diff --git "a/profile_trace/iteration_16384/rank1_trace.json" "b/profile_trace/iteration_16384/rank1_trace.json" new file mode 100644--- /dev/null +++ "b/profile_trace/iteration_16384/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": "F0F9ECBD527745BA997607AC4A769B09", + "traceEvents": [ + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: DivBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205136333.272, "dur": 117.447, + "args": { + "External id": 706049,"Record function id": 0, "Sequence number": 7674616, "Fwd thread id": 1, "Ev Idx": 0 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "DivBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205136356.060, "dur": 85.814, + "args": { + "External id": 706050,"Sequence number": 7674616, "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": 6305205136356.060, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::div", "pid": 2338707, "tid": 2379456, + "ts": 6305205136364.012, "dur": 75.574, + "args": { + "External id": 706051,"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": 6305205136465.565, "dur": 236.238, + "args": { + "External id": 706052,"Record function id": 0, "Ev Idx": 3 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward", "pid": 2338707, "tid": 2379456, + "ts": 6305205136537.740, "dur": 89.510, + "args": { + "External id": 706053,"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": 6305205136570.898, "dur": 44.903, + "args": { + "External id": 706054,"Record function id": 0, "Ev Idx": 5 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205136632.185, "dur": 1.964, + "args": { + "External id": 706055,"Sequence number": 7674615, "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": 6305205136632.185, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338707, "tid": 2379456, + "ts": 6305205136638.503, "dur": 58.702, + "args": { + "External id": 706056,"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": 6305205136648.310, "dur": 48.186, + "args": { + "External id": 706057,"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": 6305205136658.795, "dur": 4.543, + "args": { + "External id": 706058,"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": 6305205136712.542, "dur": 38532.187, + "args": { + "External id": 706059,"Record function id": 0, "Sequence number": 7674613, "Fwd thread id": 1, "Ev Idx": 10 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305205136714.401, "dur": 38512.965, + "args": { + "External id": 706060,"Sequence number": 7674613, "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": 6305205136714.401, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305205136754.385, "dur": 3.776, + "args": { + "External id": 706061,"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": 6305205136764.156, "dur": 38163.683, + "args": { + "External id": 706062,"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": 6305205136766.002, "dur": 38161.406, + "args": { + "External id": 706063,"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": 6305205136771.207, "dur": 6.745, + "args": { + "External id": 706064,"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": 6305205136779.652, "dur": 38145.978, + "args": { + "External id": 706065,"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": 6305205174933.184, "dur": 0.538, + "args": { + "External id": 706066,"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": 6305205174936.083, "dur": 2.806, + "args": { + "External id": 706067,"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": 6305205174937.683, "dur": 1.057, + "args": { + "External id": 706068,"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": 6305205174944.900, "dur": 30.000, + "args": { + "External id": 706069,"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": 6305205174983.775, "dur": 43.791, + "args": { + "External id": 706070,"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": 6305205174985.170, "dur": 42.207, + "args": { + "External id": 706071,"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": 6305205174986.656, "dur": 40.430, + "args": { + "External id": 706072,"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": 6305205175259.046, "dur": 19.982, + "args": { + "External id": 706073,"Record function id": 0, "Sequence number": 7674612, "Fwd thread id": 1, "Ev Idx": 24 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205175261.373, "dur": 15.613, + "args": { + "External id": 706074,"Sequence number": 7674612, "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": 6305205175261.373, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205175266.271, "dur": 10.467, + "args": { + "External id": 706075,"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": 6305205175270.879, "dur": 5.685, + "args": { + "External id": 706076,"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": 6305205175285.253, "dur": 112.009, + "args": { + "External id": 706077,"Record function id": 0, "Sequence number": 7674611, "Fwd thread id": 1, "Ev Idx": 28 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205175286.158, "dur": 103.327, + "args": { + "External id": 706078,"Sequence number": 7674611, "Fwd thread 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": 6305205175286.158, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338707, "tid": 2379456, + "ts": 6305205175289.796, "dur": 99.177, + "args": { + "External id": 706079,"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": 6305205175294.542, "dur": 39.444, + "args": { + "External id": 706080,"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": 6305205175299.642, "dur": 6.349, + "args": { + "External id": 706081,"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": 6305205175307.649, "dur": 25.956, + "args": { + "External id": 706082,"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": 6305205175313.230, "dur": 19.983, + "args": { + "External id": 706083,"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": 6305205175336.288, "dur": 7.481, + "args": { + "External id": 706084,"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": 6305205175339.282, "dur": 4.111, + "args": { + "External id": 706085,"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": 6305205175345.129, "dur": 42.920, + "args": { + "External id": 706086,"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": 6305205175401.788, "dur": 62.558, + "args": { + "External id": 706087,"Record function id": 0, "Sequence number": 7674610, "Fwd thread id": 1, "Ev Idx": 38 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SelectBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205175402.948, "dur": 57.699, + "args": { + "External id": 706088,"Sequence number": 7674610, "Fwd thread 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": 6305205175402.948, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select_backward", "pid": 2338707, "tid": 2379456, + "ts": 6305205175406.419, "dur": 53.857, + "args": { + "External id": 706089,"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": 6305205175412.009, "dur": 20.930, + "args": { + "External id": 706090,"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": 6305205175413.603, "dur": 2.996, + "args": { + "External id": 706091,"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": 6305205175417.531, "dur": 15.127, + "args": { + "External id": 706092,"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": 6305205175421.606, "dur": 10.634, + "args": { + "External id": 706093,"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": 6305205175434.534, "dur": 8.316, + "args": { + "External id": 706094,"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": 6305205175441.150, "dur": 0.931, + "args": { + "External id": 706095,"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": 6305205175443.572, "dur": 16.237, + "args": { + "External id": 706096,"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": 6305205175468.271, "dur": 245.538, + "args": { + "External id": 706097,"Record function id": 0, "Sequence number": 7674609, "Fwd thread id": 1, "Ev Idx": 48 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205175469.258, "dur": 239.048, + "args": { + "External id": 706098,"Sequence number": 7674609, "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": 6305205175469.258, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338707, "tid": 2379456, + "ts": 6305205175473.511, "dur": 234.294, + "args": { + "External id": 706099,"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": 6305205175477.398, "dur": 15.184, + "args": { + "External id": 706100,"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": 6305205175478.259, "dur": 2.299, + "args": { + "External id": 706101,"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": 6305205175481.238, "dur": 11.086, + "args": { + "External id": 706102,"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": 6305205175481.963, "dur": 10.002, + "args": { + "External id": 706103,"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": 6305205175493.493, "dur": 2.215, + "args": { + "External id": 706104,"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": 6305205175494.644, "dur": 0.883, + "args": { + "External id": 706105,"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": 6305205175499.781, "dur": 206.499, + "args": { + "External id": 706106,"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": 6305205175721.099, "dur": 87.241, + "args": { + "External id": 706107,"Record function id": 0, "Sequence number": 7674608, "Fwd thread id": 1, "Ev Idx": 58 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205175722.156, "dur": 82.645, + "args": { + "External id": 706108,"Sequence number": 7674608, "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": 6305205175722.156, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338707, "tid": 2379456, + "ts": 6305205175724.169, "dur": 80.237, + "args": { + "External id": 706109,"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": 6305205175727.861, "dur": 18.577, + "args": { + "External id": 706110,"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": 6305205175728.895, "dur": 2.876, + "args": { + "External id": 706111,"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": 6305205175732.485, "dur": 13.711, + "args": { + "External id": 706112,"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": 6305205175733.705, "dur": 12.137, + "args": { + "External id": 706113,"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": 6305205175747.606, "dur": 4.353, + "args": { + "External id": 706114,"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": 6305205175750.879, "dur": 0.787, + "args": { + "External id": 706115,"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": 6305205175752.877, "dur": 50.658, + "args": { + "External id": 706116,"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": 6305205175815.337, "dur": 39.654, + "args": { + "External id": 706117,"Record function id": 0, "Sequence number": 7674607, "Fwd thread id": 1, "Ev Idx": 68 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205175816.980, "dur": 0.942, + "args": { + "External id": 706118,"Sequence number": 7674607, "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": 6305205175816.980, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338707, "tid": 2379456, + "ts": 6305205175820.655, "dur": 30.953, + "args": { + "External id": 706119,"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": 6305205175823.166, "dur": 27.977, + "args": { + "External id": 706120,"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": 6305205175833.473, "dur": 0.667, + "args": { + "External id": 706121,"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": 6305205175860.498, "dur": 2458.328, + "args": { + "External id": 706122,"Record function id": 0, "Sequence number": 7674605, "Fwd thread id": 1, "Ev Idx": 73 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305205175862.049, "dur": 2417.498, + "args": { + "External id": 706123,"Sequence number": 7674605, "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": 6305205175862.049, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305205175899.439, "dur": 2.836, + "args": { + "External id": 706124,"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": 6305205175905.248, "dur": 2125.417, + "args": { + "External id": 706125,"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": 6305205175906.863, "dur": 2123.366, + "args": { + "External id": 706126,"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": 6305205175909.962, "dur": 6.919, + "args": { + "External id": 706127,"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": 6305205175918.070, "dur": 2110.812, + "args": { + "External id": 706128,"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": 6305205178034.551, "dur": 0.341, + "args": { + "External id": 706129,"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": 6305205178036.531, "dur": 4.866, + "args": { + "External id": 706130,"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": 6305205178040.420, "dur": 0.812, + "args": { + "External id": 706131,"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": 6305205178046.554, "dur": 44.859, + "args": { + "External id": 706132,"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": 6305205178099.101, "dur": 42.189, + "args": { + "External id": 706133,"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": 6305205178100.380, "dur": 40.655, + "args": { + "External id": 706134,"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": 6305205178101.810, "dur": 38.800, + "args": { + "External id": 706135,"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": 6305205178292.468, "dur": 21.944, + "args": { + "External id": 706136,"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": 6305205178331.119, "dur": 16.708, + "args": { + "External id": 706137,"Record function id": 0, "Sequence number": 7674604, "Fwd thread id": 1, "Ev Idx": 88 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205178332.668, "dur": 12.808, + "args": { + "External id": 706138,"Sequence number": 7674604, "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": 6305205178332.668, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205178339.079, "dur": 6.122, + "args": { + "External id": 706139,"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": 6305205178340.621, "dur": 4.362, + "args": { + "External id": 706140,"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": 6305205178351.398, "dur": 81.422, + "args": { + "External id": 706141,"Record function id": 0, "Sequence number": 7674603, "Fwd thread id": 1, "Ev Idx": 92 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205178352.616, "dur": 75.365, + "args": { + "External id": 706142,"Sequence number": 7674603, "Fwd thread 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": 6305205178352.616, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338707, "tid": 2379456, + "ts": 6305205178355.028, "dur": 72.593, + "args": { + "External id": 706143,"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": 6305205178362.655, "dur": 24.123, + "args": { + "External id": 706144,"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": 6305205178364.084, "dur": 3.720, + "args": { + "External id": 706145,"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": 6305205178369.154, "dur": 17.310, + "args": { + "External id": 706146,"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": 6305205178370.959, "dur": 15.084, + "args": { + "External id": 706147,"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": 6305205178388.587, "dur": 4.169, + "args": { + "External id": 706148,"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": 6305205178390.901, "dur": 1.601, + "args": { + "External id": 706149,"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": 6305205178394.023, "dur": 32.663, + "args": { + "External id": 706150,"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": 6305205178437.495, "dur": 60.285, + "args": { + "External id": 706151,"Record function id": 0, "Sequence number": 7674602, "Fwd thread id": 1, "Ev Idx": 102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SelectBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205178438.774, "dur": 55.656, + "args": { + "External id": 706152,"Sequence number": 7674602, "Fwd thread 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": 6305205178438.774, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select_backward", "pid": 2338707, "tid": 2379456, + "ts": 6305205178443.658, "dur": 50.421, + "args": { + "External id": 706153,"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": 6305205178445.733, "dur": 23.313, + "args": { + "External id": 706154,"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": 6305205178446.621, "dur": 2.391, + "args": { + "External id": 706155,"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": 6305205178453.354, "dur": 15.430, + "args": { + "External id": 706156,"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": 6305205178454.334, "dur": 14.080, + "args": { + "External id": 706157,"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": 6305205178470.610, "dur": 8.125, + "args": { + "External id": 706158,"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": 6305205178476.764, "dur": 1.310, + "args": { + "External id": 706159,"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": 6305205178479.626, "dur": 13.869, + "args": { + "External id": 706160,"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": 6305205178503.782, "dur": 152.917, + "args": { + "External id": 706161,"Record function id": 0, "Sequence number": 7674601, "Fwd thread id": 1, "Ev Idx": 112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205178504.672, "dur": 147.632, + "args": { + "External id": 706162,"Sequence number": 7674601, "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": 6305205178504.672, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338707, "tid": 2379456, + "ts": 6305205178518.976, "dur": 132.839, + "args": { + "External id": 706163,"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": 6305205178520.334, "dur": 21.672, + "args": { + "External id": 706164,"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": 6305205178521.373, "dur": 3.190, + "args": { + "External id": 706165,"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": 6305205178528.361, "dur": 13.368, + "args": { + "External id": 706166,"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": 6305205178529.603, "dur": 11.707, + "args": { + "External id": 706167,"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": 6305205178543.079, "dur": 5.091, + "args": { + "External id": 706168,"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": 6305205178546.994, "dur": 0.952, + "args": { + "External id": 706169,"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": 6305205178549.161, "dur": 101.605, + "args": { + "External id": 706170,"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": 6305205178662.791, "dur": 109.032, + "args": { + "External id": 706171,"Record function id": 0, "Sequence number": 7674600, "Fwd thread id": 1, "Ev Idx": 122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205178663.861, "dur": 85.348, + "args": { + "External id": 706172,"Sequence number": 7674600, "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": 6305205178663.861, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338707, "tid": 2379456, + "ts": 6305205178667.959, "dur": 80.913, + "args": { + "External id": 706173,"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": 6305205178668.870, "dur": 21.506, + "args": { + "External id": 706174,"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": 6305205178669.983, "dur": 2.283, + "args": { + "External id": 706175,"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": 6305205178673.050, "dur": 17.069, + "args": { + "External id": 706176,"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": 6305205178677.383, "dur": 12.422, + "args": { + "External id": 706177,"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": 6305205178691.352, "dur": 2.040, + "args": { + "External id": 706178,"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": 6305205178692.683, "dur": 0.525, + "args": { + "External id": 706179,"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": 6305205178694.235, "dur": 53.889, + "args": { + "External id": 706180,"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": 6305205178753.855, "dur": 16.534, + "args": { + "External id": 706181,"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": 6305205178776.726, "dur": 38.983, + "args": { + "External id": 706182,"Record function id": 0, "Sequence number": 7674599, "Fwd thread id": 1, "Ev Idx": 133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205178778.426, "dur": 1.096, + "args": { + "External id": 706183,"Sequence number": 7674599, "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": 6305205178778.426, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338707, "tid": 2379456, + "ts": 6305205178781.870, "dur": 30.765, + "args": { + "External id": 706184,"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": 6305205178784.205, "dur": 28.037, + "args": { + "External id": 706185,"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": 6305205178793.850, "dur": 0.643, + "args": { + "External id": 706186,"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": 6305205178820.913, "dur": 3465.502, + "args": { + "External id": 706187,"Record function id": 0, "Sequence number": 7674597, "Fwd thread id": 1, "Ev Idx": 138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305205178824.269, "dur": 3429.724, + "args": { + "External id": 706188,"Sequence number": 7674597, "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": 6305205178824.269, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305205178857.666, "dur": 2.909, + "args": { + "External id": 706189,"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": 6305205178863.240, "dur": 3157.526, + "args": { + "External id": 706190,"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": 6305205178865.011, "dur": 3155.348, + "args": { + "External id": 706191,"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": 6305205178867.544, "dur": 3.664, + "args": { + "External id": 706192,"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": 6305205178874.569, "dur": 3144.476, + "args": { + "External id": 706193,"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": 6305205182024.756, "dur": 0.353, + "args": { + "External id": 706194,"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": 6305205182026.510, "dur": 2.513, + "args": { + "External id": 706195,"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": 6305205182027.779, "dur": 1.110, + "args": { + "External id": 706196,"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": 6305205182033.618, "dur": 46.218, + "args": { + "External id": 706197,"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": 6305205182090.622, "dur": 40.183, + "args": { + "External id": 706198,"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": 6305205182091.960, "dur": 38.676, + "args": { + "External id": 706199,"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": 6305205182093.399, "dur": 36.783, + "args": { + "External id": 706200,"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": 6305205182265.580, "dur": 17.226, + "args": { + "External id": 706201,"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": 6305205182297.865, "dur": 15.619, + "args": { + "External id": 706202,"Record function id": 0, "Sequence number": 7674596, "Fwd thread id": 1, "Ev Idx": 153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205182302.007, "dur": 9.132, + "args": { + "External id": 706203,"Sequence number": 7674596, "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": 6305205182302.007, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205182305.026, "dur": 5.867, + "args": { + "External id": 706204,"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": 6305205182306.727, "dur": 3.927, + "args": { + "External id": 706205,"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": 6305205182317.187, "dur": 71.353, + "args": { + "External id": 706206,"Record function id": 0, "Sequence number": 7674595, "Fwd thread id": 1, "Ev Idx": 157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205182318.368, "dur": 66.097, + "args": { + "External id": 706207,"Sequence number": 7674595, "Fwd thread 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": 6305205182318.368, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338707, "tid": 2379456, + "ts": 6305205182322.932, "dur": 61.170, + "args": { + "External id": 706208,"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": 6305205182325.820, "dur": 22.490, + "args": { + "External id": 706209,"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": 6305205182327.434, "dur": 3.902, + "args": { + "External id": 706210,"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": 6305205182332.651, "dur": 15.396, + "args": { + "External id": 706211,"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": 6305205182335.092, "dur": 12.517, + "args": { + "External id": 706212,"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": 6305205182349.868, "dur": 5.899, + "args": { + "External id": 706213,"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": 6305205182354.262, "dur": 1.278, + "args": { + "External id": 706214,"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": 6305205182359.542, "dur": 23.811, + "args": { + "External id": 706215,"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": 6305205182392.721, "dur": 52.675, + "args": { + "External id": 706216,"Record function id": 0, "Sequence number": 7674594, "Fwd thread id": 1, "Ev Idx": 167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SelectBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205182393.900, "dur": 49.169, + "args": { + "External id": 706217,"Sequence number": 7674594, "Fwd thread 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": 6305205182393.900, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select_backward", "pid": 2338707, "tid": 2379456, + "ts": 6305205182396.204, "dur": 46.525, + "args": { + "External id": 706218,"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": 6305205182398.340, "dur": 17.018, + "args": { + "External id": 706219,"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": 6305205182399.233, "dur": 2.934, + "args": { + "External id": 706220,"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": 6305205182402.645, "dur": 12.462, + "args": { + "External id": 706221,"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": 6305205182403.642, "dur": 11.019, + "args": { + "External id": 706222,"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": 6305205182416.656, "dur": 10.136, + "args": { + "External id": 706223,"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": 6305205182425.113, "dur": 1.145, + "args": { + "External id": 706224,"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": 6305205182427.758, "dur": 14.416, + "args": { + "External id": 706225,"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": 6305205182449.359, "dur": 138.769, + "args": { + "External id": 706226,"Record function id": 0, "Sequence number": 7674593, "Fwd thread id": 1, "Ev Idx": 177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205182450.305, "dur": 132.909, + "args": { + "External id": 706227,"Sequence number": 7674593, "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": 6305205182450.305, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338707, "tid": 2379456, + "ts": 6305205182451.974, "dur": 130.768, + "args": { + "External id": 706228,"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": 6305205182453.103, "dur": 20.079, + "args": { + "External id": 706229,"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": 6305205182453.884, "dur": 4.732, + "args": { + "External id": 706230,"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": 6305205182459.211, "dur": 13.702, + "args": { + "External id": 706231,"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": 6305205182459.745, "dur": 12.770, + "args": { + "External id": 706232,"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": 6305205182474.327, "dur": 4.931, + "args": { + "External id": 706233,"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": 6305205182478.482, "dur": 0.590, + "args": { + "External id": 706234,"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": 6305205182482.782, "dur": 98.530, + "args": { + "External id": 706235,"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": 6305205182595.289, "dur": 111.732, + "args": { + "External id": 706236,"Record function id": 0, "Sequence number": 7674592, "Fwd thread id": 1, "Ev Idx": 187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205182596.547, "dur": 92.000, + "args": { + "External id": 706237,"Sequence number": 7674592, "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": 6305205182596.547, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338707, "tid": 2379456, + "ts": 6305205182601.398, "dur": 86.678, + "args": { + "External id": 706238,"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": 6305205182602.774, "dur": 18.468, + "args": { + "External id": 706239,"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": 6305205182604.054, "dur": 3.096, + "args": { + "External id": 706240,"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": 6305205182608.016, "dur": 12.972, + "args": { + "External id": 706241,"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": 6305205182609.338, "dur": 11.324, + "args": { + "External id": 706242,"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": 6305205182622.415, "dur": 5.173, + "args": { + "External id": 706243,"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": 6305205182626.676, "dur": 0.662, + "args": { + "External id": 706244,"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": 6305205182630.908, "dur": 56.151, + "args": { + "External id": 706245,"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": 6305205182692.512, "dur": 13.082, + "args": { + "External id": 706246,"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": 6305205182713.799, "dur": 35.229, + "args": { + "External id": 706247,"Record function id": 0, "Sequence number": 7674591, "Fwd thread id": 1, "Ev Idx": 198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205182715.272, "dur": 0.975, + "args": { + "External id": 706248,"Sequence number": 7674591, "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": 6305205182715.272, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338707, "tid": 2379456, + "ts": 6305205182718.342, "dur": 25.321, + "args": { + "External id": 706249,"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": 6305205182720.518, "dur": 22.763, + "args": { + "External id": 706250,"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": 6305205182725.588, "dur": 0.527, + "args": { + "External id": 706251,"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": 6305205182753.728, "dur": 3522.665, + "args": { + "External id": 706252,"Record function id": 0, "Sequence number": 7674590, "Fwd thread id": 1, "Ev Idx": 203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305205182764.938, "dur": 3477.504, + "args": { + "External id": 706253,"Sequence number": 7674590, "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": 6305205182764.938, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305205182794.574, "dur": 2.534, + "args": { + "External id": 706254,"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": 6305205182799.683, "dur": 3205.423, + "args": { + "External id": 706255,"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": 6305205182801.658, "dur": 3203.034, + "args": { + "External id": 706256,"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": 6305205182807.534, "dur": 3.431, + "args": { + "External id": 706257,"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": 6305205182811.917, "dur": 3191.686, + "args": { + "External id": 706258,"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": 6305205186009.027, "dur": 0.406, + "args": { + "External id": 706259,"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": 6305205186013.966, "dur": 2.492, + "args": { + "External id": 706260,"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": 6305205186015.303, "dur": 1.032, + "args": { + "External id": 706261,"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": 6305205186021.266, "dur": 22.193, + "args": { + "External id": 706262,"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": 6305205186048.609, "dur": 69.228, + "args": { + "External id": 706263,"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": 6305205186049.677, "dur": 67.900, + "args": { + "External id": 706264,"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": 6305205186050.879, "dur": 65.934, + "args": { + "External id": 706265,"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": 6305205186254.717, "dur": 17.289, + "args": { + "External id": 706266,"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": 6305205186291.036, "dur": 13.384, + "args": { + "External id": 706267,"Record function id": 0, "Ev Idx": 218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205186293.677, "dur": 9.103, + "args": { + "External id": 706268,"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": 6305205186296.989, "dur": 5.046, + "args": { + "External id": 706269,"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": 6305205186298.244, "dur": 3.665, + "args": { + "External id": 706270,"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": 6305205186308.127, "dur": 16.857, + "args": { + "External id": 706271,"Record function id": 0, "Sequence number": 7674589, "Fwd thread id": 1, "Ev Idx": 222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205186312.163, "dur": 10.719, + "args": { + "External id": 706272,"Sequence number": 7674589, "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": 6305205186312.163, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205186315.342, "dur": 7.278, + "args": { + "External id": 706273,"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": 6305205186318.919, "dur": 3.514, + "args": { + "External id": 706274,"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": 6305205186328.260, "dur": 71.742, + "args": { + "External id": 706275,"Record function id": 0, "Sequence number": 7674588, "Fwd thread id": 1, "Ev Idx": 226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205186329.089, "dur": 66.318, + "args": { + "External id": 706276,"Sequence number": 7674588, "Fwd thread 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": 6305205186329.089, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338707, "tid": 2379456, + "ts": 6305205186330.752, "dur": 64.123, + "args": { + "External id": 706277,"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": 6305205186333.592, "dur": 22.905, + "args": { + "External id": 706278,"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": 6305205186335.132, "dur": 3.789, + "args": { + "External id": 706279,"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": 6305205186340.038, "dur": 16.119, + "args": { + "External id": 706280,"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": 6305205186341.941, "dur": 13.761, + "args": { + "External id": 706281,"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": 6305205186358.242, "dur": 6.499, + "args": { + "External id": 706282,"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": 6305205186363.300, "dur": 1.253, + "args": { + "External id": 706283,"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": 6305205186369.310, "dur": 24.681, + "args": { + "External id": 706284,"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": 6305205186404.042, "dur": 53.542, + "args": { + "External id": 706285,"Record function id": 0, "Sequence number": 7674587, "Fwd thread id": 1, "Ev Idx": 236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SelectBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205186405.078, "dur": 49.382, + "args": { + "External id": 706286,"Sequence number": 7674587, "Fwd thread 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": 6305205186405.078, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select_backward", "pid": 2338707, "tid": 2379456, + "ts": 6305205186406.993, "dur": 47.204, + "args": { + "External id": 706287,"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": 6305205186408.978, "dur": 20.768, + "args": { + "External id": 706288,"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": 6305205186415.200, "dur": 2.632, + "args": { + "External id": 706289,"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": 6305205186418.465, "dur": 11.024, + "args": { + "External id": 706290,"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": 6305205186419.234, "dur": 9.877, + "args": { + "External id": 706291,"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": 6305205186430.967, "dur": 7.415, + "args": { + "External id": 706292,"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": 6305205186436.664, "dur": 1.120, + "args": { + "External id": 706293,"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": 6305205186439.134, "dur": 14.417, + "args": { + "External id": 706294,"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": 6305205186461.290, "dur": 137.889, + "args": { + "External id": 706295,"Record function id": 0, "Sequence number": 7674586, "Fwd thread id": 1, "Ev Idx": 246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205186462.544, "dur": 131.263, + "args": { + "External id": 706296,"Sequence number": 7674586, "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": 6305205186462.544, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338707, "tid": 2379456, + "ts": 6305205186464.562, "dur": 128.792, + "args": { + "External id": 706297,"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": 6305205186468.287, "dur": 13.902, + "args": { + "External id": 706298,"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": 6305205186468.900, "dur": 2.023, + "args": { + "External id": 706299,"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": 6305205186471.687, "dur": 10.244, + "args": { + "External id": 706300,"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": 6305205186472.455, "dur": 9.182, + "args": { + "External id": 706301,"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": 6305205186483.207, "dur": 4.874, + "args": { + "External id": 706302,"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": 6305205186484.624, "dur": 3.330, + "args": { + "External id": 706303,"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": 6305205186492.102, "dur": 99.978, + "args": { + "External id": 706304,"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": 6305205186606.182, "dur": 111.778, + "args": { + "External id": 706305,"Record function id": 0, "Sequence number": 7674585, "Fwd thread id": 1, "Ev Idx": 256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205186607.409, "dur": 91.865, + "args": { + "External id": 706306,"Sequence number": 7674585, "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": 6305205186607.409, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338707, "tid": 2379456, + "ts": 6305205186609.037, "dur": 89.880, + "args": { + "External id": 706307,"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": 6305205186610.567, "dur": 29.667, + "args": { + "External id": 706308,"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": 6305205186616.056, "dur": 2.952, + "args": { + "External id": 706309,"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": 6305205186624.402, "dur": 15.582, + "args": { + "External id": 706310,"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": 6305205186627.900, "dur": 11.694, + "args": { + "External id": 706311,"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": 6305205186643.513, "dur": 2.656, + "args": { + "External id": 706312,"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": 6305205186644.914, "dur": 0.986, + "args": { + "External id": 706313,"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": 6305205186646.751, "dur": 51.398, + "args": { + "External id": 706314,"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": 6305205186703.281, "dur": 12.646, + "args": { + "External id": 706315,"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": 6305205186724.184, "dur": 380.352, + "args": { + "External id": 706316,"Record function id": 0, "Sequence number": 7674584, "Fwd thread id": 1, "Ev Idx": 267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305205186725.389, "dur": 367.479, + "args": { + "External id": 706317,"Sequence number": 7674584, "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": 6305205186725.389, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338707, "tid": 2379456, + "ts": 6305205186894.418, "dur": 45.898, + "args": { + "External id": 706318,"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": 6305205186974.311, "dur": 25.233, + "args": { + "External id": 706319,"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": 6305205187017.294, "dur": 17.771, + "args": { + "External id": 706320,"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": 6305205187116.346, "dur": 14.979, + "args": { + "External id": 706321,"Record function id": 0, "Ev Idx": 272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205187118.978, "dur": 11.420, + "args": { + "External id": 706322,"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": 6305205187121.969, "dur": 7.506, + "args": { + "External id": 706323,"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": 6305205187126.056, "dur": 3.319, + "args": { + "External id": 706324,"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": 6305205187135.267, "dur": 38.087, + "args": { + "External id": 706325,"Record function id": 0, "Sequence number": 7674583, "Fwd thread id": 1, "Ev Idx": 276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "StackBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205187136.376, "dur": 29.956, + "args": { + "External id": 706326,"Sequence number": 7674583, "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": 6305205187136.376, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 2338707, "tid": 2379456, + "ts": 6305205187138.644, "dur": 9.791, + "args": { + "External id": 706327,"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": 6305205187144.591, "dur": 1.836, + "args": { + "External id": 706328,"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": 6305205187149.227, "dur": 8.658, + "args": { + "External id": 706329,"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": 6305205187156.158, "dur": 0.641, + "args": { + "External id": 706330,"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": 6305205187158.459, "dur": 2.190, + "args": { + "External id": 706331,"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": 6305205187159.524, "dur": 0.546, + "args": { + "External id": 706332,"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": 6305205187161.163, "dur": 4.433, + "args": { + "External id": 706333,"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": 6305205187164.374, "dur": 0.502, + "args": { + "External id": 706334,"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": 6305205187177.109, "dur": 5.434, + "args": { + "External id": 706335,"Record function id": 0, "Sequence number": 7674582, "Fwd thread id": 1, "Ev Idx": 286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205187178.117, "dur": 1.101, + "args": { + "External id": 706336,"Sequence number": 7674582, "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": 6305205187178.117, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SwiGLULinearFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305205187186.567, "dur": 566.838, + "args": { + "External id": 706337,"Record function id": 0, "Sequence number": 7674581, "Fwd thread id": 1, "Ev Idx": 288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305205187187.656, "dur": 552.518, + "args": { + "External id": 706338,"Sequence number": 7674581, "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": 6305205187187.656, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205187229.423, "dur": 13.853, + "args": { + "External id": 706339,"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": 6305205187238.258, "dur": 4.673, + "args": { + "External id": 706340,"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": 6305205187247.830, "dur": 6.733, + "args": { + "External id": 706341,"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": 6305205187250.710, "dur": 2.558, + "args": { + "External id": 706342,"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": 6305205187252.087, "dur": 0.904, + "args": { + "External id": 706343,"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": 6305205187261.303, "dur": 133.454, + "args": { + "External id": 706344,"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": 6305205187262.331, "dur": 7.609, + "args": { + "External id": 706345,"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": 6305205187262.960, "dur": 6.213, + "args": { + "External id": 706346,"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": 6305205187266.567, "dur": 2.517, + "args": { + "External id": 706347,"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": 6305205187271.438, "dur": 122.426, + "args": { + "External id": 706348,"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": 6305205187273.024, "dur": 119.497, + "args": { + "External id": 706349,"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": 6305205187400.246, "dur": 8.098, + "args": { + "External id": 706350,"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": 6305205187405.297, "dur": 2.851, + "args": { + "External id": 706351,"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": 6305205187443.465, "dur": 7.126, + "args": { + "External id": 706352,"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": 6305205187451.710, "dur": 1.901, + "args": { + "External id": 706353,"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": 6305205187456.750, "dur": 2.544, + "args": { + "External id": 706354,"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": 6305205187494.540, "dur": 2.388, + "args": { + "External id": 706355,"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": 6305205187495.538, "dur": 1.225, + "args": { + "External id": 706356,"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": 6305205187543.626, "dur": 171.635, + "args": { + "External id": 706357,"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": 6305205187550.399, "dur": 11.209, + "args": { + "External id": 706358,"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": 6305205187556.894, "dur": 1.143, + "args": { + "External id": 706359,"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": 6305205187564.410, "dur": 9.653, + "args": { + "External id": 706360,"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": 6305205187570.207, "dur": 3.095, + "args": { + "External id": 706361,"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": 6305205187575.759, "dur": 3.952, + "args": { + "External id": 706362,"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": 6305205187578.791, "dur": 0.555, + "args": { + "External id": 706363,"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": 6305205187580.414, "dur": 4.520, + "args": { + "External id": 706364,"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": 6305205187583.857, "dur": 0.594, + "args": { + "External id": 706365,"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": 6305205187589.122, "dur": 4.405, + "args": { + "External id": 706366,"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": 6305205187592.702, "dur": 0.505, + "args": { + "External id": 706367,"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": 6305205187596.799, "dur": 8.262, + "args": { + "External id": 706368,"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": 6305205187602.587, "dur": 2.283, + "args": { + "External id": 706369,"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": 6305205187605.830, "dur": 3.594, + "args": { + "External id": 706370,"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": 6305205187608.790, "dur": 0.350, + "args": { + "External id": 706371,"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": 6305205187610.170, "dur": 2.686, + "args": { + "External id": 706372,"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": 6305205187611.052, "dur": 1.668, + "args": { + "External id": 706373,"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": 6305205187614.597, "dur": 84.759, + "args": { + "External id": 706374,"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": 6305205187701.298, "dur": 4.195, + "args": { + "External id": 706375,"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": 6305205187708.514, "dur": 2.876, + "args": { + "External id": 706376,"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": 6305205187709.993, "dur": 0.897, + "args": { + "External id": 706377,"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": 6305205187713.352, "dur": 0.813, + "args": { + "External id": 706378,"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": 6305205187766.338, "dur": 10.405, + "args": { + "External id": 706379,"Record function id": 0, "Ev Idx": 330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205187768.540, "dur": 7.434, + "args": { + "External id": 706380,"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": 6305205187770.922, "dur": 4.085, + "args": { + "External id": 706381,"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": 6305205187772.431, "dur": 2.467, + "args": { + "External id": 706382,"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": 6305205187780.863, "dur": 10.148, + "args": { + "External id": 706383,"Record function id": 0, "Sequence number": 7674580, "Fwd thread id": 1, "Ev Idx": 334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205187782.107, "dur": 6.271, + "args": { + "External id": 706384,"Sequence number": 7674580, "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": 6305205187782.107, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205187786.360, "dur": 1.794, + "args": { + "External id": 706385,"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": 6305205187786.974, "dur": 1.064, + "args": { + "External id": 706386,"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": 6305205187794.868, "dur": 140.152, + "args": { + "External id": 706387,"Record function id": 0, "Sequence number": 7674579, "Fwd thread id": 1, "Ev Idx": 338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205187795.775, "dur": 132.130, + "args": { + "External id": 706388,"Sequence number": 7674579, "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": 6305205187795.775, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305205187802.629, "dur": 4.252, + "args": { + "External id": 706389,"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": 6305205187804.279, "dur": 1.949, + "args": { + "External id": 706390,"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": 6305205187805.393, "dur": 0.647, + "args": { + "External id": 706391,"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": 6305205187808.016, "dur": 49.718, + "args": { + "External id": 706392,"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": 6305205187859.371, "dur": 6.389, + "args": { + "External id": 706393,"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": 6305205187860.335, "dur": 4.897, + "args": { + "External id": 706394,"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": 6305205187864.045, "dur": 1.027, + "args": { + "External id": 706395,"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": 6305205187867.330, "dur": 5.622, + "args": { + "External id": 706396,"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": 6305205187868.447, "dur": 4.078, + "args": { + "External id": 706397,"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": 6305205187871.761, "dur": 0.689, + "args": { + "External id": 706398,"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": 6305205187873.412, "dur": 53.565, + "args": { + "External id": 706399,"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": 6305205187939.774, "dur": 9.086, + "args": { + "External id": 706400,"Record function id": 0, "Sequence number": 7674578, "Fwd thread id": 1, "Ev Idx": 351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205187940.898, "dur": 5.862, + "args": { + "External id": 706401,"Sequence number": 7674578, "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": 6305205187940.898, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205187942.242, "dur": 4.364, + "args": { + "External id": 706402,"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": 6305205187942.969, "dur": 3.507, + "args": { + "External id": 706403,"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": 6305205187952.480, "dur": 12.756, + "args": { + "External id": 706404,"Record function id": 0, "Sequence number": 7674577, "Fwd thread id": 1, "Ev Idx": 355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205187956.570, "dur": 6.217, + "args": { + "External id": 706405,"Sequence number": 7674577, "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": 6305205187956.570, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305205187957.592, "dur": 4.977, + "args": { + "External id": 706406,"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": 6305205187958.443, "dur": 3.677, + "args": { + "External id": 706407,"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": 6305205187961.488, "dur": 0.531, + "args": { + "External id": 706408,"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": 6305205187969.289, "dur": 5.470, + "args": { + "External id": 706409,"Record function id": 0, "Ev Idx": 360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205187970.902, "dur": 3.359, + "args": { + "External id": 706410,"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": 6305205187972.210, "dur": 1.784, + "args": { + "External id": 706411,"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": 6305205187972.892, "dur": 0.982, + "args": { + "External id": 706412,"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": 6305205187980.745, "dur": 9.383, + "args": { + "External id": 706413,"Record function id": 0, "Sequence number": 7674576, "Fwd thread id": 1, "Ev Idx": 364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205187981.825, "dur": 5.528, + "args": { + "External id": 706414,"Sequence number": 7674576, "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": 6305205187981.825, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205187983.161, "dur": 4.053, + "args": { + "External id": 706415,"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": 6305205187986.362, "dur": 0.751, + "args": { + "External id": 706416,"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": 6305205187993.316, "dur": 183.873, + "args": { + "External id": 706417,"Record function id": 0, "Sequence number": 7674575, "Fwd thread id": 1, "Ev Idx": 368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205187994.079, "dur": 173.549, + "args": { + "External id": 706418,"Sequence number": 7674575, "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": 6305205187994.079, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305205187996.173, "dur": 2.459, + "args": { + "External id": 706419,"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": 6305205187996.824, "dur": 1.401, + "args": { + "External id": 706420,"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": 6305205187997.607, "dur": 0.516, + "args": { + "External id": 706421,"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": 6305205188001.634, "dur": 46.678, + "args": { + "External id": 706422,"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": 6305205188049.728, "dur": 57.057, + "args": { + "External id": 706423,"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": 6305205188050.696, "dur": 55.260, + "args": { + "External id": 706424,"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": 6305205188103.903, "dur": 1.520, + "args": { + "External id": 706425,"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": 6305205188108.216, "dur": 6.651, + "args": { + "External id": 706426,"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": 6305205188109.761, "dur": 4.654, + "args": { + "External id": 706427,"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": 6305205188113.803, "dur": 0.514, + "args": { + "External id": 706428,"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": 6305205188115.347, "dur": 51.632, + "args": { + "External id": 706429,"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": 6305205188184.154, "dur": 37.578, + "args": { + "External id": 706430,"Record function id": 0, "Sequence number": 7674574, "Fwd thread id": 1, "Ev Idx": 381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205188185.373, "dur": 6.681, + "args": { + "External id": 706431,"Sequence number": 7674574, "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": 6305205188185.373, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205188187.225, "dur": 4.706, + "args": { + "External id": 706432,"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": 6305205188190.460, "dur": 1.351, + "args": { + "External id": 706433,"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": 6305205188195.766, "dur": 23.178, + "args": { + "External id": 706434,"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": 6305205188225.893, "dur": 11.059, + "args": { + "External id": 706435,"Record function id": 0, "Sequence number": 7674573, "Fwd thread id": 1, "Ev Idx": 386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205188226.780, "dur": 7.685, + "args": { + "External id": 706436,"Sequence number": 7674573, "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": 6305205188226.780, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305205188230.338, "dur": 3.922, + "args": { + "External id": 706437,"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": 6305205188231.207, "dur": 2.453, + "args": { + "External id": 706438,"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": 6305205188232.647, "dur": 0.899, + "args": { + "External id": 706439,"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": 6305205188241.203, "dur": 6.695, + "args": { + "External id": 706440,"Record function id": 0, "Ev Idx": 391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205188242.936, "dur": 4.407, + "args": { + "External id": 706441,"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": 6305205188244.583, "dur": 2.414, + "args": { + "External id": 706442,"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": 6305205188245.537, "dur": 1.317, + "args": { + "External id": 706443,"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": 6305205188252.327, "dur": 465.745, + "args": { + "External id": 706444,"Record function id": 0, "Sequence number": 7674572, "Fwd thread id": 1, "Ev Idx": 395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305205188253.700, "dur": 450.023, + "args": { + "External id": 706445,"Sequence number": 7674572, "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": 6305205188253.700, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338707, "tid": 2379456, + "ts": 6305205188281.605, "dur": 37.742, + "args": { + "External id": 706446,"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": 6305205188283.360, "dur": 35.781, + "args": { + "External id": 706447,"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": 6305205188286.323, "dur": 6.645, + "args": { + "External id": 706448,"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": 6305205188289.176, "dur": 3.263, + "args": { + "External id": 706449,"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": 6305205188294.456, "dur": 24.230, + "args": { + "External id": 706450,"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": 6305205188334.654, "dur": 2.083, + "args": { + "External id": 706451,"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": 6305205188335.304, "dur": 1.302, + "args": { + "External id": 706452,"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": 6305205188340.326, "dur": 1.786, + "args": { + "External id": 706453,"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": 6305205188341.006, "dur": 1.024, + "args": { + "External id": 706454,"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": 6305205188360.062, "dur": 5.881, + "args": { + "External id": 706455,"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": 6305205188377.792, "dur": 2.564, + "args": { + "External id": 706456,"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": 6305205188583.188, "dur": 4.242, + "args": { + "External id": 706457,"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": 6305205188592.179, "dur": 38.156, + "args": { + "External id": 706458,"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": 6305205188605.688, "dur": 0.798, + "args": { + "External id": 706459,"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": 6305205188636.506, "dur": 32.215, + "args": { + "External id": 706460,"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": 6305205188638.484, "dur": 29.998, + "args": { + "External id": 706461,"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": 6305205188642.804, "dur": 6.009, + "args": { + "External id": 706462,"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": 6305205188652.820, "dur": 15.150, + "args": { + "External id": 706463,"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": 6305205188673.492, "dur": 2.729, + "args": { + "External id": 706464,"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": 6305205188674.853, "dur": 1.235, + "args": { + "External id": 706465,"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": 6305205188683.210, "dur": 4.837, + "args": { + "External id": 706466,"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": 6305205188686.447, "dur": 1.493, + "args": { + "External id": 706467,"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": 6305205188689.996, "dur": 2.397, + "args": { + "External id": 706468,"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": 6305205188690.952, "dur": 1.335, + "args": { + "External id": 706469,"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": 6305205188731.292, "dur": 8.742, + "args": { + "External id": 706470,"Record function id": 0, "Ev Idx": 421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205188733.252, "dur": 6.092, + "args": { + "External id": 706471,"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": 6305205188735.559, "dur": 2.997, + "args": { + "External id": 706472,"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": 6305205188736.690, "dur": 1.758, + "args": { + "External id": 706473,"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": 6305205188743.619, "dur": 10.189, + "args": { + "External id": 706474,"Record function id": 0, "Sequence number": 7674571, "Fwd thread id": 1, "Ev Idx": 425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205188744.604, "dur": 6.188, + "args": { + "External id": 706475,"Sequence number": 7674571, "Fwd thread 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": 6305205188744.604, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205188748.221, "dur": 2.283, + "args": { + "External id": 706476,"Record 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": 6305205188749.008, "dur": 1.368, + "args": { + "External id": 706477,"Record 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": 6305205188760.738, "dur": 176.614, + "args": { + "External id": 706478,"Record function id": 0, "Sequence number": 7674570, "Fwd thread id": 1, "Ev Idx": 