + "args": { + "External id": 37633,"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": 2338707, "tid": 2338707, + "ts": 6197202114333.437, "dur": 0.253, + "args": { + "External id": 37634,"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": 2338707, "tid": 2338707, + "ts": 6197202114334.839, "dur": 0.227, + "args": { + "External id": 37635,"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": 2338707, "tid": 2338707, + "ts": 6197202114336.048, "dur": 0.219, + "args": { + "External id": 37636,"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": 2338707, "tid": 2338707, + "ts": 6197202114336.993, "dur": 0.215, + "args": { + "External id": 37637,"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": 2338707, "tid": 2338707, + "ts": 6197202114340.540, "dur": 0.417, + "args": { + "External id": 37638,"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": 2338707, "tid": 2338707, + "ts": 6197202114341.774, "dur": 0.404, + "args": { + "External id": 37639,"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": 2338707, "tid": 2338707, + "ts": 6197202114343.455, "dur": 0.333, + "args": { + "External id": 37640,"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": 2338707, "tid": 2338707, + "ts": 6197202114344.727, "dur": 0.217, + "args": { + "External id": 37641,"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": 2338707, "tid": 2338707, + "ts": 6197202114345.904, "dur": 0.249, + "args": { + "External id": 37642,"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": 2338707, "tid": 2338707, + "ts": 6197202114347.173, "dur": 0.376, + "args": { + "External id": 37643,"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": 2338707, "tid": 2338707, + "ts": 6197202114348.343, "dur": 0.213, + "args": { + "External id": 37644,"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": 2338707, "tid": 2338707, + "ts": 6197202114349.270, "dur": 0.334, + "args": { + "External id": 37645,"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": 2338707, "tid": 2338707, + "ts": 6197202114352.488, "dur": 0.327, + "args": { + "External id": 37646,"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": 2338707, "tid": 2338707, + "ts": 6197202114353.706, "dur": 0.214, + "args": { + "External id": 37647,"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": 2338707, "tid": 2338707, + "ts": 6197202114355.046, "dur": 0.198, + "args": { + "External id": 37648,"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": 2338707, "tid": 2338707, + "ts": 6197202114356.049, "dur": 0.218, + "args": { + "External id": 37649,"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": 2338707, "tid": 2338707, + "ts": 6197202114357.142, "dur": 0.197, + "args": { + "External id": 37650,"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": 2338707, "tid": 2338707, + "ts": 6197202114358.127, "dur": 0.363, + "args": { + "External id": 37651,"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": 2338707, "tid": 2338707, + "ts": 6197202114359.590, "dur": 0.243, + "args": { + "External id": 37652,"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": 2338707, "tid": 2338707, + "ts": 6197202114360.680, "dur": 0.222, + "args": { + "External id": 37653,"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": 2338707, "tid": 2338707, + "ts": 6197202114364.283, "dur": 0.432, + "args": { + "External id": 37654,"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": 2338707, "tid": 2338707, + "ts": 6197202114365.544, "dur": 0.223, + "args": { + "External id": 37655,"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": 2338707, "tid": 2338707, + "ts": 6197202114367.017, "dur": 0.459, + "args": { + "External id": 37656,"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": 2338707, "tid": 2338707, + "ts": 6197202114369.528, "dur": 0.203, + "args": { + "External id": 37657,"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": 2338707, "tid": 2338707, + "ts": 6197202114370.462, "dur": 0.213, + "args": { + "External id": 37658,"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": 2338707, "tid": 2338707, + "ts": 6197202114371.610, "dur": 0.476, + "args": { + "External id": 37659,"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": 2338707, "tid": 2338707, + "ts": 6197202114373.630, "dur": 0.209, + "args": { + "External id": 37660,"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": 2338707, "tid": 2338707, + "ts": 6197202114374.562, "dur": 0.213, + "args": { + "External id": 37661,"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": 2338707, "tid": 2338707, + "ts": 6197202114377.767, "dur": 0.391, + "args": { + "External id": 37662,"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": 2338707, "tid": 2338707, + "ts": 6197202114378.884, "dur": 0.406, + "args": { + "External id": 37663,"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": 2338707, "tid": 2338707, + "ts": 6197202114380.433, "dur": 0.200, + "args": { + "External id": 37664,"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": 2338707, "tid": 2338707, + "ts": 6197202114381.345, "dur": 0.202, + "args": { + "External id": 37665,"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": 2338707, "tid": 2338707, + "ts": 6197202114382.255, "dur": 0.398, + "args": { + "External id": 37666,"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": 2338707, "tid": 2338707, + "ts": 6197202114383.830, "dur": 0.195, + "args": { + "External id": 37667,"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": 2338707, "tid": 2338707, + "ts": 6197202114385.176, "dur": 0.214, + "args": { + "External id": 37668,"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": 2338707, "tid": 2338707, + "ts": 6197202114386.115, "dur": 0.204, + "args": { + "External id": 37669,"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": 2338707, "tid": 2338707, + "ts": 6197202114389.546, "dur": 0.206, + "args": { + "External id": 37670,"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": 2338707, "tid": 2338707, + "ts": 6197202114390.528, "dur": 0.202, + "args": { + "External id": 37671,"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": 2338707, "tid": 2338707, + "ts": 6197202114391.555, "dur": 0.194, + "args": { + "External id": 37672,"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": 2338707, "tid": 2338707, + "ts": 6197202114392.516, "dur": 0.203, + "args": { + "External id": 37673,"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": 2338707, "tid": 2338707, + "ts": 6197202114393.423, "dur": 0.201, + "args": { + "External id": 37674,"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": 2338707, "tid": 2338707, + "ts": 6197202114394.404, "dur": 0.206, + "args": { + "External id": 37675,"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": 2338707, "tid": 2338707, + "ts": 6197202114395.531, "dur": 0.217, + "args": { + "External id": 37676,"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": 2338707, "tid": 2338707, + "ts": 6197202114396.488, "dur": 0.440, + "args": { + "External id": 37677,"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": 2338707, "tid": 2338707, + "ts": 6197202114400.007, "dur": 0.450, + "args": { + "External id": 37678,"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": 2338707, "tid": 2338707, + "ts": 6197202114401.161, "dur": 0.432, + "args": { + "External id": 37679,"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": 2338707, "tid": 2338707, + "ts": 6197202114402.893, "dur": 0.204, + "args": { + "External id": 37680,"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": 2338707, "tid": 2338707, + "ts": 6197202114403.882, "dur": 0.205, + "args": { + "External id": 37681,"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": 2338707, "tid": 2338707, + "ts": 6197202114404.997, "dur": 0.436, + "args": { + "External id": 37682,"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": 2338707, "tid": 2338707, + "ts": 6197202114406.324, "dur": 0.416, + "args": { + "External id": 37683,"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": 2338707, "tid": 2338707, + "ts": 6197202114407.733, "dur": 0.206, + "args": { + "External id": 37684,"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": 2338707, "tid": 2338707, + "ts": 6197202114408.697, "dur": 0.429, + "args": { + "External id": 37685,"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": 2338707, "tid": 2338707, + "ts": 6197202114411.905, "dur": 0.385, + "args": { + "External id": 37686,"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": 2338707, "tid": 2338707, + "ts": 6197202114412.988, "dur": 0.247, + "args": { + "External id": 37687,"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": 2338707, "tid": 2338707, + "ts": 6197202114413.954, "dur": 0.202, + "args": { + "External id": 37688,"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": 2338707, "tid": 2338707, + "ts": 6197202114415.088, "dur": 0.213, + "args": { + "External id": 37689,"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": 2338707, "tid": 2338707, + "ts": 6197202114416.070, "dur": 0.205, + "args": { + "External id": 37690,"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": 2338707, "tid": 2338707, + "ts": 6197202114417.013, "dur": 0.200, + "args": { + "External id": 37691,"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": 2338707, "tid": 2338707, + "ts": 6197202114418.906, "dur": 0.406, + "args": { + "External id": 37692,"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": 2338707, "tid": 2338707, + "ts": 6197202114420.038, "dur": 0.355, + "args": { + "External id": 37693,"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": 2338707, "tid": 2338707, + "ts": 6197202114423.292, "dur": 0.237, + "args": { + "External id": 37694,"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": 2338707, "tid": 2338707, + "ts": 6197202114424.285, "dur": 0.357, + "args": { + "External id": 37695,"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": 2338707, "tid": 2338707, + "ts": 6197202114425.347, "dur": 0.245, + "args": { + "External id": 37696,"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": 2338707, "tid": 2338707, + "ts": 6197202114426.275, "dur": 0.200, + "args": { + "External id": 37697,"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": 2338707, "tid": 2338707, + "ts": 6197202114427.195, "dur": 0.197, + "args": { + "External id": 37698,"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": 2338707, "tid": 2338707, + "ts": 6197202114428.119, "dur": 0.209, + "args": { + "External id": 37699,"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": 2338707, "tid": 2338707, + "ts": 6197202114429.054, "dur": 0.201, + "args": { + "External id": 37700,"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": 2338707, "tid": 2338707, + "ts": 6197202114429.997, "dur": 0.198, + "args": { + "External id": 37701,"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": 2338707, "tid": 2338707, + "ts": 6197202114433.022, "dur": 0.204, + "args": { + "External id": 37702,"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": 2338707, "tid": 2338707, + "ts": 6197202114433.923, "dur": 0.199, + "args": { + "External id": 37703,"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": 2338707, "tid": 2338707, + "ts": 6197202114434.989, "dur": 0.199, + "args": { + "External id": 37704,"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": 2338707, "tid": 2338707, + "ts": 6197202114435.923, "dur": 0.201, + "args": { + "External id": 37705,"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": 2338707, "tid": 2338707, + "ts": 6197202114437.053, "dur": 0.202, + "args": { + "External id": 37706,"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": 2338707, "tid": 2338707, + "ts": 6197202114437.942, "dur": 0.198, + "args": { + "External id": 37707,"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": 2338707, "tid": 2338707, + "ts": 6197202114439.413, "dur": 0.204, + "args": { + "External id": 37708,"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": 2338707, "tid": 2338707, + "ts": 6197202114440.428, "dur": 0.203, + "args": { + "External id": 37709,"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": 2338707, "tid": 2338707, + "ts": 6197202114443.890, "dur": 0.206, + "args": { + "External id": 37710,"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": 2338707, "tid": 2338707, + "ts": 6197202114444.855, "dur": 0.424, + "args": { + "External id": 37711,"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": 2338707, "tid": 2338707, + "ts": 6197202114446.129, "dur": 0.419, + "args": { + "External id": 37712,"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": 2338707, "tid": 2338707, + "ts": 6197202114447.291, "dur": 0.211, + "args": { + "External id": 37713,"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": 2338707, "tid": 2338707, + "ts": 6197202114448.236, "dur": 0.414, + "args": { + "External id": 37714,"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": 2338707, "tid": 2338707, + "ts": 6197202114449.392, "dur": 0.379, + "args": { + "External id": 37715,"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": 2338707, "tid": 2338707, + "ts": 6197202114450.536, "dur": 0.414, + "args": { + "External id": 37716,"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": 2338707, "tid": 2338707, + "ts": 6197202114451.652, "dur": 0.414, + "args": { + "External id": 37717,"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": 2338707, "tid": 2338707, + "ts": 6197202114454.704, "dur": 0.430, + "args": { + "External id": 37718,"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": 2338707, "tid": 2338707, + "ts": 6197202114455.909, "dur": 0.425, + "args": { + "External id": 37719,"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": 2338707, "tid": 2338707, + "ts": 6197202114457.202, "dur": 0.528, + "args": { + "External id": 37720,"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": 2338707, "tid": 2338707, + "ts": 6197202114458.452, "dur": 0.203, + "args": { + "External id": 37721,"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": 2338707, "tid": 2338707, + "ts": 6197202114459.526, "dur": 0.198, + "args": { + "External id": 37722,"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": 2338707, "tid": 2338707, + "ts": 6197202114460.429, "dur": 0.206, + "args": { + "External id": 37723,"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": 2338707, "tid": 2338707, + "ts": 6197202114461.957, "dur": 0.205, + "args": { + "External id": 37724,"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": 2338707, "tid": 2338707, + "ts": 6197202114462.880, "dur": 0.198, + "args": { + "External id": 37725,"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": 2338707, "tid": 2338707, + "ts": 6197202114465.984, "dur": 0.205, + "args": { + "External id": 37726,"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": 2338707, "tid": 2338707, + "ts": 6197202114466.975, "dur": 0.195, + "args": { + "External id": 37727,"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": 2338707, "tid": 2338707, + "ts": 6197202114467.898, "dur": 0.200, + "args": { + "External id": 37728,"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": 2338707, "tid": 2338707, + "ts": 6197202114469.059, "dur": 0.207, + "args": { + "External id": 37729,"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": 2338707, "tid": 2338707, + "ts": 6197202114469.963, "dur": 0.212, + "args": { + "External id": 37730,"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": 2338707, "tid": 2338707, + "ts": 6197202114470.880, "dur": 0.203, + "args": { + "External id": 37731,"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": 2338707, "tid": 2338707, + "ts": 6197202114472.016, "dur": 0.273, + "args": { + "External id": 37732,"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": 2338707, "tid": 2338707, + "ts": 6197202114473.013, "dur": 0.206, + "args": { + "External id": 37733,"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": 2338707, "tid": 2338707, + "ts": 6197202114475.886, "dur": 0.393, + "args": { + "External id": 37734,"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": 2338707, "tid": 2338707, + "ts": 6197202114476.986, "dur": 0.206, + "args": { + "External id": 37735,"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": 2338707, "tid": 2338707, + "ts": 6197202114477.929, "dur": 0.393, + "args": { + "External id": 37736,"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": 2338707, "tid": 2338707, + "ts": 6197202114479.026, "dur": 0.209, + "args": { + "External id": 37737,"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": 2338707, "tid": 2338707, + "ts": 6197202114479.955, "dur": 0.210, + "args": { + "External id": 37738,"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": 2338707, "tid": 2338707, + "ts": 6197202114480.989, "dur": 0.210, + "args": { + "External id": 37739,"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": 2338707, "tid": 2338707, + "ts": 6197202114482.151, "dur": 0.208, + "args": { + "External id": 37740,"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": 2338707, "tid": 2338707, + "ts": 6197202114483.050, "dur": 0.209, + "args": { + "External id": 37741,"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": 2338707, "tid": 2338707, + "ts": 6197202114486.629, "dur": 0.210, + "args": { + "External id": 37742,"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": 2338707, "tid": 2338707, + "ts": 6197202114487.575, "dur": 0.208, + "args": { + "External id": 37743,"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": 2338707, "tid": 2338707, + "ts": 6197202114489.289, "dur": 0.199, + "args": { + "External id": 37744,"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": 2338707, "tid": 2338707, + "ts": 6197202114490.190, "dur": 0.199, + "args": { + "External id": 37745,"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": 2338707, "tid": 2338707, + "ts": 6197202114491.300, "dur": 0.197, + "args": { + "External id": 37746,"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": 2338707, "tid": 2338707, + "ts": 6197202114492.416, "dur": 0.216, + "args": { + "External id": 37747,"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": 2338707, "tid": 2338707, + "ts": 6197202114493.746, "dur": 0.209, + "args": { + "External id": 37748,"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": 2338707, "tid": 2338707, + "ts": 6197202114494.656, "dur": 0.199, + "args": { + "External id": 37749,"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": 2338707, "tid": 2338707, + "ts": 6197202114497.505, "dur": 0.207, + "args": { + "External id": 37750,"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": 2338707, "tid": 2338707, + "ts": 6197202114498.439, "dur": 0.197, + "args": { + "External id": 37751,"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": 2338707, "tid": 2338707, + "ts": 6197202114499.334, "dur": 0.222, + "args": { + "External id": 37752,"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": 2338707, "tid": 2338707, + "ts": 6197202114500.263, "dur": 0.199, + "args": { + "External id": 37753,"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": 2338707, "tid": 2338707, + "ts": 6197202114501.288, "dur": 0.213, + "args": { + "External id": 37754,"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": 2338707, "tid": 2338707, + "ts": 6197202114502.223, "dur": 0.206, + "args": { + "External id": 37755,"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": 2338707, "tid": 2338707, + "ts": 6197202114503.133, "dur": 0.200, + "args": { + "External id": 37756,"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": 2338707, "tid": 2338707, + "ts": 6197202114504.032, "dur": 0.203, + "args": { + "External id": 37757,"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": 2338707, "tid": 2338707, + "ts": 6197202114507.206, "dur": 0.240, + "args": { + "External id": 37758,"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": 2338707, "tid": 2338707, + "ts": 6197202114508.157, "dur": 0.222, + "args": { + "External id": 37759,"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": 2338707, "tid": 2338707, + "ts": 6197202114509.073, "dur": 0.209, + "args": { + "External id": 37760,"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": 2338707, "tid": 2338707, + "ts": 6197202114509.989, "dur": 0.204, + "args": { + "External id": 37761,"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": 2338707, "tid": 2338707, + "ts": 6197202114510.920, "dur": 0.206, + "args": { + "External id": 37762,"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": 2338707, "tid": 2338707, + "ts": 6197202114511.859, "dur": 0.206, + "args": { + "External id": 37763,"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": 2338707, "tid": 2338707, + "ts": 6197202114513.296, "dur": 0.383, + "args": { + "External id": 37764,"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": 2338707, "tid": 2338707, + "ts": 6197202114514.379, "dur": 0.208, + "args": { + "External id": 37765,"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": 2338707, "tid": 2338707, + "ts": 6197202114517.562, "dur": 0.438, + "args": { + "External id": 37766,"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": 2338707, "tid": 2338707, + "ts": 6197202114518.710, "dur": 0.396, + "args": { + "External id": 37767,"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": 2338707, "tid": 2338707, + "ts": 6197202114519.819, "dur": 0.391, + "args": { + "External id": 37768,"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": 2338707, "tid": 2338707, + "ts": 6197202114521.105, "dur": 0.217, + "args": { + "External id": 37769,"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": 2338707, "tid": 2338707, + "ts": 6197202114522.041, "dur": 0.450, + "args": { + "External id": 37770,"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": 2338707, "tid": 2338707, + "ts": 6197202114524.627, "dur": 0.222, + "args": { + "External id": 37771,"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": 2338707, "tid": 2338707, + "ts": 6197202114525.666, "dur": 0.410, + "args": { + "External id": 37772,"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": 2338707, "tid": 2338707, + "ts": 6197202114526.796, "dur": 0.202, + "args": { + "External id": 37773,"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": 2338707, "tid": 2338707, + "ts": 6197202114529.507, "dur": 0.203, + "args": { + "External id": 37774,"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": 2338707, "tid": 2338707, + "ts": 6197202114530.466, "dur": 0.208, + "args": { + "External id": 37775,"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": 2338707, "tid": 2338707, + "ts": 6197202114531.364, "dur": 0.212, + "args": { + "External id": 37776,"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": 2338707, "tid": 2338707, + "ts": 6197202114532.297, "dur": 0.205, + "args": { + "External id": 37777,"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": 2338707, "tid": 2338707, + "ts": 6197202114533.199, "dur": 0.211, + "args": { + "External id": 37778,"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": 2338707, "tid": 2338707, + "ts": 6197202114534.337, "dur": 0.214, + "args": { + "External id": 37779,"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": 2338707, "tid": 2338707, + "ts": 6197202114535.540, "dur": 0.205, + "args": { + "External id": 37780,"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": 2338707, "tid": 2338707, + "ts": 6197202114536.444, "dur": 0.209, + "args": { + "External id": 37781,"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": 2338707, "tid": 2338707, + "ts": 6197202114539.665, "dur": 0.207, + "args": { + "External id": 37782,"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": 2338707, "tid": 2338707, + "ts": 6197202114540.609, "dur": 0.217, + "args": { + "External id": 37783,"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": 2338707, "tid": 2338707, + "ts": 6197202114541.722, "dur": 0.207, + "args": { + "External id": 37784,"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": 2338707, "tid": 2338707, + "ts": 6197202114542.729, "dur": 0.206, + "args": { + "External id": 37785,"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": 2338707, "tid": 2338707, + "ts": 6197202114543.851, "dur": 0.208, + "args": { + "External id": 37786,"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": 2338707, "tid": 2338707, + "ts": 6197202114544.983, "dur": 0.205, + "args": { + "External id": 37787,"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": 2338707, "tid": 2338707, + "ts": 6197202114546.430, "dur": 0.215, + "args": { + "External id": 37788,"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": 2338707, "tid": 2338707, + "ts": 6197202114547.360, "dur": 0.203, + "args": { + "External id": 37789,"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": 2338707, "tid": 2338707, + "ts": 6197202114550.207, "dur": 0.206, + "args": { + "External id": 37790,"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": 2338707, "tid": 2338707, + "ts": 6197202114551.141, "dur": 0.203, + "args": { + "External id": 37791,"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": 2338707, "tid": 2338707, + "ts": 6197202114552.296, "dur": 0.199, + "args": { + "External id": 37792,"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": 2338707, "tid": 2338707, + "ts": 6197202114553.200, "dur": 0.209, + "args": { + "External id": 37793,"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": 2338707, "tid": 2338707, + "ts": 6197202114554.157, "dur": 0.235, + "args": { + "External id": 37794,"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": 2338707, "tid": 2338707, + "ts": 6197202114555.089, "dur": 0.414, + "args": { + "External id": 37795,"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": 2338707, "tid": 2338707, + "ts": 6197202114556.233, "dur": 0.391, + "args": { + "External id": 37796,"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": 2338707, "tid": 2338707, + "ts": 6197202114557.346, "dur": 0.437, + "args": { + "External id": 37797,"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": 2338707, "tid": 2338707, + "ts": 6197202114560.695, "dur": 0.420, + "args": { + "External id": 37798,"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": 2338707, "tid": 2338707, + "ts": 6197202114561.828, "dur": 0.411, + "args": { + "External id": 37799,"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": 2338707, "tid": 2338707, + "ts": 6197202114562.950, "dur": 0.202, + "args": { + "External id": 37800,"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": 2338707, "tid": 2338707, + "ts": 6197202114563.859, "dur": 0.205, + "args": { + "External id": 37801,"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": 2338707, "tid": 2338707, + "ts": 6197202114564.766, "dur": 0.203, + "args": { + "External id": 37802,"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": 2338707, "tid": 2338707, + "ts": 6197202114565.705, "dur": 0.381, + "args": { + "External id": 37803,"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": 2338707, "tid": 2338707, + "ts": 6197202114566.812, "dur": 0.398, + "args": { + "External id": 37804,"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": 2338707, "tid": 2338707, + "ts": 6197202114571.146, "dur": 0.451, + "args": { + "External id": 37805,"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": 2338707, "tid": 2338707, + "ts": 6197202114574.583, "dur": 0.226, + "args": { + "External id": 37806,"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": 2338707, "tid": 2338707, + "ts": 6197202114575.536, "dur": 0.380, + "args": { + "External id": 37807,"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": 2338707, "tid": 2338707, + "ts": 6197202114576.768, "dur": 0.412, + "args": { + "External id": 37808,"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": 2338707, "tid": 2338707, + "ts": 6197202114578.036, "dur": 0.208, + "args": { + "External id": 37809,"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": 2338707, "tid": 2338707, + "ts": 6197202114578.966, "dur": 0.212, + "args": { + "External id": 37810,"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": 2338707, "tid": 2338707, + "ts": 6197202114579.904, "dur": 0.377, + "args": { + "External id": 37811,"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": 2338707, "tid": 2338707, + "ts": 6197202114581.132, "dur": 0.205, + "args": { + "External id": 37812,"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": 2338707, "tid": 2338707, + "ts": 6197202114582.106, "dur": 0.200, + "args": { + "External id": 37813,"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": 2338707, "tid": 2338707, + "ts": 6197202114585.149, "dur": 0.222, + "args": { + "External id": 37814,"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": 2338707, "tid": 2338707, + "ts": 6197202114586.169, "dur": 0.359, + "args": { + "External id": 37815,"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": 2338707, "tid": 2338707, + "ts": 6197202114587.943, "dur": 0.354, + "args": { + "External id": 37816,"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": 2338707, "tid": 2338707, + "ts": 6197202114589.169, "dur": 0.206, + "args": { + "External id": 37817,"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": 2338707, "tid": 2338707, + "ts": 6197202114590.071, "dur": 0.209, + "args": { + "External id": 37818,"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": 2338707, "tid": 2338707, + "ts": 6197202114591.139, "dur": 0.211, + "args": { + "External id": 37819,"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": 2338707, "tid": 2338707, + "ts": 6197202114592.065, "dur": 0.212, + "args": { + "External id": 37820,"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": 2338707, "tid": 2338707, + "ts": 6197202114592.993, "dur": 0.213, + "args": { + "External id": 37821,"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": 2338707, "tid": 2338707, + "ts": 6197202114596.386, "dur": 0.203, + "args": { + "External id": 37822,"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": 2338707, "tid": 2338707, + "ts": 6197202114597.322, "dur": 0.207, + "args": { + "External id": 37823,"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": 2338707, "tid": 2338707, + "ts": 6197202114598.315, "dur": 0.201, + "args": { + "External id": 37824,"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": 2338707, "tid": 2338707, + "ts": 6197202114599.241, "dur": 0.208, + "args": { + "External id": 37825,"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": 2338707, "tid": 2338707, + "ts": 6197202114600.157, "dur": 0.206, + "args": { + "External id": 37826,"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": 2338707, "tid": 2338707, + "ts": 6197202114601.075, "dur": 0.200, + "args": { + "External id": 37827,"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": 2338707, "tid": 2338707, + "ts": 6197202114602.012, "dur": 0.207, + "args": { + "External id": 37828,"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": 2338707, "tid": 2338707, + "ts": 6197202114602.985, "dur": 0.228, + "args": { + "External id": 37829,"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": 2338707, "tid": 2338707, + "ts": 6197202114605.955, "dur": 0.205, + "args": { + "External id": 37830,"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": 2338707, "tid": 2338707, + "ts": 6197202114606.856, "dur": 0.200, + "args": { + "External id": 37831,"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": 2338707, "tid": 2338707, + "ts": 6197202114607.755, "dur": 0.202, + "args": { + "External id": 37832,"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": 2338707, "tid": 2338707, + "ts": 6197202114608.912, "dur": 0.198, + "args": { + "External id": 37833,"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": 2338707, "tid": 2338707, + "ts": 6197202114609.832, "dur": 0.210, + "args": { + "External id": 37834,"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": 2338707, "tid": 2338707, + "ts": 6197202114610.969, "dur": 0.212, + "args": { + "External id": 37835,"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": 2338707, "tid": 2338707, + "ts": 6197202114612.101, "dur": 0.203, + "args": { + "External id": 37836,"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": 2338707, "tid": 2338707, + "ts": 6197202114613.039, "dur": 0.415, + "args": { + "External id": 37837,"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": 2338707, "tid": 2338707, + "ts": 6197202114616.130, "dur": 0.219, + "args": { + "External id": 37838,"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": 2338707, "tid": 2338707, + "ts": 6197202114617.125, "dur": 0.216, + "args": { + "External id": 37839,"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": 2338707, "tid": 2338707, + "ts": 6197202114618.229, "dur": 0.530, + "args": { + "External id": 37840,"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": 2338707, "tid": 2338707, + "ts": 6197202114619.511, "dur": 0.199, + "args": { + "External id": 37841,"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": 2338707, "tid": 2338707, + "ts": 6197202114620.448, "dur": 0.378, + "args": { + "External id": 37842,"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": 2338707, "tid": 2338707, + "ts": 6197202114621.897, "dur": 0.382, + "args": { + "External id": 37843,"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": 2338707, "tid": 2338707, + "ts": 6197202114623.187, "dur": 0.211, + "args": { + "External id": 37844,"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": 2338707, "tid": 2338707, + "ts": 6197202114624.102, "dur": 0.202, + "args": { + "External id": 37845,"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": 2338707, "tid": 2338707, + "ts": 6197202114627.206, "dur": 0.196, + "args": { + "External id": 37846,"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": 2338707, "tid": 2338707, + "ts": 6197202114628.137, "dur": 0.205, + "args": { + "External id": 37847,"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": 2338707, "tid": 2338707, + "ts": 6197202114629.728, "dur": 0.218, + "args": { + "External id": 37848,"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": 2338707, "tid": 2338707, + "ts": 6197202114630.690, "dur": 0.206, + "args": { + "External id": 37849,"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": 2338707, "tid": 2338707, + "ts": 6197202114631.597, "dur": 0.200, + "args": { + "External id": 37850,"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": 2338707, "tid": 2338707, + "ts": 6197202114632.504, "dur": 0.212, + "args": { + "External id": 37851,"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": 2338707, "tid": 2338707, + "ts": 6197202114633.603, "dur": 0.207, + "args": { + "External id": 37852,"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": 2338707, "tid": 2338707, + "ts": 6197202114634.546, "dur": 0.199, + "args": { + "External id": 37853,"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": 2338707, "tid": 2338707, + "ts": 6197202114637.824, "dur": 0.205, + "args": { + "External id": 37854,"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": 2338707, "tid": 2338707, + "ts": 6197202114638.742, "dur": 0.201, + "args": { + "External id": 37855,"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": 2338707, "tid": 2338707, + "ts": 6197202114639.639, "dur": 0.198, + "args": { + "External id": 37856,"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": 2338707, "tid": 2338707, + "ts": 6197202114640.562, "dur": 0.200, + "args": { + "External id": 37857,"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": 2338707, "tid": 2338707, + "ts": 6197202114641.470, "dur": 0.208, + "args": { + "External id": 37858,"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": 2338707, "tid": 2338707, + "ts": 6197202114642.390, "dur": 0.202, + "args": { + "External id": 37859,"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": 2338707, "tid": 2338707, + "ts": 6197202114643.363, "dur": 0.213, + "args": { + "External id": 37860,"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": 2338707, "tid": 2338707, + "ts": 6197202114644.283, "dur": 0.202, + "args": { + "External id": 37861,"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": 2338707, "tid": 2338707, + "ts": 6197202114647.106, "dur": 0.204, + "args": { + "External id": 37862,"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": 2338707, "tid": 2338707, + "ts": 6197202114648.015, "dur": 0.211, + "args": { + "External id": 37863,"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": 2338707, "tid": 2338707, + "ts": 6197202114649.123, "dur": 0.204, + "args": { + "External id": 37864,"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": 2338707, "tid": 2338707, + "ts": 6197202114650.028, "dur": 0.198, + "args": { + "External id": 37865,"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": 2338707, "tid": 2338707, + "ts": 6197202114651.193, "dur": 0.202, + "args": { + "External id": 37866,"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": 2338707, "tid": 2338707, + "ts": 6197202114652.095, "dur": 0.201, + "args": { + "External id": 37867,"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": 2338707, "tid": 2338707, + "ts": 6197202114653.173, "dur": 0.212, + "args": { + "External id": 37868,"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": 2338707, "tid": 2338707, + "ts": 6197202114654.135, "dur": 0.204, + "args": { + "External id": 37869,"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": 2338707, "tid": 2338707, + "ts": 6197202114657.083, "dur": 0.202, + "args": { + "External id": 37870,"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": 2338707, "tid": 2338707, + "ts": 6197202114658.041, "dur": 0.207, + "args": { + "External id": 37871,"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": 2338707, "tid": 2338707, + "ts": 6197202114659.288, "dur": 0.196, + "args": { + "External id": 37872,"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": 2338707, "tid": 2338707, + "ts": 6197202114660.189, "dur": 0.208, + "args": { + "External id": 37873,"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": 2338707, "tid": 2338707, + "ts": 6197202114661.308, "dur": 0.200, + "args": { + "External id": 37874,"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": 2338707, "tid": 2338707, + "ts": 6197202114662.212, "dur": 0.191, + "args": { + "External id": 37875,"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": 2338707, "tid": 2338707, + "ts": 6197202114663.547, "dur": 0.210, + "args": { + "External id": 37876,"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": 2338707, "tid": 2338707, + "ts": 6197202114664.463, "dur": 0.199, + "args": { + "External id": 37877,"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": 2338707, "tid": 2338707, + "ts": 6197202114667.724, "dur": 0.522, + "args": { + "External id": 37878,"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": 2338707, "tid": 2338707, + "ts": 6197202114668.957, "dur": 0.400, + "args": { + "External id": 37879,"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": 2338707, "tid": 2338707, + "ts": 6197202114670.257, "dur": 0.467, + "args": { + "External id": 37880,"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": 2338707, "tid": 2338707, + "ts": 6197202114671.613, "dur": 0.212, + "args": { + "External id": 37881,"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": 2338707, "tid": 2338707, + "ts": 6197202114672.520, "dur": 0.410, + "args": { + "External id": 37882,"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": 2338707, "tid": 2338707, + "ts": 6197202114674.055, "dur": 0.202, + "args": { + "External id": 37883,"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": 2338707, "tid": 2338707, + "ts": 6197202114675.299, "dur": 0.382, + "args": { + "External id": 37884,"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": 2338707, "tid": 2338707, + "ts": 6197202114677.688, "dur": 0.223, + "args": { + "External id": 37885,"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": 2338707, "tid": 2338707, + "ts": 6197202114680.410, "dur": 0.205, + "args": { + "External id": 37886,"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": 2338707, "tid": 2338707, + "ts": 6197202114681.403, "dur": 0.199, + "args": { + "External id": 37887,"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": 2338707, "tid": 2338707, + "ts": 6197202114751.652, "dur": 1469.504, + "args": { + "External id": 37888,"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": 2338707, "tid": 2338707, + "ts": 6197202115189.343, "dur": 938.088, + "args": { + "External id": 44033,"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": 2338707, "tid": 2338707, + "ts": 6197202115197.232, "dur": 10.548, + "args": { + "External id": 44034,"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": 2338707, "tid": 2338707, + "ts": 6197202115203.585, "dur": 3.506, + "args": { + "External id": 44035,"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": 2338707, "tid": 2338707, + "ts": 6197202115208.384, "dur": 1.746, + "args": { + "External id": 44036,"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": 2338707, "tid": 2338707, + "ts": 6197202115208.961, "dur": 1.080, + "args": { + "External id": 44037,"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": 2338707, "tid": 2338707, + "ts": 6197202115210.531, "dur": 2.902, + "args": { + "External id": 44038,"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": 2338707, "tid": 2338707, + "ts": 6197202115212.369, "dur": 0.933, + "args": { + "External id": 44039,"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": 2338707, "tid": 2338707, + "ts": 6197202115213.823, "dur": 1.310, + "args": { + "External id": 44040,"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": 2338707, "tid": 2338707, + "ts": 6197202115214.251, "dur": 0.799, + "args": { + "External id": 44041,"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": 2338707, "tid": 2338707, + "ts": 6197202115215.369, "dur": 2.404, + "args": { + "External id": 44042,"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": 2338707, "tid": 2338707, + "ts": 6197202115217.069, "dur": 0.631, + "args": { + "External id": 44043,"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": 2338707, "tid": 2338707, + "ts": 6197202115218.067, "dur": 2.344, + "args": { + "External id": 44044,"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": 2338707, "tid": 2338707, + "ts": 6197202115219.725, "dur": 0.610, + "args": { + "External id": 44045,"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": 2338707, "tid": 2338707, + "ts": 6197202115223.053, "dur": 1.607, + "args": { + "External id": 44046,"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": 2338707, "tid": 2338707, + "ts": 6197202115223.434, "dur": 1.148, + "args": { + "External id": 44047,"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": 2338707, "tid": 2338707, + "ts": 6197202115224.957, "dur": 2.212, + "args": { + "External id": 44048,"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": 2338707, "tid": 2338707, + "ts": 6197202115226.312, "dur": 0.786, + "args": { + "External id": 44049,"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": 2338707, "tid": 2338707, + "ts": 6197202115227.413, "dur": 2.304, + "args": { + "External id": 44050,"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": 2338707, "tid": 2338707, + "ts": 6197202115229.140, "dur": 0.500, + "args": { + "External id": 44051,"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": 2338707, "tid": 2338707, + "ts": 6197202115230.133, "dur": 1.075, + "args": { + "External id": 44052,"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": 2338707, "tid": 2338707, + "ts": 6197202115230.505, "dur": 0.631, + "args": { + "External id": 44053,"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": 2338707, "tid": 2338707, + "ts": 6197202115231.440, "dur": 3.066, + "args": { + "External id": 44054,"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": 2338707, "tid": 2338707, + "ts": 6197202115232.955, "dur": 1.473, + "args": { + "External id": 44055,"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": 2338707, "tid": 2338707, + "ts": 6197202115234.766, "dur": 0.966, + "args": { + "External id": 44056,"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": 2338707, "tid": 2338707, + "ts": 6197202115235.160, "dur": 0.510, + "args": { + "External id": 44057,"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": 2338707, "tid": 2338707, + "ts": 6197202115235.979, "dur": 2.260, + "args": { + "External id": 44058,"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": 2338707, "tid": 2338707, + "ts": 6197202115237.640, "dur": 0.523, + "args": { + "External id": 44059,"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": 2338707, "tid": 2338707, + "ts": 6197202115238.527, "dur": 3.088, + "args": { + "External id": 44060,"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": 2338707, "tid": 2338707, + "ts": 6197202115240.627, "dur": 0.923, + "args": { + "External id": 44061,"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": 2338707, "tid": 2338707, + "ts": 6197202115243.936, "dur": 1.055, + "args": { + "External id": 44062,"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": 2338707, "tid": 2338707, + "ts": 6197202115244.313, "dur": 0.615, + "args": { + "External id": 44063,"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": 2338707, "tid": 2338707, + "ts": 