429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205188761.799, "dur": 170.976, + "args": { + "External id": 706479,"Sequence number": 7674570, "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": 6305205188761.799, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305205188765.326, "dur": 5.457, + "args": { + "External id": 706480,"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": 6305205188767.049, "dur": 3.199, + "args": { + "External id": 706481,"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": 6305205188768.938, "dur": 1.005, + "args": { + "External id": 706482,"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": 6305205188772.115, "dur": 89.353, + "args": { + "External id": 706483,"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": 6305205188862.819, "dur": 9.462, + "args": { + "External id": 706484,"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": 6305205188863.795, "dur": 7.844, + "args": { + "External id": 706485,"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": 6305205188868.247, "dur": 3.188, + "args": { + "External id": 706486,"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": 6305205188873.875, "dur": 7.514, + "args": { + "External id": 706487,"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": 6305205188875.055, "dur": 5.844, + "args": { + "External id": 706488,"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": 6305205188877.939, "dur": 2.884, + "args": { + "External id": 706489,"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": 6305205188882.302, "dur": 49.568, + "args": { + "External id": 706490,"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": 6305205188942.247, "dur": 9.387, + "args": { + "External id": 706491,"Record function id": 0, "Sequence number": 7674569, "Fwd thread id": 1, "Ev Idx": 442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205188943.204, "dur": 6.003, + "args": { + "External id": 706492,"Sequence number": 7674569, "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": 6305205188943.204, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205188944.669, "dur": 4.378, + "args": { + "External id": 706493,"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": 6305205188947.856, "dur": 1.041, + "args": { + "External id": 706494,"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": 6305205188954.983, "dur": 9.682, + "args": { + "External id": 706495,"Record function id": 0, "Sequence number": 7674568, "Fwd thread id": 1, "Ev Idx": 446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205188956.135, "dur": 6.532, + "args": { + "External id": 706496,"Sequence number": 7674568, "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": 6305205188956.135, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305205188957.079, "dur": 5.405, + "args": { + "External id": 706497,"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": 6305205188958.168, "dur": 3.815, + "args": { + "External id": 706498,"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": 6305205188961.195, "dur": 0.652, + "args": { + "External id": 706499,"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": 6305205188968.663, "dur": 5.027, + "args": { + "External id": 706500,"Record function id": 0, "Ev Idx": 451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205188969.814, "dur": 3.337, + "args": { + "External id": 706501,"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": 6305205188970.991, "dur": 1.937, + "args": { + "External id": 706502,"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": 6305205188971.696, "dur": 1.134, + "args": { + "External id": 706503,"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": 6305205188977.192, "dur": 9.163, + "args": { + "External id": 706504,"Record function id": 0, "Sequence number": 7674567, "Fwd thread id": 1, "Ev Idx": 455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205188980.983, "dur": 3.145, + "args": { + "External id": 706505,"Sequence number": 7674567, "Fwd thread 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": 6305205188980.983, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205188982.115, "dur": 1.855, + "args": { + "External id": 706506,"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": 6305205188982.796, "dur": 1.049, + "args": { + "External id": 706507,"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": 6305205188993.314, "dur": 446.197, + "args": { + "External id": 706508,"Record function id": 0, "Sequence number": 7674566, "Fwd thread id": 1, "Ev Idx": 459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFuncBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305205188994.605, "dur": 425.920, + "args": { + "External id": 706509,"Sequence number": 7674566, "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": 6305205188994.605, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338707, "tid": 2379456, + "ts": 6305205189011.196, "dur": 11.631, + "args": { + "External id": 706510,"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": 6305205189018.053, "dur": 4.162, + "args": { + "External id": 706511,"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": 6305205189024.851, "dur": 3.138, + "args": { + "External id": 706512,"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": 6305205189025.659, "dur": 2.104, + "args": { + "External id": 706513,"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": 6305205189029.312, "dur": 7.497, + "args": { + "External id": 706514,"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": 6305205189032.497, "dur": 4.151, + "args": { + "External id": 706515,"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": 6305205189119.619, "dur": 273.838, + "args": { + "External id": 706516,"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": 6305205189210.632, "dur": 4.859, + "args": { + "External id": 706517,"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": 6305205189220.236, "dur": 4.125, + "args": { + "External id": 706518,"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": 6305205189227.631, "dur": 1.580, + "args": { + "External id": 706519,"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": 6305205189230.016, "dur": 3.205, + "args": { + "External id": 706520,"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": 6305205189293.563, "dur": 2.867, + "args": { + "External id": 706521,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205189294.411, "dur": 1.885, + "args": { + "External id": 706522,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205189297.925, "dur": 29.662, + "args": { + "External id": 706523,"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": 6305205189302.363, "dur": 3.386, + "args": { + "External id": 706524,"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": 6305205189328.870, "dur": 1.749, + "args": { + "External id": 706525,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205189329.988, "dur": 0.547, + "args": { + "External id": 706526,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205189336.158, "dur": 15.144, + "args": { + "External id": 706527,"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": 6305205189339.481, "dur": 0.641, + "args": { + "External id": 706528,"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": 6305205189407.525, "dur": 4.036, + "args": { + "External id": 706529,"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": 6305205189414.527, "dur": 0.593, + "args": { + "External id": 706530,"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": 6305205189417.125, "dur": 0.441, + "args": { + "External id": 706531,"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": 6305205189451.270, "dur": 260.761, + "args": { + "External id": 706532,"Record function id": 0, "Sequence number": 7674565, "Fwd thread id": 1, "Ev Idx": 483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305205189453.265, "dur": 250.405, + "args": { + "External id": 706533,"Sequence number": 7674565, "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": 6305205189453.265, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338707, "tid": 2379456, + "ts": 6305205189474.932, "dur": 68.519, + "args": { + "External id": 706534,"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": 6305205189478.019, "dur": 3.369, + "args": { + "External id": 706535,"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": 6305205189482.883, "dur": 59.753, + "args": { + "External id": 706536,"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": 6305205189555.399, "dur": 8.432, + "args": { + "External id": 706537,"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": 6305205189560.115, "dur": 3.342, + "args": { + "External id": 706538,"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": 6305205189722.561, "dur": 172.291, + "args": { + "External id": 706539,"Record function id": 0, "Sequence number": 7674564, "Fwd thread id": 1, "Ev Idx": 490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305205189724.378, "dur": 163.927, + "args": { + "External id": 706540,"Sequence number": 7674564, "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": 6305205189724.378, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338707, "tid": 2379456, + "ts": 6305205189736.044, "dur": 48.847, + "args": { + "External id": 706541,"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": 6305205189738.999, "dur": 3.143, + "args": { + "External id": 706542,"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": 6305205189743.590, "dur": 40.674, + "args": { + "External id": 706543,"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": 6305205189791.940, "dur": 9.144, + "args": { + "External id": 706544,"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": 6305205189797.925, "dur": 2.876, + "args": { + "External id": 706545,"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": 6305205189901.459, "dur": 15.822, + "args": { + "External id": 706546,"Record function id": 0, "Sequence number": 7674563, "Fwd thread id": 1, "Ev Idx": 497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205189905.236, "dur": 9.243, + "args": { + "External id": 706547,"Sequence number": 7674563, "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": 6305205189905.236, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205189908.241, "dur": 5.923, + "args": { + "External id": 706548,"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": 6305205189909.567, "dur": 4.372, + "args": { + "External id": 706549,"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": 6305205189920.624, "dur": 8.261, + "args": { + "External id": 706550,"Record function id": 0, "Sequence number": 7674562, "Fwd thread id": 1, "Ev Idx": 501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205189921.573, "dur": 5.417, + "args": { + "External id": 706551,"Sequence number": 7674562, "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": 6305205189921.573, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205189922.686, "dur": 4.156, + "args": { + "External id": 706552,"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": 6305205189925.976, "dur": 0.708, + "args": { + "External id": 706553,"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": 6305205189931.953, "dur": 11.371, + "args": { + "External id": 706554,"Record function id": 0, "Sequence number": 7674561, "Fwd thread id": 1, "Ev Idx": 505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205189933.155, "dur": 8.186, + "args": { + "External id": 706555,"Sequence number": 7674561, "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": 6305205189933.155, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205189934.385, "dur": 6.815, + "args": { + "External id": 706556,"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": 6305205189937.625, "dur": 3.442, + "args": { + "External id": 706557,"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": 6305205189946.512, "dur": 33.730, + "args": { + "External id": 706558,"Record function id": 0, "Sequence number": 7674560, "Fwd thread id": 1, "Ev Idx": 509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205189947.277, "dur": 30.792, + "args": { + "External id": 706559,"Sequence number": 7674560, "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": 6305205189947.277, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205189950.285, "dur": 27.631, + "args": { + "External id": 706560,"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": 6305205189976.792, "dur": 0.946, + "args": { + "External id": 706561,"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": 6305205189983.717, "dur": 237.317, + "args": { + "External id": 706562,"Record function id": 0, "Sequence number": 7674559, "Fwd thread id": 1, "Ev Idx": 513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205189984.589, "dur": 226.684, + "args": { + "External id": 706563,"Sequence number": 7674559, "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": 6305205189984.589, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305205189991.510, "dur": 6.485, + "args": { + "External id": 706564,"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": 6305205189993.574, "dur": 3.747, + "args": { + "External id": 706565,"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": 6305205189995.595, "dur": 1.401, + "args": { + "External id": 706566,"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": 6305205189999.552, "dur": 135.498, + "args": { + "External id": 706567,"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": 6305205190137.876, "dur": 10.785, + "args": { + "External id": 706568,"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": 6305205190138.985, "dur": 8.606, + "args": { + "External id": 706569,"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": 6305205190143.958, "dur": 3.440, + "args": { + "External id": 706570,"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": 6305205190150.788, "dur": 4.782, + "args": { + "External id": 706571,"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": 6305205190151.793, "dur": 3.297, + "args": { + "External id": 706572,"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": 6305205190154.684, "dur": 0.336, + "args": { + "External id": 706573,"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": 6305205190156.275, "dur": 54.171, + "args": { + "External id": 706574,"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": 6305205190228.915, "dur": 8.723, + "args": { + "External id": 706575,"Record function id": 0, "Sequence number": 7674558, "Fwd thread id": 1, "Ev Idx": 526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205190230.041, "dur": 5.748, + "args": { + "External id": 706576,"Sequence number": 7674558, "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": 6305205190230.041, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205190231.353, "dur": 4.289, + "args": { + "External id": 706577,"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": 6305205190234.262, "dur": 1.254, + "args": { + "External id": 706578,"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": 6305205190241.480, "dur": 12.144, + "args": { + "External id": 706579,"Record function id": 0, "Sequence number": 7674557, "Fwd thread id": 1, "Ev Idx": 530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205190242.381, "dur": 8.975, + "args": { + "External id": 706580,"Sequence number": 7674557, "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": 6305205190242.381, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305205190243.053, "dur": 8.101, + "args": { + "External id": 706581,"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": 6305205190243.735, "dur": 6.826, + "args": { + "External id": 706582,"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": 6305205190247.566, "dur": 2.889, + "args": { + "External id": 706583,"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": 6305205190259.375, "dur": 11.819, + "args": { + "External id": 706584,"Record function id": 0, "Ev Idx": 535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205190260.842, "dur": 9.562, + "args": { + "External id": 706585,"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": 6305205190263.440, "dur": 6.539, + "args": { + "External id": 706586,"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": 6305205190267.077, "dur": 2.774, + "args": { + "External id": 706587,"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": 6305205190277.933, "dur": 5.602, + "args": { + "External id": 706588,"Record function id": 0, "Sequence number": 7674556, "Fwd thread id": 1, "Ev Idx": 539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205190278.788, "dur": 2.663, + "args": { + "External id": 706589,"Sequence number": 7674556, "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": 6305205190278.788, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205190279.849, "dur": 1.453, + "args": { + "External id": 706590,"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": 6305205190280.470, "dur": 0.733, + "args": { + "External id": 706591,"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": 6305205190286.784, "dur": 93.719, + "args": { + "External id": 706592,"Record function id": 0, "Sequence number": 7674555, "Fwd thread id": 1, "Ev Idx": 543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205190287.565, "dur": 86.921, + "args": { + "External id": 706593,"Sequence number": 7674555, "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": 6305205190287.565, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305205190289.784, "dur": 4.722, + "args": { + "External id": 706594,"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": 6305205190290.213, "dur": 3.863, + "args": { + "External id": 706595,"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": 6305205190293.365, "dur": 0.608, + "args": { + "External id": 706596,"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": 6305205190295.195, "dur": 28.743, + "args": { + "External id": 706597,"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": 6305205190325.178, "dur": 5.218, + "args": { + "External id": 706598,"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": 6305205190325.657, "dur": 4.300, + "args": { + "External id": 706599,"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": 6305205190329.109, "dur": 0.732, + "args": { + "External id": 706600,"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": 6305205190331.313, "dur": 4.477, + "args": { + "External id": 706601,"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": 6305205190334.169, "dur": 1.141, + "args": { + "External id": 706602,"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": 6305205190334.868, "dur": 0.349, + "args": { + "External id": 706603,"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": 6305205190336.192, "dur": 37.479, + "args": { + "External id": 706604,"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": 6305205190385.313, "dur": 36.768, + "args": { + "External id": 706605,"Record function id": 0, "Sequence number": 7674554, "Fwd thread id": 1, "Ev Idx": 556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205190386.480, "dur": 7.512, + "args": { + "External id": 706606,"Sequence number": 7674554, "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": 6305205190386.480, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205190387.552, "dur": 6.290, + "args": { + "External id": 706607,"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": 6305205190390.477, "dur": 3.234, + "args": { + "External id": 706608,"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": 6305205190397.430, "dur": 22.321, + "args": { + "External id": 706609,"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": 6305205190426.332, "dur": 10.371, + "args": { + "External id": 706610,"Record function id": 0, "Sequence number": 7674553, "Fwd thread id": 1, "Ev Idx": 561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205190429.819, "dur": 4.213, + "args": { + "External id": 706611,"Sequence number": 7674553, "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": 6305205190429.819, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305205190430.658, "dur": 3.142, + "args": { + "External id": 706612,"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": 6305205190431.615, "dur": 1.645, + "args": { + "External id": 706613,"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": 6305205190432.582, "dur": 0.545, + "args": { + "External id": 706614,"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": 6305205190440.431, "dur": 4.777, + "args": { + "External id": 706615,"Record function id": 0, "Ev Idx": 566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205190441.763, "dur": 2.950, + "args": { + "External id": 706616,"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": 6305205190442.896, "dur": 1.490, + "args": { + "External id": 706617,"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": 6305205190443.427, "dur": 0.873, + "args": { + "External id": 706618,"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": 6305205190448.408, "dur": 10.776, + "args": { + "External id": 706619,"Record function id": 0, "Sequence number": 7674552, "Fwd thread id": 1, "Ev Idx": 570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205190449.401, "dur": 7.576, + "args": { + "External id": 706620,"Sequence number": 7674552, "Fwd thread 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": 6305205190449.401, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205190452.780, "dur": 4.056, + "args": { + "External id": 706621,"Record 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": 6305205190455.972, "dur": 0.774, + "args": { + "External id": 706622,"Record 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": 6305205190462.287, "dur": 131.008, + "args": { + "External id": 706623,"Record function id": 0, "Sequence number": 7674551, "Fwd thread id": 1, "Ev Idx": 574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205190462.910, "dur": 121.540, + "args": { + "External id": 706624,"Sequence number": 7674551, "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": 6305205190462.910, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305205190465.145, "dur": 2.199, + "args": { + "External id": 706625,"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": 6305205190465.527, "dur": 1.435, + "args": { + "External id": 706626,"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": 6305205190466.362, "dur": 0.492, + "args": { + "External id": 706627,"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": 6305205190475.773, "dur": 51.111, + "args": { + "External id": 706628,"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": 6305205190528.876, "dur": 6.252, + "args": { + "External id": 706629,"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": 6305205190529.677, "dur": 4.750, + "args": { + "External id": 706630,"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": 6305205190530.962, "dur": 3.309, + "args": { + "External id": 706631,"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": 6305205190536.547, "dur": 7.313, + "args": { + "External id": 706632,"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": 6305205190537.251, "dur": 6.097, + "args": { + "External id": 706633,"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": 6305205190540.297, "dur": 2.979, + "args": { + "External id": 706634,"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": 6305205190546.820, "dur": 36.950, + "args": { + "External id": 706635,"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": 6305205190600.021, "dur": 24.856, + "args": { + "External id": 706636,"Record function id": 0, "Sequence number": 7674550, "Fwd thread id": 1, "Ev Idx": 587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205190600.921, "dur": 3.284, + "args": { + "External id": 706637,"Sequence number": 7674550, "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": 6305205190600.921, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205190602.023, "dur": 2.048, + "args": { + "External id": 706638,"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": 6305205190602.608, "dur": 1.323, + "args": { + "External id": 706639,"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": 6305205190606.660, "dur": 16.154, + "args": { + "External id": 706640,"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": 6305205190628.736, "dur": 12.319, + "args": { + "External id": 706641,"Record function id": 0, "Sequence number": 7674549, "Fwd thread id": 1, "Ev Idx": 592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205190629.777, "dur": 9.044, + "args": { + "External id": 706642,"Sequence number": 7674549, "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": 6305205190629.777, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305205190630.451, "dur": 8.164, + "args": { + "External id": 706643,"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": 6305205190631.454, "dur": 6.587, + "args": { + "External id": 706644,"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": 6305205190637.341, "dur": 0.596, + "args": { + "External id": 706645,"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": 6305205190645.312, "dur": 5.792, + "args": { + "External id": 706646,"Record function id": 0, "Ev Idx": 597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205190646.827, "dur": 3.680, + "args": { + "External id": 706647,"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": 6305205190648.040, "dur": 2.156, + "args": { + "External id": 706648,"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": 6305205190648.629, "dur": 1.485, + "args": { + "External id": 706649,"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": 6305205190655.428, "dur": 359.509, + "args": { + "External id": 706650,"Record function id": 0, "Sequence number": 7674548, "Fwd thread id": 1, "Ev Idx": 601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305205190656.610, "dur": 326.425, + "args": { + "External id": 706651,"Sequence number": 7674548, "Fwd thread 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": 6305205190656.610, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205190692.470, "dur": 1.833, + "args": { + "External id": 706652,"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": 6305205190693.099, "dur": 1.040, + "args": { + "External id": 706653,"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": 6305205190711.858, "dur": 4.199, + "args": { + "External id": 706654,"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": 6305205190725.196, "dur": 1.925, + "args": { + "External id": 706655,"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": 6305205190881.948, "dur": 4.103, + "args": { + "External id": 706656,"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": 6305205190889.944, "dur": 31.884, + "args": { + "External id": 706657,"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": 6305205190899.071, "dur": 0.635, + "args": { + "External id": 706658,"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": 6305205190927.371, "dur": 32.235, + "args": { + "External id": 706659,"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": 6305205190929.382, "dur": 30.020, + "args": { + "External id": 706660,"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": 6305205190935.337, "dur": 5.960, + "args": { + "External id": 706661,"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": 6305205190942.821, "dur": 16.055, + "args": { + "External id": 706662,"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": 6305205190966.302, "dur": 2.158, + "args": { + "External id": 706663,"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": 6305205190967.411, "dur": 0.912, + "args": { + "External id": 706664,"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": 6305205190974.682, "dur": 1.464, + "args": { + "External id": 706665,"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": 6305205190975.215, "dur": 0.827, + "args": { + "External id": 706666,"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": 6305205190993.322, "dur": 15.669, + "args": { + "External id": 706667,"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": 6305205191023.547, "dur": 9.755, + "args": { + "External id": 706668,"Record function id": 0, "Ev Idx": 619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205191027.836, "dur": 4.808, + "args": { + "External id": 706669,"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": 6305205191029.443, "dur": 2.247, + "args": { + "External id": 706670,"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": 6305205191030.124, "dur": 1.471, + "args": { + "External id": 706671,"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": 6305205191039.317, "dur": 5.498, + "args": { + "External id": 706672,"Record function id": 0, "Sequence number": 7674547, "Fwd thread id": 1, "Ev Idx": 623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205191040.445, "dur": 1.257, + "args": { + "External id": 706673,"Sequence number": 7674547, "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": 6305205191040.445, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SwiGLULinearFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305205191048.929, "dur": 518.502, + "args": { + "External id": 706674,"Record function id": 0, "Sequence number": 7674546, "Fwd thread id": 1, "Ev Idx": 625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305205191050.080, "dur": 504.987, + "args": { + "External id": 706675,"Sequence number": 7674546, "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": 6305205191050.080, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205191135.642, "dur": 9.402, + "args": { + "External id": 706676,"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": 6305205191140.747, "dur": 3.937, + "args": { + "External id": 706677,"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": 6305205191148.521, "dur": 10.248, + "args": { + "External id": 706678,"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": 6305205191150.067, "dur": 8.067, + "args": { + "External id": 706679,"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": 6305205191157.251, "dur": 0.739, + "args": { + "External id": 706680,"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": 6305205191164.842, "dur": 93.495, + "args": { + "External id": 706681,"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": 6305205191165.745, "dur": 2.132, + "args": { + "External id": 706682,"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": 6305205191166.276, "dur": 1.166, + "args": { + "External id": 706683,"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": 6305205191166.946, "dur": 0.420, + "args": { + "External id": 706684,"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": 6305205191169.116, "dur": 88.549, + "args": { + "External id": 706685,"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": 6305205191170.531, "dur": 86.205, + "args": { + "External id": 706686,"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": 6305205191262.250, "dur": 7.203, + "args": { + "External id": 706687,"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": 6305205191265.771, "dur": 3.546, + "args": { + "External id": 706688,"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": 6305205191303.333, "dur": 6.436, + "args": { + "External id": 706689,"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": 6305205191312.997, "dur": 1.693, + "args": { + "External id": 706690,"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": 6305205191315.383, "dur": 1.526, + "args": { + "External id": 706691,"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": 6305205191350.607, "dur": 1.978, + "args": { + "External id": 706692,"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": 6305205191351.390, "dur": 1.013, + "args": { + "External id": 706693,"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": 6305205191375.956, "dur": 152.519, + "args": { + "External id": 706694,"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": 6305205191381.481, "dur": 9.413, + "args": { + "External id": 706695,"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": 6305205191387.169, "dur": 2.941, + "args": { + "External id": 706696,"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": 6305205191392.217, "dur": 5.514, + "args": { + "External id": 706697,"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": 6305205191396.469, "dur": 0.613, + "args": { + "External id": 706698,"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": 6305205191399.289, "dur": 1.780, + "args": { + "External id": 706699,"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": 6305205191400.124, "dur": 0.529, + "args": { + "External id": 706700,"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": 6305205191403.832, "dur": 4.908, + "args": { + "External id": 706701,"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": 6305205191404.580, "dur": 3.668, + "args": { + "External id": 706702,"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": 6305205191414.966, "dur": 1.774, + "args": { + "External id": 706703,"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": 6305205191415.875, "dur": 0.545, + "args": { + "External id": 706704,"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": 6305205191419.517, "dur": 6.685, + "args": { + "External id": 706705,"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": 6305205191424.116, "dur": 1.914, + "args": { + "External id": 706706,"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": 6305205191426.899, "dur": 3.823, + "args": { + "External id": 706707,"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": 6305205191429.969, "dur": 0.488, + "args": { + "External id": 706708,"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": 6305205191431.293, "dur": 4.330, + "args": { + "External id": 706709,"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": 6305205191431.820, "dur": 3.701, + "args": { + "External id": 706710,"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": 6305205191437.074, "dur": 57.195, + "args": { + "External id": 706711,"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": 6305205191498.306, "dur": 1.154, + "args": { + "External id": 706712,"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": 6305205191500.136, "dur": 4.355, + "args": { + "External id": 706713,"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": 6305205191503.353, "dur": 0.600, + "args": { + "External id": 706714,"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": 6305205191523.154, "dur": 3.973, + "args": { + "External id": 706715,"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": 6305205191581.514, "dur": 9.330, + "args": { + "External id": 706716,"Record function id": 0, "Ev Idx": 667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205191583.715, "dur": 6.385, + "args": { + "External id": 706717,"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": 6305205191585.877, "dur": 3.498, + "args": { + "External id": 706718,"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": 6305205191586.960, "dur": 2.308, + "args": { + "External id": 706719,"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": 6305205191595.021, "dur": 6.656, + "args": { + "External id": 706720,"Record function id": 0, "Sequence number": 7674545, "Fwd thread id": 1, "Ev Idx": 671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205191595.985, "dur": 3.509, + "args": { + "External id": 706721,"Sequence number": 7674545, "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": 6305205191595.985, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205191597.705, "dur": 1.498, + "args": { + "External id": 706722,"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": 6305205191598.315, "dur": 0.745, + "args": { + "External id": 706723,"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": 6305205191605.212, "dur": 123.027, + "args": { + "External id": 706724,"Record function id": 0, "Sequence number": 7674544, "Fwd thread id": 1, "Ev Idx": 675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205191608.693, "dur": 113.061, + "args": { + "External id": 706725,"Sequence number": 7674544, "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": 6305205191608.693, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305205191611.942, "dur": 4.294, + "args": { + "External id": 706726,"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": 6305205191613.295, "dur": 2.320, + "args": { + "External id": 706727,"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": 6305205191614.700, "dur": 0.767, + "args": { + "External id": 706728,"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": 6305205191617.277, "dur": 47.885, + "args": { + "External id": 706729,"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": 6305205191666.349, "dur": 8.654, + "args": { + "External id": 706730,"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": 6305205191667.128, "dur": 7.129, + "args": { + "External id": 706731,"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": 6305205191673.103, "dur": 1.002, + "args": { + "External id": 706732,"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": 6305205191676.551, "dur": 6.453, + "args": { + "External id": 706733,"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": 6305205191681.229, "dur": 1.361, + "args": { + "External id": 706734,"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": 6305205191681.953, "dur": 0.571, + "args": { + "External id": 706735,"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": 6305205191683.594, "dur": 37.280, + "args": { + "External id": 706736,"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": 6305205191733.307, "dur": 12.959, + "args": { + "External id": 706737,"Record function id": 0, "Sequence number": 7674543, "Fwd thread id": 1, "Ev Idx": 688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205191734.384, "dur": 10.443, + "args": { + "External id": 706738,"Sequence number": 7674543, "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": 6305205191734.384, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205191738.226, "dur": 6.445, + "args": { + "External id": 706739,"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": 6305205191741.084, "dur": 3.330, + "args": { + "External id": 706740,"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": 6305205191749.998, "dur": 6.904, + "args": { + "External id": 706741,"Record function id": 0, "Sequence number": 7674542, "Fwd thread id": 1, "Ev Idx": 692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205191751.003, "dur": 3.672, + "args": { + "External id": 706742,"Sequence number": 7674542, "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": 6305205191751.003, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305205191751.904, "dur": 2.555, + "args": { + "External id": 706743,"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": 6305205191752.497, "dur": 1.469, + "args": { + "External id": 706744,"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": 6305205191753.384, "dur": 0.452, + "args": { + "External id": 706745,"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": 6305205191760.723, "dur": 7.508, + "args": { + "External id": 706746,"Record function id": 0, "Ev Idx": 697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205191761.893, "dur": 5.792, + "args": { + "External id": 706747,"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": 6305205191763.009, "dur": 4.419, + "args": { + "External id": 706748,"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": 6305205191766.353, "dur": 0.979, + "args": { + "External id": 706749,"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": 6305205191771.416, "dur": 8.171, + "args": { + "External id": 706750,"Record function id": 0, "Sequence number": 7674541, "Fwd thread id": 1, "Ev Idx": 701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205191772.386, "dur": 4.825, + "args": { + "External id": 706751,"Sequence number": 7674541, "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": 6305205191772.386, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205191773.486, "dur": 3.572, + "args": { + "External id": 706752,"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": 6305205191776.241, "dur": 0.644, + "args": { + "External id": 706753,"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": 6305205191782.613, "dur": 95.753, + "args": { + "External id": 706754,"Record function id": 0, "Sequence number": 7674540, "Fwd thread id": 1, "Ev Idx": 705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205191783.509, "dur": 87.411, + "args": { + "External id": 706755,"Sequence number": 7674540, "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": 6305205191783.509, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305205191785.557, "dur": 4.090, + "args": { + "External id": 706756,"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": 6305205191785.984, "dur": 3.249, + "args": { + "External id": 706757,"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": 6305205191788.401, "dur": 0.731, + "args": { + "External id": 706758,"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": 6305205191790.409, "dur": 32.919, + "args": { + "External id": 706759,"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": 6305205191824.208, "dur": 3.014, + "args": { + "External id": 706760,"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": 6305205191825.008, "dur": 1.781, + "args": { + "External id": 706761,"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": 6305205191825.931, "dur": 0.725, + "args": { + "External id": 706762,"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": 6305205191828.671, "dur": 7.485, + "args": { + "External id": 706763,"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": 6305205191831.963, "dur": 3.757, + "args": { + "External id": 706764,"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": 6305205191835.224, "dur": 0.407, + "args": { + "External id": 706765,"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": 6305205191836.720, "dur": 33.402, + "args": { + "External id": 706766,"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": 6305205191882.672, "dur": 29.333, + "args": { + "External id": 706767,"Record function id": 0, "Sequence number": 7674539, "Fwd thread id": 1, "Ev Idx": 718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205191883.571, "dur": 3.035, + "args": { + "External id": 706768,"Sequence number": 7674539, "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": 6305205191883.571, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205191884.746, "dur": 1.723, + "args": { + "External id": 706769,"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": 6305205191885.380, "dur": 0.965, + "args": { + "External id": 706770,"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": 6305205191889.253, "dur": 20.154, + "args": { + "External id": 706771,"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": 6305205191915.873, "dur": 9.472, + "args": { + "External id": 706772,"Record function id": 0, "Sequence number": 7674538, "Fwd thread id": 1, "Ev Idx": 723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205191916.588, "dur": 6.524, + "args": { + "External id": 706773,"Sequence number": 7674538, "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": 6305205191916.588, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305205191919.926, "dur": 2.984, + "args": { + "External id": 706774,"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": 6305205191920.591, "dur": 1.766, + "args": { + "External id": 706775,"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": 6305205191921.662, "dur": 0.609, + "args": { + "External id": 706776,"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": 6305205191931.602, "dur": 5.315, + "args": { + "External id": 706777,"Record function id": 0, "Ev Idx": 728 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205191932.845, "dur": 3.575, + "args": { + "External id": 706778,"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": 6305205191933.969, "dur": 2.145, + "args": { + "External id": 706779,"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": 6305205191934.704, "dur": 1.320, + "args": { + "External id": 706780,"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": 6305205191943.368, "dur": 484.258, + "args": { + "External id": 706781,"Record function id": 0, "Sequence number": 7674537, "Fwd thread id": 1, "Ev Idx": 732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305205191944.531, "dur": 448.345, + "args": { + "External id": 706782,"Sequence number": 7674537, "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": 6305205191944.531, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338707, "tid": 2379456, + "ts": 6305205191967.711, "dur": 31.947, + "args": { + "External id": 706783,"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": 6305205191969.329, "dur": 30.053, + "args": { + "External id": 706784,"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": 6305205191971.827, "dur": 5.961, + "args": { + "External id": 706785,"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": 6305205191974.156, "dur": 3.020, + "args": { + "External id": 706786,"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": 6305205191979.370, "dur": 19.594, + "args": { + "External id": 706787,"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": 6305205192012.992, "dur": 3.852, + "args": { + "External id": 706788,"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": 6305205192015.592, "dur": 1.116, + "args": { + "External id": 706789,"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": 6305205192020.147, "dur": 1.505, + "args": { + "External id": 706790,"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": 6305205192020.939, "dur": 0.617, + "args": { + "External id": 706791,"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": 6305205192036.498, "dur": 4.793, + "args": { + "External id": 706792,"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": 6305205192051.872, "dur": 2.036, + "args": { + "External id": 706793,"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": 6305205192273.588, "dur": 3.229, + "args": { + "External id": 706794,"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": 6305205192281.566, "dur": 38.798, + "args": { + "External id": 706795,"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": 6305205192297.234, "dur": 0.953, + "args": { + "External id": 706796,"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": 6305205192326.300, "dur": 30.647, + "args": { + "External id": 706797,"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": 6305205192327.956, "dur": 28.799, + "args": { + "External id": 706798,"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": 6305205192331.972, "dur": 4.333, + "args": { + "External id": 706799,"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": 6305205192340.359, "dur": 15.933, + "args": { + "External id": 706800,"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": 6305205192361.834, "dur": 5.282, + "args": { + "External id": 706801,"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": 6305205192366.066, "dur": 0.957, + "args": { + "External id": 706802,"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": 6305205192374.286, "dur": 2.140, + "args": { + "External id": 706803,"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": 6305205192375.120, "dur": 1.133, + "args": { + "External id": 706804,"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": 6305205192378.250, "dur": 3.624, + "args": { + "External id": 706805,"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": 6305205192380.857, "dur": 0.917, + "args": { + "External id": 706806,"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": 6305205192408.646, "dur": 17.350, + "args": { + "External id": 706807,"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": 6305205192440.969, "dur": 9.012, + "args": { + "External id": 706808,"Record function id": 0, "Ev Idx": 759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205192443.126, "dur": 6.174, + "args": { + "External id": 706809,"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": 6305205192445.476, "dur": 2.961, + "args": { + "External id": 706810,"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": 6305205192446.550, "dur": 1.747, + "args": { + "External id": 706811,"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": 6305205192454.254, "dur": 9.591, + "args": { + "External id": 706812,"Record function id": 0, "Sequence number": 7674536, "Fwd thread id": 1, "Ev Idx": 763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205192455.151, "dur": 6.189, + "args": { + "External id": 706813,"Sequence number": 7674536, "Fwd thread 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": 6305205192455.151, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205192456.586, "dur": 4.469, + "args": { + "External id": 706814,"Record 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": 6305205192459.778, "dur": 1.123, + "args": { + "External id": 706815,"Record 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": 6305205192467.402, "dur": 167.319, + "args": { + "External id": 706816,"Record function id": 0, "Sequence number": 7674535, "Fwd thread id": 1, "Ev Idx": 767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205192468.225, "dur": 158.380, + "args": { + "External id": 706817,"Sequence number": 7674535, "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": 6305205192468.225, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305205192471.428, "dur": 4.753, + "args": { + "External id": 706818,"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": 6305205192472.973, "dur": 2.620, + "args": { + "External id": 706819,"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": 6305205192474.458, "dur": 0.886, + "args": { + "External id": 706820,"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": 6305205192477.360, "dur": 90.553, + "args": { + "External id": 706821,"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": 6305205192570.283, "dur": 10.404, + "args": { + "External id": 706822,"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": 6305205192574.357, "dur": 5.569, + "args": { + "External id": 706823,"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": 6305205192578.775, "dur": 1.026, + "args": { + "External id": 706824,"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": 6305205192582.414, "dur": 2.824, + "args": { + "External id": 706825,"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": 6305205192583.562, "dur": 1.204, + "args": { + "External id": 706826,"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": 6305205192584.273, "dur": 0.425, + "args": { + "External id": 706827,"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": 6305205192585.800, "dur": 39.772, + "args": { + "External id": 706828,"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": 6305205192641.734, "dur": 12.051, + "args": { + "External id": 706829,"Record function id": 0, "Sequence number": 7674534, "Fwd thread id": 1, "Ev Idx": 780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205192642.955, "dur": 8.888, + "args": { + "External id": 706830,"Sequence number": 7674534, "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": 6305205192642.955, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205192644.038, "dur": 7.637, + "args": { + "External id": 706831,"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": 6305205192650.269, "dur": 1.269, + "args": { + "External id": 706832,"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": 6305205192659.914, "dur": 6.893, + "args": { + "External id": 706833,"Record function id": 0, "Sequence number": 7674533, "Fwd thread id": 1, "Ev Idx": 784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205192660.710, "dur": 3.955, + "args": { + "External id": 706834,"Sequence number": 7674533, "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": 6305205192660.710, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305205192661.569, "dur": 2.888, + "args": { + "External id": 706835,"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": 6305205192662.417, "dur": 1.505, + "args": { + "External id": 706836,"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": 6305205192663.292, "dur": 0.498, + "args": { + "External id": 706837,"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": 6305205192670.751, "dur": 9.473, + "args": { + "External id": 706838,"Record function id": 0, "Ev Idx": 789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205192672.231, "dur": 7.460, + "args": { + "External id": 706839,"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": 6305205192673.872, "dur": 5.509, + "args": { + "External id": 706840,"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": 6305205192674.580, "dur": 4.693, + "args": { + "External id": 706841,"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": 6305205192683.423, "dur": 7.984, + "args": { + "External id": 706842,"Record function id": 0, "Sequence number": 7674532, "Fwd thread id": 1, "Ev Idx": 793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205192686.623, "dur": 3.292, + "args": { + "External id": 706843,"Sequence number": 7674532, "Fwd thread 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": 6305205192686.623, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205192687.867, "dur": 1.894, + "args": { + "External id": 706844,"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": 6305205192688.381, "dur": 1.215, + "args": { + "External id": 706845,"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": 6305205192695.389, "dur": 352.954, + "args": { + "External id": 706846,"Record function id": 0, "Sequence number": 7674531, "Fwd thread id": 1, "Ev Idx": 797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFuncBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305205192698.801, "dur": 333.467, + "args": { + "External id": 706847,"Sequence number": 7674531, "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": 6305205192698.801, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338707, "tid": 2379456, + "ts": 6305205192715.624, "dur": 9.181, + "args": { + "External id": 706848,"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": 6305205192717.725, "dur": 6.480, + "args": { + "External id": 706849,"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": 6305205192727.114, "dur": 6.811, + "args": { + "External id": 706850,"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": 6305205192729.816, "dur": 3.878, + "args": { + "External id": 706851,"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": 6305205192735.219, "dur": 2.799, + "args": { + "External id": 706852,"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": 6305205192736.070, "dur": 1.702, + "args": { + "External id": 706853,"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": 6305205192766.720, "dur": 241.692, + "args": { + "External id": 706854,"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": 6305205192844.148, "dur": 3.140, + "args": { + "External id": 706855,"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": 6305205192851.289, "dur": 3.775, + "args": { + "External id": 706856,"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": 6305205192858.676, "dur": 4.032, + "args": { + "External id": 706857,"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": 6305205192863.685, "dur": 1.514, + "args": { + "External id": 706858,"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": 6305205192909.215, "dur": 2.407, + "args": { + "External id": 706859,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205192910.229, "dur": 1.234, + "args": { + "External id": 706860,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205192912.918, "dur": 32.467, + "args": { + "External id": 706861,"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": 6305205192922.185, "dur": 3.319, + "args": { + "External id": 706862,"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": 6305205192946.561, "dur": 1.420, + "args": { + "External id": 706863,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205192947.368, "dur": 0.531, + "args": { + "External id": 706864,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205192948.907, "dur": 14.987, + "args": { + "External id": 706865,"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": 6305205192950.226, "dur": 2.719, + "args": { + "External id": 706866,"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": 6305205193020.160, "dur": 3.387, + "args": { + "External id": 706867,"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": 6305205193026.528, "dur": 0.839, + "args": { + "External id": 706868,"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": 6305205193029.146, "dur": 0.550, + "args": { + "External id": 706869,"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": 6305205193094.438, "dur": 242.123, + "args": { + "External id": 706870,"Record function id": 0, "Sequence number": 7674530, "Fwd thread id": 1, "Ev Idx": 821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305205193097.242, "dur": 232.047, + "args": { + "External id": 706871,"Sequence number": 7674530, "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": 6305205193097.242, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338707, "tid": 2379456, + "ts": 6305205193119.442, "dur": 50.312, + "args": { + "External id": 706872,"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": 6305205193125.642, "dur": 4.877, + "args": { + "External id": 706873,"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": 6305205193132.234, "dur": 36.849, + "args": { + "External id": 706874,"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": 6305205193183.756, "dur": 4.226, + "args": { + "External id": 706875,"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": 6305205193185.214, "dur": 2.450, + "args": { + "External id": 706876,"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": 6305205193346.028, "dur": 192.091, + "args": { + "External id": 706877,"Record function id": 0, "Sequence number": 7674529, "Fwd thread id": 1, "Ev Idx": 828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305205193347.833, "dur": 181.819, + "args": { + "External id": 706878,"Sequence number": 7674529, "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": 6305205193347.833, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338707, "tid": 2379456, + "ts": 6305205193358.781, "dur": 48.642, + "args": { + "External id": 706879,"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": 6305205193363.023, "dur": 3.429, + "args": { + "External id": 706880,"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": 6305205193367.663, "dur": 39.217, + "args": { + "External id": 706881,"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": 6305205193414.232, "dur": 3.761, + "args": { + "External id": 706882,"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": 6305205193415.332, "dur": 2.375, + "args": { + "External id": 706883,"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": 6305205193547.442, "dur": 18.398, + "args": { + "External id": 706884,"Record function id": 0, "Sequence number": 7674528, "Fwd thread id": 1, "Ev Idx": 835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205193548.860, "dur": 14.243, + "args": { + "External id": 706885,"Sequence number": 7674528, "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": 6305205193548.860, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205193551.553, "dur": 11.234, + "args": { + "External id": 706886,"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": 6305205193555.381, "dur": 7.226, + "args": { + "External id": 706887,"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": 6305205193569.342, "dur": 5.873, + "args": { + "External id": 706888,"Record function id": 0, "Sequence number": 7674527, "Fwd thread id": 1, "Ev Idx": 839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205193570.547, "dur": 2.654, + "args": { + "External id": 706889,"Sequence number": 7674527, "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": 6305205193570.547, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205193571.390, "dur": 1.669, + "args": { + "External id": 706890,"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": 6305205193572.017, "dur": 0.913, + "args": { + "External id": 706891,"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": 6305205193580.742, "dur": 10.928, + "args": { + "External id": 706892,"Record function id": 0, "Sequence number": 7674526, "Fwd thread id": 1, "Ev Idx": 843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205193584.157, "dur": 5.675, + "args": { + "External id": 706893,"Sequence number": 7674526, "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": 6305205193584.157, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205193585.318, "dur": 4.379, + "args": { + "External id": 706894,"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": 6305205193588.734, "dur": 0.873, + "args": { + "External id": 706895,"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": 6305205193594.865, "dur": 5.678, + "args": { + "External id": 706896,"Record function id": 0, "Sequence number": 7674525, "Fwd thread id": 1, "Ev Idx": 847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205193595.644, "dur": 2.773, + "args": { + "External id": 706897,"Sequence number": 7674525, "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": 6305205193595.644, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205193596.675, "dur": 1.592, + "args": { + "External id": 706898,"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": 6305205193597.152, "dur": 1.024, + "args": { + "External id": 706899,"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": 6305205193603.904, "dur": 161.926, + "args": { + "External id": 706900,"Record function id": 0, "Sequence number": 7674524, "Fwd thread id": 1, "Ev Idx": 851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205193604.764, "dur": 154.847, + "args": { + "External id": 706901,"Sequence number": 7674524, "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": 6305205193604.764, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305205193610.957, "dur": 6.982, + "args": { + "External id": 706902,"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": 6305205193613.035, "dur": 4.180, + "args": { + "External id": 706903,"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": 6305205193615.542, "dur": 1.419, + "args": { + "External id": 706904,"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": 6305205193619.511, "dur": 74.747, + "args": { + "External id": 706905,"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": 6305205193695.938, "dur": 8.643, + "args": { + "External id": 706906,"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": 6305205193696.598, "dur": 7.082, + "args": { + "External id": 706907,"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": 6305205193702.200, "dur": 1.282, + "args": { + "External id": 706908,"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": 6305205193706.129, "dur": 3.307, + "args": { + "External id": 706909,"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": 6305205193707.353, "dur": 1.568, + "args": { + "External id": 706910,"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": 6305205193708.317, "dur": 0.488, + "args": { + "External id": 706911,"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": 6305205193709.943, "dur": 48.955, + "args": { + "External id": 706912,"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": 6305205193771.143, "dur": 11.568, + "args": { + "External id": 706913,"Record function id": 0, "Sequence number": 7674523, "Fwd thread id": 1, "Ev Idx": 864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205193772.216, "dur": 8.629, + "args": { + "External id": 706914,"Sequence number": 7674523, "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": 6305205193772.216, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205193773.591, "dur": 