6197202115245.271, "dur": 2.875, + "args": { + "External id": 44064,"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": 2338707, "tid": 2338707, + "ts": 6197202115247.059, "dur": 1.021, + "args": { + "External id": 44065,"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": 2338707, "tid": 2338707, + "ts": 6197202115248.372, "dur": 3.057, + "args": { + "External id": 44066,"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": 2338707, "tid": 2338707, + "ts": 6197202115250.329, "dur": 1.024, + "args": { + "External id": 44067,"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": 2338707, "tid": 2338707, + "ts": 6197202115251.762, "dur": 1.148, + "args": { + "External id": 44068,"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": 2338707, "tid": 2338707, + "ts": 6197202115252.114, "dur": 0.728, + "args": { + "External id": 44069,"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": 2338707, "tid": 2338707, + "ts": 6197202115253.152, "dur": 3.548, + "args": { + "External id": 44070,"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": 2338707, "tid": 2338707, + "ts": 6197202115254.954, "dur": 1.668, + "args": { + "External id": 44071,"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": 2338707, "tid": 2338707, + "ts": 6197202115256.930, "dur": 1.184, + "args": { + "External id": 44072,"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": 2338707, "tid": 2338707, + "ts": 6197202115257.289, "dur": 0.758, + "args": { + "External id": 44073,"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": 2338707, "tid": 2338707, + "ts": 6197202115258.346, "dur": 2.222, + "args": { + "External id": 44074,"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": 2338707, "tid": 2338707, + "ts": 6197202115259.811, "dur": 0.686, + "args": { + "External id": 44075,"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": 2338707, "tid": 2338707, + "ts": 6197202115260.793, "dur": 2.736, + "args": { + "External id": 44076,"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": 2338707, "tid": 2338707, + "ts": 6197202115262.761, "dur": 0.701, + "args": { + "External id": 44077,"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": 2338707, "tid": 2338707, + "ts": 6197202115266.140, "dur": 1.207, + "args": { + "External id": 44078,"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": 2338707, "tid": 2338707, + "ts": 6197202115266.489, "dur": 0.784, + "args": { + "External id": 44079,"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": 2338707, "tid": 2338707, + "ts": 6197202115267.589, "dur": 2.113, + "args": { + "External id": 44080,"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": 2338707, "tid": 2338707, + "ts": 6197202115268.887, "dur": 0.750, + "args": { + "External id": 44081,"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": 2338707, "tid": 2338707, + "ts": 6197202115269.938, "dur": 3.062, + "args": { + "External id": 44082,"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": 2338707, "tid": 2338707, + "ts": 6197202115272.160, "dur": 0.765, + "args": { + "External id": 44083,"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": 2338707, "tid": 2338707, + "ts": 6197202115273.520, "dur": 1.227, + "args": { + "External id": 44084,"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": 2338707, "tid": 2338707, + "ts": 6197202115273.885, "dur": 0.786, + "args": { + "External id": 44085,"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": 2338707, "tid": 2338707, + "ts": 6197202115274.978, "dur": 3.315, + "args": { + "External id": 44086,"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": 2338707, "tid": 2338707, + "ts": 6197202115276.595, "dur": 1.623, + "args": { + "External id": 44087,"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": 2338707, "tid": 2338707, + "ts": 6197202115278.550, "dur": 1.041, + "args": { + "External id": 44088,"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": 2338707, "tid": 2338707, + "ts": 6197202115278.916, "dur": 0.610, + "args": { + "External id": 44089,"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": 2338707, "tid": 2338707, + "ts": 6197202115279.855, "dur": 2.372, + "args": { + "External id": 44090,"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": 2338707, "tid": 2338707, + "ts": 6197202115281.680, "dur": 0.479, + "args": { + "External id": 44091,"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": 2338707, "tid": 2338707, + "ts": 6197202115282.553, "dur": 2.555, + "args": { + "External id": 44092,"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": 2338707, "tid": 2338707, + "ts": 6197202115284.467, "dur": 0.567, + "args": { + "External id": 44093,"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": 2338707, "tid": 2338707, + "ts": 6197202115287.165, "dur": 1.362, + "args": { + "External id": 44094,"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": 2338707, "tid": 2338707, + "ts": 6197202115287.533, "dur": 0.926, + "args": { + "External id": 44095,"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": 2338707, "tid": 2338707, + "ts": 6197202115288.855, "dur": 2.038, + "args": { + "External id": 44096,"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": 2338707, "tid": 2338707, + "ts": 6197202115290.090, "dur": 0.734, + "args": { + "External id": 44097,"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": 2338707, "tid": 2338707, + "ts": 6197202115291.118, "dur": 2.118, + "args": { + "External id": 44098,"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": 2338707, "tid": 2338707, + "ts": 6197202115292.740, "dur": 0.422, + "args": { + "External id": 44099,"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": 2338707, "tid": 2338707, + "ts": 6197202115293.486, "dur": 1.137, + "args": { + "External id": 44100,"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": 2338707, "tid": 2338707, + "ts": 6197202115293.894, "dur": 0.655, + "args": { + "External id": 44101,"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": 2338707, "tid": 2338707, + "ts": 6197202115294.863, "dur": 3.702, + "args": { + "External id": 44102,"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": 2338707, "tid": 2338707, + "ts": 6197202115296.564, "dur": 1.708, + "args": { + "External id": 44103,"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": 2338707, "tid": 2338707, + "ts": 6197202115298.798, "dur": 0.898, + "args": { + "External id": 44104,"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": 2338707, "tid": 2338707, + "ts": 6197202115299.167, "dur": 0.466, + "args": { + "External id": 44105,"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": 2338707, "tid": 2338707, + "ts": 6197202115299.920, "dur": 2.160, + "args": { + "External id": 44106,"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": 2338707, "tid": 2338707, + "ts": 6197202115301.441, "dur": 0.572, + "args": { + "External id": 44107,"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": 2338707, "tid": 2338707, + "ts": 6197202115302.344, "dur": 2.716, + "args": { + "External id": 44108,"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": 2338707, "tid": 2338707, + "ts": 6197202115304.211, "dur": 0.779, + "args": { + "External id": 44109,"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": 2338707, "tid": 2338707, + "ts": 6197202115307.737, "dur": 0.768, + "args": { + "External id": 44110,"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": 2338707, "tid": 2338707, + "ts": 6197202115308.105, "dur": 0.337, + "args": { + "External id": 44111,"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": 2338707, "tid": 2338707, + "ts": 6197202115308.763, "dur": 2.304, + "args": { + "External id": 44112,"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": 2338707, "tid": 2338707, + "ts": 6197202115310.422, "dur": 0.576, + "args": { + "External id": 44113,"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": 2338707, "tid": 2338707, + "ts": 6197202115311.303, "dur": 2.254, + "args": { + "External id": 44114,"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": 2338707, "tid": 2338707, + "ts": 6197202115313.122, "dur": 0.360, + "args": { + "External id": 44115,"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": 2338707, "tid": 2338707, + "ts": 6197202115313.779, "dur": 1.459, + "args": { + "External id": 44116,"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": 2338707, "tid": 2338707, + "ts": 6197202115314.170, "dur": 1.001, + "args": { + "External id": 44117,"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": 2338707, "tid": 2338707, + "ts": 6197202115315.460, "dur": 3.914, + "args": { + "External id": 44118,"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": 2338707, "tid": 2338707, + "ts": 6197202115317.000, "dur": 2.285, + "args": { + "External id": 44119,"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": 2338707, "tid": 2338707, + "ts": 6197202115319.607, "dur": 1.143, + "args": { + "External id": 44120,"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": 2338707, "tid": 2338707, + "ts": 6197202115319.974, "dur": 0.703, + "args": { + "External id": 44121,"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": 2338707, "tid": 2338707, + "ts": 6197202115320.973, "dur": 2.501, + "args": { + "External id": 44122,"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": 2338707, "tid": 2338707, + "ts": 6197202115322.818, "dur": 0.590, + "args": { + "External id": 44123,"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": 2338707, "tid": 2338707, + "ts": 6197202115323.756, "dur": 2.270, + "args": { + "External id": 44124,"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": 2338707, "tid": 2338707, + "ts": 6197202115325.351, "dur": 0.615, + "args": { + "External id": 44125,"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": 2338707, "tid": 2338707, + "ts": 6197202115328.052, "dur": 0.741, + "args": { + "External id": 44126,"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": 2338707, "tid": 2338707, + "ts": 6197202115328.421, "dur": 0.293, + "args": { + "External id": 44127,"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": 2338707, "tid": 2338707, + "ts": 6197202115329.026, "dur": 2.525, + "args": { + "External id": 44128,"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": 2338707, "tid": 2338707, + "ts": 6197202115330.598, "dur": 0.882, + "args": { + "External id": 44129,"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": 2338707, "tid": 2338707, + "ts": 6197202115331.784, "dur": 2.363, + "args": { + "External id": 44130,"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": 2338707, "tid": 2338707, + "ts": 6197202115333.620, "dur": 0.459, + "args": { + "External id": 44131,"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": 2338707, "tid": 2338707, + "ts": 6197202115334.382, "dur": 1.279, + "args": { + "External id": 44132,"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": 2338707, "tid": 2338707, + "ts": 6197202115334.787, "dur": 0.809, + "args": { + "External id": 44133,"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": 2338707, "tid": 2338707, + "ts": 6197202115335.885, "dur": 3.180, + "args": { + "External id": 44134,"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": 2338707, "tid": 2338707, + "ts": 6197202115337.300, "dur": 1.689, + "args": { + "External id": 44135,"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": 2338707, "tid": 2338707, + "ts": 6197202115339.335, "dur": 1.042, + "args": { + "External id": 44136,"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": 2338707, "tid": 2338707, + "ts": 6197202115339.702, "dur": 0.607, + "args": { + "External id": 44137,"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": 2338707, "tid": 2338707, + "ts": 6197202115340.621, "dur": 2.234, + "args": { + "External id": 44138,"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": 2338707, "tid": 2338707, + "ts": 6197202115342.148, "dur": 0.643, + "args": { + "External id": 44139,"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": 2338707, "tid": 2338707, + "ts": 6197202115343.102, "dur": 2.441, + "args": { + "External id": 44140,"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": 2338707, "tid": 2338707, + "ts": 6197202115344.836, "dur": 0.635, + "args": { + "External id": 44141,"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": 2338707, "tid": 2338707, + "ts": 6197202115347.685, "dur": 0.732, + "args": { + "External id": 44142,"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": 2338707, "tid": 2338707, + "ts": 6197202115348.054, "dur": 0.300, + "args": { + "External id": 44143,"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": 2338707, "tid": 2338707, + "ts": 6197202115348.661, "dur": 3.524, + "args": { + "External id": 44144,"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": 2338707, "tid": 2338707, + "ts": 6197202115350.429, "dur": 1.674, + "args": { + "External id": 44145,"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": 2338707, "tid": 2338707, + "ts": 6197202115352.413, "dur": 0.687, + "args": { + "External id": 44146,"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": 2338707, "tid": 2338707, + "ts": 6197202115352.782, "dur": 0.253, + "args": { + "External id": 44147,"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": 2338707, "tid": 2338707, + "ts": 6197202115353.365, "dur": 1.133, + "args": { + "External id": 44148,"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": 2338707, "tid": 2338707, + "ts": 6197202115353.769, "dur": 0.659, + "args": { + "External id": 44149,"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": 2338707, "tid": 2338707, + "ts": 6197202115354.820, "dur": 3.264, + "args": { + "External id": 44150,"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": 2338707, "tid": 2338707, + "ts": 6197202115357.682, "dur": 0.337, + "args": { + "External id": 44151,"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": 2338707, "tid": 2338707, + "ts": 6197202115358.374, "dur": 1.203, + "args": { + "External id": 44152,"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": 2338707, "tid": 2338707, + "ts": 6197202115358.740, "dur": 0.774, + "args": { + "External id": 44153,"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": 2338707, "tid": 2338707, + "ts": 6197202115359.801, "dur": 2.194, + "args": { + "External id": 44154,"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": 2338707, "tid": 2338707, + "ts": 6197202115361.556, "dur": 0.365, + "args": { + "External id": 44155,"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": 2338707, "tid": 2338707, + "ts": 6197202115362.331, "dur": 2.919, + "args": { + "External id": 44156,"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": 2338707, "tid": 2338707, + "ts": 6197202115364.607, "dur": 0.575, + "args": { + "External id": 44157,"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": 2338707, "tid": 2338707, + "ts": 6197202115367.348, "dur": 0.997, + "args": { + "External id": 44158,"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": 2338707, "tid": 2338707, + "ts": 6197202115367.714, "dur": 0.566, + "args": { + "External id": 44159,"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": 2338707, "tid": 2338707, + "ts": 6197202115368.567, "dur": 3.915, + "args": { + "External id": 44160,"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": 2338707, "tid": 2338707, + "ts": 6197202115370.327, "dur": 1.853, + "args": { + "External id": 44161,"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": 2338707, "tid": 2338707, + "ts": 6197202115372.709, "dur": 0.681, + "args": { + "External id": 44162,"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": 2338707, "tid": 2338707, + "ts": 6197202115373.065, "dur": 0.262, + "args": { + "External id": 44163,"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": 2338707, "tid": 2338707, + "ts": 6197202115373.613, "dur": 1.115, + "args": { + "External id": 44164,"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": 2338707, "tid": 2338707, + "ts": 6197202115374.006, "dur": 0.654, + "args": { + "External id": 44165,"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": 2338707, "tid": 2338707, + "ts": 6197202115374.948, "dur": 4.201, + "args": { + "External id": 44166,"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": 2338707, "tid": 2338707, + "ts": 6197202115378.650, "dur": 0.433, + "args": { + "External id": 44167,"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": 2338707, "tid": 2338707, + "ts": 6197202115379.411, "dur": 1.401, + "args": { + "External id": 44168,"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": 2338707, "tid": 2338707, + "ts": 6197202115379.769, "dur": 0.978, + "args": { + "External id": 44169,"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": 2338707, "tid": 2338707, + "ts": 6197202115381.059, "dur": 1.905, + "args": { + "External id": 44170,"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": 2338707, "tid": 2338707, + "ts": 6197202115382.459, "dur": 0.442, + "args": { + "External id": 44171,"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": 2338707, "tid": 2338707, + "ts": 6197202115383.198, "dur": 2.402, + "args": { + "External id": 44172,"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": 2338707, "tid": 2338707, + "ts": 6197202115384.874, "dur": 0.655, + "args": { + "External id": 44173,"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": 2338707, "tid": 2338707, + "ts": 6197202115387.660, "dur": 0.735, + "args": { + "External id": 44174,"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": 2338707, "tid": 2338707, + "ts": 6197202115388.026, "dur": 0.307, + "args": { + "External id": 44175,"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": 2338707, "tid": 2338707, + "ts": 6197202115388.652, "dur": 2.874, + "args": { + "External id": 44176,"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": 2338707, "tid": 2338707, + "ts": 6197202115389.993, "dur": 1.438, + "args": { + "External id": 44177,"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": 2338707, "tid": 2338707, + "ts": 6197202115391.753, "dur": 0.976, + "args": { + "External id": 44178,"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": 2338707, "tid": 2338707, + "ts": 6197202115392.105, "dur": 0.561, + "args": { + "External id": 44179,"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": 2338707, "tid": 2338707, + "ts": 6197202115392.951, "dur": 1.283, + "args": { + "External id": 44180,"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": 2338707, "tid": 2338707, + "ts": 6197202115393.346, "dur": 0.826, + "args": { + "External id": 44181,"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": 2338707, "tid": 2338707, + "ts": 6197202115394.458, "dur": 3.246, + "args": { + "External id": 44182,"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": 2338707, "tid": 2338707, + "ts": 6197202115397.031, "dur": 0.608, + "args": { + "External id": 44183,"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": 2338707, "tid": 2338707, + "ts": 6197202115397.964, "dur": 0.941, + "args": { + "External id": 44184,"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": 2338707, "tid": 2338707, + "ts": 6197202115398.321, "dur": 0.521, + "args": { + "External id": 44185,"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": 2338707, "tid": 2338707, + "ts": 6197202115399.152, "dur": 1.439, + "args": { + "External id": 44186,"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": 2338707, "tid": 2338707, + "ts": 6197202115400.121, "dur": 0.399, + "args": { + "External id": 44187,"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": 2338707, "tid": 2338707, + "ts": 6197202115400.906, "dur": 2.051, + "args": { + "External id": 44188,"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": 2338707, "tid": 2338707, + "ts": 6197202115402.241, "dur": 0.653, + "args": { + "External id": 44189,"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": 2338707, "tid": 2338707, + "ts": 6197202115405.346, "dur": 0.774, + "args": { + "External id": 44190,"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": 2338707, "tid": 2338707, + "ts": 6197202115405.714, "dur": 0.342, + "args": { + "External id": 44191,"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": 2338707, "tid": 2338707, + "ts": 6197202115406.344, "dur": 2.211, + "args": { + "External id": 44192,"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": 2338707, "tid": 2338707, + "ts": 6197202115407.228, "dur": 1.259, + "args": { + "External id": 44193,"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": 2338707, "tid": 2338707, + "ts": 6197202115408.782, "dur": 0.822, + "args": { + "External id": 44194,"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": 2338707, "tid": 2338707, + "ts": 6197202115409.139, "dur": 0.391, + "args": { + "External id": 44195,"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": 2338707, "tid": 2338707, + "ts": 6197202115409.858, "dur": 1.432, + "args": { + "External id": 44196,"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": 2338707, "tid": 2338707, + "ts": 6197202115410.261, "dur": 0.968, + "args": { + "External id": 44197,"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": 2338707, "tid": 2338707, + "ts": 6197202115411.622, "dur": 3.749, + "args": { + "External id": 44198,"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": 2338707, "tid": 2338707, + "ts": 6197202115414.276, "dur": 1.028, + "args": { + "External id": 44199,"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": 2338707, "tid": 2338707, + "ts": 6197202115415.630, "dur": 1.537, + "args": { + "External id": 44200,"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": 2338707, "tid": 2338707, + "ts": 6197202115416.301, "dur": 0.801, + "args": { + "External id": 44201,"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": 2338707, "tid": 2338707, + "ts": 6197202115417.389, "dur": 1.905, + "args": { + "External id": 44202,"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": 2338707, "tid": 2338707, + "ts": 6197202115418.236, "dur": 0.993, + "args": { + "External id": 44203,"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": 2338707, "tid": 2338707, + "ts": 6197202115419.518, "dur": 2.944, + "args": { + "External id": 44204,"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": 2338707, "tid": 2338707, + "ts": 6197202115421.729, "dur": 0.672, + "args": { + "External id": 44205,"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": 2338707, "tid": 2338707, + "ts": 6197202115424.934, "dur": 1.481, + "args": { + "External id": 44206,"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": 2338707, "tid": 2338707, + "ts": 6197202115425.747, "dur": 0.607, + "args": { + "External id": 44207,"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": 2338707, "tid": 2338707, + "ts": 6197202115426.640, "dur": 2.492, + "args": { + "External id": 44208,"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": 2338707, "tid": 2338707, + "ts": 6197202115427.427, "dur": 1.467, + "args": { + "External id": 44209,"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": 2338707, "tid": 2338707, + "ts": 6197202115429.358, "dur": 1.657, + "args": { + "External id": 44210,"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": 2338707, "tid": 2338707, + "ts": 6197202115430.349, "dur": 0.593, + "args": { + "External id": 44211,"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": 2338707, "tid": 2338707, + "ts": 6197202115431.321, "dur": 1.828, + "args": { + "External id": 44212,"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": 2338707, "tid": 2338707, + "ts": 6197202115432.149, "dur": 0.936, + "args": { + "External id": 44213,"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": 2338707, "tid": 2338707, + "ts": 6197202115433.372, "dur": 2.235, + "args": { + "External id": 44214,"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": 2338707, "tid": 2338707, + "ts": 6197202115434.938, "dur": 0.603, + "args": { + "External id": 44215,"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": 2338707, "tid": 2338707, + "ts": 6197202115435.857, "dur": 1.644, + "args": { + "External id": 44216,"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": 2338707, "tid": 2338707, + "ts": 6197202115436.466, "dur": 0.973, + "args": { + "External id": 44217,"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": 2338707, "tid": 2338707, + "ts": 6197202115437.725, "dur": 1.196, + "args": { + "External id": 44218,"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": 2338707, "tid": 2338707, + "ts": 6197202115438.277, "dur": 0.580, + "args": { + "External id": 44219,"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": 2338707, "tid": 2338707, + "ts": 6197202115439.142, "dur": 2.523, + "args": { + "External id": 44220,"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": 2338707, "tid": 2338707, + "ts": 6197202115440.980, "dur": 0.615, + "args": { + "External id": 44221,"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": 2338707, "tid": 2338707, + "ts": 6197202115444.137, "dur": 1.566, + "args": { + "External id": 44222,"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": 2338707, "tid": 2338707, + "ts": 6197202115444.963, "dur": 0.674, + "args": { + "External id": 44223,"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": 2338707, "tid": 2338707, + "ts": 6197202115446.012, "dur": 2.142, + "args": { + "External id": 44224,"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": 2338707, "tid": 2338707, + "ts": 6197202115446.634, "dur": 1.447, + "args": { + "External id": 44225,"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": 2338707, "tid": 2338707, + "ts": 6197202115448.378, "dur": 1.336, + "args": { + "External id": 44226,"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": 2338707, "tid": 2338707, + "ts": 6197202115449.187, "dur": 0.448, + "args": { + "External id": 44227,"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": 2338707, "tid": 2338707, + "ts": 6197202115449.974, "dur": 1.272, + "args": { + "External id": 44228,"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": 2338707, "tid": 2338707, + "ts": 6197202115450.638, "dur": 0.545, + "args": { + "External id": 44229,"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": 2338707, "tid": 2338707, + "ts": 6197202115451.534, "dur": 2.630, + "args": { + "External id": 44230,"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": 2338707, "tid": 2338707, + "ts": 6197202115453.462, "dur": 0.638, + "args": { + "External id": 44231,"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": 2338707, "tid": 2338707, + "ts": 6197202115454.402, "dur": 1.399, + "args": { + "External id": 44232,"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": 2338707, "tid": 2338707, + "ts": 6197202115455.092, "dur": 0.642, + "args": { + "External id": 44233,"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": 2338707, "tid": 2338707, + "ts": 6197202115456.116, "dur": 1.505, + "args": { + "External id": 44234,"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": 2338707, "tid": 2338707, + "ts": 6197202115456.780, "dur": 0.776, + "args": { + "External id": 44235,"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": 2338707, "tid": 2338707, + "ts": 6197202115457.845, "dur": 2.368, + "args": { + "External id": 44236,"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": 2338707, "tid": 2338707, + "ts": 6197202115459.554, "dur": 0.592, + "args": { + "External id": 44237,"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": 2338707, "tid": 2338707, + "ts": 6197202115462.426, "dur": 1.766, + "args": { + "External id": 44238,"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": 2338707, "tid": 2338707, + "ts": 6197202115463.196, "dur": 0.934, + "args": { + "External id": 44239,"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": 2338707, "tid": 2338707, + "ts": 6197202115464.427, "dur": 2.587, + "args": { + "External id": 44240,"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": 2338707, "tid": 2338707, + "ts": 6197202115465.026, "dur": 1.910, + "args": { + "External id": 44241,"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": 2338707, "tid": 2338707, + "ts": 6197202115467.287, "dur": 1.507, + "args": { + "External id": 44242,"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": 2338707, "tid": 2338707, + "ts": 6197202115467.907, "dur": 0.822, + "args": { + "External id": 44243,"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": 2338707, "tid": 2338707, + "ts": 6197202115469.015, "dur": 1.074, + "args": { + "External id": 44244,"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": 2338707, "tid": 2338707, + "ts": 6197202115469.516, "dur": 0.499, + "args": { + "External id": 44245,"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": 2338707, "tid": 2338707, + "ts": 6197202115470.354, "dur": 2.523, + "args": { + "External id": 44246,"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": 2338707, "tid": 2338707, + "ts": 6197202115472.396, "dur": 0.416, + "args": { + "External id": 44247,"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": 2338707, "tid": 2338707, + "ts": 6197202115473.175, "dur": 1.290, + "args": { + "External id": 44248,"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": 2338707, "tid": 2338707, + "ts": 6197202115473.769, "dur": 0.635, + "args": { + "External id": 44249,"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": 2338707, "tid": 2338707, + "ts": 6197202115474.791, "dur": 1.476, + "args": { + "External id": 44250,"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": 2338707, "tid": 2338707, + "ts": 6197202115475.330, "dur": 0.873, + "args": { + "External id": 44251,"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": 2338707, "tid": 2338707, + "ts": 6197202115476.527, "dur": 2.763, + "args": { + "External id": 44252,"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": 2338707, "tid": 2338707, + "ts": 6197202115478.496, "dur": 0.720, + "args": { + "External id": 44253,"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": 2338707, "tid": 2338707, + "ts": 6197202115481.780, "dur": 1.330, + "args": { + "External id": 44254,"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": 2338707, "tid": 2338707, + "ts": 6197202115482.388, "dur": 0.654, + "args": { + "External id": 44255,"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": 2338707, "tid": 2338707, + "ts": 6197202115483.334, "dur": 2.644, + "args": { + "External id": 44256,"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": 2338707, "tid": 2338707, + "ts": 6197202115484.134, "dur": 1.773, + "args": { + "External id": 44257,"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": 2338707, "tid": 2338707, + "ts": 6197202115486.216, "dur": 1.340, + "args": { + "External id": 44258,"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": 2338707, "tid": 2338707, + "ts": 6197202115486.838, "dur": 0.653, + "args": { + "External id": 44259,"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": 2338707, "tid": 2338707, + "ts": 6197202115487.779, "dur": 1.249, + "args": { + "External id": 44260,"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": 2338707, "tid": 2338707, + "ts": 6197202115488.314, "dur": 0.651, + "args": { + "External id": 44261,"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": 2338707, "tid": 2338707, + "ts": 6197202115489.270, "dur": 3.444, + "args": { + "External id": 44262,"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": 2338707, "tid": 2338707, + "ts": 6197202115491.701, "dur": 0.948, + "args": { + "External id": 44263,"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": 2338707, "tid": 2338707, + "ts": 6197202115492.954, "dur": 1.445, + "args": { + "External id": 44264,"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": 2338707, "tid": 2338707, + "ts": 6197202115493.835, "dur": 0.491, + "args": { + "External id": 44265,"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": 2338707, "tid": 2338707, + "ts": 6197202115494.631, "dur": 1.228, + "args": { + "External id": 44266,"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": 2338707, "tid": 2338707, + "ts": 6197202115495.308, "dur": 0.487, + "args": { + "External id": 44267,"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": 2338707, "tid": 2338707, + "ts": 6197202115496.082, "dur": 2.733, + "args": { + "External id": 44268,"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": 2338707, "tid": 2338707, + "ts": 6197202115497.757, "dur": 0.994, + "args": { + "External id": 44269,"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": 2338707, "tid": 2338707, + "ts": 6197202115501.131, "dur": 1.416, + "args": { + "External id": 44270,"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": 2338707, "tid": 2338707, + "ts": 6197202115501.747, "dur": 0.734, + "args": { + "External id": 44271,"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": 2338707, "tid": 2338707, + "ts": 6197202115502.777, "dur": 1.972, + "args": { + "External id": 44272,"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": 2338707, "tid": 2338707, + "ts": 6197202115503.335, "dur": 1.335, + "args": { + "External id": 44273,"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": 2338707, "tid": 2338707, + "ts": 6197202115505.018, "dur": 1.168, + "args": { + "External id": 44274,"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": 2338707, "tid": 2338707, + "ts": 6197202115505.552, "dur": 0.570, + "args": { + "External id": 44275,"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": 2338707, "tid": 2338707, + "ts": 6197202115506.440, "dur": 1.265, + "args": { + "External id": 44276,"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": 2338707, "tid": 2338707, + "ts": 6197202115507.213, "dur": 0.427, + "args": { + "External id": 44277,"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": 2338707, "tid": 2338707, + "ts": 6197202115507.966, "dur": 2.697, + "args": { + "External id": 44278,"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": 2338707, "tid": 2338707, + "ts": 6197202115509.594, "dur": 0.994, + "args": { + "External id": 44279,"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": 2338707, "tid": 2338707, + "ts": 6197202115510.928, "dur": 1.244, + "args": { + "External id": 44280,"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": 2338707, "tid": 2338707, + "ts": 6197202115511.543, "dur": 0.563, + "args": { + "External id": 44281,"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": 2338707, "tid": 2338707, + "ts": 6197202115512.417, "dur": 1.908, + "args": { + "External id": 44282,"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": 2338707, "tid": 2338707, + "ts": 6197202115513.173, "dur": 1.088, + "args": { + "External id": 44283,"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": 2338707, "tid": 2338707, + "ts": 6197202115514.555, "dur": 3.134, + "args": { + "External id": 44284,"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": 2338707, "tid": 2338707, + "ts": 6197202115516.796, "dur": 0.832, + "args": { + "External id": 44285,"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": 2338707, "tid": 2338707, + "ts": 6197202115519.765, "dur": 1.556, + "args": { + "External id": 44286,"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": 2338707, "tid": 2338707, + "ts": 6197202115520.608, "dur": 0.638, + "args": { + "External id": 44287,"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": 2338707, "tid": 2338707, + "ts": 6197202115521.587, "dur": 1.875, + "args": { + "External id": 44288,"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": 2338707, "tid": 2338707, + "ts": 6197202115522.105, "dur": 1.289, + "args": { + "External id": 44289,"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": 2338707, "tid": 2338707, + "ts": 6197202115523.689, "dur": 1.307, + "args": { + "External id": 44290,"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": 2338707, "tid": 2338707, + "ts": 6197202115524.221, "dur": 0.711, + "args": { + "External id": 44291,"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": 2338707, "tid": 2338707, + "ts": 6197202115525.218, "dur": 1.107, + "args": { + "External id": 44292,"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": 2338707, "tid": 2338707, + "ts": 6197202115525.705, "dur": 0.556, + "args": { + "External id": 44293,"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": 2338707, "tid": 2338707, + "ts": 6197202115526.582, "dur": 2.801, + "args": { + "External id": 44294,"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": 2338707, "tid": 2338707, + "ts": 6197202115528.735, "dur": 0.585, + "args": { + "External id": 44295,"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": 2338707, "tid": 2338707, + "ts": 6197202115529.621, "dur": 1.107, + "args": { + "External id": 44296,"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": 2338707, "tid": 2338707, + "ts": 6197202115530.152, "dur": 0.500, + "args": { + "External id": 44297,"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": 2338707, "tid": 2338707, + "ts": 6197202115530.969, "dur": 1.444, + "args": { + "External id": 44298,"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": 2338707, "tid": 2338707, + "ts": 6197202115531.615, "dur": 0.734, + "args": { + "External id": 44299,"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": 2338707, "tid": 2338707, + "ts": 6197202115532.636, "dur": 2.795, + "args": { + "External id": 44300,"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": 2338707, "tid": 2338707, + "ts": 6197202115534.782, "dur": 0.584, + "args": { + "External id": 44301,"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": 2338707, "tid": 2338707, + "ts": 6197202115537.773, "dur": 1.383, + "args": { + "External id": 44302,"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": 2338707, "tid": 2338707, + "ts": 6197202115538.438, "dur": 0.641, + "args": { + "External id": 44303,"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": 2338707, "tid": 2338707, + "ts": 6197202115539.398, "dur": 1.993, + "args": { + "External id": 44304,"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": 2338707, "tid": 2338707, + "ts": 6197202115539.888, "dur": 1.435, + "args": { + "External id": 44305,"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": 2338707, "tid": 2338707, + "ts": 6197202115541.629, "dur": 1.224, + "args": { + "External id": 44306,"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": 2338707, "tid": 2338707, + "ts": 6197202115542.169, "dur": 0.616, + "args": { + "External id": 44307,"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": 2338707, "tid": 2338707, + "ts": 6197202115543.098, "dur": 1.590, + "args": { + "External id": 44308,"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": 2338707, "tid": 2338707, + "ts": 6197202115543.896, "dur": 0.729, + "args": { + "External id": 44309,"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": 2338707, "tid": 2338707, + "ts": 6197202115544.940, "dur": 2.986, + "args": { + "External id": 44310,"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": 2338707, "tid": 2338707, + "ts": 6197202115546.938, "dur": 0.924, + "args": { + "External id": 44311,"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": 2338707, "tid": 2338707, + "ts": 6197202115548.187, "dur": 1.717, + "args": { + "External id": 44312,"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": 2338707, "tid": 2338707, + "ts": 6197202115549.181, "dur": 0.655, + "args": { + "External id": 44313,"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": 2338707, "tid": 2338707, + "ts": 6197202115550.132, "dur": 1.774, + "args": { + "External id": 44314,"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": 2338707, "tid": 2338707, + "ts": 6197202115550.791, "dur": 1.051, + "args": { + "External id": 44315,"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": 2338707, "tid": 2338707, + "ts": 6197202115552.328, "dur": 2.801, + "args": { + "External id": 44316,"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": 2338707, "tid": 2338707, + "ts": 6197202115554.295, "dur": 0.773, + "args": { + "External id": 44317,"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": 2338707, "tid": 2338707, + "ts": 6197202115557.706, "dur": 1.981, + "args": { + "External id": 44318,"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": 2338707, "tid": 2338707, + "ts": 6197202115558.489, "dur": 1.133, + "args": { + "External id": 44319,"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": 2338707, "tid": 2338707, + "ts": 6197202115559.922, "dur": 1.866, + "args": { + "External id": 44320,"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": 2338707, "tid": 2338707, + "ts": 6197202115560.515, "dur": 1.005, + "args": { + "External id": 44321,"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": 2338707, "tid": 2338707, + "ts": 6197202115562.042, "dur": 1.635, + "args": { + "External id": 44322,"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": 2338707, "tid": 2338707, + "ts": 6197202115562.829, "dur": 0.786, + "args": { + "External id": 44323,"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": 2338707, "tid": 2338707, + "ts": 6197202115563.943, "dur": 1.735, + "args": { + "External id": 44324,"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": 2338707, "tid": 2338707, + "ts": 6197202115564.498, "dur": 1.116, + "args": { + "External id": 44325,"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": 2338707, "tid": 2338707, + "ts": 6197202115565.905, "dur": 2.978, + "args": { + "External id": 44326,"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": 2338707, "tid": 2338707, + "ts": 6197202115567.714, "dur": 1.095, + "args": { + "External id": 44327,"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": 2338707, "tid": 2338707, + "ts": 6197202115569.121, "dur": 1.416, + "args": { + "External id": 44328,"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": 2338707, "tid": 2338707, + "ts": 6197202115569.744, "dur": 0.728, + "args": { + "External id": 44329,"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": 2338707, "tid": 2338707, + "ts": 6197202115570.762, "dur": 1.618, + "args": { + "External id": 44330,"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": 2338707, "tid": 2338707, + "ts": 6197202115571.594, "dur": 0.721, + "args": { + "External id": 44331,"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": 2338707, "tid": 2338707, + "ts": 6197202115572.615, "dur": 2.685, + "args": { + "External id": 44332,"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": 2338707, "tid": 2338707, + "ts": 6197202115574.555, "dur": 0.680, + "args": { + "External id": 44333,"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": 2338707, "tid": 2338707, + "ts": 6197202115577.563, "dur": 1.825, + "args": { + "External id": 44334,"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": 2338707, "tid": 2338707, + "ts": 6197202115578.105, "dur": 1.220, + "args": { + "External id": 44335,"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": 2338707, "tid": 2338707, + "ts": 6197202115579.641, "dur": 2.724, + "args": { + "External id": 44336,"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": 2338707, "tid": 2338707, + "ts": 6197202115580.390, "dur": 1.905, + "args": { + "External id": 44337,"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": 2338707, "tid": 2338707, + "ts": 6197202115582.628, "dur": 1.513, + "args": { + "External id": 44338,"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": 2338707, "tid": 2338707, + "ts": 6197202115583.127, "dur": 0.951, + "args": { + "External id": 44339,"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": 2338707, "tid": 2338707, + "ts": 6197202115584.460, "dur": 1.531, + "args": { + "External id": 44340,"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": 2338707, "tid": 2338707, + "ts": 6197202115585.106, "dur": 0.821, + "args": { + "External id": 44341,"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": 2338707, "tid": 2338707, + "ts": 6197202115586.226, "dur": 2.414, + "args": { + "External id": 44342,"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": 2338707, "tid": 2338707, + "ts": 6197202115587.987, "dur": 0.590, + "args": { + "External id": 44343,"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": 2338707, "tid": 2338707, + "ts": 6197202115588.876, "dur": 1.289, + "args": { + "External id": 44344,"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": 2338707, "tid": 2338707, + "ts": 6197202115589.663, "dur": 0.440, + "args": { + "External id": 44345,"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": 2338707, "tid": 2338707, + "ts": 6197202115590.422, "dur": 1.176, + "args": { + "External id": 44346,"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": 2338707, "tid": 2338707, + "ts": 6197202115591.035, "dur": 0.499, + "args": { + "External id": 44347,"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": 2338707, "tid": 2338707, + "ts": 6197202115591.932, "dur": 3.129, + "args": { + "External id": 44348,"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": 2338707, "tid": 2338707, + "ts": 6197202115594.199, "dur": 0.801, + "args": { + "External id": 44349,"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": 2338707, "tid": 2338707, + "ts": 6197202115597.182, "dur": 1.603, + "args": { + "External id": 44350,"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": 2338707, "tid": 