7.111, + "args": { + "External id": 706915,"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": 6305205193779.469, "dur": 1.138, + "args": { + "External id": 706916,"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": 6305205193786.172, "dur": 6.965, + "args": { + "External id": 706917,"Record function id": 0, "Sequence number": 7674522, "Fwd thread id": 1, "Ev Idx": 868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205193786.997, "dur": 3.673, + "args": { + "External id": 706918,"Sequence number": 7674522, "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": 6305205193786.997, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305205193787.787, "dur": 2.678, + "args": { + "External id": 706919,"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": 6305205193788.530, "dur": 1.488, + "args": { + "External id": 706920,"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": 6305205193789.435, "dur": 0.468, + "args": { + "External id": 706921,"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": 6305205193798.957, "dur": 11.754, + "args": { + "External id": 706922,"Record function id": 0, "Ev Idx": 873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205193800.397, "dur": 9.586, + "args": { + "External id": 706923,"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": 6305205193802.720, "dur": 6.808, + "args": { + "External id": 706924,"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": 6305205193807.015, "dur": 2.405, + "args": { + "External id": 706925,"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": 6305205193813.780, "dur": 7.636, + "args": { + "External id": 706926,"Record function id": 0, "Sequence number": 7674521, "Fwd thread id": 1, "Ev Idx": 877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205193814.904, "dur": 4.888, + "args": { + "External id": 706927,"Sequence number": 7674521, "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": 6305205193814.904, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205193815.981, "dur": 3.657, + "args": { + "External id": 706928,"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": 6305205193818.806, "dur": 0.709, + "args": { + "External id": 706929,"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": 6305205193824.581, "dur": 105.696, + "args": { + "External id": 706930,"Record function id": 0, "Sequence number": 7674520, "Fwd thread id": 1, "Ev Idx": 881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205193825.636, "dur": 98.438, + "args": { + "External id": 706931,"Sequence number": 7674520, "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": 6305205193825.636, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305205193827.911, "dur": 5.059, + "args": { + "External id": 706932,"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": 6305205193828.559, "dur": 3.957, + "args": { + "External id": 706933,"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": 6305205193831.887, "dur": 0.520, + "args": { + "External id": 706934,"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": 6305205193833.735, "dur": 28.277, + "args": { + "External id": 706935,"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": 6305205193863.033, "dur": 10.334, + "args": { + "External id": 706936,"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": 6305205193869.125, "dur": 3.699, + "args": { + "External id": 706937,"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": 6305205193870.143, "dur": 2.498, + "args": { + "External id": 706938,"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": 6305205193874.558, "dur": 10.168, + "args": { + "External id": 706939,"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": 6305205193878.269, "dur": 5.983, + "args": { + "External id": 706940,"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": 6305205193881.444, "dur": 2.740, + "args": { + "External id": 706941,"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": 6305205193885.252, "dur": 38.002, + "args": { + "External id": 706942,"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": 6305205193934.932, "dur": 34.622, + "args": { + "External id": 706943,"Record function id": 0, "Sequence number": 7674519, "Fwd thread id": 1, "Ev Idx": 894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205193935.765, "dur": 3.186, + "args": { + "External id": 706944,"Sequence number": 7674519, "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": 6305205193935.765, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205193937.158, "dur": 1.637, + "args": { + "External id": 706945,"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": 6305205193937.641, "dur": 1.004, + "args": { + "External id": 706946,"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": 6305205193945.548, "dur": 21.469, + "args": { + "External id": 706947,"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": 6305205193975.650, "dur": 15.439, + "args": { + "External id": 706948,"Record function id": 0, "Sequence number": 7674518, "Fwd thread id": 1, "Ev Idx": 899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205193976.738, "dur": 12.026, + "args": { + "External id": 706949,"Sequence number": 7674518, "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": 6305205193976.738, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305205193979.403, "dur": 9.158, + "args": { + "External id": 706950,"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": 6305205193980.213, "dur": 7.772, + "args": { + "External id": 706951,"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": 6305205193987.252, "dur": 0.592, + "args": { + "External id": 706952,"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": 6305205193995.041, "dur": 5.315, + "args": { + "External id": 706953,"Record function id": 0, "Ev Idx": 904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205193996.277, "dur": 3.493, + "args": { + "External id": 706954,"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": 6305205193997.217, "dur": 2.270, + "args": { + "External id": 706955,"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": 6305205193997.918, "dur": 1.436, + "args": { + "External id": 706956,"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": 6305205194005.787, "dur": 7.431, + "args": { + "External id": 706957,"Record function id": 0, "Sequence number": 7674517, "Fwd thread id": 1, "Ev Idx": 908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205194006.594, "dur": 4.864, + "args": { + "External id": 706958,"Sequence number": 7674517, "Fwd thread 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": 6305205194006.594, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205194007.553, "dur": 3.762, + "args": { + "External id": 706959,"Record 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": 6305205194010.498, "dur": 0.692, + "args": { + "External id": 706960,"Record 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": 6305205194016.239, "dur": 145.811, + "args": { + "External id": 706961,"Record function id": 0, "Sequence number": 7674516, "Fwd thread id": 1, "Ev Idx": 912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205194016.882, "dur": 136.302, + "args": { + "External id": 706962,"Sequence number": 7674516, "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": 6305205194016.882, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305205194019.143, "dur": 2.124, + "args": { + "External id": 706963,"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": 6305205194019.583, "dur": 1.268, + "args": { + "External id": 706964,"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": 6305205194020.247, "dur": 0.507, + "args": { + "External id": 706965,"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": 6305205194021.931, "dur": 74.826, + "args": { + "External id": 706966,"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": 6305205194101.330, "dur": 6.630, + "args": { + "External id": 706967,"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": 6305205194102.116, "dur": 5.052, + "args": { + "External id": 706968,"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": 6305205194106.106, "dur": 0.955, + "args": { + "External id": 706969,"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": 6305205194109.292, "dur": 3.182, + "args": { + "External id": 706970,"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": 6305205194110.548, "dur": 1.284, + "args": { + "External id": 706971,"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": 6305205194111.081, "dur": 0.644, + "args": { + "External id": 706972,"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": 6305205194115.147, "dur": 37.477, + "args": { + "External id": 706973,"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": 6305205194169.327, "dur": 29.245, + "args": { + "External id": 706974,"Record function id": 0, "Sequence number": 7674515, "Fwd thread id": 1, "Ev Idx": 925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205194170.308, "dur": 6.538, + "args": { + "External id": 706975,"Sequence number": 7674515, "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": 6305205194170.308, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205194171.553, "dur": 5.146, + "args": { + "External id": 706976,"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": 6305205194175.249, "dur": 1.327, + "args": { + "External id": 706977,"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": 6305205194179.284, "dur": 16.747, + "args": { + "External id": 706978,"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": 6305205194202.250, "dur": 9.456, + "args": { + "External id": 706979,"Record function id": 0, "Sequence number": 7674514, "Fwd thread id": 1, "Ev Idx": 930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205194203.142, "dur": 6.781, + "args": { + "External id": 706980,"Sequence number": 7674514, "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": 6305205194203.142, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305205194204.186, "dur": 5.526, + "args": { + "External id": 706981,"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": 6305205194205.146, "dur": 4.098, + "args": { + "External id": 706982,"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": 6305205194208.546, "dur": 0.586, + "args": { + "External id": 706983,"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": 6305205194215.930, "dur": 5.930, + "args": { + "External id": 706984,"Record function id": 0, "Ev Idx": 935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205194217.067, "dur": 4.253, + "args": { + "External id": 706985,"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": 6305205194218.370, "dur": 2.619, + "args": { + "External id": 706986,"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": 6305205194219.007, "dur": 1.872, + "args": { + "External id": 706987,"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": 6305205194226.143, "dur": 389.597, + "args": { + "External id": 706988,"Record function id": 0, "Sequence number": 7674513, "Fwd thread id": 1, "Ev Idx": 939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305205194227.322, "dur": 358.086, + "args": { + "External id": 706989,"Sequence number": 7674513, "Fwd thread 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": 6305205194227.322, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205194263.692, "dur": 1.583, + "args": { + "External id": 706990,"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": 6305205194264.266, "dur": 0.847, + "args": { + "External id": 706991,"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": 6305205194281.141, "dur": 6.235, + "args": { + "External id": 706992,"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": 6305205194298.825, "dur": 2.037, + "args": { + "External id": 706993,"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": 6305205194454.153, "dur": 2.293, + "args": { + "External id": 706994,"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": 6305205194460.813, "dur": 37.773, + "args": { + "External id": 706995,"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": 6305205194474.921, "dur": 0.806, + "args": { + "External id": 706996,"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": 6305205194504.395, "dur": 52.365, + "args": { + "External id": 706997,"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": 6305205194523.466, "dur": 33.028, + "args": { + "External id": 706998,"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": 6305205194528.070, "dur": 7.516, + "args": { + "External id": 706999,"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": 6305205194537.543, "dur": 18.443, + "args": { + "External id": 707000,"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": 6305205194564.798, "dur": 2.602, + "args": { + "External id": 707001,"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": 6305205194565.825, "dur": 1.448, + "args": { + "External id": 707002,"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": 6305205194576.980, "dur": 1.354, + "args": { + "External id": 707003,"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": 6305205194577.430, "dur": 0.732, + "args": { + "External id": 707004,"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": 6305205194596.157, "dur": 15.406, + "args": { + "External id": 707005,"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": 6305205194627.202, "dur": 11.180, + "args": { + "External id": 707006,"Record function id": 0, "Ev Idx": 957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205194629.266, "dur": 8.344, + "args": { + "External id": 707007,"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": 6305205194631.321, "dur": 4.952, + "args": { + "External id": 707008,"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": 6305205194634.599, "dur": 1.581, + "args": { + "External id": 707009,"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": 6305205194642.390, "dur": 5.437, + "args": { + "External id": 707010,"Record function id": 0, "Sequence number": 7674512, "Fwd thread id": 1, "Ev Idx": 961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205194643.553, "dur": 1.374, + "args": { + "External id": 707011,"Sequence number": 7674512, "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": 6305205194643.553, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SwiGLULinearFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305205194651.587, "dur": 464.846, + "args": { + "External id": 707012,"Record function id": 0, "Sequence number": 7674511, "Fwd thread id": 1, "Ev Idx": 963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305205194652.767, "dur": 450.378, + "args": { + "External id": 707013,"Sequence number": 7674511, "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": 6305205194652.767, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205194683.853, "dur": 10.450, + "args": { + "External id": 707014,"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": 6305205194690.600, "dur": 3.362, + "args": { + "External id": 707015,"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": 6305205194697.336, "dur": 6.694, + "args": { + "External id": 707016,"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": 6305205194701.240, "dur": 2.214, + "args": { + "External id": 707017,"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": 6305205194702.493, "dur": 0.801, + "args": { + "External id": 707018,"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": 6305205194707.651, "dur": 95.032, + "args": { + "External id": 707019,"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": 6305205194708.668, "dur": 4.419, + "args": { + "External id": 707020,"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": 6305205194709.227, "dur": 3.439, + "args": { + "External id": 707021,"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": 6305205194709.910, "dur": 2.627, + "args": { + "External id": 707022,"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": 6305205194716.234, "dur": 85.804, + "args": { + "External id": 707023,"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": 6305205194717.766, "dur": 83.430, + "args": { + "External id": 707024,"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": 6305205194806.828, "dur": 8.026, + "args": { + "External id": 707025,"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": 6305205194813.403, "dur": 1.323, + "args": { + "External id": 707026,"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": 6305205194846.677, "dur": 5.559, + "args": { + "External id": 707027,"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": 6305205194853.301, "dur": 1.972, + "args": { + "External id": 707028,"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": 6305205194856.054, "dur": 1.576, + "args": { + "External id": 707029,"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": 6305205194893.699, "dur": 2.028, + "args": { + "External id": 707030,"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": 6305205194894.440, "dur": 1.146, + "args": { + "External id": 707031,"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": 6305205194916.663, "dur": 129.021, + "args": { + "External id": 707032,"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": 6305205194921.955, "dur": 4.380, + "args": { + "External id": 707033,"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": 6305205194924.730, "dur": 0.673, + "args": { + "External id": 707034,"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": 6305205194929.933, "dur": 8.137, + "args": { + "External id": 707035,"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": 6305205194934.253, "dur": 3.046, + "args": { + "External id": 707036,"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": 6305205194939.453, "dur": 4.059, + "args": { + "External id": 707037,"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": 6305205194942.477, "dur": 0.658, + "args": { + "External id": 707038,"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": 6305205194944.105, "dur": 4.083, + "args": { + "External id": 707039,"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": 6305205194947.235, "dur": 0.532, + "args": { + "External id": 707040,"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": 6305205194953.844, "dur": 3.972, + "args": { + "External id": 707041,"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": 6305205194956.913, "dur": 0.611, + "args": { + "External id": 707042,"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": 6305205194958.688, "dur": 7.538, + "args": { + "External id": 707043,"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": 6305205194964.291, "dur": 1.724, + "args": { + "External id": 707044,"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": 6305205194966.886, "dur": 1.454, + "args": { + "External id": 707045,"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": 6305205194967.669, "dur": 0.392, + "args": { + "External id": 707046,"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": 6305205194971.200, "dur": 3.688, + "args": { + "External id": 707047,"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": 6305205194971.715, "dur": 3.086, + "args": { + "External id": 707048,"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": 6305205194976.112, "dur": 52.230, + "args": { + "External id": 707049,"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": 6305205195032.270, "dur": 3.161, + "args": { + "External id": 707050,"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": 6305205195036.266, "dur": 5.165, + "args": { + "External id": 707051,"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": 6305205195040.392, "dur": 0.451, + "args": { + "External id": 707052,"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": 6305205195043.626, "dur": 0.983, + "args": { + "External id": 707053,"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": 6305205195129.339, "dur": 9.989, + "args": { + "External id": 707054,"Record function id": 0, "Ev Idx": 1005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205195131.646, "dur": 6.901, + "args": { + "External id": 707055,"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": 6305205195134.112, "dur": 3.503, + "args": { + "External id": 707056,"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": 6305205195135.135, "dur": 2.359, + "args": { + "External id": 707057,"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": 6305205195143.213, "dur": 10.858, + "args": { + "External id": 707058,"Record function id": 0, "Sequence number": 7674510, "Fwd thread id": 1, "Ev Idx": 1009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205195144.047, "dur": 8.441, + "args": { + "External id": 707059,"Sequence number": 7674510, "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": 6305205195144.047, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205195145.913, "dur": 6.368, + "args": { + "External id": 707060,"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": 6305205195150.730, "dur": 1.427, + "args": { + "External id": 707061,"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": 6305205195157.655, "dur": 154.313, + "args": { + "External id": 707062,"Record function id": 0, "Sequence number": 7674509, "Fwd thread id": 1, "Ev Idx": 1013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205195158.689, "dur": 146.544, + "args": { + "External id": 707063,"Sequence number": 7674509, "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": 6305205195158.689, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305205195161.862, "dur": 3.959, + "args": { + "External id": 707064,"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": 6305205195163.167, "dur": 2.043, + "args": { + "External id": 707065,"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": 6305205195164.172, "dur": 0.827, + "args": { + "External id": 707066,"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": 6305205195169.315, "dur": 50.639, + "args": { + "External id": 707067,"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": 6305205195221.167, "dur": 3.737, + "args": { + "External id": 707068,"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": 6305205195221.783, "dur": 2.432, + "args": { + "External id": 707069,"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": 6305205195223.063, "dur": 1.013, + "args": { + "External id": 707070,"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": 6305205195226.260, "dur": 39.413, + "args": { + "External id": 707071,"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": 6305205195226.930, "dur": 38.240, + "args": { + "External id": 707072,"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": 6305205195264.512, "dur": 0.530, + "args": { + "External id": 707073,"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": 6305205195266.177, "dur": 38.246, + "args": { + "External id": 707074,"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": 6305205195323.085, "dur": 5.915, + "args": { + "External id": 707075,"Record function id": 0, "Sequence number": 7674508, "Fwd thread id": 1, "Ev Idx": 1026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205195324.062, "dur": 3.074, + "args": { + "External id": 707076,"Sequence number": 7674508, "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": 6305205195324.062, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205195325.220, "dur": 1.776, + "args": { + "External id": 707077,"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": 6305205195325.626, "dur": 1.239, + "args": { + "External id": 707078,"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": 6305205195332.379, "dur": 9.223, + "args": { + "External id": 707079,"Record function id": 0, "Sequence number": 7674507, "Fwd thread id": 1, "Ev Idx": 1030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205195333.263, "dur": 6.148, + "args": { + "External id": 707080,"Sequence number": 7674507, "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": 6305205195333.263, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305205195334.112, "dur": 5.097, + "args": { + "External id": 707081,"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": 6305205195334.693, "dur": 4.039, + "args": { + "External id": 707082,"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": 6305205195338.229, "dur": 0.389, + "args": { + "External id": 707083,"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": 6305205195347.356, "dur": 4.596, + "args": { + "External id": 707084,"Record function id": 0, "Ev Idx": 1035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205195348.622, "dur": 2.779, + "args": { + "External id": 707085,"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": 6305205195349.587, "dur": 1.534, + "args": { + "External id": 707086,"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": 6305205195349.983, "dur": 1.029, + "args": { + "External id": 707087,"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": 6305205195354.906, "dur": 5.523, + "args": { + "External id": 707088,"Record function id": 0, "Sequence number": 7674506, "Fwd thread id": 1, "Ev Idx": 1039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205195355.936, "dur": 2.374, + "args": { + "External id": 707089,"Sequence number": 7674506, "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": 6305205195355.936, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205195356.871, "dur": 1.280, + "args": { + "External id": 707090,"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": 6305205195357.427, "dur": 0.599, + "args": { + "External id": 707091,"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": 6305205195363.619, "dur": 96.658, + "args": { + "External id": 707092,"Record function id": 0, "Sequence number": 7674505, "Fwd thread id": 1, "Ev Idx": 1043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205195364.263, "dur": 89.121, + "args": { + "External id": 707093,"Sequence number": 7674505, "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": 6305205195364.263, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305205195368.510, "dur": 2.007, + "args": { + "External id": 707094,"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": 6305205195368.935, "dur": 1.121, + "args": { + "External id": 707095,"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": 6305205195369.523, "dur": 0.418, + "args": { + "External id": 707096,"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": 6305205195371.264, "dur": 35.219, + "args": { + "External id": 707097,"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": 6305205195407.573, "dur": 7.254, + "args": { + "External id": 707098,"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": 6305205195408.034, "dur": 6.229, + "args": { + "External id": 707099,"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": 6305205195413.463, "dur": 0.669, + "args": { + "External id": 707100,"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": 6305205195415.869, "dur": 4.887, + "args": { + "External id": 707101,"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": 6305205195417.114, "dur": 3.225, + "args": { + "External id": 707102,"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": 6305205195417.658, "dur": 2.612, + "args": { + "External id": 707103,"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": 6305205195421.159, "dur": 31.351, + "args": { + "External id": 707104,"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": 6305205195464.942, "dur": 37.319, + "args": { + "External id": 707105,"Record function id": 0, "Sequence number": 7674504, "Fwd thread id": 1, "Ev Idx": 1056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205195465.973, "dur": 7.937, + "args": { + "External id": 707106,"Sequence number": 7674504, "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": 6305205195465.973, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205195467.368, "dur": 6.379, + "args": { + "External id": 707107,"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": 6305205195472.524, "dur": 1.082, + "args": { + "External id": 707108,"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": 6305205195476.977, "dur": 22.747, + "args": { + "External id": 707109,"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": 6305205195525.693, "dur": 9.504, + "args": { + "External id": 707110,"Record function id": 0, "Sequence number": 7674503, "Fwd thread id": 1, "Ev Idx": 1061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205195527.251, "dur": 5.283, + "args": { + "External id": 707111,"Sequence number": 7674503, "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": 6305205195527.251, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305205195528.188, "dur": 4.127, + "args": { + "External id": 707112,"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": 6305205195529.226, "dur": 2.320, + "args": { + "External id": 707113,"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": 6305205195530.517, "dur": 0.793, + "args": { + "External id": 707114,"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": 6305205195540.197, "dur": 8.620, + "args": { + "External id": 707115,"Record function id": 0, "Ev Idx": 1066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205195541.598, "dur": 6.681, + "args": { + "External id": 707116,"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": 6305205195542.738, "dur": 5.097, + "args": { + "External id": 707117,"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": 6305205195546.228, "dur": 1.514, + "args": { + "External id": 707118,"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": 6305205195552.697, "dur": 434.481, + "args": { + "External id": 707119,"Record function id": 0, "Sequence number": 7674502, "Fwd thread id": 1, "Ev Idx": 1070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305205195553.966, "dur": 398.162, + "args": { + "External id": 707120,"Sequence number": 7674502, "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": 6305205195553.966, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338707, "tid": 2379456, + "ts": 6305205195580.067, "dur": 39.819, + "args": { + "External id": 707121,"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": 6305205195581.600, "dur": 38.070, + "args": { + "External id": 707122,"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": 6305205195586.853, "dur": 6.433, + "args": { + "External id": 707123,"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": 6305205195589.272, "dur": 3.421, + "args": { + "External id": 707124,"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": 6305205195594.628, "dur": 24.515, + "args": { + "External id": 707125,"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": 6305205195631.967, "dur": 2.212, + "args": { + "External id": 707126,"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": 6305205195632.891, "dur": 1.159, + "args": { + "External id": 707127,"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": 6305205195638.488, "dur": 5.829, + "args": { + "External id": 707128,"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": 6305205195641.303, "dur": 2.904, + "args": { + "External id": 707129,"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": 6305205195657.294, "dur": 2.276, + "args": { + "External id": 707130,"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": 6305205195672.564, "dur": 2.407, + "args": { + "External id": 707131,"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": 6305205195838.520, "dur": 2.002, + "args": { + "External id": 707132,"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": 6305205195844.580, "dur": 36.762, + "args": { + "External id": 707133,"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": 6305205195857.708, "dur": 0.726, + "args": { + "External id": 707134,"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": 6305205195886.778, "dur": 31.758, + "args": { + "External id": 707135,"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": 6305205195890.498, "dur": 27.832, + "args": { + "External id": 707136,"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": 6305205195894.255, "dur": 5.987, + "args": { + "External id": 707137,"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": 6305205195901.765, "dur": 15.934, + "args": { + "External id": 707138,"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": 6305205195922.974, "dur": 2.204, + "args": { + "External id": 707139,"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": 6305205195924.034, "dur": 0.974, + "args": { + "External id": 707140,"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": 6305205195931.655, "dur": 6.271, + "args": { + "External id": 707141,"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": 6305205195936.696, "dur": 1.129, + "args": { + "External id": 707142,"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": 6305205195939.677, "dur": 3.631, + "args": { + "External id": 707143,"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": 6305205195940.258, "dur": 2.961, + "args": { + "External id": 707144,"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": 6305205195965.866, "dur": 19.945, + "args": { + "External id": 707145,"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": 6305205195996.728, "dur": 7.094, + "args": { + "External id": 707146,"Record function id": 0, "Ev Idx": 1097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205195998.506, "dur": 4.647, + "args": { + "External id": 707147,"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": 6305205196000.139, "dur": 2.252, + "args": { + "External id": 707148,"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": 6305205196000.784, "dur": 1.511, + "args": { + "External id": 707149,"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": 6305205196007.655, "dur": 10.881, + "args": { + "External id": 707150,"Record function id": 0, "Sequence number": 7674501, "Fwd thread id": 1, "Ev Idx": 1101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205196008.615, "dur": 7.839, + "args": { + "External id": 707151,"Sequence number": 7674501, "Fwd thread 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": 6305205196008.615, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205196010.065, "dur": 6.150, + "args": { + "External id": 707152,"Record 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": 6305205196015.011, "dur": 1.067, + "args": { + "External id": 707153,"Record 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": 6305205196021.915, "dur": 197.683, + "args": { + "External id": 707154,"Record function id": 0, "Sequence number": 7674500, "Fwd thread id": 1, "Ev Idx": 1105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205196022.770, "dur": 188.375, + "args": { + "External id": 707155,"Sequence number": 7674500, "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": 6305205196022.770, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305205196025.218, "dur": 4.387, + "args": { + "External id": 707156,"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": 6305205196026.500, "dur": 2.549, + "args": { + "External id": 707157,"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": 6305205196027.982, "dur": 0.889, + "args": { + "External id": 707158,"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": 6305205196032.655, "dur": 108.241, + "args": { + "External id": 707159,"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": 6305205196144.102, "dur": 5.057, + "args": { + "External id": 707160,"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": 6305205196145.083, "dur": 3.065, + "args": { + "External id": 707161,"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": 6305205196146.485, "dur": 1.521, + "args": { + "External id": 707162,"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": 6305205196150.832, "dur": 16.940, + "args": { + "External id": 707163,"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": 6305205196160.204, "dur": 6.544, + "args": { + "External id": 707164,"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": 6305205196166.355, "dur": 0.320, + "args": { + "External id": 707165,"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": 6305205196168.369, "dur": 42.009, + "args": { + "External id": 707166,"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": 6305205196229.705, "dur": 9.376, + "args": { + "External id": 707167,"Record function id": 0, "Sequence number": 7674499, "Fwd thread id": 1, "Ev Idx": 1118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205196230.752, "dur": 6.159, + "args": { + "External id": 707168,"Sequence number": 7674499, "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": 6305205196230.752, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205196232.077, "dur": 4.694, + "args": { + "External id": 707169,"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": 6305205196232.762, "dur": 3.882, + "args": { + "External id": 707170,"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": 6305205196242.451, "dur": 10.310, + "args": { + "External id": 707171,"Record function id": 0, "Sequence number": 7674498, "Fwd thread id": 1, "Ev Idx": 1122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205196243.206, "dur": 8.006, + "args": { + "External id": 707172,"Sequence number": 7674498, "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": 6305205196243.206, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305205196243.935, "dur": 7.070, + "args": { + "External id": 707173,"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": 6305205196244.675, "dur": 5.800, + "args": { + "External id": 707174,"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": 6305205196249.862, "dur": 0.504, + "args": { + "External id": 707175,"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": 6305205196256.807, "dur": 5.439, + "args": { + "External id": 707176,"Record function id": 0, "Ev Idx": 1127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205196257.868, "dur": 3.819, + "args": { + "External id": 707177,"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": 6305205196259.492, "dur": 1.872, + "args": { + "External id": 707178,"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": 6305205196259.992, "dur": 1.279, + "args": { + "External id": 707179,"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": 6305205196265.570, "dur": 5.227, + "args": { + "External id": 707180,"Record function id": 0, "Sequence number": 7674497, "Fwd thread id": 1, "Ev Idx": 1131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205196266.288, "dur": 2.861, + "args": { + "External id": 707181,"Sequence number": 7674497, "Fwd thread 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": 6305205196266.288, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205196267.251, "dur": 1.735, + "args": { + "External id": 707182,"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": 6305205196267.799, "dur": 1.100, + "args": { + "External id": 707183,"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": 6305205196274.698, "dur": 403.795, + "args": { + "External id": 707184,"Record function id": 0, "Sequence number": 7674496, "Fwd thread id": 1, "Ev Idx": 1135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFuncBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305205196275.899, "dur": 382.274, + "args": { + "External id": 707185,"Sequence number": 7674496, "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": 6305205196275.899, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338707, "tid": 2379456, + "ts": 6305205196291.771, "dur": 11.491, + "args": { + "External id": 707186,"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": 6305205196298.573, "dur": 4.151, + "args": { + "External id": 707187,"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": 6305205196305.315, "dur": 2.741, + "args": { + "External id": 707188,"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": 6305205196305.983, "dur": 1.895, + "args": { + "External id": 707189,"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": 6305205196312.772, "dur": 6.896, + "args": { + "External id": 707190,"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": 6305205196315.899, "dur": 3.611, + "args": { + "External id": 707191,"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": 6305205196346.977, "dur": 285.020, + "args": { + "External id": 707192,"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": 6305205196429.378, "dur": 5.616, + "args": { + "External id": 707193,"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": 6305205196436.693, "dur": 4.477, + "args": { + "External id": 707194,"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": 6305205196443.949, "dur": 1.853, + "args": { + "External id": 707195,"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": 6305205196446.493, "dur": 4.075, + "args": { + "External id": 707196,"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": 6305205196524.728, "dur": 3.067, + "args": { + "External id": 707197,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205196525.546, "dur": 1.988, + "args": { + "External id": 707198,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205196531.526, "dur": 30.595, + "args": { + "External id": 707199,"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": 6305205196536.591, "dur": 1.116, + "args": { + "External id": 707200,"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": 6305205196565.212, "dur": 1.468, + "args": { + "External id": 707201,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205196565.841, "dur": 0.737, + "args": { + "External id": 707202,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205196569.148, "dur": 17.090, + "args": { + "External id": 707203,"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": 6305205196572.658, "dur": 0.351, + "args": { + "External id": 707204,"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": 6305205196645.418, "dur": 4.014, + "args": { + "External id": 707205,"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": 6305205196652.493, "dur": 0.620, + "args": { + "External id": 707206,"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": 6305205196654.955, "dur": 0.505, + "args": { + "External id": 707207,"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": 6305205196689.079, "dur": 236.643, + "args": { + "External id": 707208,"Record function id": 0, "Sequence number": 7674495, "Fwd thread id": 1, "Ev Idx": 1159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305205196690.955, "dur": 228.421, + "args": { + "External id": 707209,"Sequence number": 7674495, "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": 6305205196690.955, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338707, "tid": 2379456, + "ts": 6305205196710.554, "dur": 52.760, + "args": { + "External id": 707210,"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": 6305205196713.689, "dur": 4.228, + "args": { + "External id": 707211,"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": 6305205196719.454, "dur": 43.226, + "args": { + "External id": 707212,"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": 6305205196773.321, "dur": 6.740, + "args": { + "External id": 707213,"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": 6305205196777.262, "dur": 2.500, + "args": { + "External id": 707214,"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": 6305205196932.988, "dur": 223.527, + "args": { + "External id": 707215,"Record function id": 0, "Sequence number": 7674494, "Fwd thread id": 1, "Ev Idx": 1166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305205196934.574, "dur": 213.468, + "args": { + "External id": 707216,"Sequence number": 7674494, "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": 6305205196934.574, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338707, "tid": 2379456, + "ts": 6305205196945.982, "dur": 49.705, + "args": { + "External id": 707217,"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": 6305205196948.071, "dur": 5.220, + "args": { + "External id": 707218,"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": 6305205196954.367, "dur": 40.653, + "args": { + "External id": 707219,"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": 6305205197002.621, "dur": 9.606, + "args": { + "External id": 707220,"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": 6305205197008.194, "dur": 3.707, + "args": { + "External id": 707221,"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": 6305205197166.102, "dur": 14.085, + "args": { + "External id": 707222,"Record function id": 0, "Sequence number": 7674493, "Fwd thread id": 1, "Ev Idx": 1173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205197168.262, "dur": 9.205, + "args": { + "External id": 707223,"Sequence number": 7674493, "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": 6305205197168.262, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205197170.858, "dur": 6.289, + "args": { + "External id": 707224,"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": 6305205197171.946, "dur": 5.023, + "args": { + "External id": 707225,"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": 6305205197183.642, "dur": 11.602, + "args": { + "External id": 707226,"Record function id": 0, "Sequence number": 7674492, "Fwd thread id": 1, "Ev Idx": 1177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205197187.940, "dur": 5.434, + "args": { + "External id": 707227,"Sequence number": 7674492, "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": 6305205197187.940, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205197189.212, "dur": 4.009, + "args": { + "External id": 707228,"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": 6305205197192.147, "dur": 0.937, + "args": { + "External id": 707229,"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": 6305205197198.389, "dur": 4.799, + "args": { + "External id": 707230,"Record function id": 0, "Sequence number": 7674491, "Fwd thread id": 1, "Ev Idx": 1181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205197199.249, "dur": 2.572, + "args": { + "External id": 707231,"Sequence number": 7674491, "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": 6305205197199.249, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205197200.201, "dur": 1.481, + "args": { + "External id": 707232,"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": 6305205197200.752, "dur": 0.800, + "args": { + "External id": 707233,"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": 6305205197206.382, "dur": 10.463, + "args": { + "External id": 707234,"Record function id": 0, "Sequence number": 7674490, "Fwd thread id": 1, "Ev Idx": 1185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205197207.230, "dur": 7.532, + "args": { + "External id": 707235,"Sequence number": 7674490, "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": 6305205197207.230, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205197210.302, "dur": 4.302, + "args": { + "External id": 707236,"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": 6305205197213.547, "dur": 0.926, + "args": { + "External id": 707237,"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": 6305205197223.089, "dur": 184.484, + "args": { + "External id": 707238,"Record function id": 0, "Sequence number": 7674489, "Fwd thread id": 1, "Ev Idx": 1189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205197223.816, "dur": 176.082, + "args": { + "External id": 707239,"Sequence number": 7674489, "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": 6305205197223.816, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305205197228.251, "dur": 6.869, + "args": { + "External id": 707240,"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": 6305205197230.496, "dur": 3.988, + "args": { + "External id": 707241,"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": 6305205197232.702, "dur": 1.504, + "args": { + "External id": 707242,"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": 6305205197237.042, "dur": 72.323, + "args": { + "External id": 707243,"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": 6305205197310.597, "dur": 16.018, + "args": { + "External id": 707244,"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": 6305205197319.309, "dur": 6.340, + "args": { + "External id": 707245,"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": 6305205197320.784, "dur": 4.643, + "args": { + "External id": 707246,"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": 6305205197328.106, "dur": 5.651, + "args": { + "External id": 707247,"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": 6305205197329.338, "dur": 3.992, + "args": { + "External id": 707248,"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": 6305205197332.831, "dur": 0.423, + "args": { + "External id": 707249,"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": 6305205197334.333, "dur": 64.503, + "args": { + "External id": 707250,"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": 6305205197413.438, "dur": 9.497, + "args": { + "External id": 707251,"Record function id": 0, "Sequence number": 7674488, "Fwd thread id": 1, "Ev Idx": 1202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205197414.832, "dur": 6.389, + "args": { + "External id": 707252,"Sequence number": 7674488, "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": 6305205197414.832, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205197416.021, "dur": 5.059, + "args": { + "External id": 707253,"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": 6305205197419.534, "dur": 1.423, + "args": { + "External id": 707254,"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": 6305205197426.403, "dur": 8.411, + "args": { + "External id": 707255,"Record function id": 0, "Sequence number": 7674487, "Fwd thread id": 1, "Ev Idx": 1206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205197427.499, "dur": 5.528, + "args": { + "External id": 707256,"Sequence number": 7674487, "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": 6305205197427.499, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305205197428.187, "dur": 4.644, + "args": { + "External id": 707257,"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": 6305205197428.867, "dur": 3.480, + "args": { + "External id": 707258,"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": 6305205197431.759, "dur": 0.500, + "args": { + "External id": 707259,"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": 6305205197440.643, "dur": 12.095, + "args": { + "External id": 707260,"Record function id": 0, "Ev Idx": 1211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205197441.903, "dur": 10.020, + "args": { + "External id": 707261,"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": 6305205197444.407, "dur": 7.139, + "args": { + "External id": 707262,"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": 6305205197448.484, "dur": 2.956, + "args": { + "External id": 707263,"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": 6305205197455.939, "dur": 4.877, + "args": { + "External id": 707264,"Record function id": 0, "Sequence number": 7674486, "Fwd thread id": 1, "Ev Idx": 1215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205197456.664, "dur": 2.634, + "args": { + "External id": 707265,"Sequence number": 7674486, "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": 6305205197456.664, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205197457.690, "dur": 1.444, + "args": { + "External id": 707266,"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": 6305205197458.272, "dur": 0.751, + "args": { + "External id": 707267,"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": 6305205197464.046, "dur": 133.204, + "args": { + "External id": 707268,"Record function id": 0, "Sequence number": 7674485, "Fwd thread id": 1, "Ev Idx": 1219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205197464.825, "dur": 125.080, + "args": { + "External id": 707269,"Sequence number": 7674485, "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": 6305205197464.825, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305205197466.886, "dur": 5.138, + "args": { + "External id": 707270,"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": 6305205197467.554, "dur": 4.029, + "args": { + "External id": 707271,"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": 6305205197470.807, "dur": 0.664, + "args": { + "External id": 707272,"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": 6305205197472.577, "dur": 28.901, + "args": { + "External id": 707273,"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": 6305205197502.504, "dur": 23.200, + "args": { + "External id": 707274,"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": 6305205197502.976, "dur": 21.808, + "args": { + "External id": 707275,"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": 6305205197523.258, "dur": 1.133, + "args": { + "External id": 707276,"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": 6305205197527.253, "dur": 5.403, + "args": { + "External id": 707277,"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": 6305205197530.686, "dur": 1.513, + "args": { + "External id": 707278,"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": 6305205197531.663, "dur": 0.464, + "args": { + "External id": 707279,"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": 6305205197533.163, "dur": 55.960, + "args": { + "External id": 707280,"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": 6305205197603.527, "dur": 34.347, + "args": { + "External id": 707281,"Record function id": 0, "Sequence number": 7674484, "Fwd thread id": 1, "Ev Idx": 1232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205197604.705, "dur": 6.377, + "args": { + "External id": 707282,"Sequence number": 7674484, "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": 6305205197604.705, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205197606.225, "dur": 4.718, + "args": { + "External id": 707283,"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": 6305205197609.744, "dur": 1.103, + "args": { + "External id": 707284,"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": 6305205197614.403, "dur": 21.098, + "args": { + "External id": 707285,"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": 6305205197641.917, "dur": 8.522, + "args": { + "External id": 707286,"Record function id": 0, "Sequence number": 7674483, "Fwd thread id": 1, "Ev Idx": 1237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205197644.949, "dur": 3.851, + "args": { + "External id": 707287,"Sequence number": 7674483, "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": 6305205197644.949, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305205197645.497, "dur": 3.103, + "args": { + "External id": 707288,"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": 6305205197646.259, "dur": 1.772, + "args": { + "External id": 707289,"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": 6305205197647.356, "dur": 0.566, + "args": { + "External id": 707290,"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": 6305205197654.438, "dur": 7.881, + "args": { + "External id": 707291,"Record function id": 0, "Ev Idx": 1242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205197655.463, "dur": 6.259, + "args": { + "External id": 707292,"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": 6305205197656.792, "dur": 4.609, + "args": { + "External id": 707293,"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": 6305205197657.416, "dur": 3.882, + "args": { + "External id": 707294,"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": 6305205197665.390, "dur": 10.673, + "args": { + "External id": 707295,"Record function id": 0, "Sequence number": 7674482, "Fwd thread id": 1, "Ev Idx": 1246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205197666.294, "dur": 8.092, + "args": { + "External id": 707296,"Sequence number": 7674482, "Fwd thread 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": 6305205197666.294, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205197669.393, "dur": 4.836, + "args": { + "External id": 707297,"Record 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": 6305205197673.043, "dur": 1.035, + "args": { + "External id": 707298,"Record 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": 6305205197679.192, "dur": 131.786, + "args": { + "External id": 707299,"Record function id": 0, "Sequence number": 7674481, "Fwd thread id": 1, "Ev Idx": 1250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205197680.103, "dur": 122.851, + "args": { + "External id": 707300,"Sequence number": 7674481, "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": 6305205197680.103, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305205197681.985, "dur": 2.375, + "args": { + "External id": 707301,"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": 6305205197682.607, "dur": 1.331, + "args": { + "External id": 707302,"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": 6305205197683.283, "dur": 0.547, + "args": { + "External id": 707303,"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": 6305205197687.517, "dur": 53.642, + "args": { + "External id": 707304,"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": 6305205197742.144, "dur": 2.911, + "args": { + "External id": 707305,"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": 6305205197742.643, "dur": 1.921, + "args": { + "External id": 707306,"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": 6305205197743.658, "dur": 0.791, + "args": { + "External id": 707307,"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": 6305205197745.784, "dur": 6.583, + "args": { + "External id": 707308,"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": 6305205197746.658, "dur": 5.301, + "args": { + "External id": 707309,"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": 6305205197751.282, "dur": 0.610, + "args": { + "External id": 707310,"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": 6305205197752.933, "dur": 49.261, + "args": { + "External id": 707311,"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": 6305205197815.565, "dur": 24.947, + "args": { + "External id": 707312,"Record function id": 0, "Sequence number": 7674480, "Fwd thread id": 1, "Ev Idx": 1263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205197816.548, "dur": 3.674, + "args": { + "External id": 707313,"Sequence number": 7674480, "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": 6305205197816.548, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205197817.915, "dur": 2.162, + "args": { + "External id": 707314,"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": 6305205197818.813, "dur": 1.167, + "args": { + "External id": 707315,"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": 6305205197822.741, "dur": 15.567, + "args": { + "External id": 707316,"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": 6305205197844.178, "dur": 12.773, + "args": { + "External id": 707317,"Record function id": 0, "Sequence number": 7674479, "Fwd thread id": 1, "Ev Idx": 1268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205197844.937, "dur": 10.223, + "args": { + "External id": 707318,"Sequence number": 7674479, "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": 6305205197844.937, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305205197845.713, "dur": 9.255, + "args": { + "External id": 707319,"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": 6305205197846.447, "dur": 7.984, + "args": { + "External id": 707320,"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": 6305205197851.436, "dur": 2.870, + "args": { + "External id": 707321,"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": 6305205197860.651, "dur": 5.159, + "args": { + "External id": 707322,"Record function id": 0, "Ev Idx": 1273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205197861.880, "dur": 3.428, + "args": { + "External id": 707323,"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": 6305205197863.004, "dur": 1.681, + "args": { + "External id": 707324,"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": 6305205197863.643, "dur": 0.921, + "args": { + "External id": 707325,"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": 6305205197872.034, "dur": 411.466, + "args": { + "External id": 707326,"Record function id": 0, "Sequence number": 7674478, "Fwd thread id": 1, "Ev Idx": 1277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305205197873.283, "dur": 376.984, + "args": { + "External id": 707327,"Sequence number": 7674478, "Fwd thread 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": 6305205197873.283, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205197908.083, "dur": 1.664, + "args": { + "External id": 707328,"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": 6305205197908.784, "dur": 0.852, + "args": { + "External id": 707329,"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": 6305205197927.557, "dur": 4.250, + "args": { + "External id": 707330,"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": 6305205197941.031, "dur": 2.228, + "args": { + "External id": 707331,"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": 6305205198137.889, "dur": 3.321, + "args": { + "External id": 707332,"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": 6305205198145.481, "dur": 37.842, + "args": { + "External id": 707333,"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": 6305205198158.589, "dur": 0.872, + "args": { + "External id": 707334,"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": 6305205198189.700, "dur": 33.020, + "args": { + "External id": 707335,"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": 6305205198191.619, "dur": 30.853, + "args": { + "External id": 707336,"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": 6305205198198.166, "dur": 5.557, + "args": { + "External id": 707337,"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": 6305205198205.489, "dur": 16.473, + "args": { + "External id": 707338,"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": 6305205198229.349, "dur": 4.603, + "args": { + "External id": 707339,"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": 6305205198230.434, "dur": 3.407, + "args": { + "External id": 707340,"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": 6305205198241.584, "dur": 1.635, + "args": { + "External id": 707341,"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": 6305205198242.112, "dur": 1.003, + "args": { + "External id": 707342,"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": 6305205198261.210, "dur": 17.889, + "args": { + "External id": 707343,"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": 6305205198296.245, "dur": 12.497, + "args": { + "External id": 707344,"Record function id": 0, "Ev Idx": 1295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205198299.603, "dur": 8.404, + "args": { + "External id": 707345,"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": 6305205198301.679, "dur": 5.243, + "args": { + "External id": 707346,"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": 6305205198304.846, "dur": 1.953, + "args": { + "External id": 707347,"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": 6305205198312.640, "dur": 5.540, + "args": { + "External id": 707348,"Record function id": 0, "Sequence number": 7674477, "Fwd thread id": 1, "Ev Idx": 1299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205198313.966, "dur": 1.274, + "args": { + "External id": 707349,"Sequence number": 7674477, "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": 6305205198313.966, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SwiGLULinearFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305205198322.060, "dur": 449.892, + "args": { + "External id": 707350,"Record function id": 0, "Sequence number": 7674476, "Fwd thread id": 1, "Ev Idx": 1301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305205198323.040, "dur": 437.885, + "args": { + "External id": 707351,"Sequence number": 7674476, "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": 6305205198323.040, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205198352.847, "dur": 7.691, + "args": { + "External id": 707352,"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": 6305205198357.119, "dur": 3.131, + "args": { + "External id": 707353,"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": 6305205198363.739, "dur": 8.784, + "args": { + "External id": 707354,"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": 6305205198367.482, "dur": 4.353, + "args": { + "External id": 707355,"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": 6305205198371.003, "dur": 0.687, + "args": { + "External id": 707356,"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": 6305205198375.894, "dur": 90.752, + "args": { + "External id": 707357,"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": 6305205198376.689, "dur": 2.407, + "args": { + "External id": 707358,"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": 6305205198377.330, "dur": 1.321, + "args": { + "External id": 707359,"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": 6305205198377.900, "dur": 0.660, + "args": { + "External id": 707360,"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": 6305205198382.743, "dur": 83.475, + "args": { + "External id": 707361,"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": 6305205198384.319, "dur": 80.972, + "args": { + "External id": 707362,"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": 6305205198470.623, "dur": 2.646, + "args": { + "External id": 707363,"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": 6305205198471.646, "dur": 1.497, + "args": { + "External id": 707364,"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": 6305205198522.296, "dur": 4.827, + "args": { + "External id": 707365,"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": 6305205198530.213, "dur": 7.568, + "args": { + "External id": 707366,"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": 6305205198538.426, "dur": 1.771, + "args": { + "External id": 707367,"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": 6305205198577.872, "dur": 2.513, + "args": { + "External id": 707368,"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": 6305205198578.466, "dur": 1.761, + "args": { + "External id": 707369,"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": 6305205198603.186, "dur": 138.668, + "args": { + "External id": 707370,"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": 6305205198608.819, "dur": 7.593, + "args": { + "External id": 707371,"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": 6305205198614.572, "dur": 0.867, + "args": { + "External id": 707372,"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": 6305205198617.690, "dur": 8.521, + "args": { + "External id": 707373,"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": 6305205198624.673, "dur": 0.780, + "args": { + "External id": 707374,"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": 6305205198627.669, "dur": 1.765, + "args": { + "External id": 707375,"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": 6305205198628.537, "dur": 0.596, + "args": { + "External id": 707376,"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": 6305205198631.945, "dur": 2.489, + "args": { + "External id": 707377,"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": 6305205198633.165, "dur": 0.674, + "args": { + "External id": 707378,"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": 6305205198642.211, "dur": 2.235, + "args": { + "External id": 707379,"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": 6305205198643.380, "dur": 0.754, + "args": { + "External id": 707380,"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": 6305205198645.116, "dur": 9.793, + "args": { + "External id": 707381,"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": 6305205198649.982, "dur": 4.767, + "args": { + "External id": 707382,"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": 6305205198655.484, "dur": 4.559, + "args": { + "External id": 707383,"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": 6305205198659.153, "dur": 0.623, + "args": { + "External id": 707384,"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": 6305205198660.622, "dur": 3.485, + "args": { + "External id": 707385,"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": 6305205198661.491, "dur": 2.518, + "args": { + "External id": 707386,"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": 6305205198665.247, "dur": 60.014, + "args": { + "External id": 707387,"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": 6305205198729.205, "dur": 0.990, + "args": { + "External id": 707388,"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": 6305205198733.290, "dur": 4.529, + "args": { + "External id": 707389,"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": 6305205198736.740, "dur": 0.483, + "args": { + "External id": 707390,"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": 6305205198739.938, "dur": 0.858, + "args": { + "External id": 707391,"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": 6305205198783.414, "dur": 13.641, + "args": { + "External id": 707392,"Record function id": 0, "Ev Idx": 1343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205198785.478, "dur": 10.852, + "args": { + "External id": 707393,"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": 6305205198787.519, "dur": 8.010, + "args": { + "External id": 707394,"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": 6305205198793.387, "dur": 2.038, + "args": { + "External id": 707395,"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": 6305205198801.074, "dur": 8.558, + "args": { + "External id": 707396,"Record function id": 0, "Sequence number": 7674475, "Fwd thread id": 1, "Ev Idx": 1347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205198802.060, "dur": 5.665, + "args": { + "External id": 707397,"Sequence number": 7674475, "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": 6305205198802.060, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205198806.025, "dur": 1.458, + "args": { + "External id": 707398,"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": 6305205198806.707, "dur": 0.691, + "args": { + "External id": 707399,"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": 6305205198812.979, "dur": 111.749, + "args": { + "External id": 707400,"Record function id": 0, "Sequence number": 7674474, "Fwd thread id": 1, "Ev Idx": 1351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205198813.914, "dur": 105.218, + "args": { + "External id": 707401,"Sequence number": 7674474, "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": 6305205198813.914, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305205198817.325, "dur": 8.438, + "args": { + "External id": 707402,"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": 6305205198818.697, "dur": 6.562, + "args": { + "External id": 707403,"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": 6305205198822.309, "dur": 2.798, + "args": { + "External id": 707404,"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": 6305205198826.985, "dur": 42.899, + "args": { + "External id": 707405,"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": 6305205198871.119, "dur": 5.819, + "args": { + "External id": 707406,"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": 6305205198871.716, "dur": 4.505, + "args": { + "External id": 707407,"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": 6305205198875.250, "dur": 0.844, + "args": { + "External id": 707408,"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": 6305205198878.196, "dur": 5.514, + "args": { + "External id": 707409,"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": 6305205198879.299, "dur": 4.028, + "args": { + "External id": 707410,"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": 6305205198882.708, "dur": 0.531, + "args": { + "External id": 707411,"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": 6305205198884.436, "dur": 33.791, + "args": { + "External id": 707412,"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": 6305205198929.759, "dur": 7.857, + "args": { + "External id": 707413,"Record function id": 0, "Sequence number": 7674473, "Fwd thread id": 1, "Ev Idx": 1364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205198930.701, "dur": 5.465, + "args": { + "External id": 707414,"Sequence number": 7674473, "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": 6305205198930.701, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205198932.069, "dur": 3.945, + "args": { + "External id": 707415,"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": 6305205198934.888, "dur": 0.986, + "args": { + "External id": 707416,"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": 6305205198940.965, "dur": 8.855, + "args": { + "External id": 707417,"Record function id": 0, "Sequence number": 7674472, "Fwd thread id": 1, "Ev Idx": 1368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205198941.848, "dur": 5.796, + "args": { + "External id": 707418,"Sequence number": 7674472, "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": 6305205198941.848, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305205198942.760, "dur": 4.665, + "args": { + "External id": 707419,"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": 6305205198943.312, "dur": 3.598, + "args": { + "External id": 707420,"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": 6305205198946.388, "dur": 0.412, + "args": { + "External id": 707421,"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": 6305205198953.708, "dur": 7.817, + "args": { + "External id": 707422,"Record function id": 0, "Ev Idx": 1373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205198955.068, "dur": 5.902, + "args": { + "External id": 707423,"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": 6305205198956.105, "dur": 4.599, + "args": { + "External id": 707424,"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": 6305205198956.571, "dur": 4.005, + "args": { + "External id": 707425,"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": 6305205198964.698, "dur": 7.748, + "args": { + "External id": 707426,"Record function id": 0, "Sequence number": 7674471, "Fwd thread id": 1, "Ev Idx": 1377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205198965.664, "dur": 4.694, + "args": { + "External id": 707427,"Sequence number": 7674471, "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": 6305205198965.664, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205198968.932, "dur": 1.276, + "args": { + "External id": 707428,"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": 6305205198969.320, "dur": 0.771, + "args": { + "External id": 707429,"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": 6305205198975.495, "dur": 130.903, + "args": { + "External id": 707430,"Record function id": 0, "Sequence number": 7674470, "Fwd thread id": 1, "Ev Idx": 1381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205198978.473, "dur": 118.402, + "args": { + "External id": 707431,"Sequence number": 7674470, "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": 6305205198978.473, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305205198980.279, "dur": 2.644, + "args": { + "External id": 707432,"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": 6305205198980.953, "dur": 1.535, + "args": { + "External id": 707433,"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": 6305205198981.854, "dur": 0.442, + "args": { + "External id": 707434,"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": 6305205198983.508, "dur": 32.305, + "args": { + "External id": 707435,"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": 6305205199017.085, "dur": 4.625, + "args": { + "External id": 707436,"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": 6305205199017.539, "dur": 3.739, + "args": { + "External id": 707437,"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": 6305205199020.545, "dur": 0.612, + "args": { + "External id": 707438,"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": 6305205199022.817, "dur": 4.689, + "args": { + "External id": 707439,"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": 6305205199023.673, "dur": 3.407, + "args": { + "External id": 707440,"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": 6305205199026.524, "dur": 0.490, + "args": { + "External id": 707441,"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": 6305205199027.988, "dur": 67.371, + "args": { + "External id": 707442,"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": 6305205199116.160, "dur": 38.662, + "args": { + "External id": 707443,"Record function id": 0, "Sequence number": 7674469, "Fwd thread id": 1, "Ev Idx": 1394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205199117.435, "dur": 6.844, + "args": { + "External id": 707444,"Sequence number": 7674469, "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": 6305205199117.435, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205199121.449, "dur": 2.678, + "args": { + "External id": 707445,"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": 6305205199122.240, "dur": 1.795, + "args": { + "External id": 707446,"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": 6305205199127.444, "dur": 24.495, + "args": { + "External id": 707447,"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": 6305205199158.819, "dur": 9.670, + "args": { + "External id": 707448,"Record function id": 0, "Sequence number": 7674468, "Fwd thread id": 1, "Ev Idx": 1399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205199159.715, "dur": 7.053, + "args": { + "External id": 707449,"Sequence number": 7674468, "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": 6305205199159.715, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305205199160.908, "dur": 5.632, + "args": { + "External id": 707450,"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": 6305205199161.742, "dur": 4.186, + "args": { + "External id": 707451,"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": 6305205199165.168, "dur": 0.659, + "args": { + "External id": 707452,"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": 6305205199172.497, "dur": 8.931, + "args": { + "External id": 707453,"Record function id": 0, "Ev Idx": 1404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205199173.742, "dur": 7.121, + "args": { + "External id": 707454,"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": 6305205199175.255, "dur": 5.270, + "args": { + "External id": 707455,"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": 6305205199179.095, "dur": 1.345, + "args": { + "External id": 707456,"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": 6305205199185.024, "dur": 435.419, + "args": { + "External id": 707457,"Record function id": 0, "Sequence number": 7674467, "Fwd thread id": 1, "Ev Idx": 1408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305205199186.456, "dur": 397.447, + "args": { + "External id": 707458,"Sequence number": 7674467, "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": 6305205199186.456, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338707, "tid": 2379456, + "ts": 6305205199209.882, "dur": 35.321, + "args": { + "External id": 707459,"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": 6305205199211.863, "dur": 33.134, + "args": { + "External id": 707460,"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": 6305205199214.555, "dur": 6.280, + "args": { + "External id": 707461,"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": 6305205199217.059, "dur": 3.249, + "args": { + "External id": 707462,"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": 6305205199222.176, "dur": 22.318, + "args": { + "External id": 707463,"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": 6305205199258.089, "dur": 2.003, + "args": { + "External id": 707464,"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": 6305205199258.729, "dur": 1.212, + "args": { + "External id": 707465,"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": 6305205199266.518, "dur": 1.445, + "args": { + "External id": 707466,"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": 6305205199266.978, "dur": 0.885, + "args": { + "External id": 707467,"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": 6305205199279.985, "dur": 2.847, + "args": { + "External id": 707468,"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": 6305205199293.638, "dur": 1.962, + "args": { + "External id": 707469,"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": 6305205199452.910, "dur": 3.922, + "args": { + "External id": 707470,"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": 6305205199462.676, "dur": 33.776, + "args": { + "External id": 707471,"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": 6305205199473.303, "dur": 0.813, + "args": { + "External id": 707472,"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": 6305205199501.839, "dur": 48.963, + "args": { + "External id": 707473,"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": 6305205199503.500, "dur": 47.034, + "args": { + "External id": 707474,"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": 6305205199524.583, "dur": 5.122, + "args": { + "External id": 707475,"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": 6305205199531.165, "dur": 18.668, + "args": { + "External id": 707476,"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": 6305205199556.413, "dur": 2.675, + "args": { + "External id": 707477,"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": 6305205199557.554, "dur": 1.437, + "args": { + "External id": 707478,"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": 6305205199569.072, "dur": 1.712, + "args": { + "External id": 707479,"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": 6305205199569.727, "dur": 0.949, + "args": { + "External id": 707480,"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": 6305205199572.548, "dur": 2.042, + "args": { + "External id": 707481,"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": 6305205199573.412, "dur": 1.053, + "args": { + "External id": 707482,"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": 6305205199600.472, "dur": 18.436, + "args": { + "External id": 707483,"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": 6305205199632.331, "dur": 8.604, + "args": { + "External id": 707484,"Record function id": 0, "Ev Idx": 1435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205199634.850, "dur": 5.376, + "args": { + "External id": 707485,"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": 6305205199636.844, "dur": 2.521, + "args": { + "External id": 707486,"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": 6305205199637.810, "dur": 1.416, + "args": { + "External id": 707487,"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": 6305205199644.245, "dur": 9.660, + "args": { + "External id": 707488,"Record function id": 0, "Sequence number": 7674466, "Fwd thread id": 1, "Ev Idx": 1439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205199645.428, "dur": 5.921, + "args": { + "External id": 707489,"Sequence number": 7674466, "Fwd thread 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": 6305205199645.428, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205199649.223, "dur": 1.891, + "args": { + "External id": 707490,"Record 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": 6305205199650.008, "dur": 0.995, + "args": { + "External id": 707491,"Record 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": 6305205199657.386, "dur": 140.155, + "args": { + "External id": 707492,"Record function id": 0, "Sequence number": 7674465, "Fwd thread id": 1, "Ev Idx": 1443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205199658.145, "dur": 133.494, + "args": { + "External id": 707493,"Sequence number": 7674465, "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": 6305205199658.145, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305205199661.057, "dur": 7.153, + "args": { + "External id": 707494,"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": 6305205199662.402, "dur": 5.175, + "args": { + "External id": 707495,"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": 6305205199666.443, "dur": 0.929, + "args": { + "External id": 707496,"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": 6305205199669.547, "dur": 68.923, + "args": { + "External id": 707497,"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": 6305205199739.818, "dur": 3.976, + "args": { + "External id": 707498,"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": 6305205199740.468, "dur": 2.767, + "args": { + "External id": 707499,"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": 6305205199742.450, "dur": 0.668, + "args": { + "External id": 707500,"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": 6305205199745.225, "dur": 7.851, + "args": { + "External id": 707501,"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": 6305205199746.125, "dur": 6.408, + "args": { + "External id": 707502,"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": 6305205199750.079, "dur": 2.390, + "args": { + "External id": 707503,"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": 6305205199753.553, "dur": 37.372, + "args": { + "External id": 707504,"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": 6305205199802.637, "dur": 7.000, + "args": { + "External id": 707505,"Record function id": 0, "Sequence number": 7674464, "Fwd thread id": 1, "Ev Idx": 1456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205199803.867, "dur": 4.181, + "args": { + "External id": 707506,"Sequence number": 7674464, "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": 6305205199803.867, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205199805.532, "dur": 2.362, + "args": { + "External id": 707507,"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": 6305205199806.641, "dur": 1.149, + "args": { + "External id": 707508,"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": 6305205199815.263, "dur": 9.302, + "args": { + "External id": 707509,"Record function id": 0, "Sequence number": 7674463, "Fwd thread id": 1, "Ev Idx": 1460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205199815.998, "dur": 6.609, + "args": { + "External id": 707510,"Sequence number": 7674463, "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": 6305205199815.998, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305205199816.757, "dur": 5.633, + "args": { + "External id": 707511,"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": 6305205199819.585, "dur": 2.253, + "args": { + "External id": 707512,"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": 6305205199821.050, "dur": 0.691, + "args": { + "External id": 707513,"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": 6305205199828.504, "dur": 5.573, + "args": { + "External id": 707514,"Record function id": 0, "Ev Idx": 1465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205199830.239, "dur": 3.236, + "args": { + "External id": 707515,"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": 6305205199831.430, "dur": 1.800, + "args": { + "External id": 707516,"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": 6305205199831.982, "dur": 1.146, + "args": { + "External id": 707517,"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": 6305205199837.177, "dur": 6.335, + "args": { + "External id": 707518,"Record function id": 0, "Sequence number": 7674462, "Fwd thread id": 1, "Ev Idx": 1469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205199838.002, "dur": 3.708, + "args": { + "External id": 707519,"Sequence number": 7674462, "Fwd thread 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": 6305205199838.002, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205199839.669, "dur": 1.873, + "args": { + "External id": 707520,"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": 6305205199840.290, "dur": 1.102, + "args": { + "External id": 707521,"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": 6305205199847.926, "dur": 404.762, + "args": { + "External id": 707522,"Record function id": 0, "Sequence number": 7674461, "Fwd thread id": 1, "Ev Idx": 1473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFuncBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305205199849.601, "dur": 383.196, + "args": { + "External id": 707523,"Sequence number": 7674461, "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": 6305205199849.601, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338707, "tid": 2379456, + "ts": 6305205199865.604, "dur": 6.277, + "args": { + "External id": 707524,"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": 6305205199868.415, "dur": 3.063, + "args": { + "External id": 707525,"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": 6305205199874.010, "dur": 3.696, + "args": { + "External id": 707526,"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": 6305205199875.617, "dur": 1.913, + "args": { + "External id": 707527,"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": 6305205199879.237, "dur": 7.288, + "args": { + "External id": 707528,"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": 6305205199880.801, "dur": 5.557, + "args": { + "External id": 707529,"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": 6305205199912.040, "dur": 293.854, + "args": { + "External id": 707530,"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": 6305205199992.101, "dur": 3.393, + "args": { + "External id": 707531,"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": 6305205199997.574, "dur": 4.359, + "args": { + "External id": 707532,"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": 6305205200003.274, "dur": 1.563, + "args": { + "External id": 707533,"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": 6305205200008.035, "dur": 1.921, + "args": { + "External id": 707534,"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": 6305205200094.575, "dur": 5.970, + "args": { + "External id": 707535,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205200098.278, "dur": 1.974, + "args": { + "External id": 707536,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205200104.631, "dur": 31.343, + "args": { + "External id": 707537,"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": 6305205200110.575, "dur": 0.869, + "args": { + "External id": 707538,"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": 6305205200137.318, "dur": 2.066, + "args": { + "External id": 707539,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205200138.504, "dur": 0.760, + "args": { + "External id": 707540,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205200140.258, "dur": 18.467, + "args": { + "External id": 707541,"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": 6305205200143.010, "dur": 2.618, + "args": { + "External id": 707542,"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": 6305205200219.741, "dur": 4.035, + "args": { + "External id": 707543,"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": 6305205200226.887, "dur": 0.772, + "args": { + "External id": 707544,"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": 6305205200229.489, "dur": 0.606, + "args": { + "External id": 707545,"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": 6305205200263.704, "dur": 239.309, + "args": { + "External id": 707546,"Record function id": 0, "Sequence number": 7674460, "Fwd thread id": 1, "Ev Idx": 1497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305205200265.755, "dur": 230.661, + "args": { + "External id": 707547,"Sequence number": 7674460, "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": 6305205200265.755, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338707, "tid": 2379456, + "ts": 6305205200286.033, "dur": 51.639, + "args": { + "External id": 707548,"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": 6305205200289.831, "dur": 9.341, + "args": { + "External id": 707549,"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": 6305205200300.594, "dur": 36.320, + "args": { + "External id": 707550,"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": 6305205200348.276, "dur": 4.784, + "args": { + "External id": 707551,"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": 6305205200350.300, "dur": 2.381, + "args": { + "External id": 707552,"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": 6305205200529.714, "dur": 182.606, + "args": { + "External id": 707553,"Record function id": 0, "Sequence number": 7674459, "Fwd thread id": 1, "Ev Idx": 1504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305205200532.068, "dur": 173.288, + "args": { + "External id": 707554,"Sequence number": 7674459, "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": 6305205200532.068, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338707, "tid": 2379456, + "ts": 6305205200550.359, "dur": 46.489, + "args": { + "External id": 707555,"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": 6305205200553.364, "dur": 4.240, + "args": { + "External id": 707556,"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": 6305205200558.770, "dur": 37.620, + "args": { + "External id": 707557,"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": 6305205200604.653, "dur": 7.696, + "args": { + "External id": 707558,"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": 6305205200607.136, "dur": 4.821, + "args": { + "External id": 707559,"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": 6305205200718.537, "dur": 18.486, + "args": { + "External id": 707560,"Record function id": 0, "Sequence number": 7674458, "Fwd thread id": 1, "Ev Idx": 1511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205200719.827, "dur": 14.660, + "args": { + "External id": 707561,"Sequence number": 7674458, "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": 6305205200719.827, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205200723.120, "dur": 11.009, + "args": { + "External id": 707562,"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": 6305205200727.666, "dur": 6.272, + "args": { + "External id": 707563,"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": 6305205200742.915, "dur": 6.952, + "args": { + "External id": 707564,"Record function id": 0, "Sequence number": 7674457, "Fwd thread id": 1, "Ev Idx": 1515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205200743.633, "dur": 4.027, + "args": { + "External id": 707565,"Sequence number": 7674457, "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": 6305205200743.633, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205200745.210, "dur": 2.300, + "args": { + "External id": 707566,"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": 6305205200746.357, "dur": 1.023, + "args": { + "External id": 707567,"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": 6305205200753.125, "dur": 5.774, + "args": { + "External id": 707568,"Record function id": 0, "Sequence number": 7674456, "Fwd thread id": 1, "Ev Idx": 1519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205200753.829, "dur": 3.571, + "args": { + "External id": 707569,"Sequence number": 7674456, "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": 6305205200753.829, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205200755.428, "dur": 1.822, + "args": { + "External id": 707570,"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": 6305205200756.243, "dur": 0.885, + "args": { + "External id": 707571,"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": 6305205200762.388, "dur": 8.728, + "args": { + "External id": 707572,"Record function id": 0, "Sequence number": 7674455, "Fwd thread id": 1, "Ev Idx": 1523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205200763.926, "dur": 5.280, + "args": { + "External id": 707573,"Sequence number": 7674455, "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": 6305205200763.926, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205200765.088, "dur": 3.965, + "args": { + "External id": 707574,"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": 6305205200767.956, "dur": 0.981, + "args": { + "External id": 707575,"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": 6305205200774.248, "dur": 205.634, + "args": { + "External id": 707576,"Record function id": 0, "Sequence number": 7674454, "Fwd thread id": 1, "Ev Idx": 1527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205200775.091, "dur": 196.893, + "args": { + "External id": 707577,"Sequence number": 7674454, "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": 6305205200775.091, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305205200778.887, "dur": 9.196, + "args": { + "External id": 707578,"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": 6305205200781.076, "dur": 6.291, + "args": { + "External id": 707579,"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": 6305205200784.044, "dur": 3.026, + "args": { + "External id": 707580,"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": 6305205200792.369, "dur": 76.719, + "args": { + "External id": 707581,"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": 6305205200870.291, "dur": 5.456, + "args": { + "External id": 707582,"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": 6305205200871.064, "dur": 3.905, + "args": { + "External id": 707583,"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": 6305205200873.634, "dur": 1.188, + "args": { + "External id": 707584,"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": 6305205200905.194, "dur": 13.872, + "args": { + "External id": 707585,"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": 6305205200906.218, "dur": 12.330, + "args": { + "External id": 707586,"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": 6305205200917.901, "dur": 0.583, + "args": { + "External id": 707587,"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": 6305205200919.637, "dur": 51.426, + "args": { + "External id": 707588,"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": 6305205200985.515, "dur": 7.558, + "args": { + "External id": 707589,"Record function id": 0, "Sequence number": 7674453, "Fwd thread id": 1, "Ev Idx": 1540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205200986.514, "dur": 4.648, + "args": { + "External id": 707590,"Sequence number": 7674453, "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": 6305205200986.514, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205200988.346, "dur": 2.669, + "args": { + "External id": 707591,"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": 6305205200989.466, "dur": 1.390, + "args": { + "External id": 707592,"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": 6305205200996.513, "dur": 10.555, + "args": { + "External id": 707593,"Record function id": 0, "Sequence number": 7674452, "Fwd thread id": 1, "Ev Idx": 1544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205200997.238, "dur": 7.652, + "args": { + "External id": 707594,"Sequence number": 7674452, "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": 6305205200997.238, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305205200997.973, "dur": 6.708, + "args": { + "External id": 707595,"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": 6305205201001.274, "dur": 2.922, + "args": { + "External id": 707596,"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": 6305205201003.545, "dur": 0.566, + "args": { + "External id": 707597,"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": 6305205201013.141, "dur": 12.803, + "args": { + "External id": 707598,"Record function id": 0, "Ev Idx": 1549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205201015.192, "dur": 9.910, + "args": { + "External id": 707599,"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": 6305205201017.717, "dur": 6.928, + "args": { + "External id": 707600,"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": 6305205201018.891, "dur": 5.649, + "args": { + "External id": 707601,"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": 6305205201029.746, "dur": 6.254, + "args": { + "External id": 707602,"Record function id": 0, "Sequence number": 7674451, "Fwd thread id": 1, "Ev Idx": 1553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205201031.266, "dur": 2.907, + "args": { + "External id": 707603,"Sequence number": 7674451, "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": 6305205201031.266, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205201032.168, "dur": 1.862, + "args": { + "External id": 707604,"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": 6305205201033.055, "dur": 0.834, + "args": { + "External id": 707605,"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": 6305205201041.526, "dur": 171.189, + "args": { + "External id": 707606,"Record function id": 0, "Sequence number": 7674450, "Fwd thread id": 1, "Ev Idx": 1557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205201042.233, "dur": 160.294, + "args": { + "External id": 707607,"Sequence number": 7674450, "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": 6305205201042.233, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305205201043.865, "dur": 5.596, + "args": { + "External id": 707608,"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": 6305205201044.315, "dur": 4.670, + "args": { + "External id": 707609,"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": 6305205201048.522, "dur": 0.332, + "args": { + "External id": 707610,"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": 6305205201050.303, "dur": 89.423, + "args": { + "External id": 707611,"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": 6305205201145.693, "dur": 8.727, + "args": { + "External id": 707612,"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": 6305205201146.976, "dur": 6.328, + "args": { + "External id": 707613,"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": 6305205201149.921, "dur": 3.220, + "args": { + "External id": 707614,"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": 6305205201156.036, "dur": 2.976, + "args": { + "External id": 707615,"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": 6305205201156.701, "dur": 1.836, + "args": { + "External id": 707616,"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": 6305205201158.183, "dur": 0.290, + "args": { + "External id": 707617,"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": 6305205201161.648, "dur": 39.943, + "args": { + "External id": 707618,"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": 6305205201222.385, "dur": 36.651, + "args": { + "External id": 707619,"Record function id": 0, "Sequence number": 7674449, "Fwd thread id": 1, "Ev Idx": 1570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205201223.389, "dur": 4.855, + "args": { + "External id": 707620,"Sequence number": 7674449, "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": 6305205201223.389, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205201225.193, "dur": 2.897, + "args": { + "External id": 707621,"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": 6305205201226.404, "dur": 1.546, + "args": { + "External id": 707622,"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": 6305205201231.553, "dur": 24.753, + "args": { + "External id": 707623,"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": 6305205201263.295, "dur": 7.557, + "args": { + "External id": 707624,"Record function id": 0, "Sequence number": 7674448, "Fwd thread id": 1, "Ev Idx": 1575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205201264.145, "dur": 4.624, + "args": { + "External id": 707625,"Sequence number": 7674448, "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": 6305205201264.145, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305205201264.966, "dur": 3.614, + "args": { + "External id": 707626,"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": 6305205201265.668, "dur": 2.392, + "args": { + "External id": 707627,"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": 6305205201267.397, "dur": 0.569, + "args": { + "External id": 707628,"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": 6305205201275.070, "dur": 9.421, + "args": { + "External id": 707629,"Record function id": 0, "Ev Idx": 1580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205201276.800, "dur": 7.113, + "args": { + "External id": 707630,"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": 6305205201278.562, "dur": 5.018, + "args": { + "External id": 707631,"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": 6305205201281.737, "dur": 1.689, + "args": { + "External id": 707632,"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": 6305205201287.707, "dur": 6.282, + "args": { + "External id": 707633,"Record function id": 0, "Sequence number": 7674447, "Fwd thread id": 1, "Ev Idx": 1584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205201289.241, "dur": 2.994, + "args": { + "External id": 707634,"Sequence number": 7674447, "Fwd thread 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": 6305205201289.241, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205201290.388, "dur": 1.692, + "args": { + "External id": 707635,"Record 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": 6305205201291.165, "dur": 0.812, + "args": { + "External id": 707636,"Record 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": 6305205201297.111, "dur": 98.368, + "args": { + "External id": 707637,"Record function id": 0, "Sequence number": 7674446, "Fwd thread id": 1, "Ev Idx": 1588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205201297.832, "dur": 90.964, + "args": { + "External id": 707638,"Sequence number": 7674446, "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": 6305205201297.832, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305205201299.763, "dur": 5.186, + "args": { + "External id": 707639,"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": 6305205201302.702, "dur": 1.758, + "args": { + "External id": 707640,"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": 6305205201303.988, "dur": 0.385, + "args": { + "External id": 707641,"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": 6305205201305.624, "dur": 34.671, + "args": { + "External id": 707642,"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": 6305205201341.534, "dur": 4.176, + "args": { + "External id": 707643,"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": 6305205201342.100, "dur": 2.961, + "args": { + "External id": 707644,"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": 6305205201343.910, "dur": 1.045, + "args": { + "External id": 707645,"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": 6305205201350.020, "dur": 2.874, + "args": { + "External id": 707646,"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": 6305205201350.602, "dur": 1.876, + "args": { + "External id": 707647,"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": 6305205201352.092, "dur": 0.272, + "args": { + "External id": 707648,"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": 6305205201353.314, "dur": 34.802, + "args": { + "External id": 707649,"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": 6305205201400.002, "dur": 28.965, + "args": { + "External id": 707650,"Record function id": 0, "Sequence number": 7674445, "Fwd thread id": 1, "Ev Idx": 1601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205201401.027, "dur": 7.027, + "args": { + "External id": 707651,"Sequence number": 7674445, "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": 6305205201401.027, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205201405.454, "dur": 2.442, + "args": { + "External id": 707652,"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": 6305205201406.744, "dur": 1.027, + "args": { + "External id": 707653,"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": 6305205201410.262, "dur": 15.928, + "args": { + "External id": 707654,"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": 6305205201432.476, "dur": 6.840, + "args": { + "External id": 707655,"Record function id": 0, "Sequence number": 7674444, "Fwd thread id": 1, "Ev Idx": 1606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305205201433.262, "dur": 4.667, + "args": { + "External id": 707656,"Sequence number": 7674444, "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": 6305205201433.262, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305205201433.819, "dur": 3.921, + "args": { + "External id": 707657,"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": 6305205201434.460, "dur": 2.685, + "args": { + "External id": 707658,"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": 6305205201436.464, "dur": 0.570, + "args": { + "External id": 707659,"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": 6305205201443.053, "dur": 5.480, + "args": { + "External id": 707660,"Record function id": 0, "Ev Idx": 1611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205201444.870, "dur": 3.180, + "args": { + "External id": 707661,"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": 6305205201445.848, "dur": 1.670, + "args": { + "External id": 707662,"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": 6305205201446.547, "dur": 0.849, + "args": { + "External id": 707663,"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": 6305205201453.219, "dur": 387.851, + "args": { + "External id": 707664,"Record function id": 0, "Sequence number": 7674443, "Fwd thread id": 1, "Ev Idx": 1615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305205201455.004, "dur": 354.342, + "args": { + "External id": 707665,"Sequence number": 7674443, "Fwd thread 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": 6305205201455.004, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305205201494.159, "dur": 2.303, + "args": { + "External id": 707666,"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": 6305205201495.293, "dur": 1.037, + "args": { + "External id": 707667,"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": 6305205201528.960, "dur": 5.248, + "args": { + "External id": 707668,"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": 6305205201544.711, "dur": 2.204, + "args": { + "External id": 707669,"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": 6305205201698.849, "dur": 2.488, + "args": { + "External id": 707670,"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": 6305205201705.662, "dur": 37.908, + "args": { + "External id": 707671,"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": 6305205201719.697, "dur": 1.027, + "args": { + "External id": 707672,"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": 6305205201749.394, "dur": 34.908, + "args": { + "External id": 707673,"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": 6305205201753.869, "dur": 30.177, + "args": { + "External id": 707674,"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": 6305205201758.379, "dur": 4.309, + "args": { + "External id": 707675,"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": 6305205201764.460, "dur": 18.837, + "args": { + "External id": 707676,"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": 6305205201788.819, "dur": 2.555, + "args": { + "External id": 707677,"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": 6305205201790.120, "dur": 1.126, + "args": { + "External id": 707678,"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": 6305205201798.582, "dur": 4.191, + "args": { + "External id": 707679,"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": 6305205201801.513, "dur": 1.143, + "args": { + "External id": 707680,"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": 6305205201821.464, "dur": 15.080, + "args": { + "External id": 707681,"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": 6305205201853.062, "dur": 8.562, + "args": { + "External id": 707682,"Record function id": 0, "Ev Idx": 1633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205201855.309, "dur": 5.531, + "args": { + "External id": 707683,"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": 6305205201857.396, "dur": 2.552, + "args": { + "External id": 707684,"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": 6305205201858.180, "dur": 1.638, + "args": { + "External id": 707685,"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": 6305205201865.994, "dur": 2881.110, + "args": { + "External id": 707686,"Record function id": 0, "Ev Idx": 1637 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.25)", "pid": 2338707, "tid": 2379456, + "ts": 6305205201896.549, "dur": 944.733, + "args": { + "External id": 707687,"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": 6305205201919.915, "dur": 912.721, + "args": { + "External id": 707688,"Record function id": 0, "Ev Idx": 1639 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.24)", "pid": 2338707, "tid": 2379456, + "ts": 6305205201936.114, "dur": 881.108, + "args": { + "External id": 707689,"Record function id": 0, "Ev Idx": 1640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305205202008.629, "dur": 5.409, + "args": { + "External id": 707690,"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": 6305205202029.004, "dur": 75.547, + "args": { + "External id": 707691,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205202033.760, "dur": 1.227, + "args": { + "External id": 707692,"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": 6305205202039.018, "dur": 0.339, + "args": { + "External id": 707693,"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": 6305205202040.619, "dur": 0.280, + "args": { + "External id": 707694,"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": 6305205202042.284, "dur": 2.327, + "args": { + "External id": 707695,"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": 6305205202046.354, "dur": 2.670, + "args": { + "External id": 707696,"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": 6305205202050.619, "dur": 0.403, + "args": { + "External id": 707697,"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": 6305205202055.104, "dur": 37.410, + "args": { + "External id": 707698,"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": 6305205202095.462, "dur": 0.502, + "args": { + "External id": 707699,"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": 6305205202097.721, "dur": 0.517, + "args": { + "External id": 707700,"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": 6305205202116.068, "dur": 49.723, + "args": { + "External id": 707701,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305205202208.030, "dur": 127.185, + "args": { + "External id": 707702,"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": 6305205202219.945, "dur": 4.431, + "args": { + "External id": 707703,"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": 6305205202229.482, "dur": 12.233, + "args": { + "External id": 707704,"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": 6305205202233.486, "dur": 7.805, + "args": { + "External id": 707705,"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": 6305205202237.598, "dur": 2.348, + "args": { + "External id": 707706,"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": 6305205202249.276, "dur": 31.713, + "args": { + "External id": 707707,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205202251.898, "dur": 0.485, + "args": { + "External id": 707708,"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": 6305205202253.793, "dur": 2.684, + "args": { + "External id": 707709,"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": 6305205202257.826, "dur": 0.434, + "args": { + "External id": 707710,"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": 6305205202261.773, "dur": 0.454, + "args": { + "External id": 707711,"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": 6305205202263.768, "dur": 0.317, + "args": { + "External id": 707712,"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": 6305205202265.756, "dur": 2.124, + "args": { + "External id": 707713,"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": 6305205202269.338, "dur": 0.414, + "args": { + "External id": 707714,"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": 6305205202271.277, "dur": 0.294, + "args": { + "External id": 707715,"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": 6305205202275.302, "dur": 0.414, + "args": { + "External id": 707716,"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": 6305205202292.391, "dur": 32.652, + "args": { + "External id": 707717,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305205202395.282, "dur": 315.042, + "args": { + "External id": 707718,"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": 6305205202432.049, "dur": 272.799, + "args": { + "External id": 707719,"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": 6305205202442.840, "dur": 255.791, + "args": { + "External id": 707720,"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": 6305205202735.627, "dur": 2.389, + "args": { + "External id": 707721,"Record function id": 0, "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": 6305205202849.173, "dur": 1875.636, + "args": { + "External id": 707722,"Sequence number": 7674442, "Fwd thread 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": 6305205202849.173, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6305205202973.739, "dur": 154.414, + "args": { + "External id": 707723,"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": 6305205203178.527, "dur": 43.662, + "args": { + "External id": 707724,"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": 6305205203244.192, "dur": 58.294, + "args": { + "External id": 707725,"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": 6305205203313.611, "dur": 32.365, + "args": { + "External id": 707726,"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": 6305205203351.835, "dur": 33.511, + "args": { + "External id": 707727,"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": 6305205203391.726, "dur": 27.560, + "args": { + "External id": 707728,"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": 6305205203429.122, "dur": 28.487, + "args": { + "External id": 707729,"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": 6305205203485.883, "dur": 41.472, + "args": { + "External id": 707730,"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": 6305205203555.132, "dur": 32.814, + "args": { + "External id": 707731,"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": 6305205203612.912, "dur": 20.182, + "args": { + "External id": 707732,"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": 6305205203657.791, "dur": 16.040, + "args": { + "External id": 707733,"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": 6305205203683.954, "dur": 41.000, + "args": { + "External id": 707734,"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": 6305205203728.581, "dur": 33.763, + "args": { + "External id": 707735,"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": 6305205203792.433, "dur": 254.686, + "args": { + "External id": 707736,"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": 6305205203876.437, "dur": 9.222, + "args": { + "External id": 707737,"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": 6305205203887.698, "dur": 2.312, + "args": { + "External id": 707738,"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": 6305205203891.378, "dur": 1.683, + "args": { + "External id": 707739,"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": 6305205203894.081, "dur": 3.977, + "args": { + "External id": 707740,"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": 6305205203940.184, "dur": 7.350, + "args": { + "External id": 707741,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205203942.341, "dur": 4.940, + "args": { + "External id": 707742,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205203949.272, "dur": 31.433, + "args": { + "External id": 707743,"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": 6305205203955.601, "dur": 1.784, + "args": { + "External id": 707744,"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": 6305205203982.218, "dur": 4.500, + "args": { + "External id": 707745,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205203985.985, "dur": 0.628, + "args": { + "External id": 707746,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205203987.843, "dur": 15.823, + "args": { + "External id": 707747,"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": 6305205203989.940, "dur": 0.801, + "args": { + "External id": 707748,"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": 6305205204124.227, "dur": 31.561, + "args": { + "External id": 707749,"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": 6305205204175.509, "dur": 17.965, + "args": { + "External id": 707750,"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": 6305205204201.411, "dur": 49.365, + "args": { + "External id": 707751,"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": 6305205204257.126, "dur": 40.190, + "args": { + "External id": 707752,"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": 6305205204308.403, "dur": 22.435, + "args": { + "External id": 707753,"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": 6305205204336.252, "dur": 31.433, + "args": { + "External id": 707754,"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": 6305205204390.901, "dur": 37.049, + "args": { + "External id": 707755,"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": 6305205204435.139, "dur": 31.210, + "args": { + "External id": 707756,"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": 6305205204496.377, "dur": 42.220, + "args": { + "External id": 707757,"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": 6305205204562.283, "dur": 25.886, + "args": { + "External id": 707758,"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": 6305205204605.312, "dur": 16.939, + "args": { + "External id": 707759,"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": 6305205204645.514, "dur": 14.272, + "args": { + "External id": 707760,"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": 6305205204676.645, "dur": 17.349, + "args": { + "External id": 707761,"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": 6305205204770.172, "dur": 17.649, + "args": { + "External id": 707762,"Record function id": 0, "Ev Idx": 1713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205204773.970, "dur": 12.787, + "args": { + "External id": 707763,"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": 6305205204778.097, "dur": 7.906, + "args": { + "External id": 707764,"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": 6305205204779.526, "dur": 6.380, + "args": { + "External id": 707765,"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": 6305205204791.630, "dur": 5.024, + "args": { + "External id": 707766,"Record function id": 0, "Ev Idx": 1717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205204793.525, "dur": 2.627, + "args": { + "External id": 707767,"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": 6305205204794.167, "dur": 1.500, + "args": { + "External id": 707768,"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": 6305205204794.559, "dur": 1.022, + "args": { + "External id": 707769,"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": 6305205204799.913, "dur": 7.267, + "args": { + "External id": 707770,"Record function id": 0, "Ev Idx": 1721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205204801.631, "dur": 5.002, + "args": { + "External id": 707771,"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": 6305205204802.194, "dur": 3.987, + "args": { + "External id": 707772,"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": 6305205204802.913, "dur": 3.165, + "args": { + "External id": 707773,"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": 6305205204810.758, "dur": 4.245, + "args": { + "External id": 707774,"Record function id": 0, "Ev Idx": 1725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205204812.174, "dur": 2.440, + "args": { + "External id": 707775,"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": 6305205204813.030, "dur": 1.191, + "args": { + "External id": 707776,"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": 6305205204813.316, "dur": 0.829, + "args": { + "External id": 707777,"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": 6305205204818.290, "dur": 13.315, + "args": { + "External id": 707778,"Record function id": 0, "Ev Idx": 1729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205204819.649, "dur": 11.505, + "args": { + "External id": 707779,"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": 6305205204829.149, "dur": 1.202, + "args": { + "External id": 707780,"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": 6305205204829.514, "dur": 0.765, + "args": { + "External id": 707781,"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": 6305205204834.999, "dur": 6.420, + "args": { + "External id": 707782,"Record function id": 0, "Ev Idx": 1733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205204836.512, "dur": 4.512, + "args": { + "External id": 707783,"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": 6305205204837.067, "dur": 3.513, + "args": { + "External id": 707784,"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": 6305205204839.811, "dur": 0.671, + "args": { + "External id": 707785,"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": 6305205204846.646, "dur": 4.086, + "args": { + "External id": 707786,"Record function id": 0, "Ev Idx": 1737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205204847.975, "dur": 2.288, + "args": { + "External id": 707787,"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": 6305205204848.517, "dur": 1.355, + "args": { + "External id": 707788,"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": 6305205204849.238, "dur": 0.553, + "args": { + "External id": 707789,"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": 6305205204853.829, "dur": 4.117, + "args": { + "External id": 707790,"Record function id": 0, "Ev Idx": 1741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205204855.554, "dur": 1.988, + "args": { + "External id": 707791,"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": 6305205204856.031, "dur": 1.056, + "args": { + "External id": 707792,"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": 6305205204856.314, "dur": 0.698, + "args": { + "External id": 707793,"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": 6305205204861.144, "dur": 3.849, + "args": { + "External id": 707794,"Record function id": 0, "Ev Idx": 1745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205204862.554, "dur": 2.039, + "args": { + "External id": 707795,"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": 6305205204863.126, "dur": 1.050, + "args": { + "External id": 707796,"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": 6305205204863.500, "dur": 0.601, + "args": { + "External id": 707797,"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": 6305205204869.000, "dur": 280878.772, + "args": { + "External id": 707798,"Record function id": 0, "Sequence number": 7674441, "Fwd thread id": 1, "Ev Idx": 1749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305205204870.147, "dur": 280868.534, + "args": { + "External id": 707799,"Sequence number": 7674441, "Fwd thread 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": 6305205204870.147, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.25)", "pid": 2338707, "tid": 2379456, + "ts": 6305205204901.319, "dur": 42.203, + "args": { + "External id": 707800,"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": 6305205204951.020, "dur": 66.231, + "args": { + "External id": 707801,"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": 6305205205023.883, "dur": 280706.253, + "args": { + "External id": 707802,"Record function id": 0, "Ev Idx": 