2338707, + "ts": 6197202115598.028, "dur": 0.693, + "args": { + "External id": 44351,"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": 2338707, "tid": 2338707, + "ts": 6197202115599.025, "dur": 2.419, + "args": { + "External id": 44352,"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": 2338707, "tid": 2338707, + "ts": 6197202115599.529, "dur": 1.838, + "args": { + "External id": 44353,"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": 2338707, "tid": 2338707, + "ts": 6197202115601.669, "dur": 1.542, + "args": { + "External id": 44354,"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": 2338707, "tid": 2338707, + "ts": 6197202115602.549, "dur": 0.597, + "args": { + "External id": 44355,"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": 2338707, "tid": 2338707, + "ts": 6197202115603.460, "dur": 1.282, + "args": { + "External id": 44356,"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": 2338707, "tid": 2338707, + "ts": 6197202115604.138, "dur": 0.541, + "args": { + "External id": 44357,"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": 2338707, "tid": 2338707, + "ts": 6197202115605.046, "dur": 3.516, + "args": { + "External id": 44358,"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": 2338707, "tid": 2338707, + "ts": 6197202115607.770, "dur": 0.722, + "args": { + "External id": 44359,"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": 2338707, "tid": 2338707, + "ts": 6197202115608.823, "dur": 1.415, + "args": { + "External id": 44360,"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": 2338707, "tid": 2338707, + "ts": 6197202115609.648, "dur": 0.530, + "args": { + "External id": 44361,"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": 2338707, "tid": 2338707, + "ts": 6197202115610.507, "dur": 1.353, + "args": { + "External id": 44362,"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": 2338707, "tid": 2338707, + "ts": 6197202115611.180, "dur": 0.617, + "args": { + "External id": 44363,"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": 2338707, "tid": 2338707, + "ts": 6197202115612.095, "dur": 2.685, + "args": { + "External id": 44364,"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": 2338707, "tid": 2338707, + "ts": 6197202115614.131, "dur": 0.572, + "args": { + "External id": 44365,"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": 2338707, "tid": 2338707, + "ts": 6197202115617.041, "dur": 1.890, + "args": { + "External id": 44366,"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": 2338707, "tid": 2338707, + "ts": 6197202115617.862, "dur": 1.005, + "args": { + "External id": 44367,"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": 2338707, "tid": 2338707, + "ts": 6197202115619.181, "dur": 2.184, + "args": { + "External id": 44368,"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": 2338707, "tid": 2338707, + "ts": 6197202115619.845, "dur": 1.360, + "args": { + "External id": 44369,"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": 2338707, "tid": 2338707, + "ts": 6197202115621.598, "dur": 1.591, + "args": { + "External id": 44370,"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": 2338707, "tid": 2338707, + "ts": 6197202115622.131, "dur": 0.994, + "args": { + "External id": 44371,"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": 2338707, "tid": 2338707, + "ts": 6197202115623.422, "dur": 1.493, + "args": { + "External id": 44372,"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": 2338707, "tid": 2338707, + "ts": 6197202115624.208, "dur": 0.640, + "args": { + "External id": 44373,"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": 2338707, "tid": 2338707, + "ts": 6197202115625.142, "dur": 2.969, + "args": { + "External id": 44374,"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": 2338707, "tid": 2338707, + "ts": 6197202115627.199, "dur": 0.847, + "args": { + "External id": 44375,"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": 2338707, "tid": 2338707, + "ts": 6197202115628.385, "dur": 1.605, + "args": { + "External id": 44376,"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": 2338707, "tid": 2338707, + "ts": 6197202115628.899, "dur": 1.027, + "args": { + "External id": 44377,"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": 2338707, "tid": 2338707, + "ts": 6197202115630.212, "dur": 1.397, + "args": { + "External id": 44378,"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": 2338707, "tid": 2338707, + "ts": 6197202115630.814, "dur": 0.724, + "args": { + "External id": 44379,"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": 2338707, "tid": 2338707, + "ts": 6197202115631.855, "dur": 2.250, + "args": { + "External id": 44380,"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": 2338707, "tid": 2338707, + "ts": 6197202115633.407, "dur": 0.633, + "args": { + "External id": 44381,"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": 2338707, "tid": 2338707, + "ts": 6197202115636.302, "dur": 1.553, + "args": { + "External id": 44382,"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": 2338707, "tid": 2338707, + "ts": 6197202115637.176, "dur": 0.603, + "args": { + "External id": 44383,"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": 2338707, "tid": 2338707, + "ts": 6197202115638.106, "dur": 1.964, + "args": { + "External id": 44384,"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": 2338707, "tid": 2338707, + "ts": 6197202115638.836, "dur": 1.155, + "args": { + "External id": 44385,"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": 2338707, "tid": 2338707, + "ts": 6197202115640.303, "dur": 1.402, + "args": { + "External id": 44386,"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": 2338707, "tid": 2338707, + "ts": 6197202115641.118, "dur": 0.519, + "args": { + "External id": 44387,"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": 2338707, "tid": 2338707, + "ts": 6197202115641.935, "dur": 1.211, + "args": { + "External id": 44388,"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": 2338707, "tid": 2338707, + "ts": 6197202115642.591, "dur": 0.482, + "args": { + "External id": 44389,"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": 2338707, "tid": 2338707, + "ts": 6197202115643.375, "dur": 2.887, + "args": { + "External id": 44390,"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": 2338707, "tid": 2338707, + "ts": 6197202115645.605, "dur": 0.590, + "args": { + "External id": 44391,"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": 2338707, "tid": 2338707, + "ts": 6197202115646.501, "dur": 1.325, + "args": { + "External id": 44392,"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": 2338707, "tid": 2338707, + "ts": 6197202115647.246, "dur": 0.506, + "args": { + "External id": 44393,"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": 2338707, "tid": 2338707, + "ts": 6197202115648.057, "dur": 1.593, + "args": { + "External id": 44394,"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": 2338707, "tid": 2338707, + "ts": 6197202115648.478, "dur": 1.107, + "args": { + "External id": 44395,"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": 2338707, "tid": 2338707, + "ts": 6197202115649.895, "dur": 2.805, + "args": { + "External id": 44396,"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": 2338707, "tid": 2338707, + "ts": 6197202115652.156, "dur": 0.476, + "args": { + "External id": 44397,"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": 2338707, "tid": 2338707, + "ts": 6197202115654.870, "dur": 1.239, + "args": { + "External id": 44398,"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": 2338707, "tid": 2338707, + "ts": 6197202115655.525, "dur": 0.519, + "args": { + "External id": 44399,"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": 2338707, "tid": 2338707, + "ts": 6197202115656.362, "dur": 3.146, + "args": { + "External id": 44400,"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": 2338707, "tid": 2338707, + "ts": 6197202115658.362, "dur": 1.078, + "args": { + "External id": 44401,"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": 2338707, "tid": 2338707, + "ts": 6197202115659.789, "dur": 1.356, + "args": { + "External id": 44402,"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": 2338707, "tid": 2338707, + "ts": 6197202115660.477, "dur": 0.603, + "args": { + "External id": 44403,"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": 2338707, "tid": 2338707, + "ts": 6197202115661.395, "dur": 1.689, + "args": { + "External id": 44404,"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": 2338707, "tid": 2338707, + "ts": 6197202115661.938, "dur": 1.082, + "args": { + "External id": 44405,"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": 2338707, "tid": 2338707, + "ts": 6197202115663.378, "dur": 2.177, + "args": { + "External id": 44406,"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": 2338707, "tid": 2338707, + "ts": 6197202115664.960, "dur": 0.533, + "args": { + "External id": 44407,"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": 2338707, "tid": 2338707, + "ts": 6197202115665.804, "dur": 1.041, + "args": { + "External id": 44408,"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": 2338707, "tid": 2338707, + "ts": 6197202115666.447, "dur": 0.331, + "args": { + "External id": 44409,"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": 2338707, "tid": 2338707, + "ts": 6197202115667.067, "dur": 1.113, + "args": { + "External id": 44410,"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": 2338707, "tid": 2338707, + "ts": 6197202115667.636, "dur": 0.480, + "args": { + "External id": 44411,"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": 2338707, "tid": 2338707, + "ts": 6197202115668.491, "dur": 2.746, + "args": { + "External id": 44412,"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": 2338707, "tid": 2338707, + "ts": 6197202115670.360, "dur": 0.809, + "args": { + "External id": 44413,"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": 2338707, "tid": 2338707, + "ts": 6197202115673.316, "dur": 1.078, + "args": { + "External id": 44414,"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": 2338707, "tid": 2338707, + "ts": 6197202115673.853, "dur": 0.477, + "args": { + "External id": 44415,"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": 2338707, "tid": 2338707, + "ts": 6197202115674.616, "dur": 2.205, + "args": { + "External id": 44416,"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": 2338707, "tid": 2338707, + "ts": 6197202115675.222, "dur": 1.526, + "args": { + "External id": 44417,"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": 2338707, "tid": 2338707, + "ts": 6197202115677.046, "dur": 1.314, + "args": { + "External id": 44418,"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": 2338707, "tid": 2338707, + "ts": 6197202115677.816, "dur": 0.479, + "args": { + "External id": 44419,"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": 2338707, "tid": 2338707, + "ts": 6197202115679.109, "dur": 1.549, + "args": { + "External id": 44420,"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": 2338707, "tid": 2338707, + "ts": 6197202115679.719, "dur": 0.876, + "args": { + "External id": 44421,"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": 2338707, "tid": 2338707, + "ts": 6197202115680.886, "dur": 2.488, + "args": { + "External id": 44422,"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": 2338707, "tid": 2338707, + "ts": 6197202115682.732, "dur": 0.578, + "args": { + "External id": 44423,"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": 2338707, "tid": 2338707, + "ts": 6197202115683.631, "dur": 1.745, + "args": { + "External id": 44424,"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": 2338707, "tid": 2338707, + "ts": 6197202115684.575, "dur": 0.736, + "args": { + "External id": 44425,"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": 2338707, "tid": 2338707, + "ts": 6197202115685.612, "dur": 1.562, + "args": { + "External id": 44426,"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": 2338707, "tid": 2338707, + "ts": 6197202115686.434, "dur": 0.677, + "args": { + "External id": 44427,"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": 2338707, "tid": 2338707, + "ts": 6197202115687.397, "dur": 1.924, + "args": { + "External id": 44428,"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": 2338707, "tid": 2338707, + "ts": 6197202115688.860, "dur": 0.398, + "args": { + "External id": 44429,"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": 2338707, "tid": 2338707, + "ts": 6197202115691.353, "dur": 1.239, + "args": { + "External id": 44430,"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": 2338707, "tid": 2338707, + "ts": 6197202115691.785, "dur": 0.744, + "args": { + "External id": 44431,"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": 2338707, "tid": 2338707, + "ts": 6197202115692.814, "dur": 2.482, + "args": { + "External id": 44432,"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": 2338707, "tid": 2338707, + "ts": 6197202115693.727, "dur": 1.499, + "args": { + "External id": 44433,"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": 2338707, "tid": 2338707, + "ts": 6197202115695.522, "dur": 1.262, + "args": { + "External id": 44434,"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": 2338707, "tid": 2338707, + "ts": 6197202115696.117, "dur": 0.603, + "args": { + "External id": 44435,"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": 2338707, "tid": 2338707, + "ts": 6197202115697.007, "dur": 1.564, + "args": { + "External id": 44436,"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": 2338707, "tid": 2338707, + "ts": 6197202115697.819, "dur": 0.690, + "args": { + "External id": 44437,"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": 2338707, "tid": 2338707, + "ts": 6197202115698.809, "dur": 17.459, + "args": { + "External id": 44438,"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": 2338707, "tid": 2338707, + "ts": 6197202115712.923, "dur": 2.209, + "args": { + "External id": 44439,"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": 2338707, "tid": 2338707, + "ts": 6197202115717.964, "dur": 2.930, + "args": { + "External id": 44440,"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": 2338707, "tid": 2338707, + "ts": 6197202115719.842, "dur": 0.867, + "args": { + "External id": 44441,"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": 2338707, "tid": 2338707, + "ts": 6197202115721.392, "dur": 2.027, + "args": { + "External id": 44442,"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": 2338707, "tid": 2338707, + "ts": 6197202115722.549, "dur": 0.694, + "args": { + "External id": 44443,"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": 2338707, "tid": 2338707, + "ts": 6197202115723.869, "dur": 3.252, + "args": { + "External id": 44444,"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": 2338707, "tid": 2338707, + "ts": 6197202115726.123, "dur": 0.831, + "args": { + "External id": 44445,"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": 2338707, "tid": 2338707, + "ts": 6197202115729.588, "dur": 2.326, + "args": { + "External id": 44446,"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": 2338707, "tid": 2338707, + "ts": 6197202115730.779, "dur": 0.977, + "args": { + "External id": 44447,"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": 2338707, "tid": 2338707, + "ts": 6197202115732.367, "dur": 3.047, + "args": { + "External id": 44448,"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": 2338707, "tid": 2338707, + "ts": 6197202115733.349, "dur": 1.898, + "args": { + "External id": 44449,"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": 2338707, "tid": 2338707, + "ts": 6197202115735.946, "dur": 2.273, + "args": { + "External id": 44450,"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": 2338707, "tid": 2338707, + "ts": 6197202115737.085, "dur": 0.911, + "args": { + "External id": 44451,"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": 2338707, "tid": 2338707, + "ts": 6197202115738.916, "dur": 2.258, + "args": { + "External id": 44452,"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": 2338707, "tid": 2338707, + "ts": 6197202115739.997, "dur": 1.014, + "args": { + "External id": 44453,"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": 2338707, "tid": 2338707, + "ts": 6197202115741.693, "dur": 3.324, + "args": { + "External id": 44454,"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": 2338707, "tid": 2338707, + "ts": 6197202115743.756, "dur": 1.099, + "args": { + "External id": 44455,"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": 2338707, "tid": 2338707, + "ts": 6197202115745.540, "dur": 2.305, + "args": { + "External id": 44456,"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": 2338707, "tid": 2338707, + "ts": 6197202115746.609, "dur": 1.078, + "args": { + "External id": 44457,"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": 2338707, "tid": 2338707, + "ts": 6197202115748.509, "dur": 2.780, + "args": { + "External id": 44458,"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": 2338707, "tid": 2338707, + "ts": 6197202115749.765, "dur": 1.364, + "args": { + "External id": 44459,"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": 2338707, "tid": 2338707, + "ts": 6197202115751.776, "dur": 3.697, + "args": { + "External id": 44460,"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": 2338707, "tid": 2338707, + "ts": 6197202115754.315, "dur": 1.005, + "args": { + "External id": 44461,"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": 2338707, "tid": 2338707, + "ts": 6197202115757.723, "dur": 2.193, + "args": { + "External id": 44462,"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": 2338707, "tid": 2338707, + "ts": 6197202115758.988, "dur": 0.764, + "args": { + "External id": 44463,"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": 2338707, "tid": 2338707, + "ts": 6197202115760.389, "dur": 3.558, + "args": { + "External id": 44464,"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": 2338707, "tid": 2338707, + "ts": 6197202115761.416, "dur": 2.361, + "args": { + "External id": 44465,"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": 2338707, "tid": 2338707, + "ts": 6197202115764.454, "dur": 2.323, + "args": { + "External id": 44466,"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": 2338707, "tid": 2338707, + "ts": 6197202115765.483, "dur": 0.950, + "args": { + "External id": 44467,"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": 2338707, "tid": 2338707, + "ts": 6197202115767.289, "dur": 2.184, + "args": { + "External id": 44468,"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": 2338707, "tid": 2338707, + "ts": 6197202115768.487, "dur": 0.821, + "args": { + "External id": 44469,"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": 2338707, "tid": 2338707, + "ts": 6197202115770.063, "dur": 3.490, + "args": { + "External id": 44470,"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": 2338707, "tid": 2338707, + "ts": 6197202115772.632, "dur": 0.774, + "args": { + "External id": 44471,"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": 2338707, "tid": 2338707, + "ts": 6197202115774.045, "dur": 2.838, + "args": { + "External id": 44472,"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": 2338707, "tid": 2338707, + "ts": 6197202115775.156, "dur": 1.315, + "args": { + "External id": 44473,"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": 2338707, "tid": 2338707, + "ts": 6197202115777.489, "dur": 1.584, + "args": { + "External id": 44474,"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": 2338707, "tid": 2338707, + "ts": 6197202115778.301, "dur": 0.697, + "args": { + "External id": 44475,"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": 2338707, "tid": 2338707, + "ts": 6197202115779.316, "dur": 2.533, + "args": { + "External id": 44476,"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": 2338707, "tid": 2338707, + "ts": 6197202115781.094, "dur": 0.683, + "args": { + "External id": 44477,"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": 2338707, "tid": 2338707, + "ts": 6197202115783.589, "dur": 1.548, + "args": { + "External id": 44478,"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": 2338707, "tid": 2338707, + "ts": 6197202115784.179, "dur": 0.883, + "args": { + "External id": 44479,"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": 2338707, "tid": 2338707, + "ts": 6197202115785.374, "dur": 1.986, + "args": { + "External id": 44480,"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": 2338707, "tid": 2338707, + "ts": 6197202115786.147, "dur": 1.125, + "args": { + "External id": 44481,"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": 2338707, "tid": 2338707, + "ts": 6197202115787.590, "dur": 1.878, + "args": { + "External id": 44482,"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": 2338707, "tid": 2338707, + "ts": 6197202115788.400, "dur": 1.005, + "args": { + "External id": 44483,"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": 2338707, "tid": 2338707, + "ts": 6197202115789.712, "dur": 1.167, + "args": { + "External id": 44484,"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": 2338707, "tid": 2338707, + "ts": 6197202115790.345, "dur": 0.464, + "args": { + "External id": 44485,"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": 2338707, "tid": 2338707, + "ts": 6197202115791.130, "dur": 3.020, + "args": { + "External id": 44486,"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": 2338707, "tid": 2338707, + "ts": 6197202115793.531, "dur": 0.552, + "args": { + "External id": 44487,"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": 2338707, "tid": 2338707, + "ts": 6197202115794.399, "dur": 1.755, + "args": { + "External id": 44488,"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": 2338707, "tid": 2338707, + "ts": 6197202115795.023, "dur": 1.064, + "args": { + "External id": 44489,"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": 2338707, "tid": 2338707, + "ts": 6197202115796.392, "dur": 1.495, + "args": { + "External id": 44490,"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": 2338707, "tid": 2338707, + "ts": 6197202115796.989, "dur": 0.827, + "args": { + "External id": 44491,"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": 2338707, "tid": 2338707, + "ts": 6197202115798.111, "dur": 2.069, + "args": { + "External id": 44492,"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": 2338707, "tid": 2338707, + "ts": 6197202115799.550, "dur": 0.557, + "args": { + "External id": 44493,"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": 2338707, "tid": 2338707, + "ts": 6197202115802.296, "dur": 5.227, + "args": { + "External