1753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305205205115.315, "dur": 9.675, + "args": { + "External id": 707803,"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": 6305205205136.361, "dur": 7.613, + "args": { + "External id": 707804,"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": 6305205205166.035, "dur": 279629.706, + "args": { + "External id": 707805,"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": 6305205205181.390, "dur": 279599.548, + "args": { + "External id": 707806,"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": 6305205205355.435, "dur": 4.737, + "args": { + "External id": 707807,"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": 6305205205391.369, "dur": 279339.570, + "args": { + "External id": 707808,"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": 6305205205394.254, "dur": 279335.436, + "args": { + "External id": 707809,"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": 6305205205399.063, "dur": 13.754, + "args": { + "External id": 707810,"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": 6305205205414.892, "dur": 279309.245, + "args": { + "External id": 707811,"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": 6305205484910.589, "dur": 17.920, + "args": { + "External id": 707812,"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": 6305205484918.462, "dur": 9.694, + "args": { + "External id": 707813,"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": 6305205484971.291, "dur": 404.465, + "args": { + "External id": 707814,"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": 6305205485005.836, "dur": 364.172, + "args": { + "External id": 707815,"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": 6305205485017.236, "dur": 346.469, + "args": { + "External id": 707816,"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": 6305205485401.493, "dur": 2.699, + "args": { + "External id": 707817,"Record function id": 0, "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": 6305205485470.105, "dur": 7.181, + "args": { + "External id": 707818,"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": 6305205485551.883, "dur": 1.960, + "args": { + "External id": 707819,"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": 6305205485573.941, "dur": 4.072, + "args": { + "External id": 707820,"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": 6305205485591.942, "dur": 0.807, + "args": { + "External id": 707821,"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": 6305205485607.713, "dur": 0.738, + "args": { + "External id": 707822,"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": 6305205485621.346, "dur": 0.697, + "args": { + "External id": 707823,"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": 6305205485634.152, "dur": 2.695, + "args": { + "External id": 707824,"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": 6305205485650.626, "dur": 2.636, + "args": { + "External id": 707825,"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": 6305205485663.702, "dur": 1.118, + "args": { + "External id": 707826,"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": 6305205485764.602, "dur": 2997.490, + "args": { + "External id": 707827,"Record function id": 0, "Ev Idx": 1778 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.24)", "pid": 2338707, "tid": 2379456, + "ts": 6305205485784.715, "dur": 1143.132, + "args": { + "External id": 707828,"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": 6305205485799.393, "dur": 403.182, + "args": { + "External id": 707829,"Record function id": 0, "Ev Idx": 1780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6305205485888.756, "dur": 4.542, + "args": { + "External id": 707830,"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": 6305205485896.831, "dur": 1.018, + "args": { + "External id": 707831,"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": 6305205485899.397, "dur": 3.385, + "args": { + "External id": 707832,"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": 6305205485904.414, "dur": 0.842, + "args": { + "External id": 707833,"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": 6305205485907.107, "dur": 1.051, + "args": { + "External id": 707834,"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": 6305205485911.809, "dur": 1.124, + "args": { + "External id": 707835,"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": 6305205485914.549, "dur": 2.649, + "args": { + "External id": 707836,"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": 6305205485918.669, "dur": 0.858, + "args": { + "External id": 707837,"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": 6305205485920.948, "dur": 0.891, + "args": { + "External id": 707838,"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": 6305205485924.947, "dur": 0.667, + "args": { + "External id": 707839,"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": 6305205485943.602, "dur": 220.691, + "args": { + "External id": 707840,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305205485959.531, "dur": 198.951, + "args": { + "External id": 707841,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305205485997.185, "dur": 15.895, + "args": { + "External id": 707842,"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": 6305205486017.014, "dur": 108.024, + "args": { + "External id": 707843,"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": 6305205486019.632, "dur": 104.964, + "args": { + "External id": 707844,"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": 6305205486025.401, "dur": 7.345, + "args": { + "External id": 707845,"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": 6305205486034.454, "dur": 88.998, + "args": { + "External id": 707846,"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": 6305205486291.077, "dur": 628.610, + "args": { + "External id": 707847,"Record function id": 0, "Ev Idx": 1798 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.23)", "pid": 2338707, "tid": 2379456, + "ts": 6305205486309.567, "dur": 595.953, + "args": { + "External id": 707848,"Record function id": 0, "Ev Idx": 1799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305205486369.386, "dur": 6.055, + "args": { + "External id": 707849,"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": 6305205486390.702, "dur": 37.050, + "args": { + "External id": 707850,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205486395.969, "dur": 1.353, + "args": { + "External id": 707851,"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": 6305205486399.635, "dur": 2.453, + "args": { + "External id": 707852,"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": 6305205486404.028, "dur": 0.386, + "args": { + "External id": 707853,"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": 6305205486405.996, "dur": 0.371, + "args": { + "External id": 707854,"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": 6305205486410.482, "dur": 0.420, + "args": { + "External id": 707855,"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": 6305205486412.119, "dur": 2.710, + "args": { + "External id": 707856,"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": 6305205486416.260, "dur": 0.318, + "args": { + "External id": 707857,"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": 6305205486419.654, "dur": 0.460, + "args": { + "External id": 707858,"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": 6305205486421.521, "dur": 0.516, + "args": { + "External id": 707859,"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": 6305205486438.242, "dur": 39.795, + "args": { + "External id": 707860,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305205486525.666, "dur": 132.157, + "args": { + "External id": 707861,"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": 6305205486537.064, "dur": 4.885, + "args": { + "External id": 707862,"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": 6305205486547.874, "dur": 16.547, + "args": { + "External id": 707863,"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": 6305205486557.929, "dur": 6.092, + "args": { + "External id": 707864,"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": 6305205486561.781, "dur": 0.689, + "args": { + "External id": 707865,"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": 6305205486572.197, "dur": 31.365, + "args": { + "External id": 707866,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205486574.589, "dur": 0.476, + "args": { + "External id": 707867,"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": 6305205486578.696, "dur": 0.477, + "args": { + "External id": 707868,"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": 6305205486580.821, "dur": 2.486, + "args": { + "External id": 707869,"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": 6305205486584.575, "dur": 2.400, + "args": { + "External id": 707870,"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": 6305205486588.198, "dur": 0.539, + "args": { + "External id": 707871,"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": 6305205486589.995, "dur": 0.400, + "args": { + "External id": 707872,"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": 6305205486593.961, "dur": 0.317, + "args": { + "External id": 707873,"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": 6305205486595.647, "dur": 0.242, + "args": { + "External id": 707874,"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": 6305205486597.997, "dur": 0.330, + "args": { + "External id": 707875,"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": 6305205486617.089, "dur": 31.594, + "args": { + "External id": 707876,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305205486705.236, "dur": 126.915, + "args": { + "External id": 707877,"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": 6305205486737.980, "dur": 90.410, + "args": { + "External id": 707878,"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": 6305205486747.983, "dur": 75.660, + "args": { + "External id": 707879,"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": 6305205486850.645, "dur": 2.012, + "args": { + "External id": 707880,"Record function id": 0, "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": 6305205486935.227, "dur": 1804.062, + "args": { + "External id": 707881,"Sequence number": 7674440, "Fwd thread 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": 6305205486935.227, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6305205487049.251, "dur": 152.302, + "args": { + "External id": 707882,"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": 6305205487249.448, "dur": 38.583, + "args": { + "External id": 707883,"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": 6305205487305.875, "dur": 51.192, + "args": { + "External id": 707884,"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": 6305205487370.539, "dur": 31.586, + "args": { + "External id": 707885,"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": 6305205487410.170, "dur": 32.782, + "args": { + "External id": 707886,"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": 6305205487450.879, "dur": 27.046, + "args": { + "External id": 707887,"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": 6305205487484.976, "dur": 44.214, + "args": { + "External id": 707888,"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": 6305205487560.813, "dur": 27.169, + "args": { + "External id": 707889,"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": 6305205487609.086, "dur": 27.712, + "args": { + "External id": 707890,"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": 6305205487658.839, "dur": 17.867, + "args": { + "External id": 707891,"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": 6305205487693.454, "dur": 17.673, + "args": { + "External id": 707892,"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": 6305205487718.364, "dur": 40.573, + "args": { + "External id": 707893,"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": 6305205487762.413, "dur": 33.230, + "args": { + "External id": 707894,"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": 6305205487827.691, "dur": 294.400, + "args": { + "External id": 707895,"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": 6305205487911.380, "dur": 6.070, + "args": { + "External id": 707896,"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": 6305205487919.479, "dur": 1.960, + "args": { + "External id": 707897,"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": 6305205487922.510, "dur": 2.007, + "args": { + "External id": 707898,"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": 6305205487925.752, "dur": 4.020, + "args": { + "External id": 707899,"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": 6305205487973.537, "dur": 5.265, + "args": { + "External id": 707900,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205487975.771, "dur": 2.818, + "args": { + "External id": 707901,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205487980.760, "dur": 37.174, + "args": { + "External id": 707902,"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": 6305205487986.302, "dur": 5.199, + "args": { + "External id": 707903,"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": 6305205488019.623, "dur": 1.884, + "args": { + "External id": 707904,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205488020.700, "dur": 0.725, + "args": { + "External id": 707905,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205488022.643, "dur": 17.736, + "args": { + "External id": 707906,"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": 6305205488027.247, "dur": 0.398, + "args": { + "External id": 707907,"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": 6305205488162.954, "dur": 31.714, + "args": { + "External id": 707908,"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": 6305205488213.334, "dur": 16.780, + "args": { + "External id": 707909,"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": 6305205488238.330, "dur": 48.095, + "args": { + "External id": 707910,"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": 6305205488293.061, "dur": 39.176, + "args": { + "External id": 707911,"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": 6305205488342.191, "dur": 20.891, + "args": { + "External id": 707912,"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": 6305205488368.252, "dur": 31.016, + "args": { + "External id": 707913,"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": 6305205488405.777, "dur": 28.360, + "args": { + "External id": 707914,"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": 6305205488441.004, "dur": 29.575, + "args": { + "External id": 707915,"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": 6305205488492.257, "dur": 41.938, + "args": { + "External id": 707916,"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": 6305205488569.989, "dur": 31.848, + "args": { + "External id": 707917,"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": 6305205488621.259, "dur": 19.566, + "args": { + "External id": 707918,"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": 6305205488661.350, "dur": 13.301, + "args": { + "External id": 707919,"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": 6305205488690.243, "dur": 15.357, + "args": { + "External id": 707920,"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": 6305205488787.841, "dur": 15.765, + "args": { + "External id": 707921,"Record function id": 0, "Ev Idx": 1872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205488791.522, "dur": 11.092, + "args": { + "External id": 707922,"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": 6305205488796.091, "dur": 5.565, + "args": { + "External id": 707923,"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": 6305205488797.591, "dur": 3.980, + "args": { + "External id": 707924,"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": 6305205488807.456, "dur": 4.297, + "args": { + "External id": 707925,"Record function id": 0, "Ev Idx": 1876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205488808.910, "dur": 2.430, + "args": { + "External id": 707926,"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": 6305205488809.500, "dur": 1.395, + "args": { + "External id": 707927,"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": 6305205488809.962, "dur": 0.838, + "args": { + "External id": 707928,"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": 6305205488815.125, "dur": 6.911, + "args": { + "External id": 707929,"Record function id": 0, "Ev Idx": 1880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205488816.506, "dur": 5.057, + "args": { + "External id": 707930,"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": 6305205488817.241, "dur": 3.922, + "args": { + "External id": 707931,"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": 6305205488817.839, "dur": 3.234, + "args": { + "External id": 707932,"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": 6305205488825.361, "dur": 3.699, + "args": { + "External id": 707933,"Record function id": 0, "Ev Idx": 1884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205488826.591, "dur": 2.054, + "args": { + "External id": 707934,"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": 6305205488827.103, "dur": 1.134, + "args": { + "External id": 707935,"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": 6305205488827.398, "dur": 0.761, + "args": { + "External id": 707936,"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": 6305205488832.239, "dur": 3.243, + "args": { + "External id": 707937,"Record function id": 0, "Ev Idx": 1888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205488833.303, "dur": 1.783, + "args": { + "External id": 707938,"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": 6305205488833.736, "dur": 0.915, + "args": { + "External id": 707939,"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": 6305205488834.022, "dur": 0.562, + "args": { + "External id": 707940,"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": 6305205488838.650, "dur": 3.876, + "args": { + "External id": 707941,"Record function id": 0, "Ev Idx": 1892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205488840.115, "dur": 1.999, + "args": { + "External id": 707942,"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": 6305205488840.606, "dur": 1.109, + "args": { + "External id": 707943,"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": 6305205488840.966, "dur": 0.689, + "args": { + "External id": 707944,"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": 6305205488845.926, "dur": 13.285, + "args": { + "External id": 707945,"Record function id": 0, "Ev Idx": 1896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205488847.548, "dur": 11.083, + "args": { + "External id": 707946,"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": 6305205488848.100, "dur": 10.122, + "args": { + "External id": 707947,"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": 6305205488857.275, "dur": 0.855, + "args": { + "External id": 707948,"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": 6305205488862.429, "dur": 4.329, + "args": { + "External id": 707949,"Record function id": 0, "Ev Idx": 1900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205488863.883, "dur": 2.478, + "args": { + "External id": 707950,"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": 6305205488864.353, "dur": 1.597, + "args": { + "External id": 707951,"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": 6305205488864.877, "dur": 0.989, + "args": { + "External id": 707952,"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": 6305205488869.863, "dur": 3.652, + "args": { + "External id": 707953,"Record function id": 0, "Ev Idx": 1904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205488871.237, "dur": 1.882, + "args": { + "External id": 707954,"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": 6305205488871.688, "dur": 1.015, + "args": { + "External id": 707955,"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": 6305205488872.036, "dur": 0.594, + "args": { + "External id": 707956,"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": 6305205488877.223, "dur": 80754.639, + "args": { + "External id": 707957,"Record function id": 0, "Sequence number": 7674439, "Fwd thread id": 1, "Ev Idx": 1908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305205488878.413, "dur": 80744.477, + "args": { + "External id": 707958,"Sequence number": 7674439, "Fwd thread 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": 6305205488878.413, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.24)", "pid": 2338707, "tid": 2379456, + "ts": 6305205488911.750, "dur": 40.541, + "args": { + "External id": 707959,"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": 6305205488959.773, "dur": 62.912, + "args": { + "External id": 707960,"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": 6305205489028.553, "dur": 80586.132, + "args": { + "External id": 707961,"Record function id": 0, "Ev Idx": 1912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305205489161.175, "dur": 8.156, + "args": { + "External id": 707962,"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": 6305205489180.858, "dur": 7.701, + "args": { + "External id": 707963,"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": 6305205489206.438, "dur": 79610.931, + "args": { + "External id": 707964,"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": 6305205489220.778, "dur": 79583.391, + "args": { + "External id": 707965,"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": 6305205489367.831, "dur": 18.381, + "args": { + "External id": 707966,"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": 6305205489415.767, "dur": 79339.159, + "args": { + "External id": 707967,"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": 6305205489418.618, "dur": 79335.098, + "args": { + "External id": 707968,"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": 6305205489424.075, "dur": 12.357, + "args": { + "External id": 707969,"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": 6305205489438.505, "dur": 79309.417, + "args": { + "External id": 707970,"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": 6305205568927.501, "dur": 12.788, + "args": { + "External id": 707971,"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": 6305205568931.307, "dur": 8.579, + "args": { + "External id": 707972,"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": 6305205568972.144, "dur": 308.632, + "args": { + "External id": 707973,"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": 6305205569007.315, "dur": 268.130, + "args": { + "External id": 707974,"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": 6305205569020.977, "dur": 248.305, + "args": { + "External id": 707975,"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": 6305205569304.893, "dur": 2.419, + "args": { + "External id": 707976,"Record function id": 0, "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": 6305205569369.118, "dur": 6.954, + "args": { + "External id": 707977,"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": 6305205569423.598, "dur": 1.459, + "args": { + "External id": 707978,"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": 6305205569441.924, "dur": 3.325, + "args": { + "External id": 707979,"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": 6305205569459.092, "dur": 0.944, + "args": { + "External id": 707980,"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": 6305205569475.333, "dur": 0.673, + "args": { + "External id": 707981,"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": 6305205569487.274, "dur": 0.870, + "args": { + "External id": 707982,"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": 6305205569498.706, "dur": 2.585, + "args": { + "External id": 707983,"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": 6305205569534.135, "dur": 3.188, + "args": { + "External id": 707984,"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": 6305205569549.458, "dur": 0.885, + "args": { + "External id": 707985,"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": 6305205569647.619, "dur": 2975.979, + "args": { + "External id": 707986,"Record function id": 0, "Ev Idx": 1937 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.23)", "pid": 2338707, "tid": 2379456, + "ts": 6305205569666.953, "dur": 1132.801, + "args": { + "External id": 707987,"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": 6305205569682.286, "dur": 354.403, + "args": { + "External id": 707988,"Record function id": 0, "Ev Idx": 1939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6305205569765.098, "dur": 4.153, + "args": { + "External id": 707989,"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": 6305205569772.575, "dur": 0.736, + "args": { + "External id": 707990,"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": 6305205569775.279, "dur": 2.743, + "args": { + "External id": 707991,"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": 6305205569779.681, "dur": 0.644, + "args": { + "External id": 707992,"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": 6305205569783.849, "dur": 0.904, + "args": { + "External id": 707993,"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": 6305205569786.125, "dur": 0.949, + "args": { + "External id": 707994,"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": 6305205569788.503, "dur": 2.089, + "args": { + "External id": 707995,"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": 6305205569792.012, "dur": 1.150, + "args": { + "External id": 707996,"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": 6305205569796.358, "dur": 0.860, + "args": { + "External id": 707997,"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": 6305205569798.838, "dur": 0.629, + "args": { + "External id": 707998,"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": 6305205569828.877, "dur": 175.335, + "args": { + "External id": 707999,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305205569847.052, "dur": 152.390, + "args": { + "External id": 708000,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305205569877.085, "dur": 16.304, + "args": { + "External id": 708001,"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": 6305205569896.833, "dur": 72.227, + "args": { + "External id": 708002,"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": 6305205569901.605, "dur": 67.092, + "args": { + "External id": 708003,"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": 6305205569905.738, "dur": 6.901, + "args": { + "External id": 708004,"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": 6305205569914.562, "dur": 53.305, + "args": { + "External id": 708005,"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": 6305205570168.073, "dur": 623.869, + "args": { + "External id": 708006,"Record function id": 0, "Ev Idx": 1957 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.22)", "pid": 2338707, "tid": 2379456, + "ts": 6305205570186.694, "dur": 592.819, + "args": { + "External id": 708007,"Record function id": 0, "Ev Idx": 1958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305205570245.299, "dur": 6.141, + "args": { + "External id": 708008,"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": 6305205570267.193, "dur": 41.895, + "args": { + "External id": 708009,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205570272.951, "dur": 1.830, + "args": { + "External id": 708010,"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": 6305205570276.894, "dur": 1.998, + "args": { + "External id": 708011,"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": 6305205570280.418, "dur": 0.410, + "args": { + "External id": 708012,"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": 6305205570282.436, "dur": 0.421, + "args": { + "External id": 708013,"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": 6305205570289.727, "dur": 0.380, + "args": { + "External id": 708014,"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": 6305205570291.904, "dur": 2.792, + "args": { + "External id": 708015,"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": 6305205570296.141, "dur": 0.513, + "args": { + "External id": 708016,"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": 6305205570299.751, "dur": 0.305, + "args": { + "External id": 708017,"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": 6305205570301.423, "dur": 0.295, + "args": { + "External id": 708018,"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": 6305205570319.228, "dur": 45.702, + "args": { + "External id": 708019,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305205570396.070, "dur": 126.866, + "args": { + "External id": 708020,"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": 6305205570405.472, "dur": 3.380, + "args": { + "External id": 708021,"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": 6305205570414.214, "dur": 10.804, + "args": { + "External id": 708022,"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": 6305205570418.562, "dur": 6.045, + "args": { + "External id": 708023,"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": 6305205570422.568, "dur": 0.726, + "args": { + "External id": 708024,"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": 6305205570431.326, "dur": 29.985, + "args": { + "External id": 708025,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205570433.682, "dur": 0.632, + "args": { + "External id": 708026,"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": 6305205570437.974, "dur": 0.532, + "args": { + "External id": 708027,"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": 6305205570439.822, "dur": 2.817, + "args": { + "External id": 708028,"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": 6305205570443.968, "dur": 1.782, + "args": { + "External id": 708029,"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": 6305205570447.156, "dur": 0.433, + "args": { + "External id": 708030,"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": 6305205570449.087, "dur": 0.295, + "args": { + "External id": 708031,"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": 6305205570452.667, "dur": 0.369, + "args": { + "External id": 708032,"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": 6305205570454.236, "dur": 0.404, + "args": { + "External id": 708033,"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": 6305205570455.774, "dur": 0.254, + "args": { + "External id": 708034,"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": 6305205570471.986, "dur": 27.864, + "args": { + "External id": 708035,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305205570573.492, "dur": 131.412, + "args": { + "External id": 708036,"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": 6305205570606.112, "dur": 94.982, + "args": { + "External id": 708037,"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": 6305205570616.042, "dur": 79.938, + "args": { + "External id": 708038,"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": 6305205570723.788, "dur": 1.814, + "args": { + "External id": 708039,"Record function id": 0, "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": 6305205570807.210, "dur": 1795.200, + "args": { + "External id": 708040,"Sequence number": 7674438, "Fwd thread 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": 6305205570807.210, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6305205570917.638, "dur": 110.494, + "args": { + "External id": 708041,"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": 6305205571110.463, "dur": 43.660, + "args": { + "External id": 708042,"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": 6305205571173.577, "dur": 59.579, + "args": { + "External id": 708043,"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": 6305205571246.007, "dur": 33.677, + "args": { + "External id": 708044,"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": 6305205571285.812, "dur": 34.113, + "args": { + "External id": 708045,"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": 6305205571328.034, "dur": 29.484, + "args": { + "External id": 708046,"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": 6305205571364.653, "dur": 29.833, + "args": { + "External id": 708047,"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": 6305205571422.881, "dur": 24.131, + "args": { + "External id": 708048,"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": 6305205571465.132, "dur": 26.761, + "args": { + "External id": 708049,"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": 6305205571531.265, "dur": 21.376, + "args": { + "External id": 708050,"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": 6305205571567.228, "dur": 16.877, + "args": { + "External id": 708051,"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": 6305205571592.085, "dur": 40.089, + "args": { + "External id": 708052,"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": 6305205571636.298, "dur": 32.779, + "args": { + "External id": 708053,"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": 6305205571700.169, "dur": 253.305, + "args": { + "External id": 708054,"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": 6305205571783.693, "dur": 6.580, + "args": { + "External id": 708055,"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": 6305205571792.071, "dur": 1.994, + "args": { + "External id": 708056,"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": 6305205571795.156, "dur": 1.589, + "args": { + "External id": 708057,"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": 6305205571798.053, "dur": 1.369, + "args": { + "External id": 708058,"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": 6305205571847.482, "dur": 5.297, + "args": { + "External id": 708059,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205571849.882, "dur": 2.725, + "args": { + "External id": 708060,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205571854.534, "dur": 35.573, + "args": { + "External id": 708061,"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": 6305205571860.226, "dur": 5.800, + "args": { + "External id": 708062,"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": 6305205571891.459, "dur": 1.522, + "args": { + "External id": 708063,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205571892.334, "dur": 0.546, + "args": { + "External id": 708064,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205571894.139, "dur": 13.655, + "args": { + "External id": 708065,"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": 6305205571896.233, "dur": 0.537, + "args": { + "External id": 708066,"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": 6305205571989.723, "dur": 25.999, + "args": { + "External id": 708067,"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": 6305205572034.577, "dur": 16.468, + "args": { + "External id": 708068,"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": 6305205572095.427, "dur": 50.198, + "args": { + "External id": 708069,"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": 6305205572153.956, "dur": 38.998, + "args": { + "External id": 708070,"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": 6305205572204.254, "dur": 20.383, + "args": { + "External id": 708071,"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": 6305205572230.333, "dur": 30.900, + "args": { + "External id": 708072,"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": 6305205572268.657, "dur": 27.422, + "args": { + "External id": 708073,"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": 6305205572302.041, "dur": 29.616, + "args": { + "External id": 708074,"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": 6305205572353.818, "dur": 25.362, + "args": { + "External id": 708075,"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": 6305205572395.834, "dur": 23.295, + "args": { + "External id": 708076,"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": 6305205572435.787, "dur": 31.595, + "args": { + "External id": 708077,"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": 6305205572496.353, "dur": 33.788, + "args": { + "External id": 708078,"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": 6305205572550.486, "dur": 17.757, + "args": { + "External id": 708079,"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": 6305205572646.085, "dur": 18.702, + "args": { + "External id": 708080,"Record function id": 0, "Ev Idx": 2031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205572652.789, "dur": 10.889, + "args": { + "External id": 708081,"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": 6305205572657.311, "dur": 5.558, + "args": { + "External id": 708082,"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": 6305205572658.810, "dur": 3.972, + "args": { + "External id": 708083,"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": 6305205572668.883, "dur": 4.545, + "args": { + "External id": 708084,"Record function id": 0, "Ev Idx": 2035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205572670.575, "dur": 2.351, + "args": { + "External id": 708085,"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": 6305205572671.180, "dur": 1.201, + "args": { + "External id": 708086,"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": 6305205572671.575, "dur": 0.718, + "args": { + "External id": 708087,"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": 6305205572676.777, "dur": 6.939, + "args": { + "External id": 708088,"Record function id": 0, "Ev Idx": 2039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205572678.106, "dur": 5.131, + "args": { + "External id": 708089,"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": 6305205572678.848, "dur": 3.998, + "args": { + "External id": 708090,"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": 6305205572679.482, "dur": 3.273, + "args": { + "External id": 708091,"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": 6305205572686.991, "dur": 3.835, + "args": { + "External id": 708092,"Record function id": 0, "Ev Idx": 2043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205572688.231, "dur": 2.171, + "args": { + "External id": 708093,"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": 6305205572688.717, "dur": 1.302, + "args": { + "External id": 708094,"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": 6305205572689.049, "dur": 0.860, + "args": { + "External id": 708095,"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": 6305205572693.982, "dur": 42.357, + "args": { + "External id": 708096,"Record function id": 0, "Ev Idx": 2047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205572733.367, "dur": 2.508, + "args": { + "External id": 708097,"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": 6305205572734.136, "dur": 1.219, + "args": { + "External id": 708098,"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": 6305205572734.423, "dur": 0.858, + "args": { + "External id": 708099,"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": 6305205572739.681, "dur": 12.012, + "args": { + "External id": 708100,"Record function id": 0, "Ev Idx": 2051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205572746.990, "dur": 4.260, + "args": { + "External id": 708101,"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": 6305205572747.507, "dur": 3.255, + "args": { + "External id": 708102,"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": 6305205572750.019, "dur": 0.647, + "args": { + "External id": 708103,"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": 6305205572756.051, "dur": 4.224, + "args": { + "External id": 708104,"Record function id": 0, "Ev Idx": 2055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205572757.578, "dur": 2.282, + "args": { + "External id": 708105,"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": 6305205572758.238, "dur": 1.202, + "args": { + "External id": 708106,"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": 6305205572758.716, "dur": 0.647, + "args": { + "External id": 708107,"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": 6305205572763.453, "dur": 3.508, + "args": { + "External id": 708108,"Record function id": 0, "Ev Idx": 2059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205572764.637, "dur": 1.913, + "args": { + "External id": 708109,"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": 6305205572765.136, "dur": 0.996, + "args": { + "External id": 708110,"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": 6305205572765.395, "dur": 0.660, + "args": { + "External id": 708111,"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": 6305205572770.130, "dur": 3.542, + "args": { + "External id": 708112,"Record function id": 0, "Ev Idx": 2063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205572771.239, "dur": 2.024, + "args": { + "External id": 708113,"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": 6305205572771.723, "dur": 1.123, + "args": { + "External id": 708114,"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": 6305205572772.200, "dur": 0.572, + "args": { + "External id": 708115,"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": 6305205572777.476, "dur": 69566.561, + "args": { + "External id": 708116,"Record function id": 0, "Sequence number": 7674437, "Fwd thread id": 1, "Ev Idx": 2067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305205572781.402, "dur": 69552.896, + "args": { + "External id": 708117,"Sequence number": 7674437, "Fwd thread 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": 6305205572781.402, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.23)", "pid": 2338707, "tid": 2379456, + "ts": 6305205572814.135, "dur": 39.812, + "args": { + "External id": 708118,"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": 6305205572862.019, "dur": 64.837, + "args": { + "External id": 708119,"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": 6305205572932.409, "dur": 69393.246, + "args": { + "External id": 708120,"Record function id": 0, "Ev Idx": 2071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305205573024.518, "dur": 7.621, + "args": { + "External id": 708121,"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": 6305205573042.170, "dur": 6.719, + "args": { + "External id": 708122,"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": 6305205573104.469, "dur": 68346.604, + "args": { + "External id": 708123,"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": 6305205573119.462, "dur": 68318.138, + "args": { + "External id": 708124,"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": 6305205573218.959, "dur": 18.986, + "args": { + "External id": 708125,"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": 6305205573258.452, "dur": 68133.267, + "args": { + "External id": 708126,"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": 6305205573261.628, "dur": 68128.844, + "args": { + "External id": 708127,"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": 6305205573266.482, "dur": 12.461, + "args": { + "External id": 708128,"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": 6305205573281.031, "dur": 68103.661, + "args": { + "External id": 708129,"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": 6305205641575.313, "dur": 13.251, + "args": { + "External id": 708130,"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": 6305205641578.924, "dur": 9.056, + "args": { + "External id": 708131,"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": 6305205641618.905, "dur": 356.713, + "args": { + "External id": 708132,"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": 6305205641654.560, "dur": 315.967, + "args": { + "External id": 708133,"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": 6305205641668.107, "dur": 297.141, + "args": { + "External id": 708134,"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": 6305205642000.541, "dur": 2.172, + "args": { + "External id": 708135,"Record function id": 0, "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": 6305205642095.039, "dur": 7.287, + "args": { + "External id": 708136,"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": 6305205642152.237, "dur": 1.450, + "args": { + "External id": 708137,"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": 6305205642170.997, "dur": 4.144, + "args": { + "External id": 708138,"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": 6305205642188.375, "dur": 1.345, + "args": { + "External id": 708139,"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": 6305205642203.238, "dur": 1.086, + "args": { + "External id": 708140,"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": 6305205642217.548, "dur": 1.463, + "args": { + "External id": 708141,"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": 6305205642230.260, "dur": 3.175, + "args": { + "External id": 708142,"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": 6305205642244.806, "dur": 3.021, + "args": { + "External id": 708143,"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": 6305205642260.936, "dur": 0.852, + "args": { + "External id": 708144,"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": 6305205642360.075, "dur": 2961.414, + "args": { + "External id": 708145,"Record function id": 0, "Ev Idx": 2096 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.22)", "pid": 2338707, "tid": 2379456, + "ts": 6305205642379.555, "dur": 1098.944, + "args": { + "External id": 708146,"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": 6305205642393.684, "dur": 364.447, + "args": { + "External id": 708147,"Record function id": 0, "Ev Idx": 2098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6305205642476.791, "dur": 4.287, + "args": { + "External id": 708148,"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": 6305205642484.028, "dur": 0.879, + "args": { + "External id": 708149,"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": 6305205642486.790, "dur": 2.986, + "args": { + "External id": 708150,"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": 6305205642491.754, "dur": 1.073, + "args": { + "External id": 708151,"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": 6305205642494.240, "dur": 0.924, + "args": { + "External id": 708152,"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": 6305205642496.874, "dur": 0.663, + "args": { + "External id": 708153,"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": 6305205642499.186, "dur": 2.272, + "args": { + "External id": 708154,"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": 6305205642519.345, "dur": 1.683, + "args": { + "External id": 708155,"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": 6305205642525.049, "dur": 0.747, + "args": { + "External id": 708156,"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": 6305205642527.238, "dur": 0.710, + "args": { + "External id": 708157,"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": 6305205642546.363, "dur": 177.600, + "args": { + "External id": 708158,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305205642563.203, "dur": 155.647, + "args": { + "External id": 708159,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305205642599.062, "dur": 17.210, + "args": { + "External id": 708160,"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": 6305205642620.056, "dur": 70.750, + "args": { + "External id": 708161,"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": 6305205642624.530, "dur": 65.919, + "args": { + "External id": 708162,"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": 6305205642628.650, "dur": 8.087, + "args": { + "External id": 708163,"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": 6305205642638.309, "dur": 51.522, + "args": { + "External id": 708164,"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": 6305205642839.255, "dur": 631.317, + "args": { + "External id": 708165,"Record function id": 0, "Ev Idx": 2116 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.21)", "pid": 2338707, "tid": 2379456, + "ts": 6305205642855.456, "dur": 602.481, + "args": { + "External id": 708166,"Record function id": 0, "Ev Idx": 2117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305205642912.224, "dur": 4.952, + "args": { + "External id": 708167,"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": 6305205642932.536, "dur": 36.775, + "args": { + "External id": 708168,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205642937.828, "dur": 1.863, + "args": { + "External id": 708169,"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": 6305205642943.644, "dur": 0.291, + "args": { + "External id": 708170,"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": 6305205642945.491, "dur": 0.362, + "args": { + "External id": 708171,"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": 6305205642947.444, "dur": 0.613, + "args": { + "External id": 708172,"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": 6305205642951.715, "dur": 0.485, + "args": { + "External id": 708173,"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": 6305205642953.769, "dur": 2.752, + "args": { + "External id": 708174,"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": 6305205642957.867, "dur": 2.406, + "args": { + "External id": 708175,"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": 6305205642962.198, "dur": 0.543, + "args": { + "External id": 708176,"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": 6305205642964.034, "dur": 0.270, + "args": { + "External id": 708177,"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": 6305205642980.176, "dur": 39.711, + "args": { + "External id": 708178,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305205643049.674, "dur": 161.889, + "args": { + "External id": 708179,"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": 6305205643097.105, "dur": 5.435, + "args": { + "External id": 708180,"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": 6305205643108.171, "dur": 11.790, + "args": { + "External id": 708181,"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": 6305205643112.805, "dur": 6.774, + "args": { + "External id": 708182,"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": 6305205643117.165, "dur": 0.820, + "args": { + "External id": 708183,"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": 6305205643126.737, "dur": 29.918, + "args": { + "External id": 708184,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205643129.339, "dur": 2.120, + "args": { + "External id": 708185,"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": 6305205643132.902, "dur": 0.307, + "args": { + "External id": 708186,"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": 6305205643134.382, "dur": 2.349, + "args": { + "External id": 708187,"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": 6305205643139.497, "dur": 0.412, + "args": { + "External id": 708188,"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": 6305205643141.307, "dur": 0.605, + "args": { + "External id": 708189,"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": 6305205643143.306, "dur": 0.492, + "args": { + "External id": 708190,"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": 6305205643146.197, "dur": 0.570, + "args": { + "External id": 708191,"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": 6305205643148.203, "dur": 0.388, + "args": { + "External id": 708192,"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": 6305205643150.025, "dur": 1.869, + "args": { + "External id": 708193,"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": 6305205643171.279, "dur": 31.930, + "args": { + "External id": 708194,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305205643260.504, "dur": 123.242, + "args": { + "External id": 708195,"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": 6305205643290.171, "dur": 90.163, + "args": { + "External id": 708196,"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": 6305205643302.447, "dur": 73.284, + "args": { + "External id": 708197,"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": 6305205643402.339, "dur": 2.093, + "args": { + "External id": 708198,"Record function id": 0, "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": 6305205643486.120, "dur": 1809.618, + "args": { + "External id": 708199,"Sequence number": 7674436, "Fwd thread 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": 6305205643486.120, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6305205643614.793, "dur": 113.721, + "args": { + "External id": 708200,"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": 6305205643771.273, "dur": 38.265, + "args": { + "External id": 708201,"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": 6305205643825.588, "dur": 51.844, + "args": { + "External id": 708202,"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": 6305205643900.851, "dur": 32.452, + "args": { + "External id": 708203,"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": 6305205643940.216, "dur": 32.638, + "args": { + "External id": 708204,"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": 6305205643979.181, "dur": 28.247, + "args": { + "External id": 708205,"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": 6305205644015.061, "dur": 29.357, + "args": { + "External id": 708206,"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": 6305205644118.219, "dur": 26.546, + "args": { + "External id": 708207,"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": 6305205644167.662, "dur": 27.192, + "args": { + "External id": 708208,"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": 6305205644219.248, "dur": 20.882, + "args": { + "External id": 708209,"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": 6305205644254.090, "dur": 14.771, + "args": { + "External id": 708210,"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": 6305205644278.404, "dur": 41.296, + "args": { + "External id": 708211,"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": 6305205644324.102, "dur": 33.038, + "args": { + "External id": 708212,"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": 6305205644386.406, "dur": 276.772, + "args": { + "External id": 708213,"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": 6305205644468.423, "dur": 6.939, + "args": { + "External id": 708214,"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": 6305205644477.252, "dur": 3.724, + "args": { + "External id": 708215,"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": 6305205644482.017, "dur": 3.592, + "args": { + "External id": 708216,"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": 6305205644486.625, "dur": 1.590, + "args": { + "External id": 708217,"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": 6305205644549.709, "dur": 8.370, + "args": { + "External id": 708218,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205644554.336, "dur": 3.339, + "args": { + "External id": 708219,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205644560.133, "dur": 36.139, + "args": { + "External id": 708220,"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": 6305205644566.321, "dur": 4.106, + "args": { + "External id": 708221,"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": 6305205644597.820, "dur": 2.210, + "args": { + "External id": 708222,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205644599.225, "dur": 0.744, + "args": { + "External id": 708223,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205644601.256, "dur": 16.008, + "args": { + "External id": 708224,"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": 6305205644603.179, "dur": 0.750, + "args": { + "External id": 708225,"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": 6305205644701.803, "dur": 28.353, + "args": { + "External id": 708226,"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": 6305205644749.503, "dur": 17.548, + "args": { + "External id": 708227,"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": 6305205644774.355, "dur": 46.524, + "args": { + "External id": 708228,"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": 6305205644827.477, "dur": 38.527, + "args": { + "External id": 708229,"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": 6305205644876.210, "dur": 19.903, + "args": { + "External id": 708230,"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": 6305205644901.689, "dur": 30.583, + "args": { + "External id": 708231,"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": 6305205644939.272, "dur": 28.280, + "args": { + "External id": 708232,"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": 6305205644976.076, "dur": 29.969, + "args": { + "External id": 708233,"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": 6305205645026.760, "dur": 20.791, + "args": { + "External id": 708234,"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": 6305205645103.245, "dur": 35.479, + "args": { + "External id": 708235,"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": 6305205645167.617, "dur": 24.968, + "args": { + "External id": 708236,"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": 6305205645214.241, "dur": 13.599, + "args": { + "External id": 708237,"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": 6305205645244.565, "dur": 19.759, + "args": { + "External id": 708238,"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": 6305205645344.712, "dur": 15.720, + "args": { + "External id": 708239,"Record function id": 0, "Ev Idx": 2190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205645348.342, "dur": 11.109, + "args": { + "External id": 708240,"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": 6305205645352.815, "dur": 5.767, + "args": { + "External id": 708241,"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": 6305205645354.469, "dur": 4.023, + "args": { + "External id": 708242,"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": 6305205645364.457, "dur": 5.417, + "args": { + "External id": 708243,"Record function id": 0, "Ev Idx": 2194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205645366.230, "dur": 3.161, + "args": { + "External id": 708244,"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": 6305205645367.036, "dur": 1.892, + "args": { + "External id": 708245,"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": 6305205645367.871, "dur": 0.969, + "args": { + "External id": 708246,"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": 6305205645373.208, "dur": 6.944, + "args": { + "External id": 708247,"Record function id": 0, "Ev Idx": 2198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205645374.668, "dur": 5.064, + "args": { + "External id": 708248,"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": 6305205645375.454, "dur": 3.878, + "args": { + "External id": 708249,"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": 6305205645376.154, "dur": 3.072, + "args": { + "External id": 708250,"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": 6305205645383.525, "dur": 4.711, + "args": { + "External id": 708251,"Record function id": 0, "Ev Idx": 2202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205645384.965, "dur": 2.867, + "args": { + "External id": 708252,"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": 6305205645385.751, "dur": 1.690, + "args": { + "External id": 708253,"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": 6305205645386.567, "dur": 0.798, + "args": { + "External id": 708254,"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": 6305205645391.352, "dur": 4.393, + "args": { + "External id": 708255,"Record function id": 0, "Ev Idx": 2206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205645392.925, "dur": 2.414, + "args": { + "External id": 708256,"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": 6305205645393.664, "dur": 1.281, + "args": { + "External id": 708257,"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": 6305205645394.068, "dur": 0.816, + "args": { + "External id": 708258,"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": 6305205645398.932, "dur": 4.138, + "args": { + "External id": 708259,"Record function id": 0, "Ev Idx": 2210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205645400.286, "dur": 2.374, + "args": { + "External id": 708260,"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": 6305205645400.956, "dur": 1.302, + "args": { + "External id": 708261,"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": 6305205645401.637, "dur": 0.546, + "args": { + "External id": 708262,"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": 6305205645406.354, "dur": 4.214, + "args": { + "External id": 708263,"Record function id": 0, "Ev Idx": 2214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205645407.708, "dur": 2.436, + "args": { + "External id": 708264,"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": 6305205645408.612, "dur": 1.117, + "args": { + "External id": 708265,"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": 6305205645408.895, "dur": 0.768, + "args": { + "External id": 708266,"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": 6305205645413.825, "dur": 5.445, + "args": { + "External id": 708267,"Record function id": 0, "Ev Idx": 2218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205645415.025, "dur": 3.838, + "args": { + "External id": 708268,"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": 6305205645415.552, "dur": 2.919, + "args": { + "External id": 708269,"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": 6305205645417.692, "dur": 0.718, + "args": { + "External id": 708270,"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": 6305205645423.799, "dur": 4.122, + "args": { + "External id": 708271,"Record function id": 0, "Ev Idx": 2222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205645425.008, "dur": 2.517, + "args": { + "External id": 708272,"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": 6305205645425.828, "dur": 1.289, + "args": { + "External id": 708273,"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": 6305205645426.250, "dur": 0.800, + "args": { + "External id": 708274,"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": 6305205645431.699, "dur": 64514.428, + "args": { + "External id": 708275,"Record function id": 0, "Sequence number": 7674435, "Fwd thread id": 1, "Ev Idx": 2226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305205645432.974, "dur": 64504.296, + "args": { + "External id": 708276,"Sequence number": 7674435, "Fwd thread 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": 6305205645432.974, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.22)", "pid": 2338707, "tid": 2379456, + "ts": 6305205645462.728, "dur": 40.671, + "args": { + "External id": 708277,"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": 6305205645528.819, "dur": 67.247, + "args": { + "External id": 708278,"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": 6305205645601.750, "dur": 64327.577, + "args": { + "External id": 708279,"Record function id": 0, "Ev Idx": 2230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305205645693.458, "dur": 7.683, + "args": { + "External id": 708280,"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": 6305205645712.341, "dur": 7.512, + "args": { + "External id": 708281,"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": 6305205645737.019, "dur": 63294.972, + "args": { + "External id": 708282,"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": 6305205645752.913, "dur": 63265.811, + "args": { + "External id": 708283,"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": 6305205645852.028, "dur": 17.904, + "args": { + "External id": 708284,"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": 6305205645889.833, "dur": 63083.064, + "args": { + "External id": 708285,"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": 6305205645892.627, "dur": 63079.116, + "args": { + "External id": 708286,"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": 6305205645897.674, "dur": 10.885, + "args": { + "External id": 708287,"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": 6305205645910.731, "dur": 63055.984, + "args": { + "External id": 708288,"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": 6305205709166.532, "dur": 12.856, + "args": { + "External id": 708289,"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": 6305205709170.261, "dur": 8.490, + "args": { + "External id": 708290,"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": 6305205709210.140, "dur": 396.573, + "args": { + "External id": 708291,"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": 6305205709245.077, "dur": 356.066, + "args": { + "External id": 708292,"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": 6305205709259.135, "dur": 336.130, + "args": { + "External id": 708293,"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": 6305205709635.054, "dur": 2.574, + "args": { + "External id": 708294,"Record function id": 0, "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": 6305205709702.211, "dur": 7.070, + "args": { + "External id": 708295,"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": 6305205709758.549, "dur": 1.382, + "args": { + "External id": 708296,"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": 6305205709777.249, "dur": 3.299, + "args": { + "External id": 708297,"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": 6305205709793.952, "dur": 1.245, + "args": { + "External id": 708298,"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": 6305205709808.353, "dur": 0.968, + "args": { + "External id": 708299,"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": 6305205709821.543, "dur": 0.751, + "args": { + "External id": 708300,"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": 6305205709834.168, "dur": 3.223, + "args": { + "External id": 708301,"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": 6305205709848.868, "dur": 3.040, + "args": { + "External id": 708302,"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": 6305205709864.610, "dur": 1.090, + "args": { + "External id": 708303,"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": 6305205709961.009, "dur": 3014.330, + "args": { + "External id": 708304,"Record function id": 0, "Ev Idx": 2255 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.21)", "pid": 2338707, "tid": 2379456, + "ts": 6305205709984.326, "dur": 1163.923, + "args": { + "External id": 708305,"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": 6305205709998.522, "dur": 400.283, + "args": { + "External id": 708306,"Record function id": 0, "Ev Idx": 2257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6305205710129.300, "dur": 5.227, + "args": { + "External id": 708307,"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": 6305205710138.566, "dur": 1.023, + "args": { + "External id": 708308,"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": 6305205710141.947, "dur": 2.925, + "args": { + "External id": 708309,"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": 6305205710147.129, "dur": 0.652, + "args": { + "External id": 708310,"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": 6305205710149.436, "dur": 0.967, + "args": { + "External id": 708311,"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": 6305205710151.976, "dur": 1.189, + "args": { + "External id": 708312,"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": 6305205710154.813, "dur": 2.433, + "args": { + "External id": 708313,"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": 6305205710160.878, "dur": 0.873, + "args": { + "External id": 708314,"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": 6305205710163.256, "dur": 0.855, + "args": { + "External id": 708315,"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": 6305205710165.348, "dur": 0.968, + "args": { + "External id": 708316,"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": 6305205710184.320, "dur": 179.964, + "args": { + "External id": 708317,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305205710201.001, "dur": 158.330, + "args": { + "External id": 708318,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305205710237.523, "dur": 17.814, + "args": { + "External id": 708319,"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": 6305205710258.825, "dur": 71.477, + "args": { + "External id": 708320,"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": 6305205710262.118, "dur": 67.781, + "args": { + "External id": 708321,"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": 6305205710268.034, "dur": 6.821, + "args": { + "External id": 708322,"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": 6305205710276.453, "dur": 52.672, + "args": { + "External id": 708323,"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": 6305205710483.742, "dur": 656.575, + "args": { + "External id": 708324,"Record function id": 0, "Ev Idx": 2275 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.20)", "pid": 2338707, "tid": 2379456, + "ts": 6305205710501.114, "dur": 624.830, + "args": { + "External id": 708325,"Record function id": 0, "Ev Idx": 2276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305205710578.672, "dur": 6.358, + "args": { + "External id": 708326,"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": 6305205710601.454, "dur": 34.817, + "args": { + "External id": 708327,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205710606.569, "dur": 1.871, + "args": { + "External id": 708328,"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": 6305205710610.766, "dur": 2.374, + "args": { + "External id": 708329,"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": 6305205710614.798, "dur": 0.525, + "args": { + "External id": 708330,"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": 6305205710616.877, "dur": 0.511, + "args": { + "External id": 708331,"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": 6305205710620.356, "dur": 0.365, + "args": { + "External id": 708332,"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": 6305205710622.069, "dur": 2.266, + "args": { + "External id": 708333,"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": 6305205710625.566, "dur": 0.600, + "args": { + "External id": 708334,"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": 6305205710628.691, "dur": 0.362, + "args": { + "External id": 708335,"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": 6305205710630.472, "dur": 0.460, + "args": { + "External id": 708336,"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": 6305205710647.273, "dur": 44.067, + "args": { + "External id": 708337,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305205710725.162, "dur": 116.669, + "args": { + "External id": 708338,"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": 6305205710736.120, "dur": 3.697, + "args": { + "External id": 708339,"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": 6305205710745.144, "dur": 10.803, + "args": { + "External id": 708340,"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": 6305205710749.339, "dur": 6.214, + "args": { + "External id": 708341,"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": 6305205710753.622, "dur": 0.734, + "args": { + "External id": 708342,"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": 6305205710762.714, "dur": 31.308, + "args": { + "External id": 708343,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205710764.994, "dur": 0.637, + "args": { + "External id": 708344,"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": 6305205710769.129, "dur": 0.547, + "args": { + "External id": 708345,"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": 6305205710771.044, "dur": 3.148, + "args": { + "External id": 708346,"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": 6305205710775.900, "dur": 2.328, + "args": { + "External id": 708347,"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": 6305205710779.444, "dur": 0.643, + "args": { + "External id": 708348,"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": 6305205710781.224, "dur": 0.461, + "args": { + "External id": 708349,"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": 6305205710784.713, "dur": 0.288, + "args": { + "External id": 708350,"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": 6305205710786.395, "dur": 0.574, + "args": { + "External id": 708351,"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": 6305205710788.378, "dur": 0.752, + "args": { + "External id": 708352,"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": 6305205710803.871, "dur": 30.041, + "args": { + "External id": 708353,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305205710887.593, "dur": 125.932, + "args": { + "External id": 708354,"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": 6305205710917.647, "dur": 92.332, + "args": { + "External id": 708355,"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": 6305205710929.100, "dur": 76.569, + "args": { + "External id": 708356,"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": 6305205711031.688, "dur": 2.137, + "args": { + "External id": 708357,"Record function id": 0, "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": 6305205711156.392, "dur": 1796.946, + "args": { + "External id": 708358,"Sequence number": 7674434, "Fwd thread 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": 6305205711156.392, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6305205711265.880, "dur": 111.366, + "args": { + "External id": 708359,"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": 6305205711420.076, "dur": 38.124, + "args": { + "External id": 708360,"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": 6305205711475.099, "dur": 69.077, + "args": { + "External id": 708361,"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": 6305205711560.124, "dur": 35.690, + "args": { + "External id": 708362,"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": 6305205711601.940, "dur": 32.287, + "args": { + "External id": 708363,"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": 6305205711644.114, "dur": 27.396, + "args": { + "External id": 708364,"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": 6305205711678.688, "dur": 31.044, + "args": { + "External id": 708365,"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": 6305205711740.285, "dur": 24.506, + "args": { + "External id": 708366,"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": 6305205711783.204, "dur": 27.152, + "args": { + "External id": 708367,"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": 6305205711834.535, "dur": 18.787, + "args": { + "External id": 708368,"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": 6305205711865.625, "dur": 16.066, + "args": { + "External id": 708369,"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": 6305205711888.759, "dur": 36.612, + "args": { + "External id": 708370,"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": 6305205711928.790, "dur": 32.984, + "args": { + "External id": 708371,"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": 6305205711994.141, "dur": 301.016, + "args": { + "External id": 708372,"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": 6305205712113.269, "dur": 6.986, + "args": { + "External id": 708373,"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": 6305205712122.483, "dur": 2.142, + "args": { + "External id": 708374,"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": 6305205712125.718, "dur": 3.450, + "args": { + "External id": 708375,"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": 6305205712130.368, "dur": 1.447, + "args": { + "External id": 708376,"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": 6305205712181.792, "dur": 7.630, + "args": { + "External id": 708377,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205712186.504, "dur": 2.712, + "args": { + "External id": 708378,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205712191.316, "dur": 36.591, + "args": { + "External id": 708379,"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": 6305205712197.136, "dur": 3.720, + "args": { + "External id": 708380,"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": 6305205712229.556, "dur": 2.008, + "args": { + "External id": 708381,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205712230.932, "dur": 0.529, + "args": { + "External id": 708382,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205712232.683, "dur": 16.529, + "args": { + "External id": 708383,"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": 6305205712234.928, "dur": 0.683, + "args": { + "External id": 708384,"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": 6305205712337.661, "dur": 30.066, + "args": { + "External id": 708385,"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": 6305205712390.863, "dur": 18.771, + "args": { + "External id": 708386,"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": 6305205712417.880, "dur": 52.378, + "args": { + "External id": 708387,"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": 6305205712477.316, "dur": 59.076, + "args": { + "External id": 708388,"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": 6305205712550.738, "dur": 25.703, + "args": { + "External id": 708389,"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": 6305205712582.430, "dur": 32.773, + "args": { + "External id": 708390,"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": 6305205712622.418, "dur": 27.366, + "args": { + "External id": 708391,"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": 6305205712655.622, "dur": 30.778, + "args": { + "External id": 708392,"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": 6305205712723.532, "dur": 35.800, + "args": { + "External id": 708393,"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": 6305205712788.147, "dur": 25.017, + "args": { + "External id": 708394,"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": 6305205712835.712, "dur": 17.980, + "args": { + "External id": 708395,"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": 6305205712871.241, "dur": 15.171, + "args": { + "External id": 708396,"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": 6305205712906.880, "dur": 16.684, + "args": { + "External id": 708397,"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": 6305205712998.882, "dur": 18.586, + "args": { + "External id": 708398,"Record function id": 0, "Ev Idx": 2349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205713002.613, "dur": 13.868, + "args": { + "External id": 708399,"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": 6305205713007.221, "dur": 8.261, + "args": { + "External id": 708400,"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": 6305205713008.970, "dur": 6.362, + "args": { + "External id": 708401,"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": 6305205713021.558, "dur": 5.468, + "args": { + "External id": 708402,"Record function id": 0, "Ev Idx": 2353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205713023.151, "dur": 3.411, + "args": { + "External id": 708403,"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": 6305205713024.054, "dur": 1.923, + "args": { + "External id": 708404,"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": 6305205713024.830, "dur": 1.057, + "args": { + "External id": 708405,"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": 6305205713030.458, "dur": 6.520, + "args": { + "External id": 708406,"Record function id": 0, "Ev Idx": 2357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205713031.897, "dur": 4.650, + "args": { + "External id": 708407,"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": 6305205713032.577, "dur": 3.546, + "args": { + "External id": 708408,"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": 6305205713033.226, "dur": 2.791, + "args": { + "External id": 708409,"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": 6305205713040.299, "dur": 3.813, + "args": { + "External id": 708410,"Record function id": 0, "Ev Idx": 2361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205713041.666, "dur": 2.026, + "args": { + "External id": 708411,"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": 6305205713042.238, "dur": 1.024, + "args": { + "External id": 708412,"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": 6305205713042.521, "dur": 0.664, + "args": { + "External id": 708413,"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": 6305205713047.285, "dur": 3.687, + "args": { + "External id": 708414,"Record function id": 0, "Ev Idx": 2365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205713048.525, "dur": 2.042, + "args": { + "External id": 708415,"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": 6305205713048.994, "dur": 1.153, + "args": { + "External id": 708416,"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": 6305205713049.485, "dur": 0.596, + "args": { + "External id": 708417,"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": 6305205713095.501, "dur": 6.624, + "args": { + "External id": 708418,"Record function id": 0, "Ev Idx": 2369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205713097.393, "dur": 4.097, + "args": { + "External id": 708419,"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": 6305205713098.410, "dur": 2.138, + "args": { + "External id": 708420,"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": 6305205713099.026, "dur": 1.348, + "args": { + "External id": 708421,"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": 6305205713105.539, "dur": 4.200, + "args": { + "External id": 708422,"Record function id": 0, "Ev Idx": 2373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205713106.883, "dur": 2.429, + "args": { + "External id": 708423,"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": 6305205713107.423, "dur": 1.451, + "args": { + "External id": 708424,"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": 6305205713107.980, "dur": 0.828, + "args": { + "External id": 708425,"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": 6305205713112.921, "dur": 6.498, + "args": { + "External id": 708426,"Record function id": 0, "Ev Idx": 2377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205713114.320, "dur": 4.711, + "args": { + "External id": 708427,"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": 6305205713115.125, "dur": 3.463, + "args": { + "External id": 708428,"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": 6305205713117.857, "dur": 0.633, + "args": { + "External id": 708429,"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": 6305205713123.474, "dur": 4.669, + "args": { + "External id": 708430,"Record function id": 0, "Ev Idx": 2381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205713124.976, "dur": 2.769, + "args": { + "External id": 708431,"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": 6305205713125.885, "dur": 1.427, + "args": { + "External id": 708432,"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": 6305205713126.614, "dur": 0.609, + "args": { + "External id": 708433,"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": 6305205713131.819, "dur": 65517.672, + "args": { + "External id": 708434,"Record function id": 0, "Sequence number": 7674433, "Fwd thread id": 1, "Ev Idx": 2385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305205713133.125, "dur": 65506.464, + "args": { + "External id": 708435,"Sequence number": 7674433, "Fwd thread 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": 6305205713133.125, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.21)", "pid": 2338707, "tid": 2379456, + "ts": 6305205713166.870, "dur": 42.045, + "args": { + "External id": 708436,"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": 6305205713216.847, "dur": 64.622, + "args": { + "External id": 708437,"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": 6305205713287.053, "dur": 65344.308, + "args": { + "External id": 708438,"Record function id": 0, "Ev Idx": 2389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305205713377.380, "dur": 7.746, + "args": { + "External id": 708439,"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": 6305205713395.116, "dur": 6.950, + "args": { + "External id": 708440,"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": 6305205713417.499, "dur": 64233.873, + "args": { + "External id": 708441,"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": 6305205713434.114, "dur": 64203.681, + "args": { + "External id": 708442,"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": 6305205713542.753, "dur": 19.742, + "args": { + "External id": 708443,"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": 6305205713583.217, "dur": 64011.802, + "args": { + "External id": 708444,"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": 6305205713589.373, "dur": 64004.523, + "args": { + "External id": 708445,"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": 6305205713593.910, "dur": 13.661, + "args": { + "External id": 708446,"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": 6305205713610.140, "dur": 63978.776, + "args": { + "External id": 708447,"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": 6305205777756.904, "dur": 12.628, + "args": { + "External id": 708448,"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": 6305205777760.737, "dur": 8.384, + "args": { + "External id": 708449,"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": 6305205777802.222, "dur": 470.648, + "args": { + "External id": 708450,"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": 6305205777836.393, "dur": 430.413, + "args": { + "External id": 708451,"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": 6305205777849.550, "dur": 410.855, + "args": { + "External id": 708452,"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": 6305205778308.260, "dur": 2.680, + "args": { + "External id": 708453,"Record function id": 0, "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": 6305205778380.717, "dur": 7.343, + "args": { + "External id": 708454,"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": 6305205778440.206, "dur": 1.588, + "args": { + "External id": 708455,"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": 6305205778459.260, "dur": 4.304, + "args": { + "External id": 708456,"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": 6305205778476.851, "dur": 1.219, + "args": { + "External id": 708457,"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": 6305205778490.465, "dur": 1.094, + "args": { + "External id": 708458,"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": 6305205778503.307, "dur": 0.884, + "args": { + "External id": 708459,"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": 6305205778535.311, "dur": 3.513, + "args": { + "External id": 708460,"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": 6305205778550.915, "dur": 2.747, + "args": { + "External id": 708461,"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": 6305205778567.073, "dur": 0.887, + "args": { + "External id": 708462,"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": 6305205778666.516, "dur": 3044.681, + "args": { + "External id": 708463,"Record function id": 0, "Ev Idx": 2414 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.20)", "pid": 2338707, "tid": 2379456, + "ts": 6305205778685.485, "dur": 1126.610, + "args": { + "External id": 708464,"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": 6305205778701.385, "dur": 344.106, + "args": { + "External id": 708465,"Record function id": 0, "Ev Idx": 2416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6305205778787.091, "dur": 4.188, + "args": { + "External id": 708466,"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": 6305205778794.759, "dur": 0.901, + "args": { + "External id": 708467,"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": 6305205778797.646, "dur": 3.334, + "args": { + "External id": 708468,"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": 6305205778802.862, "dur": 1.149, + "args": { + "External id": 708469,"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": 6305205778805.376, "dur": 0.931, + "args": { + "External id": 708470,"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": 6305205778807.942, "dur": 0.907, + "args": { + "External id": 708471,"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": 6305205778810.347, "dur": 2.503, + "args": { + "External id": 708472,"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": 6305205778816.605, "dur": 0.834, + "args": { + "External id": 708473,"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": 6305205778818.894, "dur": 1.065, + "args": { + "External id": 708474,"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": 6305205778821.658, "dur": 0.810, + "args": { + "External id": 708475,"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": 6305205778840.086, "dur": 171.941, + "args": { + "External id": 708476,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305205778856.320, "dur": 150.952, + "args": { + "External id": 708477,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305205778888.434, "dur": 18.164, + "args": { + "External id": 708478,"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": 6305205778910.144, "dur": 66.347, + "args": { + "External id": 708479,"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": 6305205778912.993, "dur": 63.233, + "args": { + "External id": 708480,"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": 6305205778917.530, "dur": 6.363, + "args": { + "External id": 708481,"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": 6305205778925.540, "dur": 49.938, + "args": { + "External id": 708482,"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": 6305205779174.482, "dur": 629.131, + "args": { + "External id": 708483,"Record function id": 0, "Ev Idx": 2434 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.19)", "pid": 2338707, "tid": 2379456, + "ts": 6305205779191.382, "dur": 599.457, + "args": { + "External id": 708484,"Record function id": 0, "Ev Idx": 2435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305205779250.964, "dur": 6.863, + "args": { + "External id": 708485,"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": 6305205779273.492, "dur": 36.210, + "args": { + "External id": 708486,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205779279.053, "dur": 2.892, + "args": { + "External id": 708487,"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": 6305205779283.984, "dur": 0.596, + "args": { + "External id": 708488,"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": 6305205779286.276, "dur": 0.301, + "args": { + "External id": 708489,"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": 6305205779289.788, "dur": 0.417, + "args": { + "External id": 708490,"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": 6305205779291.527, "dur": 0.310, + "args": { + "External id": 708491,"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": 6305205779293.546, "dur": 2.536, + "args": { + "External id": 708492,"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": 6305205779298.905, "dur": 0.342, + "args": { + "External id": 708493,"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": 6305205779300.347, "dur": 0.526, + "args": { + "External id": 708494,"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": 6305205779302.275, "dur": 1.427, + "args": { + "External id": 708495,"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": 6305205779320.909, "dur": 50.453, + "args": { + "External id": 708496,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305205779402.629, "dur": 134.663, + "args": { + "External id": 708497,"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": 6305205779412.474, "dur": 3.678, + "args": { + "External id": 708498,"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": 6305205779421.451, "dur": 10.759, + "args": { + "External id": 708499,"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": 6305205779425.952, "dur": 5.859, + "args": { + "External id": 708500,"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": 6305205779429.867, "dur": 0.640, + "args": { + "External id": 708501,"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": 6305205779438.835, "dur": 28.079, + "args": { + "External id": 708502,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205779441.014, "dur": 0.595, + "args": { + "External id": 708503,"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": 6305205779443.245, "dur": 0.571, + "args": { + "External id": 708504,"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": 6305205779445.391, "dur": 3.156, + "args": { + "External id": 708505,"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": 6305205779450.053, "dur": 0.303, + "args": { + "External id": 708506,"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": 6305205779451.721, "dur": 0.425, + "args": { + "External id": 708507,"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": 6305205779454.669, "dur": 0.430, + "args": { + "External id": 708508,"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": 6305205779456.665, "dur": 0.633, + "args": { + "External id": 708509,"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": 6305205779458.565, "dur": 0.314, + "args": { + "External id": 708510,"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": 6305205779461.046, "dur": 0.456, + "args": { + "External id": 708511,"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": 6305205779479.364, "dur": 48.775, + "args": { + "External id": 708512,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305205779586.232, "dur": 125.163, + "args": { + "External id": 708513,"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": 6305205779616.942, "dur": 91.000, + "args": { + "External id": 708514,"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": 6305205779629.498, "dur": 73.231, + "args": { + "External id": 708515,"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": 6305205779731.109, "dur": 2.098, + "args": { + "External id": 708516,"Record function id": 0, "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": 6305205779819.898, "dur": 1868.503, + "args": { + "External id": 708517,"Sequence number": 7674432, "Fwd thread 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": 6305205779819.898, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6305205779934.642, "dur": 108.963, + "args": { + "External id": 708518,"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": 6305205780131.426, "dur": 41.039, + "args": { + "External id": 708519,"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": 6305205780191.035, "dur": 59.826, + "args": { + "External id": 708520,"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": 6305205780264.055, "dur": 32.341, + "args": { + "External id": 708521,"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": 6305205780303.285, "dur": 32.496, + "args": { + "External id": 708522,"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": 6305205780342.488, "dur": 27.887, + "args": { + "External id": 708523,"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": 6305205780378.353, "dur": 29.524, + "args": { + "External id": 708524,"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": 6305205780435.513, "dur": 24.121, + "args": { + "External id": 708525,"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": 6305205780477.718, "dur": 41.620, + "args": { + "External id": 708526,"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": 6305205780549.555, "dur": 21.092, + "args": { + "External id": 708527,"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": 6305205780585.452, "dur": 14.179, + "args": { + "External id": 708528,"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": 6305205780608.049, "dur": 43.738, + "args": { + "External id": 708529,"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": 6305205780655.268, "dur": 33.938, + "args": { + "External id": 708530,"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": 6305205780724.395, "dur": 257.545, + "args": { + "External id": 708531,"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": 6305205780808.319, "dur": 6.468, + "args": { + "External id": 708532,"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": 6305205780816.802, "dur": 3.045, + "args": { + "External id": 708533,"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": 6305205780821.194, "dur": 2.710, + "args": { + "External id": 708534,"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": 6305205780825.223, "dur": 2.421, + "args": { + "External id": 708535,"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": 6305205780872.101, "dur": 8.205, + "args": { + "External id": 708536,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205780877.463, "dur": 2.638, + "args": { + "External id": 708537,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205780882.543, "dur": 34.507, + "args": { + "External id": 708538,"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": 6305205780888.618, "dur": 4.280, + "args": { + "External id": 708539,"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": 6305205780918.391, "dur": 1.858, + "args": { + "External id": 708540,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205780919.519, "dur": 0.631, + "args": { + "External id": 708541,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205780921.705, "dur": 15.318, + "args": { + "External id": 708542,"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": 6305205780924.070, "dur": 0.622, + "args": { + "External id": 708543,"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": 6305205781018.270, "dur": 28.873, + "args": { + "External id": 708544,"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": 6305205781103.312, "dur": 22.293, + "args": { + "External id": 708545,"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": 6305205781135.669, "dur": 50.677, + "args": { + "External id": 708546,"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": 6305205781193.354, "dur": 40.660, + "args": { + "External id": 708547,"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": 6305205781244.692, "dur": 22.942, + "args": { + "External id": 708548,"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": 6305205781273.120, "dur": 46.914, + "args": { + "External id": 708549,"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": 6305205781336.369, "dur": 34.032, + "args": { + "External id": 708550,"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": 6305205781377.121, "dur": 31.474, + "args": { + "External id": 708551,"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": 6305205781437.649, "dur": 24.615, + "args": { + "External id": 708552,"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": 6305205781502.986, "dur": 43.935, + "args": { + "External id": 708553,"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": 6305205781569.410, "dur": 17.360, + "args": { + "External id": 708554,"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": 6305205781607.708, "dur": 16.914, + "args": { + "External id": 708555,"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": 6305205781640.111, "dur": 15.639, + "args": { + "External id": 708556,"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": 6305205781733.643, "dur": 16.383, + "args": { + "External id": 708557,"Record function id": 0, "Ev Idx": 2508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205781737.613, "dur": 11.486, + "args": { + "External id": 708558,"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": 6305205781742.123, "dur": 6.219, + "args": { + "External id": 708559,"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": 6305205781743.855, "dur": 4.380, + "args": { + "External id": 708560,"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": 6305205781754.052, "dur": 5.432, + "args": { + "External id": 708561,"Record function id": 0, "Ev Idx": 2512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205781755.848, "dur": 3.181, + "args": { + "External id": 708562,"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": 6305205781756.822, "dur": 1.767, + "args": { + "External id": 708563,"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": 6305205781757.359, "dur": 1.156, + "args": { + "External id": 708564,"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": 6305205781762.802, "dur": 7.921, + "args": { + "External id": 708565,"Record function id": 0, "Ev Idx": 2516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205781764.468, "dur": 5.831, + "args": { + "External id": 708566,"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": 6305205781764.950, "dur": 4.799, + "args": { + "External id": 708567,"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": 6305205781765.934, "dur": 3.727, + "args": { + "External id": 708568,"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": 6305205781774.081, "dur": 4.386, + "args": { + "External id": 708569,"Record function id": 0, "Ev Idx": 2520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205781775.848, "dur": 2.197, + "args": { + "External id": 708570,"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": 6305205781776.378, "dur": 1.250, + "args": { + "External id": 708571,"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": 6305205781776.839, "dur": 0.711, + "args": { + "External id": 708572,"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": 6305205781782.102, "dur": 4.174, + "args": { + "External id": 708573,"Record function id": 0, "Ev Idx": 2524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205781783.646, "dur": 2.215, + "args": { + "External id": 708574,"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": 6305205781784.402, "dur": 1.072, + "args": { + "External id": 708575,"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": 6305205781784.686, "dur": 0.720, + "args": { + "External id": 708576,"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": 6305205781789.779, "dur": 4.494, + "args": { + "External id": 708577,"Record function id": 0, "Ev Idx": 2528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205781791.295, "dur": 2.547, + "args": { + "External id": 708578,"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": 6305205781791.943, "dur": 1.517, + "args": { + "External id": 708579,"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": 6305205781792.724, "dur": 0.669, + "args": { + "External id": 708580,"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": 6305205781797.555, "dur": 5.152, + "args": { + "External id": 708581,"Record function id": 0, "Ev Idx": 2532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205781799.216, "dur": 3.077, + "args": { + "External id": 708582,"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": 6305205781800.382, "dur": 1.434, + "args": { + "External id": 708583,"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": 6305205781800.910, "dur": 0.822, + "args": { + "External id": 708584,"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": 6305205781806.279, "dur": 6.076, + "args": { + "External id": 708585,"Record function id": 0, "Ev Idx": 2536 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205781807.915, "dur": 4.035, + "args": { + "External id": 708586,"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": 6305205781808.372, "dur": 3.163, + "args": { + "External id": 708587,"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": 6305205781810.881, "dur": 0.588, + "args": { + "External id": 708588,"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": 6305205781815.868, "dur": 4.004, + "args": { + "External id": 708589,"Record function id": 0, "Ev Idx": 2540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205781817.529, "dur": 1.921, + "args": { + "External id": 708590,"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": 6305205781817.990, "dur": 1.071, + "args": { + "External id": 708591,"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": 6305205781818.268, "dur": 0.728, + "args": { + "External id": 708592,"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": 6305205781824.034, "dur": 62077.318, + "args": { + "External id": 708593,"Record function id": 0, "Sequence number": 7674431, "Fwd thread id": 1, "Ev Idx": 2544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305205781825.475, "dur": 62066.979, + "args": { + "External id": 708594,"Sequence number": 7674431, "Fwd thread 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": 6305205781825.475, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.20)", "pid": 2338707, "tid": 2379456, + "ts": 6305205781857.406, "dur": 39.996, + "args": { + "External id": 708595,"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": 6305205781905.186, "dur": 62.217, + "args": { + "External id": 708596,"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": 6305205781972.616, "dur": 61911.973, + "args": { + "External id": 708597,"Record function id": 0, "Ev Idx": 2548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305205782098.869, "dur": 9.067, + "args": { + "External id": 708598,"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": 6305205782120.875, "dur": 7.093, + "args": { + "External id": 708599,"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": 6305205782143.306, "dur": 60771.310, + "args": { + "External id": 708600,"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": 6305205782159.876, "dur": 60741.125, + "args": { + "External id": 708601,"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": 6305205782246.319, "dur": 17.083, + "args": { + "External id": 708602,"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": 6305205782286.504, "dur": 60567.670, + "args": { + "External id": 708603,"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": 6305205782289.153, "dur": 60563.761, + "args": { + "External id": 708604,"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": 6305205782295.565, "dur": 10.098, + "args": { + "External id": 708605,"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": 6305205782310.513, "dur": 60537.040, + "args": { + "External id": 708606,"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": 6305205843024.094, "dur": 16.942, + "args": { + "External id": 708607,"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": 6305205843027.673, "dur": 12.945, + "args": { + "External id": 708608,"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": 6305205843152.452, "dur": 407.497, + "args": { + "External id": 708609,"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": 6305205843188.400, "dur": 365.634, + "args": { + "External id": 708610,"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": 6305205843202.901, "dur": 345.247, + "args": { + "External id": 708611,"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": 6305205843585.089, "dur": 2.432, + "args": { + "External id": 708612,"Record function id": 0, "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": 6305205843657.690, "dur": 7.460, + "args": { + "External id": 708613,"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": 6305205843713.545, "dur": 1.581, + "args": { + "External id": 708614,"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": 6305205843732.091, "dur": 4.454, + "args": { + "External id": 708615,"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": 6305205843750.208, "dur": 0.879, + "args": { + "External id": 708616,"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": 6305205843765.558, "dur": 0.804, + "args": { + "External id": 708617,"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": 6305205843778.045, "dur": 0.830, + "args": { + "External id": 708618,"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": 6305205843790.985, "dur": 3.225, + "args": { + "External id": 708619,"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": 6305205843805.422, "dur": 2.788, + "args": { + "External id": 708620,"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": 6305205843819.282, "dur": 1.831, + "args": { + "External id": 708621,"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": 6305205843916.317, "dur": 3032.837, + "args": { + "External id": 708622,"Record function id": 0, "Ev Idx": 2573 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.19)", "pid": 2338707, "tid": 2379456, + "ts": 6305205843937.940, "dur": 1156.444, + "args": { + "External id": 708623,"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": 6305205843952.022, "dur": 389.723, + "args": { + "External id": 708624,"Record function id": 0, "Ev Idx": 2575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6305205844036.968, "dur": 4.202, + "args": { + "External id": 708625,"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": 6305205844044.352, "dur": 0.979, + "args": { + "External id": 708626,"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": 6305205844047.045, "dur": 3.003, + "args": { + "External id": 708627,"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": 6305205844051.941, "dur": 34.882, + "args": { + "External id": 708628,"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": 6305205844091.488, "dur": 1.075, + "args": { + "External id": 708629,"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": 6305205844093.998, "dur": 0.989, + "args": { + "External id": 708630,"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": 6305205844096.849, "dur": 2.965, + "args": { + "External id": 708631,"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": 6305205844103.500, "dur": 0.719, + "args": { + "External id": 708632,"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": 6305205844105.532, "dur": 0.738, + "args": { + "External id": 708633,"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": 6305205844107.617, "dur": 1.341, + "args": { + "External id": 708634,"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": 6305205844128.973, "dur": 178.305, + "args": { + "External id": 708635,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305205844145.128, "dur": 156.889, + "args": { + "External id": 708636,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305205844176.061, "dur": 18.334, + "args": { + "External id": 708637,"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": 6305205844200.483, "dur": 70.648, + "args": { + "External id": 708638,"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": 6305205844203.477, "dur": 67.238, + "args": { + "External id": 708639,"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": 6305205844207.861, "dur": 6.411, + "args": { + "External id": 708640,"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": 6305205844216.043, "dur": 53.790, + "args": { + "External id": 708641,"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": 6305205844428.454, "dur": 618.172, + "args": { + "External id": 708642,"Record function id": 0, "Ev Idx": 2593 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.18)", "pid": 2338707, "tid": 2379456, + "ts": 6305205844446.927, "dur": 584.174, + "args": { + "External id": 708643,"Record function id": 0, "Ev Idx": 2594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305205844521.651, "dur": 7.123, + "args": { + "External id": 708644,"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": 6305205844546.885, "dur": 34.294, + "args": { + "External id": 708645,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205844552.536, "dur": 1.953, + "args": { + "External id": 708646,"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": 6305205844556.988, "dur": 1.485, + "args": { + "External id": 708647,"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": 6305205844560.477, "dur": 0.338, + "args": { + "External id": 708648,"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": 6305205844562.253, "dur": 0.337, + "args": { + "External id": 708649,"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": 6305205844565.214, "dur": 0.320, + "args": { + "External id": 708650,"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": 6305205844566.941, "dur": 2.073, + "args": { + "External id": 708651,"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": 6305205844570.408, "dur": 0.371, + "args": { + "External id": 708652,"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": 6305205844572.737, "dur": 0.328, + "args": { + "External id": 708653,"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": 6305205844574.663, "dur": 0.443, + "args": { + "External id": 708654,"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": 6305205844591.956, "dur": 44.862, + "args": { + "External id": 708655,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305205844670.059, "dur": 113.618, + "args": { + "External id": 708656,"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": 6305205844680.412, "dur": 4.389, + "args": { + "External id": 708657,"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": 6305205844690.332, "dur": 10.654, + "args": { + "External id": 708658,"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": 6305205844694.766, "dur": 5.802, + "args": { + "External id": 708659,"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": 6305205844698.521, "dur": 0.613, + "args": { + "External id": 708660,"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": 6305205844707.442, "dur": 27.724, + "args": { + "External id": 708661,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205844709.433, "dur": 0.464, + "args": { + "External id": 708662,"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": 6305205844712.420, "dur": 0.294, + "args": { + "External id": 708663,"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": 6305205844714.498, "dur": 2.437, + "args": { + "External id": 708664,"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": 6305205844718.380, "dur": 0.588, + "args": { + "External id": 708665,"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": 6305205844720.454, "dur": 0.472, + "args": { + "External id": 708666,"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": 6305205844722.886, "dur": 0.400, + "args": { + "External id": 708667,"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": 6305205844725.179, "dur": 0.380, + "args": { + "External id": 708668,"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": 6305205844727.343, "dur": 0.471, + "args": { + "External id": 708669,"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": 6305205844729.975, "dur": 0.421, + "args": { + "External id": 708670,"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": 6305205844746.291, "dur": 29.122, + "args": { + "External id": 708671,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305205844831.156, "dur": 126.146, + "args": { + "External id": 708672,"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": 6305205844859.885, "dur": 93.836, + "args": { + "External id": 708673,"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": 6305205844873.837, "dur": 75.484, + "args": { + "External id": 708674,"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": 6305205844975.692, "dur": 1.920, + "args": { + "External id": 708675,"Record function id": 0, "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": 6305205845103.950, "dur": 1823.772, + "args": { + "External id": 708676,"Sequence number": 7674430, "Fwd thread 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": 6305205845103.950, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6305205845219.157, "dur": 114.716, + "args": { + "External id": 708677,"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": 6305205845376.414, "dur": 39.875, + "args": { + "External id": 708678,"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": 6305205845432.787, "dur": 51.465, + "args": { + "External id": 708679,"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": 6305205845496.013, "dur": 51.769, + "args": { + "External id": 708680,"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": 6305205845557.370, "dur": 34.540, + "args": { + "External id": 708681,"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": 6305205845598.822, "dur": 28.734, + "args": { + "External id": 708682,"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": 6305205845634.619, "dur": 28.689, + "args": { + "External id": 708683,"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": 6305205845695.695, "dur": 26.038, + "args": { + "External id": 708684,"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": 6305205845742.429, "dur": 30.288, + "args": { + "External id": 708685,"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": 6305205845795.143, "dur": 20.912, + "args": { + "External id": 708686,"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": 6305205845830.729, "dur": 16.851, + "args": { + "External id": 708687,"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": 6305205845856.823, "dur": 38.370, + "args": { + "External id": 708688,"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": 6305205845899.330, "dur": 35.287, + "args": { + "External id": 708689,"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": 6305205845965.557, "dur": 314.642, + "args": { + "External id": 708690,"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": 6305205846049.736, "dur": 42.208, + "args": { + "External id": 708691,"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": 6305205846096.038, "dur": 3.083, + "args": { + "External id": 708692,"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": 6305205846100.927, "dur": 2.451, + "args": { + "External id": 708693,"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": 6305205846104.938, "dur": 2.381, + "args": { + "External id": 708694,"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": 6305205846161.207, "dur": 5.529, + "args": { + "External id": 708695,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205846163.720, "dur": 2.800, + "args": { + "External id": 708696,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205846169.419, "dur": 36.837, + "args": { + "External id": 708697,"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": 6305205846176.040, "dur": 3.459, + "args": { + "External id": 708698,"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": 6305205846207.855, "dur": 1.914, + "args": { + "External id": 708699,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205846208.939, "dur": 0.729, + "args": { + "External id": 708700,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205846211.313, "dur": 16.821, + "args": { + "External id": 708701,"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": 6305205846213.320, "dur": 0.642, + "args": { + "External id": 708702,"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": 6305205846315.996, "dur": 32.994, + "args": { + "External id": 708703,"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": 6305205846366.293, "dur": 19.671, + "args": { + "External id": 708704,"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": 6305205846396.117, "dur": 49.131, + "args": { + "External id": 708705,"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": 6305205846452.531, "dur": 43.249, + "args": { + "External id": 708706,"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": 6305205846522.853, "dur": 28.543, + "args": { + "External id": 708707,"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": 6305205846560.876, "dur": 33.992, + "args": { + "External id": 708708,"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": 6305205846603.239, "dur": 29.396, + "args": { + "External id": 708709,"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": 6305205846643.688, "dur": 31.755, + "args": { + "External id": 708710,"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": 6305205846715.146, "dur": 32.294, + "args": { + "External id": 708711,"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": 6305205846765.849, "dur": 24.955, + "args": { + "External id": 708712,"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": 6305205846805.072, "dur": 22.560, + "args": { + "External id": 708713,"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": 6305205846845.042, "dur": 16.200, + "args": { + "External id": 708714,"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": 6305205846875.473, "dur": 21.067, + "args": { + "External id": 708715,"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": 6305205846972.115, "dur": 16.016, + "args": { + "External id": 708716,"Record function id": 0, "Ev Idx": 2667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205846975.774, "dur": 11.366, + "args": { + "External id": 708717,"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": 6305205846979.995, "dur": 6.245, + "args": { + "External id": 708718,"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": 6305205846981.971, "dur": 4.156, + "args": { + "External id": 708719,"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": 6305205846992.309, "dur": 5.652, + "args": { + "External id": 708720,"Record function id": 0, "Ev Idx": 2671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205846993.853, "dur": 3.591, + "args": { + "External id": 708721,"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": 6305205846994.666, "dur": 2.301, + "args": { + "External id": 708722,"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": 6305205846995.624, "dur": 1.247, + "args": { + "External id": 708723,"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": 6305205847001.480, "dur": 7.467, + "args": { + "External id": 708724,"Record function id": 0, "Ev Idx": 2675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205847002.647, "dur": 5.822, + "args": { + "External id": 708725,"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": 6305205847003.116, "dur": 4.953, + "args": { + "External id": 708726,"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": 6305205847003.625, "dur": 4.373, + "args": { + "External id": 708727,"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": 6305205847012.400, "dur": 4.259, + "args": { + "External id": 708728,"Record function id": 0, "Ev Idx": 2679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205847013.681, "dur": 2.568, + "args": { + "External id": 708729,"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": 6305205847014.339, "dur": 1.497, + "args": { + "External id": 708730,"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": 6305205847014.935, "dur": 0.801, + "args": { + "External id": 708731,"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": 6305205847020.006, "dur": 4.361, + "args": { + "External id": 708732,"Record function id": 0, "Ev Idx": 2683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205847021.373, "dur": 2.548, + "args": { + "External id": 708733,"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": 6305205847022.031, "dur": 1.472, + "args": { + "External id": 708734,"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": 6305205847022.849, "dur": 0.590, + "args": { + "External id": 708735,"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": 6305205847027.906, "dur": 4.881, + "args": { + "External id": 708736,"Record function id": 0, "Ev Idx": 2687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205847029.198, "dur": 3.156, + "args": { + "External id": 708737,"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": 6305205847029.955, "dur": 1.983, + "args": { + "External id": 708738,"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": 6305205847030.604, "dur": 1.214, + "args": { + "External id": 708739,"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": 6305205847036.222, "dur": 4.065, + "args": { + "External id": 708740,"Record function id": 0, "Ev Idx": 2691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205847037.604, "dur": 2.271, + "args": { + "External id": 708741,"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": 6305205847038.040, "dur": 1.452, + "args": { + "External id": 708742,"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": 6305205847038.646, "dur": 0.775, + "args": { + "External id": 708743,"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": 6305205847043.616, "dur": 3.819, + "args": { + "External id": 708744,"Record function id": 0, "Ev Idx": 2695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205847044.698, "dur": 2.300, + "args": { + "External id": 708745,"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": 6305205847045.576, "dur": 1.040, + "args": { + "External id": 708746,"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": 6305205847045.867, "dur": 0.634, + "args": { + "External id": 708747,"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": 6305205847050.755, "dur": 42.539, + "args": { + "External id": 708748,"Record function id": 0, "Ev Idx": 2699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205847086.497, "dur": 5.714, + "args": { + "External id": 708749,"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": 6305205847088.590, "dur": 2.701, + "args": { + "External id": 708750,"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": 6305205847089.615, "dur": 1.383, + "args": { + "External id": 708751,"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": 6305205847099.302, "dur": 63422.604, + "args": { + "External id": 708752,"Record function id": 0, "Sequence number": 7674429, "Fwd thread id": 1, "Ev Idx": 2703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305205847100.835, "dur": 63397.532, + "args": { + "External id": 708753,"Sequence number": 7674429, "Fwd thread 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": 6305205847100.835, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.19)", "pid": 2338707, "tid": 2379456, + "ts": 6305205847133.134, "dur": 39.944, + "args": { + "External id": 708754,"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": 6305205847180.995, "dur": 61.086, + "args": { + "External id": 708755,"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": 6305205847247.641, "dur": 63242.609, + "args": { + "External id": 708756,"Record function id": 0, "Ev Idx": 2707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305205847338.882, "dur": 7.609, + "args": { + "External id": 708757,"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": 6305205847357.263, "dur": 6.759, + "args": { + "External id": 708758,"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": 6305205847380.315, "dur": 62223.496, + "args": { + "External id": 708759,"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": 6305205847395.011, "dur": 62194.640, + "args": { + "External id": 708760,"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": 6305205847538.616, "dur": 20.267, + "args": { + "External id": 708761,"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": 6305205847580.476, "dur": 61958.010, + "args": { + "External id": 708762,"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": 6305205847583.791, "dur": 61953.587, + "args": { + "External id": 708763,"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": 6305205847588.604, "dur": 11.581, + "args": { + "External id": 708764,"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": 6305205847602.536, "dur": 61929.771, + "args": { + "External id": 708765,"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": 6305205909711.146, "dur": 13.960, + "args": { + "External id": 708766,"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": 6305205909715.675, "dur": 9.009, + "args": { + "External id": 708767,"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": 6305205909758.144, "dur": 409.668, + "args": { + "External id": 708768,"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": 6305205909788.338, "dur": 373.638, + "args": { + "External id": 708769,"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": 6305205909800.413, "dur": 355.601, + "args": { + "External id": 708770,"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": 6305205910190.486, "dur": 2.259, + "args": { + "External id": 708771,"Record function id": 0, "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": 6305205910254.506, "dur": 6.714, + "args": { + "External id": 708772,"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": 6305205910310.779, "dur": 1.531, + "args": { + "External id": 