id": 44494,"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": 2338707, "tid": 2338707, + "ts": 6197202115807.147, "dur": 0.309, + "args": { + "External id": 44495,"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": 2338707, "tid": 2338707, + "ts": 6197202115807.779, "dur": 2.909, + "args": { + "External id": 44496,"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": 2338707, "tid": 2338707, + "ts": 6197202115809.144, "dur": 1.456, + "args": { + "External id": 44497,"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": 2338707, "tid": 2338707, + "ts": 6197202115811.012, "dur": 1.686, + "args": { + "External id": 44498,"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": 2338707, "tid": 2338707, + "ts": 6197202115811.609, "dur": 1.029, + "args": { + "External id": 44499,"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": 2338707, "tid": 2338707, + "ts": 6197202115813.383, "dur": 1.797, + "args": { + "External id": 44500,"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": 2338707, "tid": 2338707, + "ts": 6197202115813.987, "dur": 1.130, + "args": { + "External id": 44501,"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": 2338707, "tid": 2338707, + "ts": 6197202115815.432, "dur": 2.963, + "args": { + "External id": 44502,"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": 2338707, "tid": 2338707, + "ts": 6197202115817.419, "dur": 0.912, + "args": { + "External id": 44503,"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": 2338707, "tid": 2338707, + "ts": 6197202115818.636, "dur": 1.414, + "args": { + "External id": 44504,"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": 2338707, "tid": 2338707, + "ts": 6197202115819.398, "dur": 0.587, + "args": { + "External id": 44505,"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": 2338707, "tid": 2338707, + "ts": 6197202115820.269, "dur": 1.388, + "args": { + "External id": 44506,"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": 2338707, "tid": 2338707, + "ts": 6197202115820.896, "dur": 0.698, + "args": { + "External id": 44507,"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": 2338707, "tid": 2338707, + "ts": 6197202115821.899, "dur": 1.978, + "args": { + "External id": 44508,"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": 2338707, "tid": 2338707, + "ts": 6197202115823.408, "dur": 0.406, + "args": { + "External id": 44509,"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": 2338707, "tid": 2338707, + "ts": 6197202115825.888, "dur": 1.083, + "args": { + "External id": 44510,"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": 2338707, "tid": 2338707, + "ts": 6197202115826.419, "dur": 0.490, + "args": { + "External id": 44511,"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": 2338707, "tid": 2338707, + "ts": 6197202115827.214, "dur": 2.185, + "args": { + "External id": 44512,"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": 2338707, "tid": 2338707, + "ts": 6197202115827.836, "dur": 1.489, + "args": { + "External id": 44513,"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": 2338707, "tid": 2338707, + "ts": 6197202115829.664, "dur": 1.450, + "args": { + "External id": 44514,"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": 2338707, "tid": 2338707, + "ts": 6197202115830.605, "dur": 0.445, + "args": { + "External id": 44515,"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": 2338707, "tid": 2338707, + "ts": 6197202115831.336, "dur": 1.538, + "args": { + "External id": 44516,"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": 2338707, "tid": 2338707, + "ts": 6197202115831.953, "dur": 0.855, + "args": { + "External id": 44517,"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": 2338707, "tid": 2338707, + "ts": 6197202115833.094, "dur": 2.816, + "args": { + "External id": 44518,"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": 2338707, "tid": 2338707, + "ts": 6197202115835.218, "dur": 0.618, + "args": { + "External id": 44519,"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": 2338707, "tid": 2338707, + "ts": 6197202115836.191, "dur": 1.265, + "args": { + "External id": 44520,"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": 2338707, "tid": 2338707, + "ts": 6197202115836.960, "dur": 0.431, + "args": { + "External id": 44521,"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": 2338707, "tid": 2338707, + "ts": 6197202115837.705, "dur": 1.528, + "args": { + "External id": 44522,"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": 2338707, "tid": 2338707, + "ts": 6197202115838.345, "dur": 0.807, + "args": { + "External id": 44523,"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": 2338707, "tid": 2338707, + "ts": 6197202115839.453, "dur": 2.912, + "args": { + "External id": 44524,"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": 2338707, "tid": 2338707, + "ts": 6197202115841.482, "dur": 0.815, + "args": { + "External id": 44525,"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": 2338707, "tid": 2338707, + "ts": 6197202115844.678, "dur": 1.418, + "args": { + "External id": 44526,"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": 2338707, "tid": 2338707, + "ts": 6197202115845.505, "dur": 0.529, + "args": { + "External id": 44527,"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": 2338707, "tid": 2338707, + "ts": 6197202115846.332, "dur": 1.945, + "args": { + "External id": 44528,"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": 2338707, "tid": 2338707, + "ts": 6197202115846.966, "dur": 1.221, + "args": { + "External id": 44529,"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": 2338707, "tid": 2338707, + "ts": 6197202115848.566, "dur": 1.456, + "args": { + "External id": 44530,"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": 2338707, "tid": 2338707, + "ts": 6197202115849.298, "dur": 0.659, + "args": { + "External id": 44531,"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": 2338707, "tid": 2338707, + "ts": 6197202115850.335, "dur": 1.263, + "args": { + "External id": 44532,"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": 2338707, "tid": 2338707, + "ts": 6197202115851.143, "dur": 0.381, + "args": { + "External id": 44533,"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": 2338707, "tid": 2338707, + "ts": 6197202115851.872, "dur": 2.755, + "args": { + "External id": 44534,"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": 2338707, "tid": 2338707, + "ts": 6197202115853.950, "dur": 0.609, + "args": { + "External id": 44535,"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": 2338707, "tid": 2338707, + "ts": 6197202115854.870, "dur": 1.133, + "args": { + "External id": 44536,"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": 2338707, "tid": 2338707, + "ts": 6197202115855.369, "dur": 0.568, + "args": { + "External id": 44537,"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": 2338707, "tid": 2338707, + "ts": 6197202115856.237, "dur": 1.787, + "args": { + "External id": 44538,"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": 2338707, "tid": 2338707, + "ts": 6197202115856.907, "dur": 1.054, + "args": { + "External id": 44539,"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": 2338707, "tid": 2338707, + "ts": 6197202115858.245, "dur": 2.834, + "args": { + "External id": 44540,"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": 2338707, "tid": 2338707, + "ts": 6197202115860.230, "dur": 0.786, + "args": { + "External id": 44541,"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": 2338707, "tid": 2338707, + "ts": 6197202115863.106, "dur": 1.168, + "args": { + "External id": 44542,"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": 2338707, "tid": 2338707, + "ts": 6197202115863.690, "dur": 0.521, + "args": { + "External id": 44543,"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": 2338707, "tid": 2338707, + "ts": 6197202115864.498, "dur": 27.620, + "args": { + "External id": 44544,"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": 2338707, "tid": 2338707, + "ts": 6197202115889.350, "dur": 2.647, + "args": { + "External id": 44545,"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": 2338707, "tid": 2338707, + "ts": 6197202115892.371, "dur": 1.222, + "args": { + "External id": 44546,"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": 2338707, "tid": 2338707, + "ts": 6197202115892.959, "dur": 0.544, + "args": { + "External id": 44547,"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": 2338707, "tid": 2338707, + "ts": 6197202115893.845, "dur": 1.059, + "args": { + "External id": 44548,"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": 2338707, "tid": 2338707, + "ts": 6197202115894.230, "dur": 0.613, + "args": { + "External id": 44549,"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": 2338707, "tid": 2338707, + "ts": 6197202115895.242, "dur": 1.882, + "args": { + "External id": 44550,"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": 2338707, "tid": 2338707, + "ts": 6197202115896.503, "dur": 0.553, + "args": { + "External id": 44551,"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": 2338707, "tid": 2338707, + "ts": 6197202115897.365, "dur": 1.125, + "args": { + "External id": 44552,"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": 2338707, "tid": 2338707, + "ts": 6197202115897.872, "dur": 0.550, + "args": { + "External id": 44553,"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": 2338707, "tid": 2338707, + "ts": 6197202115898.730, "dur": 0.837, + "args": { + "External id": 44554,"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": 2338707, "tid": 2338707, + "ts": 6197202115899.136, "dur": 0.365, + "args": { + "External id": 44555,"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": 2338707, "tid": 2338707, + "ts": 6197202115900.128, "dur": 2.187, + "args": { + "External id": 44556,"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": 2338707, "tid": 2338707, + "ts": 6197202115901.809, "dur": 0.442, + "args": { + "External id": 44557,"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": 2338707, "tid": 2338707, + "ts": 6197202115904.513, "dur": 1.540, + "args": { + "External id": 44558,"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": 2338707, "tid": 2338707, + "ts": 6197202115905.182, "dur": 0.768, + "args": { + "External id": 44559,"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": 2338707, "tid": 2338707, + "ts": 6197202115906.311, "dur": 1.983, + "args": { + "External id": 44560,"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": 2338707, "tid": 2338707, + "ts": 6197202115906.916, "dur": 1.308, + "args": { + "External id": 44561,"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": 2338707, "tid": 2338707, + "ts": 6197202115908.540, "dur": 1.516, + "args": { + "External id": 44562,"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": 2338707, "tid": 2338707, + "ts": 6197202115909.320, "dur": 0.676, + "args": { + "External id": 44563,"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": 2338707, "tid": 2338707, + "ts": 6197202115910.577, "dur": 1.013, + "args": { + "External id": 44564,"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": 2338707, "tid": 2338707, + "ts": 6197202115911.113, "dur": 0.412, + "args": { + "External id": 44565,"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": 2338707, "tid": 2338707, + "ts": 6197202115911.823, "dur": 3.050, + "args": { + "External id": 44566,"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": 2338707, "tid": 2338707, + "ts": 6197202115914.230, "dur": 0.555, + "args": { + "External id": 44567,"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": 2338707, "tid": 2338707, + "ts": 6197202115915.112, "dur": 1.520, + "args": { + "External id": 44568,"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": 2338707, "tid": 2338707, + "ts": 6197202115915.780, "dur": 0.780, + "args": { + "External id": 44569,"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": 2338707, "tid": 2338707, + "ts": 6197202115916.986, "dur": 1.111, + "args": { + "External id": 44570,"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": 2338707, "tid": 2338707, + "ts": 6197202115917.584, "dur": 0.449, + "args": { + "External id": 44571,"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": 2338707, "tid": 2338707, + "ts": 6197202115918.448, "dur": 2.884, + "args": { + "External id": 44572,"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": 2338707, "tid": 2338707, + "ts": 6197202115920.543, "dur": 0.725, + "args": { + "External id": 44573,"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": 2338707, "tid": 2338707, + "ts": 6197202115923.336, "dur": 1.786, + "args": { + "External id": 44574,"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": 2338707, "tid": 2338707, + "ts": 6197202115924.205, "dur": 0.850, + "args": { + "External id": 44575,"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": 2338707, "tid": 2338707, + "ts": 6197202115925.429, "dur": 2.278, + "args": { + "External id": 44576,"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": 2338707, "tid": 2338707, + "ts": 6197202115925.954, "dur": 1.686, + "args": { + "External id": 44577,"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": 2338707, "tid": 2338707, + "ts": 6197202115927.938, "dur": 1.412, + "args": { + "External id": 44578,"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": 2338707, "tid": 2338707, + "ts": 6197202115928.451, "dur": 0.838, + "args": { + "External id": 44579,"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": 2338707, "tid": 2338707, + "ts": 6197202115950.333, "dur": 164.443, + "args": { + "External id": 44580,"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": 2338707, "tid": 2338707, + "ts": 6197202116236.887, "dur": 146.392, + "args": { + "External id": 44581,"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": 2338707, "tid": 2338707, + "ts": 6197202116310.163, "dur": 51.219, + "args": { + "External id": 44582,"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": 2338707, "tid": 2338707, + "ts": 6197202116326.306, "dur": 1.237, + "args": { + "External id": 44583,"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": 2338707, "tid": 2338707, + "ts": 6197202116758.217, "dur": 1152.713, + "args": { + "External id": 44584,"Sequence number": 480230, "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": 2338707, "tid": 2338707, + "ts": 6197202116831.990, "dur": 75.423, + "args": { + "External id": 44585,"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": 2338707, "tid": 2338707, + "ts": 6197202116838.010, "dur": 1.820, + "args": { + "External id": 44586,"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": 2338707, "tid": 2338707, + "ts": 6197202116842.356, "dur": 0.616, + "args": { + "External id": 44587,"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": 2338707, "tid": 2338707, + "ts": 6197202116998.283, "dur": 505.492, + "args": { + "External id": 44588,"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": 2338707, "tid": 2338707, + "ts": 6197202117002.183, "dur": 88.212, + "args": { + "External id": 44589,"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": 2338707, "tid": 2338707, + "ts": 6197202117007.656, "dur": 11.987, + "args": { + "External id": 44590,"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": 2338707, "tid": 2338707, + "ts": 6197202117012.895, "dur": 5.591, + "args": { + "External id": 44591,"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": 2338707, "tid": 2338707, + "ts": 6197202117021.203, "dur": 68.087, + "args": { + "External id": 44592,"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": 2338707, "tid": 2338707, + "ts": 6197202117100.645, "dur": 399.559, + "args": { + "External id": 44593,"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": 2338707, "tid": 2338707, + "ts": 6197202117138.716, "dur": 354.685, + "args": { + "External id": 44594,"Record function id": 0, "Collective name": "allreduce", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 1, "Input Strides": [[[]], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "1", "", "[]", "[]", "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": 2338707, "tid": 2338707, + "ts": 6197202117152.755, "dur": 334.411, + "args": { + "External id": 44595,"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": 2338707, "tid": 2338707, + "ts": 6197202117584.894, "dur": 280.915, + "args": { + "External id": 44596,"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": 2338707, "tid": 2338707, + "ts": 6197202117721.563, "dur": 47.732, + "args": { + "External id": 44597,"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": 2338707, "tid": 2338707, + "ts": 6197202117748.900, "dur": 7.358, + "args": { + "External id": 44598,"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": ["", "", "1", "", "[]", "[]", "-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": 1, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::pow", "pid": 2338707, "tid": 2338707, + "ts": 6197202117804.081, "dur": 54.527, + "args": { + "External id": 44599,"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": 2338707, "tid": 2338707, + "ts": 6197202117807.527, "dur": 1.513, + "args": { + "External id": 44600,"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": 2338707, "tid": 2338707, + "ts": 6197202117810.859, "dur": 0.582, + "args": { + "External id": 44601,"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": 2338707, "tid": 2338707, + "ts": 6197202117930.250, "dur": 22.498, + "args": { + "External id": 44602,"Sequence number": 480231, "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": 2338707, "tid": 2338707, + "ts": 6197202117940.337, "dur": 9.231, + "args": { + "External id": 44603,"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": 2338707, "tid": 2338707, + "ts": 6197202117943.302, "dur": 6.091, + "args": { + "External id": 44604,"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": 2338707, "tid": 2338707, + "ts": 6197202118338.524, "dur": 40.776, + "args": { + "External id": 44605,"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": 2338707, "tid": 2338707, + "ts": 6197202118390.540, "dur": 21.064, + "args": { + "External id": 44606,"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": 2338707, "tid": 2338707, + "ts": 6197202118419.329, "dur": 20.412, + "args": { + "External id": 44607,"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": 2338707, "tid": 2338707, + "ts": 6197202118454.371, "dur": 24.911, + "args": { + "External id": 44608,"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": 2338707, "tid": 2338707, + "ts": 6197202118457.519, "dur": 0.445, + "args": { + "External id": 44609,"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": 2338707, "tid": 2338707, + "ts": 6197202118497.561, "dur": 0.470, + "args": { + "External id": 44610,"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": 2338707, "tid": 2338707, + "ts": 6197202118619.052, "dur": 1172.925, + "args": { + "External id": 44611,"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": 2338707, "tid": 2338707, + "ts": 6197202119088.425, "dur": 649.724, + "args": { + "External id": 44612,"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": 2338707, "tid": 2338707, + "ts": 6197202119846.526, "dur": 37.453, + "args": { + "External id": 44613,"Sequence number": 480232, "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": 2338707, "tid": 2338707, + "ts": 6197202119850.866, "dur": 32.466, + "args": { + "External id": 44614,"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": 2338707, "tid": 2338707, + "ts": 6197202119887.952, "dur": 9699.684, + "args": { + "External id": 44615,"Sequence number": 480232, "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": 2338707, "tid": 2338707, + "ts": 6197202119890.317, "dur": 9696.628, + "args": { + "External id": 44616,"Sequence number": 480232, "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": 2338707, "tid": 2338707, + "ts": 6197202119894.812, "dur": 9689.250, + "args": { + "External id": 44617,"Sequence number": 480232, "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": 2338707, "tid": 2338707, + "ts": 6197202129605.718, "dur": 86.100, + "args": { + "External id": 44618,"Sequence number": 480232, "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": 2338707, "tid": 2338707, + "ts": 6197202129609.700, "dur": 50.520, + "args": { + "External id": 44619,"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": 2338707, "tid": 2338707, + "ts": 6197202129617.446, "dur": 5.288, + "args": { + "External id": 44620,"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": 2338707, "tid": 2338707, + "ts": 6197202129624.770, "dur": 34.988, + "args": { + "External id": 44621,"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": 2338707, "tid": 2338707, + "ts": 6197202129634.271, "dur": 3.757, + "args": { + "External id": 44622,"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": 2338707, "tid": 2338707, + "ts": 6197202129662.239, "dur": 28.585, + "args": { + "External id": 44623,"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": 2338707, "tid": 2338707, + "ts": 6197202129695.433, "dur": 63.902, + "args": { + "External id": 44624,"Sequence number": 480232, "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": 2338707, "tid": 2338707, + "ts": 6197202129696.741, "dur": 62.345, + "args": { + "External id": 44625,"Sequence number": 480232, "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": 2338707, "tid": 2338707, + "ts": 6197202129698.018, "dur": 60.079, + "args": { + "External id": 44626,"Sequence number": 480232, "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": 2338707, "tid": 2338707, + "ts": 6197202129805.930, "dur": 6093.206, + "args": { + "External id": 44627,"Record function id": 0, "Ev Idx": 21655 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "Optimizer.step#AdamW.step", "pid": 2338707, "tid": 2338707, + "ts": 6197202129843.194, "dur": 6030.877, + "args": { + "External id": 44628,"Record function id": 0, "Ev Idx": 21656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_add_", "pid": 2338707, "tid": 2338707, + "ts": 6197202131260.056, "dur": 254.509, + "args": { + "External id": 44629,"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": 2338707, "tid": 2338707, + "ts": 6197202131280.103, "dur": 1.375, + "args": { + "External id": 44630,"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": 2338707, "tid": 2338707, + "ts": 6197202131282.596, "dur": 0.333, + "args": { + "External id": 44631,"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": 2338707, "tid": 2338707, + "ts": 6197202131283.614, "dur": 0.102, + "args": { + "External id": 44632,"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": 2338707, "tid": 2338707, + "ts": 6197202131284.233, "dur": 0.288, + "args": { + "External id": 44633,"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": 2338707, "tid": 2338707, + "ts": 6197202131285.020, "dur": 0.083, + "args": { + "External id": 44634,"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": 2338707, "tid": 2338707, + "ts": 6197202131285.456, "dur": 0.087, + "args": { + "External id": 44635,"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": 2338707, "tid": 2338707, + "ts": 6197202131285.861, "dur": 0.244, + "args": { + "External id": 44636,"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": 2338707, "tid": 2338707, + "ts": 6197202131286.421, "dur": 0.280, + "args": { + "External id": 44637,"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": 2338707, "tid": 2338707, + "ts": 6197202131287.141, "dur": 0.122, + "args": { + "External id": 44638,"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": 2338707, "tid": 2338707, + "ts": 6197202131287.529, "dur": 0.079, + "args": { + "External id": 44639,"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": 2338707, "tid": 2338707, + "ts": 6197202131287.965, "dur": 0.310, + "args": { + "External id": 44640,"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": 2338707, "tid": 2338707, + "ts": 6197202131288.536, "dur": 0.066, + "args": { + "External id": 44641,"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": 2338707, "tid": 2338707, + "ts": 6197202131288.895, "dur": 0.055, + "args": { + "External id": 44642,"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": 2338707, "tid": 2338707, + "ts": 6197202131289.201, "dur": 0.049, + "args": { + "External id": 44643,"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": 2338707, "tid": 2338707, + "ts": 6197202131289.772, "dur": 0.066, + "args": { + "External id": 44644,"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": 2338707, "tid": 2338707, + "ts": 6197202131290.152, "dur": 0.055, + "args": { + "External id": 44645,"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": 2338707, "tid": 2338707, + "ts": 6197202131290.461, "dur": 0.053, + "args": { + "External id": 44646,"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": 2338707, "tid": 2338707, + "ts": 6197202131291.053, "dur": 0.054, + "args": { + "External id": 44647,"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": 2338707, "tid": 2338707, + "ts": 6197202131291.576, "dur": 0.064, + "args": { + "External id": 44648,"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": 2338707, "tid": 2338707, + "ts": 6197202131292.103, "dur": 0.070, + "args": { + "External id": 44649,"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": 2338707, "tid": 2338707, + "ts": 6197202131292.725, "dur": 0.058, + "args": { + "External id": 44650,"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": 2338707, "tid": 2338707, + "ts": 6197202131293.246, "dur": 0.057, + "args": { + "External id": 44651,"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": 2338707, "tid": 2338707, + "ts": 6197202131293.764, "dur": 0.055, + "args": { + "External id": 44652,"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": 2338707, "tid": 2338707, + "ts": 6197202131294.245, "dur": 0.058, + "args": { + "External id": 44653,"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": 2338707, "tid": 2338707, + "ts": 6197202131294.710, "dur": 0.053, + "args": { + "External id": 44654,"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": 2338707, "tid": 2338707, + "ts": 6197202131295.178, "dur": 0.050, + "args": { + "External id": 44655,"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": 2338707, "tid": 2338707, + "ts": 6197202131295.582, "dur": 0.065, + "args": { + "External id": 44656,"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": 2338707, "tid": 2338707, + "ts": 6197202131296.080, "dur": 0.068, + "args": { + "External id": 44657,"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": 2338707, "tid": 2338707, + "ts": 6197202131296.641, "dur": 0.055, + "args": { + "External id": 44658,"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": 2338707, "tid": 2338707, + "ts": 6197202131297.056, "dur": 0.059, + "args": { + "External id": 44659,"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": 2338707, "tid": 2338707, + "ts": 6197202131297.465, "dur": 0.055, + "args": { + "External id": 44660,"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": 2338707, "tid": 2338707, + "ts": 6197202131297.938, "dur": 0.058, + "args": { + "External id": 44661,"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": 2338707, "tid": 2338707, + "ts": 6197202131298.263, "dur": 0.059, + "args": { + "External id": 44662,"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": 2338707, "tid": 2338707, + "ts": 6197202131298.754, "dur": 0.056, + "args": { + "External id": 44663,"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": 2338707, "tid": 2338707, + "ts": 6197202131299.441, "dur": 0.056, + "args": { + "External id": 44664,"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": 2338707, "tid": 2338707, + "ts": 6197202131299.990, "dur": 0.066, + "args": { + "External id": 44665,"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": 2338707, "tid": 2338707, + "ts": 6197202131300.744, "dur": 0.052, + "args": { + "External id": 44666,"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": 2338707, "tid": 2338707, + "ts": 6197202131301.175, "dur": 0.064, + "args": { + "External id": 44667,"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": 2338707, "tid": 2338707, + "ts": 6197202131301.720, "dur": 0.058, + "args": { + "External id": 44668,"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": 2338707, "tid": 2338707, + "ts": 6197202131302.157, "dur": 0.052, + "args": { + "External id": 44669,"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": 2338707, "tid": 2338707, + "ts": 6197202131302.674, "dur": 0.056, + "args": { + "External id": 44670,"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": 2338707, "tid": 2338707, + "ts": 6197202131303.215, "dur": 0.055, + "args": { + "External id": 44671,"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": 2338707, "tid": 2338707, + "ts": 6197202131303.745, "dur": 0.049, + "args": { + "External id": 44672,"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": 2338707, "tid": 2338707, + "ts": 6197202131304.268, "dur": 0.056, + "args": { + "External id": 44673,"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": 2338707, "tid": 2338707, + "ts": 6197202131304.783, "dur": 0.054, + "args": { + "External id": 44674,"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": 2338707, "tid": 2338707, + "ts": 6197202131305.220, "dur": 0.065, + "args": { + "External id": 44675,"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": 2338707, "tid": 2338707, + "ts": 6197202131305.673, "dur": 0.057, + "args": { + "External id": 44676,"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": 2338707, "tid": 2338707, + "ts": 6197202131305.996, "dur": 0.059, + "args": { + "External id": 44677,"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": 2338707, "tid": 2338707, + "ts": 6197202131306.501, "dur": 0.058, + "args": { + "External id": 44678,"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": 2338707, "tid": 2338707, + "ts": 6197202131307.030, "dur": 0.057, + "args": { + "External id": 44679,"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": 2338707, "tid": 2338707, + "ts": 6197202131307.641, "dur": 0.075, + "args": { + "External id": 44680,"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": 2338707, "tid": 2338707, + "ts": 6197202131308.158, "dur": 0.065, + "args": { + "External id": 44681,"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": 2338707, "tid": 2338707, + "ts": 6197202131308.714, "dur": 0.067, + "args": { + "External id": 44682,"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": 2338707, "tid": 2338707, + "ts": 6197202131309.283, "dur": 0.069, + "args": { + "External id": 44683,"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": 2338707, "tid": 2338707, + "ts": 6197202131309.782, "dur": 0.055, + "args": { + "External id": 44684,"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": 2338707, "tid": 2338707, + "ts": 6197202131310.477, "dur": 0.069, + "args": { + "External id": 44685,"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": 2338707, "tid": 2338707, + "ts": 6197202131310.905, "dur": 0.060, + "args": { + "External id": 44686,"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": 2338707, "tid": 2338707, + "ts": 6197202131311.350, "dur": 0.059, + "args": { + "External id": 44687,"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": 2338707, "tid": 2338707, + "ts": 6197202131311.670, "dur": 0.053, + "args": { + "External id": 44688,"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": 2338707, "tid": 2338707, + "ts": 6197202131312.130, "dur": 0.060, + "args": { + "External id": 44689,"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": 2338707, "tid": 2338707, + "ts": 6197202131312.659, "dur": 0.066, + "args": { + "External id": 44690,"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": 2338707, "tid": 2338707, + "ts": 6197202131313.236, "dur": 0.055, + "args": { + "External id": 44691,"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": 2338707, "tid": 2338707, + "ts": 6197202131313.887, "dur": 0.064, + "args": { + "External id": 44692,"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": 2338707, "tid": 2338707, + "ts": 6197202131314.417, "dur": 0.088, + "args": { + "External id": 44693,"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": 2338707, "tid": 2338707, + "ts": 6197202131315.141, "dur": 0.057, + "args": { + "External id": 44694,"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": 2338707, "tid": 2338707, + "ts": 6197202131315.682, "dur": 0.061, + "args": { + "External id": 44695,"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": 2338707, "tid": 2338707, + "ts": 6197202131316.181, "dur": 0.235, + "args": { + "External id": 44696,"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": 2338707, "tid": 2338707, + "ts": 6197202131316.789, "dur": 0.055, + "args": { + "External id": 44697,"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": 2338707, "tid": 2338707, + "ts": 6197202131317.498, "dur": 0.055, + "args": { + "External id": 44698,"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": 2338707, "tid": 2338707, + "ts": 6197202131317.927, "dur": 0.072, + "args": { + "External id": 44699,"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": 2338707, "tid": 2338707, + "ts": 6197202131318.336, "dur": 0.074, + "args": { + "External id": 44700,"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": 2338707, "tid": 2338707, + "ts": 6197202131318.763, "dur": 0.067, + "args": { + "External id": 44701,"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": 2338707, "tid": 2338707, + "ts": 6197202131319.287, "dur": 0.057, + "args": { + "External id": 44702,"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": 2338707, "tid": 2338707, + "ts": 6197202131319.730, "dur": 0.059, + "args": { + "External id": 44703,"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": 2338707, "tid": 2338707, + "ts": 6197202131320.215, "dur": 0.057, + "args": { + "External id": 44704,"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": 2338707, "tid": 2338707, + "ts": 6197202131320.701, "dur": 0.066, + "args": { + "External id": 44705,"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": 2338707, "tid": 2338707, + "ts": 6197202131321.272, "dur": 0.069, + "args": { + "External id": 44706,"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": 2338707, "tid": 2338707, + "ts": 6197202131321.848, "dur": 0.049, + "args": { + "External id": 44707,"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": 2338707, "tid": 2338707, + "ts": 6197202131322.361, "dur": 0.068, + "args": { + "External id": 44708,"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": 2338707, "tid": 2338707, + "ts": 6197202131323.036, "dur": 0.068, + "args": { + "External id": 44709,"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": 2338707, "tid": 2338707, + "ts": 6197202131323.516, "dur": 0.068, + "args": { + "External id": 44710,"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": 2338707, "tid": 2338707, + "ts": 6197202131324.156, "dur": 0.104, + "args": { + "External id": 44711,"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": 2338707, "tid": 2338707, + "ts": 6197202131324.839, "dur": 0.052, + "args": { + "External id": 44712,"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": 2338707, "tid": 2338707, + "ts": 6197202131325.159, "dur": 0.059, + "args": { + "External id": 44713,"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": 2338707, "tid": 2338707, + "ts": 6197202131325.683, "dur": 0.063, + "args": { + "External id": 44714,"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": 2338707, "tid": 2338707, + "ts": 6197202131326.196, "dur": 0.067, + "args": { + "External id": 44715,"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": 2338707, "tid": 2338707, + "ts": 6197202131327.034, "dur": 0.280, + "args": { + "External id": 44716,"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": 2338707, "tid": 2338707, + "ts": 6197202131327.775, "dur": 0.316, + "args": { + "External id": 44717,"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": 2338707, "tid": 2338707, + "ts": 6197202131328.525, "dur": 0.271, + "args": { + "External id": 44718,"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": 2338707, "tid": 2338707, + "ts": 6197202131329.356, "dur": 0.322, + "args": { + "External id": 44719,"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": 2338707, "tid": 2338707, + "ts": 6197202131330.162, "dur": 0.062, + "args": { + "External id": 44720,"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": 2338707, "tid": 2338707, + "ts": 6197202131330.676, "dur": 0.049, + "args": { + "External id": 44721,"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": 2338707, "tid": 2338707, + "ts": 6197202131331.157, "dur": 0.068, + "args": { + "External id": 44722,"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": 2338707, "tid": 2338707, + "ts": 6197202131331.646, "dur": 0.068, + "args": { + "External id": 44723,"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": 2338707, "tid": 2338707, + "ts": 6197202131331.987, "dur": 0.065, + "args": { + "External id": 44724,"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": 2338707, "tid": 2338707, + "ts": 6197202131332.441, "dur": 0.063, + "args": { + "External id": 44725,"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": 2338707, "tid": 2338707, + "ts": 6197202131333.105, "dur": 0.066, + "args": { + "External id": 44726,"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": 2338707, "tid": 2338707, + "ts": 6197202131333.687, "dur": 0.060, + "args": { + "External id": 44727,"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": 2338707, "tid": 2338707, + "ts": 6197202131334.216, "dur": 0.069, + "args": { + "External id": 44728,"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": 2338707, "tid": 2338707, + "ts": 6197202131334.755, "dur": 0.068, + "args": { + "External id": 44729,"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": 2338707, "tid": 2338707, + "ts": 6197202131335.271, "dur": 0.063, + "args": { + "External id": 44730,"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": 2338707, "tid": 2338707, + "ts": 6197202131335.710, "dur": 0.068, + "args": { + "External id": 44731,"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": 2338707, "tid": 2338707, + "ts": 6197202131336.355, "dur": 0.064, + "args": { + "External id": 44732,"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": 2338707, "tid": 2338707, + "ts": 6197202131336.690, "dur": 0.067, + "args": { + "External id": 44733,"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": 2338707, "tid": 2338707, + "ts": 6197202131337.247, "dur": 0.070, + "args": { + "External id": 44734,"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": 2338707, "tid": 2338707, + "ts": 6197202131337.675, "dur": 0.067, + "args": { + "External id": 44735,"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": 2338707, "tid": 2338707, + "ts": 6197202131338.181, "dur": 0.108, + "args": { + "External id": 44736,"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": 2338707, "tid": 2338707, + "ts": 6197202131338.904, "dur": 0.063, + "args": { + "External id": 44737,"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": 2338707, "tid": 2338707, + "ts": 6197202131339.539, "dur": 0.096, + "args": { + "External id": 44738,"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": 2338707, "tid": 2338707, + "ts": 6197202131340.037, "dur": 0.087, + "args": { + "External id": 44739,"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": 2338707, "tid": 2338707, + "ts": 6197202131340.550, "dur": 0.087, + "args": { + "External id": 44740,"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": 2338707, "tid": 2338707, + "ts": 6197202131341.121, "dur": 0.280, + "args": { + "External id": 44741,"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": 2338707, "tid": 2338707, + "ts": 6197202131341.808, "dur": 0.273, + "args": { + "External id": 44742,"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": 2338707, "tid": 2338707, + "ts": 6197202131342.522, "dur": 0.277, + "args": { + "External id": 44743,"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": 2338707, "tid": 2338707, + "ts": 6197202131343.259, "dur": 0.415, + "args": { + "External id": 44744,"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": 2338707, "tid": 2338707, + "ts": 6197202131344.237, "dur": 0.063, + "args": { + "External id": 44745,"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": 2338707, "tid": 2338707, + "ts": 6197202131344.730, "dur": 0.056, + "args": { + "External id": 44746,"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": 2338707, "tid": 2338707, + "ts": 6197202131345.277, "dur": 0.253, + "args": { + "External id": 44747,"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": 2338707, "tid": 2338707, + "ts": 6197202131346.011, "dur": 0.067, + "args": { + "External id": 44748,"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": 2338707, "tid": 2338707, + "ts": 6197202131346.599, "dur": 0.063, + "args": { + "External id": 44749,"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": 2338707, "tid": 2338707, + "ts": 6197202131347.156, "dur": 0.062, + "args": { + "External id": 44750,"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": 2338707, "tid": 2338707, + "ts": 6197202131347.641, "dur": 0.071, + "args": { + "External id": 44751,"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": 2338707, "tid": 2338707, + "ts": 6197202131348.396, "dur": 0.064, + "args": { + "External id": 44752,"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": 2338707, "tid": 2338707, + "ts": 6197202131348.803, "dur": 0.068, + "args": { + "External id": 44753,"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": 2338707, "tid": 2338707, + "ts": 6197202131349.547, "dur": 0.051, + "args": { + "External id": 44754,"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": 2338707, "tid": 2338707, + "ts": 6197202131350.107, "dur": 0.067, + "args": { + "External id": 44755,"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": 2338707, "tid": 2338707, + "ts": 6197202131350.646, "dur": 0.064, + "args": { + "External id": 44756,"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": 2338707, "tid": 2338707, + "ts": 6197202131351.517, "dur": 0.066, + "args": { + "External id": 44757,"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": 2338707, "tid": 2338707, + "ts": 6197202131352.149, "dur": 0.065, + "args": { + "External id": 44758,"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": 2338707, "tid": 2338707, + "ts": 6197202131352.749, "dur": 0.086, + "args": { + "External id": 44759,"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": 2338707, "tid": 2338707, + "ts": 6197202131353.194, "dur": 0.087, + "args": { + "External id": 44760,"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": 2338707, "tid": 2338707, + "ts": 6197202131353.823, "dur": 0.068, + "args": { + "External id": 44761,"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": 2338707, "tid": 2338707, + "ts": 6197202131354.298, "dur": 0.067, + "args": { + "External id": 44762,"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": 2338707, "tid": 2338707, + "ts": 6197202131354.814, "dur": 0.067, + "args": { + "External id": 44763,"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": 2338707, "tid": 2338707, + "ts": 6197202131355.254, "dur": 0.299, + "args": { + "External id": 44764,"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": 2338707, "tid": 2338707, + "ts": 6197202131356.023, "dur": 0.090, + "args": { + "External id": 44765,"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": 2338707, "tid": 2338707, + "ts": 6197202131356.581, "dur": 0.084, + "args": { + "External id": 44766,"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": 2338707, "tid": 2338707, + "ts": 6197202131357.037, "dur": 0.084, + "args": { + "External id": 44767,"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": 2338707, "tid": 2338707, + "ts": 6197202131357.498, "dur": 0.059, + "args": { + "External id": 44768,"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": 2338707, "tid": 2338707, + "ts": 6197202131358.042, "dur": 0.066, + "args": { + "External id": 44769,"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": 2338707, "tid": 2338707, + "ts": 6197202131358.554, "dur": 0.064, + "args": { + "External id": 44770,"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": 2338707, "tid": 2338707, + "ts": 6197202131359.096, "dur": 0.051, + "args": { + "External id": 44771,"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": 2338707, "tid": 2338707, + "ts": 6197202131359.466, "dur": 0.067, + "args": { + "External id": 44772,"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": 2338707, "tid": 2338707, + "ts": 6197202131359.934, "dur": 0.069, + "args": { + "External id": 44773,"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": 2338707, "tid": 2338707, + "ts": 6197202131360.295, "dur": 0.062, + "args": { + "External id": 44774,"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": 2338707, "tid": 2338707, + "ts": 6197202131360.699, "dur": 0.061, + "args": { + "External id": 44775,"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": 2338707, "tid": 2338707, + "ts": 