708773,"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": 6305205910329.821, "dur": 3.484, + "args": { + "External id": 708774,"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": 6305205910346.642, "dur": 1.080, + "args": { + "External id": 708775,"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": 6305205910360.151, "dur": 1.088, + "args": { + "External id": 708776,"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": 6305205910373.790, "dur": 1.046, + "args": { + "External id": 708777,"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": 6305205910387.716, "dur": 2.695, + "args": { + "External id": 708778,"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": 6305205910402.512, "dur": 2.453, + "args": { + "External id": 708779,"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": 6305205910426.019, "dur": 0.858, + "args": { + "External id": 708780,"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": 6305205910538.891, "dur": 3062.955, + "args": { + "External id": 708781,"Record function id": 0, "Ev Idx": 2732 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.18)", "pid": 2338707, "tid": 2379456, + "ts": 6305205910560.247, "dur": 1124.730, + "args": { + "External id": 708782,"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": 6305205910575.419, "dur": 357.730, + "args": { + "External id": 708783,"Record function id": 0, "Ev Idx": 2734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6305205910665.191, "dur": 4.978, + "args": { + "External id": 708784,"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": 6305205910673.638, "dur": 0.956, + "args": { + "External id": 708785,"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": 6305205910676.282, "dur": 2.979, + "args": { + "External id": 708786,"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": 6305205910680.821, "dur": 1.043, + "args": { + "External id": 708787,"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": 6305205910683.487, "dur": 1.561, + "args": { + "External id": 708788,"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": 6305205910686.686, "dur": 0.843, + "args": { + "External id": 708789,"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": 6305205910689.637, "dur": 2.237, + "args": { + "External id": 708790,"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": 6305205910693.532, "dur": 0.917, + "args": { + "External id": 708791,"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": 6305205910695.875, "dur": 1.133, + "args": { + "External id": 708792,"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": 6305205910698.482, "dur": 0.848, + "args": { + "External id": 708793,"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": 6305205910717.158, "dur": 180.598, + "args": { + "External id": 708794,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305205910732.959, "dur": 160.023, + "args": { + "External id": 708795,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305205910762.725, "dur": 17.989, + "args": { + "External id": 708796,"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": 6305205910784.759, "dur": 76.846, + "args": { + "External id": 708797,"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": 6305205910787.720, "dur": 73.564, + "args": { + "External id": 708798,"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": 6305205910795.787, "dur": 6.167, + "args": { + "External id": 708799,"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": 6305205910804.097, "dur": 56.465, + "args": { + "External id": 708800,"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": 6305205911015.961, "dur": 659.756, + "args": { + "External id": 708801,"Record function id": 0, "Ev Idx": 2752 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.17)", "pid": 2338707, "tid": 2379456, + "ts": 6305205911035.642, "dur": 626.179, + "args": { + "External id": 708802,"Record function id": 0, "Ev Idx": 2753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305205911134.171, "dur": 6.725, + "args": { + "External id": 708803,"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": 6305205911157.296, "dur": 34.743, + "args": { + "External id": 708804,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205911163.395, "dur": 1.786, + "args": { + "External id": 708805,"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": 6305205911167.540, "dur": 0.662, + "args": { + "External id": 708806,"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": 6305205911169.789, "dur": 0.497, + "args": { + "External id": 708807,"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": 6305205911172.222, "dur": 0.396, + "args": { + "External id": 708808,"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": 6305205911174.197, "dur": 0.614, + "args": { + "External id": 708809,"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": 6305205911177.204, "dur": 2.783, + "args": { + "External id": 708810,"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": 6305205911182.238, "dur": 0.423, + "args": { + "External id": 708811,"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": 6305205911184.289, "dur": 0.369, + "args": { + "External id": 708812,"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": 6305205911186.204, "dur": 0.383, + "args": { + "External id": 708813,"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": 6305205911206.174, "dur": 48.533, + "args": { + "External id": 708814,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305205911288.916, "dur": 117.478, + "args": { + "External id": 708815,"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": 6305205911299.553, "dur": 3.637, + "args": { + "External id": 708816,"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": 6305205911309.000, "dur": 10.968, + "args": { + "External id": 708817,"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": 6305205911313.748, "dur": 5.811, + "args": { + "External id": 708818,"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": 6305205911317.655, "dur": 0.748, + "args": { + "External id": 708819,"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": 6305205911327.127, "dur": 28.011, + "args": { + "External id": 708820,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205911329.925, "dur": 0.547, + "args": { + "External id": 708821,"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": 6305205911332.427, "dur": 0.459, + "args": { + "External id": 708822,"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": 6305205911335.027, "dur": 2.433, + "args": { + "External id": 708823,"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": 6305205911339.269, "dur": 0.496, + "args": { + "External id": 708824,"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": 6305205911341.533, "dur": 0.439, + "args": { + "External id": 708825,"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": 6305205911343.553, "dur": 0.341, + "args": { + "External id": 708826,"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": 6305205911345.742, "dur": 0.447, + "args": { + "External id": 708827,"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": 6305205911348.006, "dur": 0.372, + "args": { + "External id": 708828,"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": 6305205911350.370, "dur": 0.573, + "args": { + "External id": 708829,"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": 6305205911367.374, "dur": 31.462, + "args": { + "External id": 708830,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305205911454.730, "dur": 133.464, + "args": { + "External id": 708831,"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": 6305205911478.316, "dur": 105.442, + "args": { + "External id": 708832,"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": 6305205911488.438, "dur": 90.666, + "args": { + "External id": 708833,"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": 6305205911605.057, "dur": 2.048, + "args": { + "External id": 708834,"Record function id": 0, "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": 6305205911692.914, "dur": 1887.245, + "args": { + "External id": 708835,"Sequence number": 7674428, "Fwd thread 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": 6305205911692.914, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6305205911804.698, "dur": 111.936, + "args": { + "External id": 708836,"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": 6305205911956.025, "dur": 40.177, + "args": { + "External id": 708837,"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": 6305205912015.230, "dur": 97.962, + "args": { + "External id": 708838,"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": 6305205912131.549, "dur": 40.417, + "args": { + "External id": 708839,"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": 6305205912180.666, "dur": 36.518, + "args": { + "External id": 708840,"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": 6305205912225.974, "dur": 30.362, + "args": { + "External id": 708841,"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": 6305205912264.223, "dur": 31.824, + "args": { + "External id": 708842,"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": 6305205912325.390, "dur": 28.571, + "args": { + "External id": 708843,"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": 6305205912373.332, "dur": 30.947, + "args": { + "External id": 708844,"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": 6305205912425.492, "dur": 21.356, + "args": { + "External id": 708845,"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": 6305205912463.407, "dur": 16.566, + "args": { + "External id": 708846,"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": 6305205912489.087, "dur": 62.630, + "args": { + "External id": 708847,"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": 6305205912557.499, "dur": 39.724, + "args": { + "External id": 708848,"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": 6305205912632.047, "dur": 265.868, + "args": { + "External id": 708849,"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": 6305205912719.083, "dur": 6.315, + "args": { + "External id": 708850,"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": 6305205912727.690, "dur": 2.417, + "args": { + "External id": 708851,"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": 6305205912731.448, "dur": 2.112, + "args": { + "External id": 708852,"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": 6305205912734.775, "dur": 2.155, + "args": { + "External id": 708853,"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": 6305205912786.839, "dur": 5.231, + "args": { + "External id": 708854,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205912789.201, "dur": 2.716, + "args": { + "External id": 708855,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205912794.778, "dur": 36.714, + "args": { + "External id": 708856,"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": 6305205912800.474, "dur": 3.807, + "args": { + "External id": 708857,"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": 6305205912833.348, "dur": 1.885, + "args": { + "External id": 708858,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205912834.524, "dur": 0.634, + "args": { + "External id": 708859,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205912836.666, "dur": 17.115, + "args": { + "External id": 708860,"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": 6305205912838.837, "dur": 0.631, + "args": { + "External id": 708861,"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": 6305205912933.517, "dur": 26.953, + "args": { + "External id": 708862,"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": 6305205912977.096, "dur": 22.926, + "args": { + "External id": 708863,"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": 6305205913009.212, "dur": 84.712, + "args": { + "External id": 708864,"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": 6305205913104.760, "dur": 47.915, + "args": { + "External id": 708865,"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": 6305205913166.055, "dur": 25.220, + "args": { + "External id": 708866,"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": 6305205913198.188, "dur": 33.722, + "args": { + "External id": 708867,"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": 6305205913255.132, "dur": 42.170, + "args": { + "External id": 708868,"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": 6305205913308.021, "dur": 32.756, + "args": { + "External id": 708869,"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": 6305205913363.428, "dur": 26.801, + "args": { + "External id": 708870,"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": 6305205913405.596, "dur": 24.470, + "args": { + "External id": 708871,"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": 6305205913446.691, "dur": 18.097, + "args": { + "External id": 708872,"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": 6305205913481.475, "dur": 17.088, + "args": { + "External id": 708873,"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": 6305205913527.212, "dur": 18.397, + "args": { + "External id": 708874,"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": 6305205913624.592, "dur": 16.059, + "args": { + "External id": 708875,"Record function id": 0, "Ev Idx": 2826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205913628.086, "dur": 11.548, + "args": { + "External id": 708876,"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": 6305205913632.472, "dur": 6.170, + "args": { + "External id": 708877,"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": 6305205913634.370, "dur": 4.154, + "args": { + "External id": 708878,"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": 6305205913644.950, "dur": 5.864, + "args": { + "External id": 708879,"Record function id": 0, "Ev Idx": 2830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205913646.714, "dur": 3.610, + "args": { + "External id": 708880,"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": 6305205913647.503, "dur": 2.367, + "args": { + "External id": 708881,"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": 6305205913648.569, "dur": 1.196, + "args": { + "External id": 708882,"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": 6305205913654.389, "dur": 6.730, + "args": { + "External id": 708883,"Record function id": 0, "Ev Idx": 2834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205913655.779, "dur": 4.920, + "args": { + "External id": 708884,"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": 6305205913656.337, "dur": 3.958, + "args": { + "External id": 708885,"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": 6305205913656.863, "dur": 3.341, + "args": { + "External id": 708886,"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": 6305205913664.518, "dur": 4.081, + "args": { + "External id": 708887,"Record function id": 0, "Ev Idx": 2838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205913665.906, "dur": 2.218, + "args": { + "External id": 708888,"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": 6305205913666.617, "dur": 1.122, + "args": { + "External id": 708889,"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": 6305205913667.019, "dur": 0.647, + "args": { + "External id": 708890,"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": 6305205913671.966, "dur": 4.483, + "args": { + "External id": 708891,"Record function id": 0, "Ev Idx": 2842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205913673.286, "dur": 2.728, + "args": { + "External id": 708892,"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": 6305205913673.734, "dur": 1.901, + "args": { + "External id": 708893,"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": 6305205913674.564, "dur": 1.007, + "args": { + "External id": 708894,"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": 6305205913679.812, "dur": 4.325, + "args": { + "External id": 708895,"Record function id": 0, "Ev Idx": 2846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205913681.191, "dur": 2.521, + "args": { + "External id": 708896,"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": 6305205913681.848, "dur": 1.459, + "args": { + "External id": 708897,"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": 6305205913682.378, "dur": 0.835, + "args": { + "External id": 708898,"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": 6305205913687.546, "dur": 3.458, + "args": { + "External id": 708899,"Record function id": 0, "Ev Idx": 2850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205913688.854, "dur": 1.721, + "args": { + "External id": 708900,"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": 6305205913689.271, "dur": 0.900, + "args": { + "External id": 708901,"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": 6305205913689.531, "dur": 0.544, + "args": { + "External id": 708902,"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": 6305205913694.204, "dur": 4.043, + "args": { + "External id": 708903,"Record function id": 0, "Ev Idx": 2854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205913695.632, "dur": 2.139, + "args": { + "External id": 708904,"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": 6305205913696.084, "dur": 1.282, + "args": { + "External id": 708905,"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": 6305205913696.376, "dur": 0.925, + "args": { + "External id": 708906,"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": 6305205913701.650, "dur": 4.492, + "args": { + "External id": 708907,"Record function id": 0, "Ev Idx": 2858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205913703.236, "dur": 2.483, + "args": { + "External id": 708908,"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": 6305205913703.656, "dur": 1.685, + "args": { + "External id": 708909,"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": 6305205913704.264, "dur": 0.988, + "args": { + "External id": 708910,"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": 6305205913710.214, "dur": 66403.656, + "args": { + "External id": 708911,"Record function id": 0, "Sequence number": 7674427, "Fwd thread id": 1, "Ev Idx": 2862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305205913711.442, "dur": 66392.467, + "args": { + "External id": 708912,"Sequence number": 7674427, "Fwd thread 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": 6305205913711.442, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.18)", "pid": 2338707, "tid": 2379456, + "ts": 6305205913741.621, "dur": 41.519, + "args": { + "External id": 708913,"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": 6305205913791.246, "dur": 63.742, + "args": { + "External id": 708914,"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": 6305205913860.724, "dur": 66233.866, + "args": { + "External id": 708915,"Record function id": 0, "Ev Idx": 2866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305205913950.946, "dur": 7.950, + "args": { + "External id": 708916,"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": 6305205913969.135, "dur": 6.668, + "args": { + "External id": 708917,"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": 6305205913991.416, "dur": 65144.341, + "args": { + "External id": 708918,"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": 6305205914005.818, "dur": 65116.138, + "args": { + "External id": 708919,"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": 6305205914174.444, "dur": 21.399, + "args": { + "External id": 708920,"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": 6305205914217.729, "dur": 64831.331, + "args": { + "External id": 708921,"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": 6305205914220.942, "dur": 64826.884, + "args": { + "External id": 708922,"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": 6305205914225.782, "dur": 12.104, + "args": { + "External id": 708923,"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": 6305205914240.350, "dur": 64798.802, + "args": { + "External id": 708924,"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": 6305205979248.314, "dur": 14.051, + "args": { + "External id": 708925,"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": 6305205979252.682, "dur": 9.272, + "args": { + "External id": 708926,"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": 6305205979295.110, "dur": 434.610, + "args": { + "External id": 708927,"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": 6305205979324.759, "dur": 398.893, + "args": { + "External id": 708928,"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": 6305205979337.350, "dur": 379.549, + "args": { + "External id": 708929,"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": 6305205979752.655, "dur": 2.195, + "args": { + "External id": 708930,"Record function id": 0, "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": 6305205979830.020, "dur": 7.200, + "args": { + "External id": 708931,"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": 6305205979885.890, "dur": 1.533, + "args": { + "External id": 708932,"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": 6305205979904.373, "dur": 3.313, + "args": { + "External id": 708933,"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": 6305205979921.852, "dur": 1.127, + "args": { + "External id": 708934,"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": 6305205979935.194, "dur": 0.996, + "args": { + "External id": 708935,"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": 6305205979949.092, "dur": 1.158, + "args": { + "External id": 708936,"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": 6305205979963.294, "dur": 3.118, + "args": { + "External id": 708937,"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": 6305205979978.239, "dur": 2.304, + "args": { + "External id": 708938,"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": 6305205979992.436, "dur": 0.854, + "args": { + "External id": 708939,"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": 6305205980132.017, "dur": 3063.949, + "args": { + "External id": 708940,"Record function id": 0, "Ev Idx": 2891 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.17)", "pid": 2338707, "tid": 2379456, + "ts": 6305205980153.839, "dur": 1139.785, + "args": { + "External id": 708941,"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": 6305205980169.760, "dur": 384.626, + "args": { + "External id": 708942,"Record function id": 0, "Ev Idx": 2893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6305205980264.517, "dur": 4.937, + "args": { + "External id": 708943,"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": 6305205980272.867, "dur": 1.226, + "args": { + "External id": 708944,"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": 6305205980276.014, "dur": 3.072, + "args": { + "External id": 708945,"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": 6305205980281.079, "dur": 1.058, + "args": { + "External id": 708946,"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": 6305205980284.060, "dur": 0.896, + "args": { + "External id": 708947,"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": 6305205980286.736, "dur": 0.719, + "args": { + "External id": 708948,"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": 6305205980288.969, "dur": 2.145, + "args": { + "External id": 708949,"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": 6305205980292.573, "dur": 1.021, + "args": { + "External id": 708950,"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": 6305205980295.070, "dur": 0.783, + "args": { + "External id": 708951,"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": 6305205980297.561, "dur": 0.865, + "args": { + "External id": 708952,"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": 6305205980330.407, "dur": 170.016, + "args": { + "External id": 708953,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305205980347.257, "dur": 148.203, + "args": { + "External id": 708954,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305205980375.634, "dur": 16.118, + "args": { + "External id": 708955,"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": 6305205980395.967, "dur": 69.461, + "args": { + "External id": 708956,"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": 6305205980398.796, "dur": 66.308, + "args": { + "External id": 708957,"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": 6305205980403.330, "dur": 5.631, + "args": { + "External id": 708958,"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": 6305205980411.106, "dur": 53.246, + "args": { + "External id": 708959,"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": 6305205980645.229, "dur": 639.207, + "args": { + "External id": 708960,"Record function id": 0, "Ev Idx": 2911 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.16)", "pid": 2338707, "tid": 2379456, + "ts": 6305205980666.774, "dur": 603.883, + "args": { + "External id": 708961,"Record function id": 0, "Ev Idx": 2912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305205980730.493, "dur": 6.149, + "args": { + "External id": 708962,"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": 6305205980752.226, "dur": 35.492, + "args": { + "External id": 708963,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205980758.211, "dur": 1.848, + "args": { + "External id": 708964,"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": 6305205980762.751, "dur": 0.605, + "args": { + "External id": 708965,"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": 6305205980765.243, "dur": 0.405, + "args": { + "External id": 708966,"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": 6305205980767.468, "dur": 0.591, + "args": { + "External id": 708967,"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": 6305205980770.212, "dur": 0.607, + "args": { + "External id": 708968,"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": 6305205980772.730, "dur": 2.468, + "args": { + "External id": 708969,"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": 6305205980777.123, "dur": 0.416, + "args": { + "External id": 708970,"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": 6305205980779.256, "dur": 0.756, + "args": { + "External id": 708971,"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": 6305205980781.637, "dur": 0.484, + "args": { + "External id": 708972,"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": 6305205980798.372, "dur": 48.510, + "args": { + "External id": 708973,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305205980879.054, "dur": 117.622, + "args": { + "External id": 708974,"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": 6305205980889.736, "dur": 3.566, + "args": { + "External id": 708975,"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": 6305205980898.422, "dur": 10.725, + "args": { + "External id": 708976,"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": 6305205980902.792, "dur": 5.944, + "args": { + "External id": 708977,"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": 6305205980906.916, "dur": 0.576, + "args": { + "External id": 708978,"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": 6305205980915.658, "dur": 28.951, + "args": { + "External id": 708979,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205980918.247, "dur": 0.520, + "args": { + "External id": 708980,"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": 6305205980920.528, "dur": 0.368, + "args": { + "External id": 708981,"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": 6305205980922.735, "dur": 2.586, + "args": { + "External id": 708982,"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": 6305205980927.302, "dur": 0.666, + "args": { + "External id": 708983,"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": 6305205980929.969, "dur": 0.452, + "args": { + "External id": 708984,"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": 6305205980932.307, "dur": 0.415, + "args": { + "External id": 708985,"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": 6305205980934.571, "dur": 0.556, + "args": { + "External id": 708986,"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": 6305205980937.085, "dur": 0.398, + "args": { + "External id": 708987,"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": 6305205980939.405, "dur": 0.478, + "args": { + "External id": 708988,"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": 6305205980955.366, "dur": 33.622, + "args": { + "External id": 708989,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305205981041.393, "dur": 156.407, + "args": { + "External id": 708990,"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": 6305205981100.444, "dur": 92.941, + "args": { + "External id": 708991,"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": 6305205981112.141, "dur": 76.407, + "args": { + "External id": 708992,"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": 6305205981212.731, "dur": 1.752, + "args": { + "External id": 708993,"Record function id": 0, "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": 6305205981301.077, "dur": 1871.123, + "args": { + "External id": 708994,"Sequence number": 7674426, "Fwd thread 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": 6305205981301.077, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6305205981419.323, "dur": 128.074, + "args": { + "External id": 708995,"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": 6305205981589.586, "dur": 38.859, + "args": { + "External id": 708996,"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": 6305205981648.281, "dur": 57.657, + "args": { + "External id": 708997,"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": 6305205981718.991, "dur": 34.511, + "args": { + "External id": 708998,"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": 6305205981761.472, "dur": 33.685, + "args": { + "External id": 708999,"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": 6305205981803.179, "dur": 28.000, + "args": { + "External id": 709000,"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": 6305205981839.510, "dur": 29.272, + "args": { + "External id": 709001,"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": 6305205981895.155, "dur": 23.589, + "args": { + "External id": 709002,"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": 6305205981957.123, "dur": 28.848, + "args": { + "External id": 709003,"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": 6305205982008.179, "dur": 19.886, + "args": { + "External id": 709004,"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": 6305205982042.504, "dur": 51.700, + "args": { + "External id": 709005,"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": 6305205982111.483, "dur": 46.743, + "args": { + "External id": 709006,"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": 6305205982162.615, "dur": 37.513, + "args": { + "External id": 709007,"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": 6305205982230.901, "dur": 261.000, + "args": { + "External id": 709008,"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": 6305205982312.093, "dur": 6.267, + "args": { + "External id": 709009,"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": 6305205982320.635, "dur": 2.702, + "args": { + "External id": 709010,"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": 6305205982331.245, "dur": 1.895, + "args": { + "External id": 709011,"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": 6305205982334.534, "dur": 1.590, + "args": { + "External id": 709012,"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": 6305205982382.487, "dur": 5.550, + "args": { + "External id": 709013,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205982384.968, "dur": 2.898, + "args": { + "External id": 709014,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205982390.661, "dur": 34.909, + "args": { + "External id": 709015,"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": 6305205982397.003, "dur": 3.382, + "args": { + "External id": 709016,"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": 6305205982427.333, "dur": 1.954, + "args": { + "External id": 709017,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205982428.516, "dur": 0.689, + "args": { + "External id": 709018,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305205982430.570, "dur": 15.203, + "args": { + "External id": 709019,"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": 6305205982432.946, "dur": 0.625, + "args": { + "External id": 709020,"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": 6305205982547.356, "dur": 31.840, + "args": { + "External id": 709021,"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": 6305205982597.608, "dur": 18.219, + "args": { + "External id": 709022,"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": 6305205982626.005, "dur": 49.950, + "args": { + "External id": 709023,"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": 6305205982683.372, "dur": 41.052, + "args": { + "External id": 709024,"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": 6305205982736.432, "dur": 21.521, + "args": { + "External id": 709025,"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": 6305205982764.265, "dur": 49.723, + "args": { + "External id": 709026,"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": 6305205982830.196, "dur": 32.131, + "args": { + "External id": 709027,"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": 6305205982870.469, "dur": 32.008, + "args": { + "External id": 709028,"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": 6305205982927.762, "dur": 24.287, + "args": { + "External id": 709029,"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": 6305205982967.721, "dur": 26.901, + "args": { + "External id": 709030,"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": 6305205983009.168, "dur": 18.804, + "args": { + "External id": 709031,"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": 6305205983047.416, "dur": 53.668, + "args": { + "External id": 709032,"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": 6305205983119.309, "dur": 19.298, + "args": { + "External id": 709033,"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": 6305205983218.965, "dur": 16.512, + "args": { + "External id": 709034,"Record function id": 0, "Ev Idx": 2985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205983222.569, "dur": 11.869, + "args": { + "External id": 709035,"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": 6305205983227.064, "dur": 6.484, + "args": { + "External id": 709036,"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": 6305205983229.056, "dur": 4.374, + "args": { + "External id": 709037,"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": 6305205983239.711, "dur": 5.276, + "args": { + "External id": 709038,"Record function id": 0, "Ev Idx": 2989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205983241.287, "dur": 3.277, + "args": { + "External id": 709039,"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": 6305205983242.100, "dur": 2.012, + "args": { + "External id": 709040,"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": 6305205983242.922, "dur": 1.089, + "args": { + "External id": 709041,"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": 6305205983248.440, "dur": 6.639, + "args": { + "External id": 709042,"Record function id": 0, "Ev Idx": 2993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205983249.863, "dur": 4.790, + "args": { + "External id": 709043,"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": 6305205983250.451, "dur": 3.784, + "args": { + "External id": 709044,"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": 6305205983250.780, "dur": 3.387, + "args": { + "External id": 709045,"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": 6305205983258.657, "dur": 4.212, + "args": { + "External id": 709046,"Record function id": 0, "Ev Idx": 2997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205983259.994, "dur": 2.463, + "args": { + "External id": 709047,"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": 6305205983260.496, "dur": 1.584, + "args": { + "External id": 709048,"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": 6305205983261.182, "dur": 0.829, + "args": { + "External id": 709049,"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": 6305205983266.300, "dur": 4.313, + "args": { + "External id": 709050,"Record function id": 0, "Ev Idx": 3001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205983267.757, "dur": 2.426, + "args": { + "External id": 709051,"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": 6305205983268.320, "dur": 1.447, + "args": { + "External id": 709052,"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": 6305205983268.720, "dur": 0.978, + "args": { + "External id": 709053,"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": 6305205983273.980, "dur": 4.681, + "args": { + "External id": 709054,"Record function id": 0, "Ev Idx": 3005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205983275.376, "dur": 2.857, + "args": { + "External id": 709055,"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": 6305205983276.047, "dur": 1.717, + "args": { + "External id": 709056,"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": 6305205983276.746, "dur": 0.909, + "args": { + "External id": 709057,"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": 6305205983281.851, "dur": 3.939, + "args": { + "External id": 709058,"Record function id": 0, "Ev Idx": 3009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205983283.147, "dur": 2.238, + "args": { + "External id": 709059,"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": 6305205983283.582, "dur": 1.415, + "args": { + "External id": 709060,"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": 6305205983284.137, "dur": 0.782, + "args": { + "External id": 709061,"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": 6305205983289.108, "dur": 3.903, + "args": { + "External id": 709062,"Record function id": 0, "Ev Idx": 3013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205983290.577, "dur": 2.033, + "args": { + "External id": 709063,"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": 6305205983290.995, "dur": 1.224, + "args": { + "External id": 709064,"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": 6305205983291.501, "dur": 0.650, + "args": { + "External id": 709065,"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": 6305205983296.289, "dur": 4.133, + "args": { + "External id": 709066,"Record function id": 0, "Ev Idx": 3017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305205983297.741, "dur": 2.293, + "args": { + "External id": 709067,"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": 6305205983298.174, "dur": 1.443, + "args": { + "External id": 709068,"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": 6305205983298.685, "dur": 0.846, + "args": { + "External id": 709069,"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": 6305205983304.596, "dur": 71507.892, + "args": { + "External id": 709070,"Record function id": 0, "Sequence number": 7674425, "Fwd thread id": 1, "Ev Idx": 3021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305205983306.053, "dur": 71497.457, + "args": { + "External id": 709071,"Sequence number": 7674425, "Fwd thread 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": 6305205983306.053, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.17)", "pid": 2338707, "tid": 2379456, + "ts": 6305205983335.943, "dur": 40.379, + "args": { + "External id": 709072,"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": 6305205983384.204, "dur": 62.481, + "args": { + "External id": 709073,"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": 6305205983452.258, "dur": 71342.421, + "args": { + "External id": 709074,"Record function id": 0, "Ev Idx": 3025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305205983559.111, "dur": 8.366, + "args": { + "External id": 709075,"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": 6305205983578.965, "dur": 6.777, + "args": { + "External id": 709076,"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": 6305205983602.064, "dur": 70289.822, + "args": { + "External id": 709077,"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": 6305205983616.945, "dur": 70261.716, + "args": { + "External id": 709078,"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": 6305205983718.998, "dur": 17.927, + "args": { + "External id": 709079,"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": 6305205983757.373, "dur": 70068.681, + "args": { + "External id": 709080,"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": 6305205983760.559, "dur": 70064.366, + "args": { + "External id": 709081,"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": 6305205983765.728, "dur": 9.258, + "args": { + "External id": 709082,"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": 6305205983780.529, "dur": 70039.168, + "args": { + "External id": 709083,"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": 6305206054004.984, "dur": 13.917, + "args": { + "External id": 709084,"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": 6305206054009.586, "dur": 8.865, + "args": { + "External id": 709085,"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": 6305206054091.548, "dur": 378.673, + "args": { + "External id": 709086,"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": 6305206054123.590, "dur": 341.432, + "args": { + "External id": 709087,"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": 6305206054136.186, "dur": 323.533, + "args": { + "External id": 709088,"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": 6305206054491.043, "dur": 2.499, + "args": { + "External id": 709089,"Record function id": 0, "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": 6305206054574.889, "dur": 7.641, + "args": { + "External id": 709090,"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": 6305206054631.572, "dur": 1.510, + "args": { + "External id": 709091,"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": 6305206054649.939, "dur": 2.921, + "args": { + "External id": 709092,"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": 6305206054665.435, "dur": 0.927, + "args": { + "External id": 709093,"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": 6305206054678.003, "dur": 0.845, + "args": { + "External id": 709094,"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": 6305206054690.393, "dur": 1.309, + "args": { + "External id": 709095,"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": 6305206054702.637, "dur": 3.288, + "args": { + "External id": 709096,"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": 6305206054718.022, "dur": 2.733, + "args": { + "External id": 709097,"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": 6305206054731.452, "dur": 1.088, + "args": { + "External id": 709098,"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": 6305206054828.965, "dur": 3046.978, + "args": { + "External id": 709099,"Record function id": 0, "Ev Idx": 3050 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.16)", "pid": 2338707, "tid": 2379456, + "ts": 6305206054847.879, "dur": 1156.913, + "args": { + "External id": 709100,"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": 6305206054863.509, "dur": 393.662, + "args": { + "External id": 709101,"Record function id": 0, "Ev Idx": 3052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6305206054948.838, "dur": 4.358, + "args": { + "External id": 709102,"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": 6305206054956.856, "dur": 0.767, + "args": { + "External id": 709103,"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": 6305206054959.479, "dur": 3.126, + "args": { + "External id": 709104,"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": 6305206054964.309, "dur": 1.135, + "args": { + "External id": 709105,"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": 6305206054967.032, "dur": 1.046, + "args": { + "External id": 709106,"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": 6305206054969.723, "dur": 0.758, + "args": { + "External id": 709107,"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": 6305206054972.044, "dur": 2.592, + "args": { + "External id": 709108,"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": 6305206054975.968, "dur": 1.089, + "args": { + "External id": 709109,"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": 6305206054978.601, "dur": 0.891, + "args": { + "External id": 709110,"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": 6305206054981.102, "dur": 1.197, + "args": { + "External id": 709111,"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": 6305206055013.643, "dur": 207.020, + "args": { + "External id": 709112,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305206055030.431, "dur": 184.663, + "args": { + "External id": 709113,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305206055092.308, "dur": 19.341, + "args": { + "External id": 709114,"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": 6305206055115.792, "dur": 68.766, + "args": { + "External id": 709115,"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": 6305206055118.553, "dur": 65.718, + "args": { + "External id": 709116,"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": 6305206055122.762, "dur": 6.594, + "args": { + "External id": 709117,"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": 6305206055131.238, "dur": 52.467, + "args": { + "External id": 709118,"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": 6305206055344.813, "dur": 651.085, + "args": { + "External id": 709119,"Record function id": 0, "Ev Idx": 3070 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.15)", "pid": 2338707, "tid": 2379456, + "ts": 6305206055363.112, "dur": 617.874, + "args": { + "External id": 709120,"Record function id": 0, "Ev Idx": 3071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305206055454.865, "dur": 5.755, + "args": { + "External id": 709121,"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": 6305206055476.252, "dur": 49.120, + "args": { + "External id": 709122,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206055485.256, "dur": 1.779, + "args": { + "External id": 709123,"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": 6305206055489.019, "dur": 0.573, + "args": { + "External id": 709124,"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": 6305206055491.051, "dur": 0.531, + "args": { + "External id": 709125,"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": 6305206055492.908, "dur": 0.331, + "args": { + "External id": 709126,"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": 6305206055494.704, "dur": 0.427, + "args": { + "External id": 709127,"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": 6305206055496.605, "dur": 2.506, + "args": { + "External id": 709128,"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": 6305206055500.978, "dur": 0.573, + "args": { + "External id": 709129,"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": 6305206055502.939, "dur": 0.442, + "args": { + "External id": 709130,"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": 6305206055504.687, "dur": 0.358, + "args": { + "External id": 709131,"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": 6305206055537.597, "dur": 57.111, + "args": { + "External id": 709132,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305206055629.498, "dur": 120.355, + "args": { + "External id": 709133,"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": 6305206055641.332, "dur": 4.376, + "args": { + "External id": 709134,"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": 6305206055651.572, "dur": 11.122, + "args": { + "External id": 709135,"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": 6305206055655.987, "dur": 6.318, + "args": { + "External id": 709136,"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": 6305206055660.415, "dur": 0.591, + "args": { + "External id": 709137,"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": 6305206055669.448, "dur": 25.634, + "args": { + "External id": 709138,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206055672.408, "dur": 0.420, + "args": { + "External id": 709139,"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": 6305206055674.827, "dur": 0.602, + "args": { + "External id": 709140,"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": 6305206055676.945, "dur": 2.335, + "args": { + "External id": 709141,"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": 6305206055680.804, "dur": 0.402, + "args": { + "External id": 709142,"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": 6305206055682.711, "dur": 0.552, + "args": { + "External id": 709143,"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": 6305206055684.733, "dur": 0.345, + "args": { + "External id": 709144,"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": 6305206055686.423, "dur": 0.636, + "args": { + "External id": 709145,"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": 6305206055688.579, "dur": 0.338, + "args": { + "External id": 709146,"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": 6305206055690.484, "dur": 0.327, + "args": { + "External id": 709147,"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": 6305206055707.455, "dur": 34.275, + "args": { + "External id": 709148,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305206055800.899, "dur": 112.197, + "args": { + "External id": 709149,"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": 6305206055823.278, "dur": 85.913, + "args": { + "External id": 709150,"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": 6305206055833.895, "dur": 70.940, + "args": { + "External id": 709151,"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": 6305206055927.129, "dur": 1.941, + "args": { + "External id": 709152,"Record function id": 0, "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": 6305206056012.643, "dur": 1842.825, + "args": { + "External id": 709153,"Sequence number": 7674424, "Fwd thread 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": 6305206056012.643, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6305206056165.987, "dur": 111.361, + "args": { + "External id": 709154,"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": 6305206056334.587, "dur": 39.282, + "args": { + "External id": 709155,"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": 6305206056394.115, "dur": 52.984, + "args": { + "External id": 709156,"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": 6305206056460.253, "dur": 34.392, + "args": { + "External id": 709157,"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": 6305206056502.386, "dur": 51.221, + "args": { + "External id": 709158,"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": 6305206056564.663, "dur": 31.371, + "args": { + "External id": 709159,"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": 6305206056604.415, "dur": 29.502, + "args": { + "External id": 709160,"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": 6305206056663.027, "dur": 23.951, + "args": { + "External id": 709161,"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": 6305206056706.324, "dur": 30.119, + "args": { + "External id": 709162,"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": 6305206056755.621, "dur": 19.616, + "args": { + "External id": 709163,"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": 6305206056788.158, "dur": 14.691, + "args": { + "External id": 709164,"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": 6305206056812.111, "dur": 37.553, + "args": { + "External id": 709165,"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": 6305206056853.438, "dur": 34.051, + "args": { + "External id": 709166,"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": 6305206056918.405, "dur": 288.253, + "args": { + "External id": 709167,"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": 6305206056996.043, "dur": 5.784, + "args": { + "External id": 709168,"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": 6305206057003.876, "dur": 2.907, + "args": { + "External id": 709169,"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": 6305206057008.036, "dur": 1.792, + "args": { + "External id": 709170,"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": 6305206057010.994, "dur": 1.798, + "args": { + "External id": 709171,"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": 6305206057092.268, "dur": 6.168, + "args": { + "External id": 709172,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206057094.834, "dur": 3.196, + "args": { + "External id": 709173,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206057101.050, "dur": 36.561, + "args": { + "External id": 709174,"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": 6305206057107.078, "dur": 3.444, + "args": { + "External id": 709175,"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": 6305206057139.550, "dur": 1.806, + "args": { + "External id": 709176,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206057140.659, "dur": 0.605, + "args": { + "External id": 709177,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206057142.813, "dur": 14.923, + "args": { + "External id": 709178,"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": 6305206057145.203, "dur": 0.723, + "args": { + "External id": 709179,"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": 6305206057243.929, "dur": 28.653, + "args": { + "External id": 709180,"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": 6305206057289.331, "dur": 17.267, + "args": { + "External id": 709181,"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": 6305206057319.665, "dur": 50.086, + "args": { + "External id": 709182,"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": 6305206057381.330, "dur": 43.128, + "args": { + "External id": 709183,"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": 6305206057436.238, "dur": 23.818, + "args": { + "External id": 709184,"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": 6305206057467.509, "dur": 33.712, + "args": { + "External id": 709185,"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": 6305206057525.425, "dur": 52.436, + "args": { + "External id": 709186,"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": 6305206057596.299, "dur": 39.103, + "args": { + "External id": 709187,"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": 6305206057656.222, "dur": 30.021, + "args": { + "External id": 709188,"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": 6305206057701.652, "dur": 28.763, + "args": { + "External id": 709189,"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": 6305206057743.844, "dur": 18.428, + "args": { + "External id": 709190,"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": 6305206057777.763, "dur": 16.518, + "args": { + "External id": 709191,"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": 6305206057806.742, "dur": 18.405, + "args": { + "External id": 709192,"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": 6305206057898.743, "dur": 16.133, + "args": { + "External id": 709193,"Record function id": 0, "Ev Idx": 3144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206057902.146, "dur": 11.754, + "args": { + "External id": 709194,"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": 6305206057906.389, "dur": 6.576, + "args": { + "External id": 709195,"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": 6305206057908.829, "dur": 3.963, + "args": { + "External id": 709196,"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": 6305206057918.968, "dur": 26.940, + "args": { + "External id": 709197,"Record function id": 0, "Ev Idx": 3148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206057920.403, "dur": 24.952, + "args": { + "External id": 709198,"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": 6305206057921.087, "dur": 23.669, + "args": { + "External id": 709199,"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": 6305206057943.333, "dur": 1.310, + "args": { + "External id": 709200,"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": 6305206057949.442, "dur": 6.637, + "args": { + "External id": 709201,"Record function id": 0, "Ev Idx": 3152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206057950.693, "dur": 4.966, + "args": { + "External id": 709202,"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": 6305206057951.141, "dur": 4.098, + "args": { + "External id": 709203,"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": 6305206057951.715, "dur": 3.427, + "args": { + "External id": 709204,"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": 6305206057959.467, "dur": 4.327, + "args": { + "External id": 709205,"Record function id": 0, "Ev Idx": 3156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206057960.757, "dur": 2.612, + "args": { + "External id": 709206,"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": 6305206057961.277, "dur": 1.668, + "args": { + "External id": 709207,"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": 6305206057961.999, "dur": 0.877, + "args": { + "External id": 709208,"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": 6305206057966.979, "dur": 4.433, + "args": { + "External id": 709209,"Record function id": 0, "Ev Idx": 3160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206057968.253, "dur": 2.737, + "args": { + "External id": 709210,"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": 6305206057969.127, "dur": 1.423, + "args": { + "External id": 709211,"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": 6305206057969.636, "dur": 0.853, + "args": { + "External id": 709212,"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": 6305206057974.703, "dur": 4.357, + "args": { + "External id": 709213,"Record function id": 0, "Ev Idx": 3164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206057976.269, "dur": 2.391, + "args": { + "External id": 709214,"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": 6305206057976.716, "dur": 1.540, + "args": { + "External id": 709215,"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": 6305206057977.494, "dur": 0.684, + "args": { + "External id": 709216,"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": 6305206057982.334, "dur": 5.526, + "args": { + "External id": 709217,"Record function id": 0, "Ev Idx": 3168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206057983.353, "dur": 4.112, + "args": { + "External id": 709218,"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": 6305206057984.045, "dur": 2.994, + "args": { + "External id": 709219,"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": 6305206057986.334, "dur": 0.640, + "args": { + "External id": 709220,"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": 6305206057991.117, "dur": 4.079, + "args": { + "External id": 709221,"Record function id": 0, "Ev Idx": 3172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206057992.622, "dur": 2.170, + "args": { + "External id": 709222,"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": 6305206057993.178, "dur": 1.193, + "args": { + "External id": 709223,"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": 6305206057993.579, "dur": 0.730, + "args": { + "External id": 709224,"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": 6305206057998.458, "dur": 3.369, + "args": { + "External id": 709225,"Record function id": 0, "Ev Idx": 3176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206057999.559, "dur": 1.851, + "args": { + "External id": 709226,"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": 6305206058000.096, "dur": 0.908, + "args": { + "External id": 709227,"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": 6305206058000.388, "dur": 0.554, + "args": { + "External id": 709228,"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": 6305206058005.669, "dur": 72621.171, + "args": { + "External id": 709229,"Record function id": 0, "Sequence number": 7674423, "Fwd thread id": 1, "Ev Idx": 3180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305206058006.996, "dur": 72610.940, + "args": { + "External id": 709230,"Sequence number": 7674423, "Fwd thread 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": 6305206058006.996, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.16)", "pid": 2338707, "tid": 2379456, + "ts": 6305206058039.375, "dur": 74.994, + "args": { + "External id": 709231,"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": 6305206058123.829, "dur": 62.167, + "args": { + "External id": 709232,"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": 6305206058191.134, "dur": 72418.798, + "args": { + "External id": 709233,"Record function id": 0, "Ev Idx": 3184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305206058281.783, "dur": 7.858, + "args": { + "External id": 709234,"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": 6305206058300.480, "dur": 7.047, + "args": { + "External id": 709235,"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": 6305206058323.849, "dur": 71661.634, + "args": { + "External id": 709236,"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": 6305206058337.852, "dur": 71633.635, + "args": { + "External id": 709237,"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": 6305206058430.527, "dur": 18.667, + "args": { + "External id": 709238,"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": 6305206058469.556, "dur": 71449.377, + "args": { + "External id": 709239,"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": 6305206058472.885, "dur": 71444.987, + "args": { + "External id": 709240,"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": 6305206058481.201, "dur": 9.267, + "args": { + "External id": 709241,"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": 6305206058492.995, "dur": 71419.896, + "args": { + "External id": 709242,"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": 6305206130125.659, "dur": 13.943, + "args": { + "External id": 709243,"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": 6305206130129.635, "dur": 9.346, + "args": { + "External id": 709244,"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": 6305206130171.290, "dur": 137.173, + "args": { + "External id": 709245,"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": 6305206130200.693, "dur": 103.678, + "args": { + "External id": 709246,"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": 6305206130212.934, "dur": 87.068, + "args": { + "External id": 709247,"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": 6305206130324.657, "dur": 1.991, + "args": { + "External id": 709248,"Record function id": 0, "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": 6305206130373.082, "dur": 6.427, + "args": { + "External id": 709249,"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": 6305206130425.287, "dur": 1.274, + "args": { + "External id": 709250,"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": 6305206130443.512, "dur": 3.383, + "args": { + "External id": 709251,"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": 6305206130459.871, "dur": 0.825, + "args": { + "External id": 709252,"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": 6305206130472.176, "dur": 1.143, + "args": { + "External id": 709253,"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": 6305206130485.137, "dur": 0.940, + "args": { + "External id": 709254,"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": 6305206130498.129, "dur": 3.014, + "args": { + "External id": 709255,"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": 6305206130532.565, "dur": 3.066, + "args": { + "External id": 709256,"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": 6305206130547.404, "dur": 0.841, + "args": { + "External id": 709257,"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": 6305206130642.847, "dur": 2938.491, + "args": { + "External id": 709258,"Record function id": 0, "Ev Idx": 3209 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.15)", "pid": 