6197202131361.153, "dur": 0.054, + "args": { + "External id": 44776,"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": 2338707, "tid": 2338707, + "ts": 6197202131361.632, "dur": 0.065, + "args": { + "External id": 44777,"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": 2338707, "tid": 2338707, + "ts": 6197202131362.204, "dur": 0.054, + "args": { + "External id": 44778,"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": 2338707, "tid": 2338707, + "ts": 6197202131362.677, "dur": 0.066, + "args": { + "External id": 44779,"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": 2338707, "tid": 2338707, + "ts": 6197202131363.042, "dur": 0.063, + "args": { + "External id": 44780,"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": 2338707, "tid": 2338707, + "ts": 6197202131363.588, "dur": 0.057, + "args": { + "External id": 44781,"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": 2338707, "tid": 2338707, + "ts": 6197202131363.957, "dur": 0.054, + "args": { + "External id": 44782,"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": 2338707, "tid": 2338707, + "ts": 6197202131364.494, "dur": 0.064, + "args": { + "External id": 44783,"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": 2338707, "tid": 2338707, + "ts": 6197202131364.818, "dur": 0.067, + "args": { + "External id": 44784,"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": 2338707, "tid": 2338707, + "ts": 6197202131365.261, "dur": 0.069, + "args": { + "External id": 44785,"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": 2338707, "tid": 2338707, + "ts": 6197202131365.674, "dur": 0.066, + "args": { + "External id": 44786,"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": 2338707, "tid": 2338707, + "ts": 6197202131366.177, "dur": 0.065, + "args": { + "External id": 44787,"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": 2338707, "tid": 2338707, + "ts": 6197202131366.693, "dur": 0.066, + "args": { + "External id": 44788,"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": 2338707, "tid": 2338707, + "ts": 6197202131367.108, "dur": 0.066, + "args": { + "External id": 44789,"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": 2338707, "tid": 2338707, + "ts": 6197202131367.866, "dur": 0.071, + "args": { + "External id": 44790,"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": 2338707, "tid": 2338707, + "ts": 6197202131368.259, "dur": 0.055, + "args": { + "External id": 44791,"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": 2338707, "tid": 2338707, + "ts": 6197202131368.712, "dur": 0.065, + "args": { + "External id": 44792,"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": 2338707, "tid": 2338707, + "ts": 6197202131369.118, "dur": 0.069, + "args": { + "External id": 44793,"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": 2338707, "tid": 2338707, + "ts": 6197202131369.565, "dur": 0.069, + "args": { + "External id": 44794,"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": 2338707, "tid": 2338707, + "ts": 6197202131369.928, "dur": 0.066, + "args": { + "External id": 44795,"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": 2338707, "tid": 2338707, + "ts": 6197202131370.394, "dur": 0.068, + "args": { + "External id": 44796,"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": 2338707, "tid": 2338707, + "ts": 6197202131370.826, "dur": 0.068, + "args": { + "External id": 44797,"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": 2338707, "tid": 2338707, + "ts": 6197202131371.341, "dur": 0.066, + "args": { + "External id": 44798,"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": 2338707, "tid": 2338707, + "ts": 6197202131371.792, "dur": 0.072, + "args": { + "External id": 44799,"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": 2338707, "tid": 2338707, + "ts": 6197202131372.294, "dur": 0.093, + "args": { + "External id": 44800,"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": 2338707, "tid": 2338707, + "ts": 6197202131372.786, "dur": 0.067, + "args": { + "External id": 44801,"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": 2338707, "tid": 2338707, + "ts": 6197202131373.211, "dur": 0.067, + "args": { + "External id": 44802,"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": 2338707, "tid": 2338707, + "ts": 6197202131373.570, "dur": 0.065, + "args": { + "External id": 44803,"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": 2338707, "tid": 2338707, + "ts": 6197202131374.049, "dur": 0.066, + "args": { + "External id": 44804,"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": 2338707, "tid": 2338707, + "ts": 6197202131374.425, "dur": 0.069, + "args": { + "External id": 44805,"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": 2338707, "tid": 2338707, + "ts": 6197202131374.949, "dur": 0.066, + "args": { + "External id": 44806,"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": 2338707, "tid": 2338707, + "ts": 6197202131375.458, "dur": 0.067, + "args": { + "External id": 44807,"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": 2338707, "tid": 2338707, + "ts": 6197202131375.923, "dur": 0.082, + "args": { + "External id": 44808,"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": 2338707, "tid": 2338707, + "ts": 6197202131376.368, "dur": 0.068, + "args": { + "External id": 44809,"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": 2338707, "tid": 2338707, + "ts": 6197202131377.013, "dur": 0.069, + "args": { + "External id": 44810,"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": 2338707, "tid": 2338707, + "ts": 6197202131377.574, "dur": 0.060, + "args": { + "External id": 44811,"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": 2338707, "tid": 2338707, + "ts": 6197202131377.997, "dur": 0.062, + "args": { + "External id": 44812,"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": 2338707, "tid": 2338707, + "ts": 6197202131378.491, "dur": 0.067, + "args": { + "External id": 44813,"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": 2338707, "tid": 2338707, + "ts": 6197202131378.927, "dur": 0.060, + "args": { + "External id": 44814,"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": 2338707, "tid": 2338707, + "ts": 6197202131379.450, "dur": 0.055, + "args": { + "External id": 44815,"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": 2338707, "tid": 2338707, + "ts": 6197202131379.893, "dur": 0.057, + "args": { + "External id": 44816,"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": 2338707, "tid": 2338707, + "ts": 6197202131380.308, "dur": 0.056, + "args": { + "External id": 44817,"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": 2338707, "tid": 2338707, + "ts": 6197202131380.783, "dur": 0.058, + "args": { + "External id": 44818,"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": 2338707, "tid": 2338707, + "ts": 6197202131381.231, "dur": 0.064, + "args": { + "External id": 44819,"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": 2338707, "tid": 2338707, + "ts": 6197202131381.755, "dur": 0.061, + "args": { + "External id": 44820,"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": 2338707, "tid": 2338707, + "ts": 6197202131382.283, "dur": 0.060, + "args": { + "External id": 44821,"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": 2338707, "tid": 2338707, + "ts": 6197202131382.967, "dur": 0.061, + "args": { + "External id": 44822,"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": 2338707, "tid": 2338707, + "ts": 6197202131383.457, "dur": 0.060, + "args": { + "External id": 44823,"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": 2338707, "tid": 2338707, + "ts": 6197202131383.873, "dur": 0.058, + "args": { + "External id": 44824,"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": 2338707, "tid": 2338707, + "ts": 6197202131384.276, "dur": 0.054, + "args": { + "External id": 44825,"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": 2338707, "tid": 2338707, + "ts": 6197202131384.712, "dur": 0.069, + "args": { + "External id": 44826,"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": 2338707, "tid": 2338707, + "ts": 6197202131385.234, "dur": 0.050, + "args": { + "External id": 44827,"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": 2338707, "tid": 2338707, + "ts": 6197202131385.562, "dur": 0.068, + "args": { + "External id": 44828,"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": 2338707, "tid": 2338707, + "ts": 6197202131386.121, "dur": 0.066, + "args": { + "External id": 44829,"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": 2338707, "tid": 2338707, + "ts": 6197202131386.583, "dur": 0.072, + "args": { + "External id": 44830,"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": 2338707, "tid": 2338707, + "ts": 6197202131387.003, "dur": 0.058, + "args": { + "External id": 44831,"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": 2338707, "tid": 2338707, + "ts": 6197202131387.350, "dur": 0.061, + "args": { + "External id": 44832,"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": 2338707, "tid": 2338707, + "ts": 6197202131387.813, "dur": 0.068, + "args": { + "External id": 44833,"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": 2338707, "tid": 2338707, + "ts": 6197202131388.183, "dur": 0.266, + "args": { + "External id": 44834,"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": 2338707, "tid": 2338707, + "ts": 6197202131388.783, "dur": 0.058, + "args": { + "External id": 44835,"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": 2338707, "tid": 2338707, + "ts": 6197202131389.253, "dur": 0.048, + "args": { + "External id": 44836,"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": 2338707, "tid": 2338707, + "ts": 6197202131389.591, "dur": 0.060, + "args": { + "External id": 44837,"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": 2338707, "tid": 2338707, + "ts": 6197202131390.030, "dur": 0.059, + "args": { + "External id": 44838,"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": 2338707, "tid": 2338707, + "ts": 6197202131390.378, "dur": 0.069, + "args": { + "External id": 44839,"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": 2338707, "tid": 2338707, + "ts": 6197202131390.738, "dur": 0.273, + "args": { + "External id": 44840,"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": 2338707, "tid": 2338707, + "ts": 6197202131391.395, "dur": 0.059, + "args": { + "External id": 44841,"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": 2338707, "tid": 2338707, + "ts": 6197202131391.844, "dur": 0.253, + "args": { + "External id": 44842,"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": 2338707, "tid": 2338707, + "ts": 6197202131392.463, "dur": 0.087, + "args": { + "External id": 44843,"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": 2338707, "tid": 2338707, + "ts": 6197202131393.022, "dur": 0.076, + "args": { + "External id": 44844,"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": 2338707, "tid": 2338707, + "ts": 6197202131393.497, "dur": 0.079, + "args": { + "External id": 44845,"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": 2338707, "tid": 2338707, + "ts": 6197202131393.947, "dur": 0.061, + "args": { + "External id": 44846,"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": 2338707, "tid": 2338707, + "ts": 6197202131394.449, "dur": 0.235, + "args": { + "External id": 44847,"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": 2338707, "tid": 2338707, + "ts": 6197202131395.181, "dur": 0.058, + "args": { + "External id": 44848,"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": 2338707, "tid": 2338707, + "ts": 6197202131395.631, "dur": 0.060, + "args": { + "External id": 44849,"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": 2338707, "tid": 2338707, + "ts": 6197202131396.082, "dur": 0.058, + "args": { + "External id": 44850,"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": 2338707, "tid": 2338707, + "ts": 6197202131396.516, "dur": 0.055, + "args": { + "External id": 44851,"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": 2338707, "tid": 2338707, + "ts": 6197202131397.008, "dur": 0.066, + "args": { + "External id": 44852,"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": 2338707, "tid": 2338707, + "ts": 6197202131397.690, "dur": 0.058, + "args": { + "External id": 44853,"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": 2338707, "tid": 2338707, + "ts": 6197202131398.182, "dur": 0.071, + "args": { + "External id": 44854,"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": 2338707, "tid": 2338707, + "ts": 6197202131398.905, "dur": 0.056, + "args": { + "External id": 44855,"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": 2338707, "tid": 2338707, + "ts": 6197202131399.384, "dur": 0.047, + "args": { + "External id": 44856,"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": 2338707, "tid": 2338707, + "ts": 6197202131399.784, "dur": 0.093, + "args": { + "External id": 44857,"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": 2338707, "tid": 2338707, + "ts": 6197202131400.140, "dur": 0.070, + "args": { + "External id": 44858,"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": 2338707, "tid": 2338707, + "ts": 6197202131400.581, "dur": 0.069, + "args": { + "External id": 44859,"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": 2338707, "tid": 2338707, + "ts": 6197202131401.024, "dur": 0.059, + "args": { + "External id": 44860,"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": 2338707, "tid": 2338707, + "ts": 6197202131401.512, "dur": 0.057, + "args": { + "External id": 44861,"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": 2338707, "tid": 2338707, + "ts": 6197202131402.127, "dur": 0.065, + "args": { + "External id": 44862,"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": 2338707, "tid": 2338707, + "ts": 6197202131402.694, "dur": 0.062, + "args": { + "External id": 44863,"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": 2338707, "tid": 2338707, + "ts": 6197202131403.203, "dur": 0.101, + "args": { + "External id": 44864,"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": 2338707, "tid": 2338707, + "ts": 6197202131403.799, "dur": 0.066, + "args": { + "External id": 44865,"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": 2338707, "tid": 2338707, + "ts": 6197202131404.370, "dur": 0.259, + "args": { + "External id": 44866,"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": 2338707, "tid": 2338707, + "ts": 6197202131404.890, "dur": 0.257, + "args": { + "External id": 44867,"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": 2338707, "tid": 2338707, + "ts": 6197202131405.550, "dur": 0.248, + "args": { + "External id": 44868,"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": 2338707, "tid": 2338707, + "ts": 6197202131406.317, "dur": 0.253, + "args": { + "External id": 44869,"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": 2338707, "tid": 2338707, + "ts": 6197202131406.972, "dur": 0.270, + "args": { + "External id": 44870,"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": 2338707, "tid": 2338707, + "ts": 6197202131407.591, "dur": 0.310, + "args": { + "External id": 44871,"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": 2338707, "tid": 2338707, + "ts": 6197202131408.291, "dur": 0.073, + "args": { + "External id": 44872,"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": 2338707, "tid": 2338707, + "ts": 6197202131408.700, "dur": 0.057, + "args": { + "External id": 44873,"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": 2338707, "tid": 2338707, + "ts": 6197202131409.124, "dur": 0.059, + "args": { + "External id": 44874,"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": 2338707, "tid": 2338707, + "ts": 6197202131409.463, "dur": 0.059, + "args": { + "External id": 44875,"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": 2338707, "tid": 2338707, + "ts": 6197202131409.934, "dur": 0.051, + "args": { + "External id": 44876,"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": 2338707, "tid": 2338707, + "ts": 6197202131410.365, "dur": 0.055, + "args": { + "External id": 44877,"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": 2338707, "tid": 2338707, + "ts": 6197202131410.766, "dur": 0.071, + "args": { + "External id": 44878,"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": 2338707, "tid": 2338707, + "ts": 6197202131411.186, "dur": 0.060, + "args": { + "External id": 44879,"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": 2338707, "tid": 2338707, + "ts": 6197202131411.571, "dur": 0.070, + "args": { + "External id": 44880,"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": 2338707, "tid": 2338707, + "ts": 6197202131412.070, "dur": 0.059, + "args": { + "External id": 44881,"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": 2338707, "tid": 2338707, + "ts": 6197202131412.579, "dur": 0.066, + "args": { + "External id": 44882,"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": 2338707, "tid": 2338707, + "ts": 6197202131413.101, "dur": 0.066, + "args": { + "External id": 44883,"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": 2338707, "tid": 2338707, + "ts": 6197202131413.594, "dur": 0.065, + "args": { + "External id": 44884,"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": 2338707, "tid": 2338707, + "ts": 6197202131414.010, "dur": 0.067, + "args": { + "External id": 44885,"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": 2338707, "tid": 2338707, + "ts": 6197202131414.368, "dur": 0.065, + "args": { + "External id": 44886,"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": 2338707, "tid": 2338707, + "ts": 6197202131414.897, "dur": 0.057, + "args": { + "External id": 44887,"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": 2338707, "tid": 2338707, + "ts": 6197202131415.346, "dur": 0.064, + "args": { + "External id": 44888,"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": 2338707, "tid": 2338707, + "ts": 6197202131415.909, "dur": 0.068, + "args": { + "External id": 44889,"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": 2338707, "tid": 2338707, + "ts": 6197202131416.373, "dur": 0.057, + "args": { + "External id": 44890,"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": 2338707, "tid": 2338707, + "ts": 6197202131416.734, "dur": 0.059, + "args": { + "External id": 44891,"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": 2338707, "tid": 2338707, + "ts": 6197202131417.190, "dur": 0.263, + "args": { + "External id": 44892,"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": 2338707, "tid": 2338707, + "ts": 6197202131417.897, "dur": 0.430, + "args": { + "External id": 44893,"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": 2338707, "tid": 2338707, + "ts": 6197202131418.704, "dur": 0.091, + "args": { + "External id": 44894,"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": 2338707, "tid": 2338707, + "ts": 6197202131419.189, "dur": 0.073, + "args": { + "External id": 44895,"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": 2338707, "tid": 2338707, + "ts": 6197202131419.677, "dur": 0.251, + "args": { + "External id": 44896,"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": 2338707, "tid": 2338707, + "ts": 6197202131420.324, "dur": 0.066, + "args": { + "External id": 44897,"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": 2338707, "tid": 2338707, + "ts": 6197202131420.777, "dur": 0.072, + "args": { + "External id": 44898,"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": 2338707, "tid": 2338707, + "ts": 6197202131421.212, "dur": 0.226, + "args": { + "External id": 44899,"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": 2338707, "tid": 2338707, + "ts": 6197202131421.804, "dur": 0.236, + "args": { + "External id": 44900,"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": 2338707, "tid": 2338707, + "ts": 6197202131422.455, "dur": 0.111, + "args": { + "External id": 44901,"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": 2338707, "tid": 2338707, + "ts": 6197202131422.954, "dur": 0.308, + "args": { + "External id": 44902,"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": 2338707, "tid": 2338707, + "ts": 6197202132042.255, "dur": 3727.770, + "args": { + "External id": 44903,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "1.9988974953137451e-05", "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": 2338707, "tid": 2338707, + "ts": 6197202134564.899, "dur": 992.211, + "args": { + "External id": 44904,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "1.9988974953137451e-05", "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": 6197195553849.786, "pid": 2338707, "tid": 0, + "args": { + "name": "python3.12" + } + }, + { + "name": "process_labels", "ph": "M", "ts": 6197195553849.786, "pid": 2338707, "tid": 0, + "args": { + "labels": "CPU" + } + }, + { + "name": "process_sort_index", "ph": "M", "ts": 6197195553849.786, "pid": 2338707, "tid": 0, + "args": { + "sort_index": 2338707 + } + }, + { + "name": "thread_name", "ph": "M", "ts": 6197195553849.786, "pid": 2338707, "tid": 2379456, + "args": { + "name": "thread 2379456 (pt_autograd_1)" + } + }, + { + "name": "thread_sort_index", "ph": "M", "ts": 6197195553849.786, "pid": 2338707, "tid": 2379456, + "args": { + "sort_index": 2379456 + } + }, + { + "name": "thread_name", "ph": "M", "ts": 6197195553849.786, "pid": 2338707, "tid": 2379456, + "args": { + "name": "thread 2379456 (python3.12)" + } + }, + { + "name": "thread_sort_index", "ph": "M", "ts": 6197195553849.786, "pid": 2338707, "tid": 2379456, + "args": { + "sort_index": 2379456 + } + }, + { + "name": "thread_name", "ph": "M", "ts": 6197195553849.786, "pid": 2338707, "tid": 2338707, + "args": { + "name": "thread 2338707 (python3.12)" + } + }, + { + "name": "thread_sort_index", "ph": "M", "ts": 6197195553849.786, "pid": 2338707, "tid": 2338707, + "args": { + "sort_index": 2338707 + } + }, + { + "ph": "X", "cat": "Trace", "ts": 6197195553768.648, "dur": 6589232.982, + "pid": "Spans", "tid": "PyTorch Profiler", + "name": "PyTorch Profiler (0)", + "args": { + "Op count": 0 + } + }, + { + "name": "process_sort_index", "ph": "M", "ts": 6197195553768.648, + "pid": "Spans", "tid": 0, + "args": { + "sort_index": 536870912 + } + }, + { + "name": "Iteration Start: PyTorch Profiler", "ph": "i", "s": "g", + "pid": "Traces", "tid": "Trace PyTorch Profiler", "ts": 6197195553768.648 + }, + { + "name": "Record Window End", "ph": "i", "s": "g", + "pid": "", "tid": "", "ts": 6197202228630.066 + } + ], + "traceName": "exp/mtp.code.7B.batch8.seqlen4096.context4096.warmup400.update2.steps40000.lr2e-5.cosine/profile_trace/iteration_1024/rank1_trace.json", + "displayTimeUnit": "ms", + "baseTimeNanoseconds": 1751410836000000000 +} \ No newline at end of file