2338707, "tid": 2379456, + "ts": 6305206130662.511, "dur": 1100.438, + "args": { + "External id": 709259,"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": 6305206130676.956, "dur": 338.930, + "args": { + "External id": 709260,"Record function id": 0, "Ev Idx": 3211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6305206130760.524, "dur": 4.327, + "args": { + "External id": 709261,"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": 6305206130768.093, "dur": 0.874, + "args": { + "External id": 709262,"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": 6305206130771.029, "dur": 3.075, + "args": { + "External id": 709263,"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": 6305206130775.931, "dur": 1.434, + "args": { + "External id": 709264,"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": 6305206130779.037, "dur": 0.847, + "args": { + "External id": 709265,"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": 6305206130781.449, "dur": 1.071, + "args": { + "External id": 709266,"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": 6305206130784.266, "dur": 1.692, + "args": { + "External id": 709267,"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": 6305206130787.109, "dur": 0.927, + "args": { + "External id": 709268,"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": 6305206130789.324, "dur": 0.999, + "args": { + "External id": 709269,"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": 6305206130791.809, "dur": 0.885, + "args": { + "External id": 709270,"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": 6305206130810.055, "dur": 176.589, + "args": { + "External id": 709271,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305206130837.140, "dur": 144.543, + "args": { + "External id": 709272,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305206130863.663, "dur": 16.355, + "args": { + "External id": 709273,"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": 6305206130884.120, "dur": 66.662, + "args": { + "External id": 709274,"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": 6305206130886.892, "dur": 63.608, + "args": { + "External id": 709275,"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": 6305206130891.373, "dur": 5.557, + "args": { + "External id": 709276,"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": 6305206130899.054, "dur": 50.586, + "args": { + "External id": 709277,"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": 6305206131152.621, "dur": 601.313, + "args": { + "External id": 709278,"Record function id": 0, "Ev Idx": 3229 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.14)", "pid": 2338707, "tid": 2379456, + "ts": 6305206131171.692, "dur": 569.387, + "args": { + "External id": 709279,"Record function id": 0, "Ev Idx": 3230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305206131230.564, "dur": 6.160, + "args": { + "External id": 709280,"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": 6305206131252.487, "dur": 32.257, + "args": { + "External id": 709281,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206131257.949, "dur": 1.962, + "args": { + "External id": 709282,"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": 6305206131261.929, "dur": 0.642, + "args": { + "External id": 709283,"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": 6305206131264.500, "dur": 0.716, + "args": { + "External id": 709284,"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": 6305206131266.453, "dur": 0.462, + "args": { + "External id": 709285,"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": 6305206131268.436, "dur": 0.435, + "args": { + "External id": 709286,"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": 6305206131270.770, "dur": 2.665, + "args": { + "External id": 709287,"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": 6305206131274.676, "dur": 0.614, + "args": { + "External id": 709288,"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": 6305206131276.754, "dur": 0.604, + "args": { + "External id": 709289,"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": 6305206131278.817, "dur": 0.396, + "args": { + "External id": 709290,"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": 6305206131294.590, "dur": 50.084, + "args": { + "External id": 709291,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305206131376.158, "dur": 112.233, + "args": { + "External id": 709292,"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": 6305206131386.440, "dur": 3.489, + "args": { + "External id": 709293,"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": 6305206131395.298, "dur": 11.125, + "args": { + "External id": 709294,"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": 6305206131399.825, "dur": 6.211, + "args": { + "External id": 709295,"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": 6305206131403.815, "dur": 0.859, + "args": { + "External id": 709296,"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": 6305206131412.572, "dur": 26.296, + "args": { + "External id": 709297,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206131415.322, "dur": 0.473, + "args": { + "External id": 709298,"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": 6305206131417.672, "dur": 0.458, + "args": { + "External id": 709299,"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": 6305206131419.819, "dur": 2.081, + "args": { + "External id": 709300,"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": 6305206131423.416, "dur": 0.446, + "args": { + "External id": 709301,"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": 6305206131425.618, "dur": 0.432, + "args": { + "External id": 709302,"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": 6305206131427.784, "dur": 0.378, + "args": { + "External id": 709303,"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": 6305206131429.738, "dur": 0.447, + "args": { + "External id": 709304,"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": 6305206131431.778, "dur": 0.471, + "args": { + "External id": 709305,"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": 6305206131434.326, "dur": 0.337, + "args": { + "External id": 709306,"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": 6305206131449.178, "dur": 31.126, + "args": { + "External id": 709307,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305206131554.085, "dur": 118.806, + "args": { + "External id": 709308,"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": 6305206131576.997, "dur": 91.962, + "args": { + "External id": 709309,"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": 6305206131587.620, "dur": 76.865, + "args": { + "External id": 709310,"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": 6305206131687.131, "dur": 1.881, + "args": { + "External id": 709311,"Record function id": 0, "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": 6305206131770.087, "dur": 1789.184, + "args": { + "External id": 709312,"Sequence number": 7674422, "Fwd thread 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": 6305206131770.087, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6305206131880.019, "dur": 111.848, + "args": { + "External id": 709313,"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": 6305206132029.223, "dur": 81.702, + "args": { + "External id": 709314,"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": 6305206132133.007, "dur": 63.080, + "args": { + "External id": 709315,"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": 6305206132209.030, "dur": 34.924, + "args": { + "External id": 709316,"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": 6305206132251.874, "dur": 36.054, + "args": { + "External id": 709317,"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": 6305206132296.448, "dur": 29.983, + "args": { + "External id": 709318,"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": 6305206132333.515, "dur": 32.361, + "args": { + "External id": 709319,"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": 6305206132393.541, "dur": 26.331, + "args": { + "External id": 709320,"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": 6305206132437.918, "dur": 28.987, + "args": { + "External id": 709321,"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": 6305206132485.918, "dur": 18.930, + "args": { + "External id": 709322,"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": 6305206132535.922, "dur": 18.353, + "args": { + "External id": 709323,"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": 6305206132564.652, "dur": 42.443, + "args": { + "External id": 709324,"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": 6305206132611.294, "dur": 33.925, + "args": { + "External id": 709325,"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": 6305206132676.818, "dur": 259.017, + "args": { + "External id": 709326,"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": 6305206132760.836, "dur": 6.155, + "args": { + "External id": 709327,"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": 6305206132769.176, "dur": 2.322, + "args": { + "External id": 709328,"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": 6305206132772.650, "dur": 2.031, + "args": { + "External id": 709329,"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": 6305206132776.231, "dur": 1.596, + "args": { + "External id": 709330,"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": 6305206132823.013, "dur": 5.342, + "args": { + "External id": 709331,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206132825.261, "dur": 2.834, + "args": { + "External id": 709332,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206132830.496, "dur": 38.126, + "args": { + "External id": 709333,"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": 6305206132836.125, "dur": 4.240, + "args": { + "External id": 709334,"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": 6305206132870.289, "dur": 2.085, + "args": { + "External id": 709335,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206132871.329, "dur": 0.975, + "args": { + "External id": 709336,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206132873.990, "dur": 14.727, + "args": { + "External id": 709337,"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": 6305206132875.815, "dur": 0.558, + "args": { + "External id": 709338,"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": 6305206132968.903, "dur": 26.679, + "args": { + "External id": 709339,"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": 6305206133012.011, "dur": 17.356, + "args": { + "External id": 709340,"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": 6305206133037.844, "dur": 86.409, + "args": { + "External id": 709341,"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": 6305206133134.897, "dur": 42.112, + "args": { + "External id": 709342,"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": 6305206133190.435, "dur": 23.070, + "args": { + "External id": 709343,"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": 6305206133220.211, "dur": 33.350, + "args": { + "External id": 709344,"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": 6305206133261.962, "dur": 30.113, + "args": { + "External id": 709345,"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": 6305206133300.035, "dur": 30.685, + "args": { + "External id": 709346,"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": 6305206133349.134, "dur": 24.611, + "args": { + "External id": 709347,"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": 6305206133388.399, "dur": 24.446, + "args": { + "External id": 709348,"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": 6305206133425.495, "dur": 20.295, + "args": { + "External id": 709349,"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": 6305206133461.694, "dur": 15.655, + "args": { + "External id": 709350,"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": 6305206133490.301, "dur": 34.070, + "args": { + "External id": 709351,"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": 6305206133604.774, "dur": 16.261, + "args": { + "External id": 709352,"Record function id": 0, "Ev Idx": 3303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206133608.083, "dur": 11.586, + "args": { + "External id": 709353,"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": 6305206133612.500, "dur": 6.192, + "args": { + "External id": 709354,"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": 6305206133614.497, "dur": 4.065, + "args": { + "External id": 709355,"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": 6305206133625.125, "dur": 17.024, + "args": { + "External id": 709356,"Record function id": 0, "Ev Idx": 3307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206133626.671, "dur": 11.520, + "args": { + "External id": 709357,"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": 6305206133627.332, "dur": 2.167, + "args": { + "External id": 709358,"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": 6305206133628.352, "dur": 1.049, + "args": { + "External id": 709359,"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": 6305206133649.158, "dur": 9.878, + "args": { + "External id": 709360,"Record function id": 0, "Ev Idx": 3311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206133651.108, "dur": 7.304, + "args": { + "External id": 709361,"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": 6305206133652.208, "dur": 5.260, + "args": { + "External id": 709362,"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": 6305206133652.944, "dur": 4.436, + "args": { + "External id": 709363,"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": 6305206133662.621, "dur": 4.566, + "args": { + "External id": 709364,"Record function id": 0, "Ev Idx": 3315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206133664.126, "dur": 2.645, + "args": { + "External id": 709365,"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": 6305206133664.879, "dur": 1.476, + "args": { + "External id": 709366,"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": 6305206133665.473, "dur": 0.803, + "args": { + "External id": 709367,"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": 6305206133670.272, "dur": 4.505, + "args": { + "External id": 709368,"Record function id": 0, "Ev Idx": 3319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206133671.917, "dur": 2.463, + "args": { + "External id": 709369,"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": 6305206133672.531, "dur": 1.303, + "args": { + "External id": 709370,"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": 6305206133673.035, "dur": 0.717, + "args": { + "External id": 709371,"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": 6305206133677.977, "dur": 4.415, + "args": { + "External id": 709372,"Record function id": 0, "Ev Idx": 3323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206133679.238, "dur": 2.734, + "args": { + "External id": 709373,"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": 6305206133679.975, "dur": 1.594, + "args": { + "External id": 709374,"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": 6305206133680.769, "dur": 0.651, + "args": { + "External id": 709375,"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": 6305206133685.600, "dur": 3.883, + "args": { + "External id": 709376,"Record function id": 0, "Ev Idx": 3327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206133687.019, "dur": 2.056, + "args": { + "External id": 709377,"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": 6305206133687.448, "dur": 1.261, + "args": { + "External id": 709378,"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": 6305206133688.023, "dur": 0.605, + "args": { + "External id": 709379,"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": 6305206133692.564, "dur": 3.964, + "args": { + "External id": 709380,"Record function id": 0, "Ev Idx": 3331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206133693.752, "dur": 2.352, + "args": { + "External id": 709381,"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": 6305206133694.526, "dur": 1.172, + "args": { + "External id": 709382,"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": 6305206133695.028, "dur": 0.558, + "args": { + "External id": 709383,"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": 6305206133699.566, "dur": 4.125, + "args": { + "External id": 709384,"Record function id": 0, "Ev Idx": 3335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206133700.738, "dur": 2.550, + "args": { + "External id": 709385,"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": 6305206133701.368, "dur": 1.538, + "args": { + "External id": 709386,"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": 6305206133702.185, "dur": 0.623, + "args": { + "External id": 709387,"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": 6305206133707.414, "dur": 66712.232, + "args": { + "External id": 709388,"Record function id": 0, "Sequence number": 7674421, "Fwd thread id": 1, "Ev Idx": 3339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305206133708.653, "dur": 66702.282, + "args": { + "External id": 709389,"Sequence number": 7674421, "Fwd thread 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": 6305206133708.653, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.15)", "pid": 2338707, "tid": 2379456, + "ts": 6305206133744.030, "dur": 44.073, + "args": { + "External id": 709390,"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": 6305206133795.834, "dur": 65.092, + "args": { + "External id": 709391,"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": 6305206133866.715, "dur": 66535.610, + "args": { + "External id": 709392,"Record function id": 0, "Ev Idx": 3343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305206133958.679, "dur": 7.148, + "args": { + "External id": 709393,"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": 6305206133975.353, "dur": 6.598, + "args": { + "External id": 709394,"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": 6305206133997.048, "dur": 65432.584, + "args": { + "External id": 709395,"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": 6305206134010.928, "dur": 65405.426, + "args": { + "External id": 709396,"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": 6305206134184.829, "dur": 20.079, + "args": { + "External id": 709397,"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": 6305206134226.378, "dur": 65142.954, + "args": { + "External id": 709398,"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": 6305206134229.480, "dur": 65138.753, + "args": { + "External id": 709399,"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": 6305206134234.394, "dur": 11.539, + "args": { + "External id": 709400,"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": 6305206134248.415, "dur": 65115.189, + "args": { + "External id": 709401,"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": 6305206199552.568, "dur": 14.083, + "args": { + "External id": 709402,"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": 6305206199556.816, "dur": 9.302, + "args": { + "External id": 709403,"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": 6305206199599.147, "dur": 436.562, + "args": { + "External id": 709404,"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": 6305206199627.942, "dur": 402.552, + "args": { + "External id": 709405,"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": 6305206199640.822, "dur": 383.757, + "args": { + "External id": 709406,"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": 6305206200089.289, "dur": 3.859, + "args": { + "External id": 709407,"Record function id": 0, "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": 6305206200163.586, "dur": 7.520, + "args": { + "External id": 709408,"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": 6305206200220.754, "dur": 1.551, + "args": { + "External id": 709409,"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": 6305206200239.972, "dur": 3.229, + "args": { + "External id": 709410,"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": 6305206200256.501, "dur": 1.092, + "args": { + "External id": 709411,"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": 6305206200270.474, "dur": 1.131, + "args": { + "External id": 709412,"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": 6305206200283.459, "dur": 1.066, + "args": { + "External id": 709413,"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": 6305206200296.478, "dur": 2.847, + "args": { + "External id": 709414,"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": 6305206200321.609, "dur": 2.327, + "args": { + "External id": 709415,"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": 6305206200336.872, "dur": 0.920, + "args": { + "External id": 709416,"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": 6305206200436.283, "dur": 3065.043, + "args": { + "External id": 709417,"Record function id": 0, "Ev Idx": 3368 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.14)", "pid": 2338707, "tid": 2379456, + "ts": 6305206200456.526, "dur": 1163.008, + "args": { + "External id": 709418,"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": 6305206200471.375, "dur": 370.144, + "args": { + "External id": 709419,"Record function id": 0, "Ev Idx": 3370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6305206200577.805, "dur": 4.761, + "args": { + "External id": 709420,"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": 6305206200586.092, "dur": 0.798, + "args": { + "External id": 709421,"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": 6305206200588.836, "dur": 3.405, + "args": { + "External id": 709422,"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": 6305206200593.881, "dur": 0.639, + "args": { + "External id": 709423,"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": 6305206200596.265, "dur": 1.096, + "args": { + "External id": 709424,"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": 6305206200598.944, "dur": 0.868, + "args": { + "External id": 709425,"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": 6305206200601.334, "dur": 2.342, + "args": { + "External id": 709426,"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": 6305206200605.192, "dur": 0.911, + "args": { + "External id": 709427,"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": 6305206200607.558, "dur": 0.869, + "args": { + "External id": 709428,"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": 6305206200609.876, "dur": 0.851, + "args": { + "External id": 709429,"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": 6305206200628.559, "dur": 180.445, + "args": { + "External id": 709430,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305206200645.279, "dur": 158.237, + "args": { + "External id": 709431,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305206200673.145, "dur": 21.541, + "args": { + "External id": 709432,"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": 6305206200698.610, "dur": 72.602, + "args": { + "External id": 709433,"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": 6305206200701.643, "dur": 69.232, + "args": { + "External id": 709434,"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": 6305206200706.183, "dur": 5.656, + "args": { + "External id": 709435,"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": 6305206200714.010, "dur": 56.078, + "args": { + "External id": 709436,"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": 6305206200927.901, "dur": 683.179, + "args": { + "External id": 709437,"Record function id": 0, "Ev Idx": 3388 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.13)", "pid": 2338707, "tid": 2379456, + "ts": 6305206200946.348, "dur": 647.846, + "args": { + "External id": 709438,"Record function id": 0, "Ev Idx": 3389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305206201004.121, "dur": 4.886, + "args": { + "External id": 709439,"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": 6305206201024.637, "dur": 91.800, + "args": { + "External id": 709440,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206201034.409, "dur": 1.932, + "args": { + "External id": 709441,"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": 6305206201038.666, "dur": 0.576, + "args": { + "External id": 709442,"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": 6305206201040.837, "dur": 0.422, + "args": { + "External id": 709443,"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": 6305206201043.220, "dur": 0.622, + "args": { + "External id": 709444,"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": 6305206201045.428, "dur": 0.413, + "args": { + "External id": 709445,"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": 6305206201047.609, "dur": 2.355, + "args": { + "External id": 709446,"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": 6305206201103.081, "dur": 1.157, + "args": { + "External id": 709447,"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": 6305206201107.735, "dur": 0.526, + "args": { + "External id": 709448,"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": 6305206201110.156, "dur": 0.458, + "args": { + "External id": 709449,"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": 6305206201127.538, "dur": 53.701, + "args": { + "External id": 709450,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305206201215.928, "dur": 121.094, + "args": { + "External id": 709451,"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": 6305206201227.490, "dur": 4.812, + "args": { + "External id": 709452,"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": 6305206201238.175, "dur": 11.293, + "args": { + "External id": 709453,"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": 6305206201242.828, "dur": 6.206, + "args": { + "External id": 709454,"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": 6305206201247.088, "dur": 0.626, + "args": { + "External id": 709455,"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": 6305206201256.319, "dur": 26.739, + "args": { + "External id": 709456,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206201258.775, "dur": 0.499, + "args": { + "External id": 709457,"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": 6305206201261.112, "dur": 0.457, + "args": { + "External id": 709458,"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": 6305206201263.353, "dur": 3.043, + "args": { + "External id": 709459,"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": 6305206201268.231, "dur": 0.373, + "args": { + "External id": 709460,"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": 6305206201270.354, "dur": 0.433, + "args": { + "External id": 709461,"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": 6305206201272.672, "dur": 0.419, + "args": { + "External id": 709462,"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": 6305206201274.608, "dur": 0.442, + "args": { + "External id": 709463,"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": 6305206201276.586, "dur": 0.381, + "args": { + "External id": 709464,"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": 6305206201278.761, "dur": 0.435, + "args": { + "External id": 709465,"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": 6305206201295.181, "dur": 34.156, + "args": { + "External id": 709466,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305206201387.658, "dur": 113.299, + "args": { + "External id": 709467,"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": 6305206201411.006, "dur": 86.054, + "args": { + "External id": 709468,"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": 6305206201421.570, "dur": 70.343, + "args": { + "External id": 709469,"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": 6305206201531.686, "dur": 2.470, + "args": { + "External id": 709470,"Record function id": 0, "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": 6305206201627.507, "dur": 1853.312, + "args": { + "External id": 709471,"Sequence number": 7674420, "Fwd thread 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": 6305206201627.507, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6305206201737.994, "dur": 113.400, + "args": { + "External id": 709472,"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": 6305206201889.804, "dur": 40.957, + "args": { + "External id": 709473,"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": 6305206201948.997, "dur": 54.204, + "args": { + "External id": 709474,"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": 6305206202015.365, "dur": 34.175, + "args": { + "External id": 709475,"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": 6305206202114.067, "dur": 46.861, + "args": { + "External id": 709476,"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": 6305206202171.473, "dur": 31.638, + "args": { + "External id": 709477,"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": 6305206202211.053, "dur": 30.067, + "args": { + "External id": 709478,"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": 6305206202270.518, "dur": 26.552, + "args": { + "External id": 709479,"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": 6305206202314.155, "dur": 28.361, + "args": { + "External id": 709480,"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": 6305206202362.605, "dur": 19.532, + "args": { + "External id": 709481,"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": 6305206202393.916, "dur": 15.382, + "args": { + "External id": 709482,"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": 6305206202418.773, "dur": 38.233, + "args": { + "External id": 709483,"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": 6305206202460.946, "dur": 35.644, + "args": { + "External id": 709484,"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": 6305206202547.173, "dur": 261.431, + "args": { + "External id": 709485,"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": 6305206202629.187, "dur": 5.885, + "args": { + "External id": 709486,"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": 6305206202637.654, "dur": 2.445, + "args": { + "External id": 709487,"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": 6305206202641.442, "dur": 1.931, + "args": { + "External id": 709488,"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": 6305206202644.706, "dur": 2.044, + "args": { + "External id": 709489,"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": 6305206202699.199, "dur": 5.620, + "args": { + "External id": 709490,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206202701.577, "dur": 3.046, + "args": { + "External id": 709491,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206202707.110, "dur": 36.316, + "args": { + "External id": 709492,"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": 6305206202712.892, "dur": 3.972, + "args": { + "External id": 709493,"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": 6305206202745.122, "dur": 1.871, + "args": { + "External id": 709494,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206202746.204, "dur": 0.707, + "args": { + "External id": 709495,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206202748.411, "dur": 16.459, + "args": { + "External id": 709496,"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": 6305206202750.188, "dur": 0.645, + "args": { + "External id": 709497,"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": 6305206202841.437, "dur": 28.607, + "args": { + "External id": 709498,"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": 6305206202889.916, "dur": 17.848, + "args": { + "External id": 709499,"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": 6305206202916.685, "dur": 51.750, + "args": { + "External id": 709500,"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": 6305206202976.311, "dur": 45.220, + "args": { + "External id": 709501,"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": 6305206203033.710, "dur": 79.305, + "args": { + "External id": 709502,"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": 6305206203134.545, "dur": 43.728, + "args": { + "External id": 709503,"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": 6305206203187.532, "dur": 31.128, + "args": { + "External id": 709504,"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": 6305206203226.180, "dur": 34.717, + "args": { + "External id": 709505,"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": 6305206203283.486, "dur": 31.792, + "args": { + "External id": 709506,"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": 6305206203331.131, "dur": 24.330, + "args": { + "External id": 709507,"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": 6305206203369.760, "dur": 17.422, + "args": { + "External id": 709508,"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": 6305206203404.312, "dur": 14.888, + "args": { + "External id": 709509,"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": 6305206203432.713, "dur": 16.112, + "args": { + "External id": 709510,"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": 6305206203542.536, "dur": 17.738, + "args": { + "External id": 709511,"Record function id": 0, "Ev Idx": 3462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206203546.505, "dur": 12.577, + "args": { + "External id": 709512,"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": 6305206203550.732, "dur": 6.959, + "args": { + "External id": 709513,"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": 6305206203552.729, "dur": 4.751, + "args": { + "External id": 709514,"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": 6305206203564.483, "dur": 5.073, + "args": { + "External id": 709515,"Record function id": 0, "Ev Idx": 3466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206203566.010, "dur": 3.141, + "args": { + "External id": 709516,"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": 6305206203566.585, "dur": 2.100, + "args": { + "External id": 709517,"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": 6305206203567.306, "dur": 1.287, + "args": { + "External id": 709518,"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": 6305206203572.921, "dur": 6.865, + "args": { + "External id": 709519,"Record function id": 0, "Ev Idx": 3470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206203574.158, "dur": 5.224, + "args": { + "External id": 709520,"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": 6305206203574.726, "dur": 4.176, + "args": { + "External id": 709521,"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": 6305206203575.178, "dur": 3.662, + "args": { + "External id": 709522,"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": 6305206203583.129, "dur": 3.611, + "args": { + "External id": 709523,"Record function id": 0, "Ev Idx": 3474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206203584.215, "dur": 2.130, + "args": { + "External id": 709524,"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": 6305206203584.764, "dur": 1.170, + "args": { + "External id": 709525,"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": 6305206203585.053, "dur": 0.817, + "args": { + "External id": 709526,"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": 6305206203589.999, "dur": 3.703, + "args": { + "External id": 709527,"Record function id": 0, "Ev Idx": 3478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206203591.259, "dur": 2.034, + "args": { + "External id": 709528,"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": 6305206203591.716, "dur": 1.132, + "args": { + "External id": 709529,"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": 6305206203592.040, "dur": 0.715, + "args": { + "External id": 709530,"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": 6305206203596.975, "dur": 4.180, + "args": { + "External id": 709531,"Record function id": 0, "Ev Idx": 3482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206203598.180, "dur": 2.587, + "args": { + "External id": 709532,"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": 6305206203598.975, "dur": 1.393, + "args": { + "External id": 709533,"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": 6305206203599.550, "dur": 0.714, + "args": { + "External id": 709534,"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": 6305206203604.274, "dur": 3.772, + "args": { + "External id": 709535,"Record function id": 0, "Ev Idx": 3486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206203605.744, "dur": 1.916, + "args": { + "External id": 709536,"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": 6305206203606.266, "dur": 0.994, + "args": { + "External id": 709537,"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": 6305206203606.595, "dur": 0.563, + "args": { + "External id": 709538,"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": 6305206203611.195, "dur": 3.811, + "args": { + "External id": 709539,"Record function id": 0, "Ev Idx": 3490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206203612.314, "dur": 2.271, + "args": { + "External id": 709540,"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": 6305206203613.013, "dur": 1.165, + "args": { + "External id": 709541,"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": 6305206203613.283, "dur": 0.831, + "args": { + "External id": 709542,"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": 6305206203618.120, "dur": 3.690, + "args": { + "External id": 709543,"Record function id": 0, "Ev Idx": 3494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206203619.309, "dur": 2.106, + "args": { + "External id": 709544,"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": 6305206203619.749, "dur": 1.261, + "args": { + "External id": 709545,"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": 6305206203620.153, "dur": 0.769, + "args": { + "External id": 709546,"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": 6305206203625.964, "dur": 62839.347, + "args": { + "External id": 709547,"Record function id": 0, "Sequence number": 7674419, "Fwd thread id": 1, "Ev Idx": 3498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305206203627.373, "dur": 62828.578, + "args": { + "External id": 709548,"Sequence number": 7674419, "Fwd thread 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": 6305206203627.373, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.14)", "pid": 2338707, "tid": 2379456, + "ts": 6305206203658.991, "dur": 40.029, + "args": { + "External id": 709549,"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": 6305206203706.399, "dur": 62.063, + "args": { + "External id": 709550,"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": 6305206203774.440, "dur": 62673.171, + "args": { + "External id": 709551,"Record function id": 0, "Ev Idx": 3502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305206203865.944, "dur": 6.900, + "args": { + "External id": 709552,"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": 6305206203882.922, "dur": 6.532, + "args": { + "External id": 709553,"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": 6305206203905.030, "dur": 61658.420, + "args": { + "External id": 709554,"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": 6305206203918.731, "dur": 61630.924, + "args": { + "External id": 709555,"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": 6305206204044.516, "dur": 59.698, + "args": { + "External id": 709556,"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": 6305206204128.831, "dur": 61361.819, + "args": { + "External id": 709557,"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": 6305206204132.449, "dur": 61357.119, + "args": { + "External id": 709558,"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": 6305206204137.695, "dur": 12.808, + "args": { + "External id": 709559,"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": 6305206204152.795, "dur": 61332.073, + "args": { + "External id": 709560,"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": 6305206265671.907, "dur": 12.058, + "args": { + "External id": 709561,"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": 6305206265675.947, "dur": 7.613, + "args": { + "External id": 709562,"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": 6305206265715.635, "dur": 415.808, + "args": { + "External id": 709563,"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": 6305206265745.241, "dur": 379.936, + "args": { + "External id": 709564,"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": 6305206265757.440, "dur": 361.316, + "args": { + "External id": 709565,"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": 6305206266153.349, "dur": 2.206, + "args": { + "External id": 709566,"Record function id": 0, "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": 6305206266219.447, "dur": 10.862, + "args": { + "External id": 709567,"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": 6305206266281.983, "dur": 1.530, + "args": { + "External id": 709568,"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": 6305206266301.667, "dur": 3.164, + "args": { + "External id": 709569,"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": 6305206266318.430, "dur": 1.012, + "args": { + "External id": 709570,"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": 6305206266331.436, "dur": 1.412, + "args": { + "External id": 709571,"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": 6305206266343.541, "dur": 0.946, + "args": { + "External id": 709572,"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": 6305206266355.237, "dur": 3.278, + "args": { + "External id": 709573,"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": 6305206266370.765, "dur": 2.499, + "args": { + "External id": 709574,"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": 6305206266384.746, "dur": 0.742, + "args": { + "External id": 709575,"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": 6305206266480.601, "dur": 3084.413, + "args": { + "External id": 709576,"Record function id": 0, "Ev Idx": 3527 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.13)", "pid": 2338707, "tid": 2379456, + "ts": 6305206266500.156, "dur": 1155.009, + "args": { + "External id": 709577,"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": 6305206266534.500, "dur": 357.862, + "args": { + "External id": 709578,"Record function id": 0, "Ev Idx": 3529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6305206266624.186, "dur": 5.010, + "args": { + "External id": 709579,"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": 6305206266632.634, "dur": 1.362, + "args": { + "External id": 709580,"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": 6305206266636.070, "dur": 3.283, + "args": { + "External id": 709581,"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": 6305206266641.056, "dur": 0.700, + "args": { + "External id": 709582,"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": 6305206266643.144, "dur": 0.632, + "args": { + "External id": 709583,"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": 6305206266645.273, "dur": 0.745, + "args": { + "External id": 709584,"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": 6305206266647.407, "dur": 2.272, + "args": { + "External id": 709585,"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": 6305206266651.248, "dur": 0.931, + "args": { + "External id": 709586,"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": 6305206266653.358, "dur": 0.871, + "args": { + "External id": 709587,"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": 6305206266655.561, "dur": 4.741, + "args": { + "External id": 709588,"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": 6305206266678.248, "dur": 180.990, + "args": { + "External id": 709589,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305206266695.453, "dur": 158.874, + "args": { + "External id": 709590,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305206266735.854, "dur": 16.918, + "args": { + "External id": 709591,"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": 6305206266756.958, "dur": 67.329, + "args": { + "External id": 709592,"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": 6305206266759.805, "dur": 64.193, + "args": { + "External id": 709593,"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": 6305206266764.059, "dur": 5.682, + "args": { + "External id": 709594,"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": 6305206266771.766, "dur": 51.539, + "args": { + "External id": 709595,"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": 6305206266976.444, "dur": 670.010, + "args": { + "External id": 709596,"Record function id": 0, "Ev Idx": 3547 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.12)", "pid": 2338707, "tid": 2379456, + "ts": 6305206266993.792, "dur": 638.946, + "args": { + "External id": 709597,"Record function id": 0, "Ev Idx": 3548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305206267052.037, "dur": 43.242, + "args": { + "External id": 709598,"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": 6305206267113.824, "dur": 39.176, + "args": { + "External id": 709599,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206267119.447, "dur": 1.885, + "args": { + "External id": 709600,"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": 6305206267123.111, "dur": 0.694, + "args": { + "External id": 709601,"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": 6305206267125.450, "dur": 0.537, + "args": { + "External id": 709602,"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": 6305206267127.679, "dur": 0.375, + "args": { + "External id": 709603,"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": 6305206267129.947, "dur": 0.442, + "args": { + "External id": 709604,"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": 6305206267131.960, "dur": 2.553, + "args": { + "External id": 709605,"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": 6305206267136.168, "dur": 0.485, + "args": { + "External id": 709606,"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": 6305206267144.361, "dur": 0.588, + "args": { + "External id": 709607,"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": 6305206267146.446, "dur": 0.341, + "args": { + "External id": 709608,"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": 6305206267166.557, "dur": 50.488, + "args": { + "External id": 709609,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305206267250.122, "dur": 122.210, + "args": { + "External id": 709610,"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": 6305206267264.597, "dur": 3.505, + "args": { + "External id": 709611,"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": 6305206267273.645, "dur": 10.711, + "args": { + "External id": 709612,"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": 6305206267278.359, "dur": 5.587, + "args": { + "External id": 709613,"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": 6305206267282.048, "dur": 0.563, + "args": { + "External id": 709614,"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": 6305206267291.284, "dur": 24.252, + "args": { + "External id": 709615,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206267293.420, "dur": 0.538, + "args": { + "External id": 709616,"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": 6305206267295.768, "dur": 0.408, + "args": { + "External id": 709617,"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": 6305206267297.387, "dur": 2.548, + "args": { + "External id": 709618,"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": 6305206267301.459, "dur": 0.308, + "args": { + "External id": 709619,"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": 6305206267303.225, "dur": 0.511, + "args": { + "External id": 709620,"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": 6305206267305.041, "dur": 0.408, + "args": { + "External id": 709621,"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": 6305206267306.913, "dur": 0.467, + "args": { + "External id": 709622,"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": 6305206267308.935, "dur": 0.451, + "args": { + "External id": 709623,"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": 6305206267310.672, "dur": 0.442, + "args": { + "External id": 709624,"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": 6305206267326.287, "dur": 37.942, + "args": { + "External id": 709625,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305206267423.703, "dur": 133.564, + "args": { + "External id": 709626,"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": 6305206267446.728, "dur": 106.160, + "args": { + "External id": 709627,"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": 6305206267456.956, "dur": 91.412, + "args": { + "External id": 709628,"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": 6305206267573.376, "dur": 2.027, + "args": { + "External id": 709629,"Record function id": 0, "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": 6305206267662.756, "dur": 1879.464, + "args": { + "External id": 709630,"Sequence number": 7674418, "Fwd thread 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": 6305206267662.756, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6305206267776.676, "dur": 114.144, + "args": { + "External id": 709631,"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": 6305206267932.077, "dur": 38.954, + "args": { + "External id": 709632,"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": 6305206268017.829, "dur": 104.781, + "args": { + "External id": 709633,"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": 6305206268141.728, "dur": 38.108, + "args": { + "External id": 709634,"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": 6305206268187.943, "dur": 34.299, + "args": { + "External id": 709635,"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": 6305206268230.887, "dur": 29.048, + "args": { + "External id": 709636,"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": 6305206268267.218, "dur": 32.192, + "args": { + "External id": 709637,"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": 6305206268328.529, "dur": 28.499, + "args": { + "External id": 709638,"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": 6305206268377.091, "dur": 28.857, + "args": { + "External id": 709639,"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": 6305206268427.009, "dur": 18.733, + "args": { + "External id": 709640,"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": 6305206268458.112, "dur": 14.906, + "args": { + "External id": 709641,"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": 6305206268482.551, "dur": 54.127, + "args": { + "External id": 709642,"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": 6305206268542.468, "dur": 38.168, + "args": { + "External id": 709643,"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": 6305206268614.183, "dur": 256.046, + "args": { + "External id": 709644,"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": 6305206268695.066, "dur": 6.287, + "args": { + "External id": 709645,"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": 6305206268703.349, "dur": 2.104, + "args": { + "External id": 709646,"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": 6305206268706.708, "dur": 1.700, + "args": { + "External id": 709647,"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": 6305206268709.657, "dur": 1.760, + "args": { + "External id": 709648,"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": 6305206268758.502, "dur": 5.428, + "args": { + "External id": 709649,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206268760.891, "dur": 2.874, + "args": { + "External id": 709650,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206268766.366, "dur": 36.652, + "args": { + "External id": 709651,"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": 6305206268774.874, "dur": 3.469, + "args": { + "External id": 709652,"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": 6305206268804.748, "dur": 1.898, + "args": { + "External id": 709653,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206268805.800, "dur": 0.770, + "args": { + "External id": 709654,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206268807.986, "dur": 14.027, + "args": { + "External id": 709655,"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": 6305206268809.545, "dur": 0.682, + "args": { + "External id": 709656,"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": 6305206268904.424, "dur": 26.704, + "args": { + "External id": 709657,"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": 6305206268947.065, "dur": 16.154, + "args": { + "External id": 709658,"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": 6305206268971.419, "dur": 41.585, + "args": { + "External id": 709659,"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": 6305206269020.760, "dur": 92.039, + "args": { + "External id": 709660,"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": 6305206269130.522, "dur": 28.022, + "args": { + "External id": 709661,"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": 6305206269166.057, "dur": 32.726, + "args": { + "External id": 709662,"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": 6305206269207.467, "dur": 29.519, + "args": { + "External id": 709663,"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": 6305206269244.274, "dur": 31.858, + "args": { + "External id": 709664,"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": 6305206269310.733, "dur": 34.875, + "args": { + "External id": 709665,"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": 6305206269363.393, "dur": 25.143, + "args": { + "External id": 709666,"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": 6305206269402.553, "dur": 22.440, + "args": { + "External id": 709667,"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": 6305206269442.389, "dur": 16.378, + "args": { + "External id": 709668,"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": 6305206269471.803, "dur": 21.862, + "args": { + "External id": 709669,"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": 6305206269588.232, "dur": 16.501, + "args": { + "External id": 709670,"Record function id": 0, "Ev Idx": 3621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206269591.807, "dur": 11.782, + "args": { + "External id": 709671,"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": 6305206269596.357, "dur": 6.150, + "args": { + "External id": 709672,"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": 6305206269598.141, "dur": 4.240, + "args": { + "External id": 709673,"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": 6305206269612.236, "dur": 5.218, + "args": { + "External id": 709674,"Record function id": 0, "Ev Idx": 3625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206269613.461, "dur": 3.485, + "args": { + "External id": 709675,"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": 6305206269614.088, "dur": 2.262, + "args": { + "External id": 709676,"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": 6305206269614.969, "dur": 1.268, + "args": { + "External id": 709677,"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": 6305206269620.851, "dur": 5.985, + "args": { + "External id": 709678,"Record function id": 0, "Ev Idx": 3629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206269621.988, "dur": 4.422, + "args": { + "External id": 709679,"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": 6305206269622.553, "dur": 3.358, + "args": { + "External id": 709680,"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": 6305206269622.843, "dur": 2.985, + "args": { + "External id": 709681,"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": 6305206269630.246, "dur": 3.986, + "args": { + "External id": 709682,"Record function id": 0, "Ev Idx": 3633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206269631.420, "dur": 2.392, + "args": { + "External id": 709683,"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": 6305206269631.913, "dur": 1.481, + "args": { + "External id": 709684,"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": 6305206269632.485, "dur": 0.837, + "args": { + "External id": 709685,"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": 6305206269637.568, "dur": 3.769, + "args": { + "External id": 709686,"Record function id": 0, "Ev Idx": 3637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206269638.668, "dur": 2.213, + "args": { + "External id": 709687,"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": 6305206269639.306, "dur": 1.094, + "args": { + "External id": 709688,"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": 6305206269639.714, "dur": 0.618, + "args": { + "External id": 709689,"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": 6305206269644.746, "dur": 4.356, + "args": { + "External id": 709690,"Record function id": 0, "Ev Idx": 3641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206269646.030, "dur": 2.656, + "args": { + "External id": 709691,"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": 6305206269646.488, "dur": 1.798, + "args": { + "External id": 709692,"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": 6305206269647.135, "dur": 1.039, + "args": { + "External id": 709693,"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": 6305206269652.412, "dur": 3.836, + "args": { + "External id": 709694,"Record function id": 0, "Ev Idx": 3645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206269653.632, "dur": 2.197, + "args": { + "External id": 709695,"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": 6305206269654.320, "dur": 1.075, + "args": { + "External id": 709696,"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": 6305206269654.594, "dur": 0.718, + "args": { + "External id": 709697,"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": 6305206269659.472, "dur": 3.601, + "args": { + "External id": 709698,"Record function id": 0, "Ev Idx": 3649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206269660.678, "dur": 1.980, + "args": { + "External id": 709699,"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": 6305206269661.229, "dur": 1.009, + "args": { + "External id": 709700,"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": 6305206269661.513, "dur": 0.652, + "args": { + "External id": 709701,"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": 6305206269666.161, "dur": 7.004, + "args": { + "External id": 709702,"Record function id": 0, "Ev Idx": 3653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206269670.753, "dur": 2.017, + "args": { + "External id": 709703,"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": 6305206269671.187, "dur": 1.163, + "args": { + "External id": 709704,"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": 6305206269671.714, "dur": 0.547, + "args": { + "External id": 709705,"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": 6305206269677.092, "dur": 62644.580, + "args": { + "External id": 709706,"Record function id": 0, "Sequence number": 7674417, "Fwd thread id": 1, "Ev Idx": 3657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305206269678.413, "dur": 62634.277, + "args": { + "External id": 709707,"Sequence number": 7674417, "Fwd thread 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": 6305206269678.413, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.13)", "pid": 2338707, "tid": 2379456, + "ts": 6305206269709.677, "dur": 40.311, + "args": { + "External id": 709708,"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": 6305206269757.581, "dur": 63.863, + "args": { + "External id": 709709,"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": 6305206269827.293, "dur": 62477.036, + "args": { + "External id": 709710,"Record function id": 0, "Ev Idx": 3661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305206269915.815, "dur": 7.111, + "args": { + "External id": 709711,"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": 6305206269932.571, "dur": 6.800, + "args": { + "External id": 709712,"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": 6305206269954.262, "dur": 61411.665, + "args": { + "External id": 709713,"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": 6305206269968.459, "dur": 61384.263, + "args": { + "External id": 709714,"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": 6305206270128.051, "dur": 20.548, + "args": { + "External id": 709715,"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": 6305206270169.675, "dur": 61133.679, + "args": { + "External id": 709716,"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": 6305206270172.950, "dur": 61129.273, + "args": { + "External id": 709717,"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": 6305206270177.682, "dur": 12.971, + "args": { + "External id": 709718,"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": 6305206270192.595, "dur": 61104.588, + "args": { + "External id": 709719,"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": 6305206331476.268, "dur": 12.667, + "args": { + "External id": 709720,"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": 6305206331480.122, "dur": 8.423, + "args": { + "External id": 709721,"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": 6305206331535.069, "dur": 413.636, + "args": { + "External id": 709722,"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": 6305206331563.993, "dur": 379.724, + "args": { + "External id": 709723,"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": 6305206331576.409, "dur": 361.948, + "args": { + "External id": 709724,"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": 6305206331968.636, "dur": 2.221, + "args": { + "External id": 709725,"Record function id": 0, "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": 6305206332033.688, "dur": 6.822, + "args": { + "External id": 709726,"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": 6305206332128.577, "dur": 2.780, + "args": { + "External id": 709727,"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": 6305206332149.992, "dur": 3.256, + "args": { + "External id": 709728,"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": 6305206332165.757, "dur": 1.639, + "args": { + "External id": 709729,"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": 6305206332178.928, "dur": 1.274, + "args": { + "External id": 709730,"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": 6305206332191.751, "dur": 1.073, + "args": { + "External id": 709731,"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": 6305206332205.198, "dur": 2.772, + "args": { + "External id": 709732,"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": 6305206332220.214, "dur": 2.437, + "args": { + "External id": 709733,"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": 6305206332233.401, "dur": 0.971, + "args": { + "External id": 709734,"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": 6305206332342.899, "dur": 2990.522, + "args": { + "External id": 709735,"Record function id": 0, "Ev Idx": 3686 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.12)", "pid": 2338707, "tid": 2379456, + "ts": 6305206332363.690, "dur": 1119.221, + "args": { + "External id": 709736,"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": 6305206332379.184, "dur": 385.685, + "args": { + "External id": 709737,"Record function id": 0, "Ev Idx": 3688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6305206332466.505, "dur": 7.608, + "args": { + "External id": 709738,"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": 6305206332477.345, "dur": 0.954, + "args": { + "External id": 709739,"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": 6305206332480.231, "dur": 3.004, + "args": { + "External id": 709740,"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": 6305206332484.957, "dur": 0.905, + "args": { + "External id": 709741,"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": 6305206332487.359, "dur": 1.091, + "args": { + "External id": 709742,"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": 6305206332489.941, "dur": 0.824, + "args": { + "External id": 709743,"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": 6305206332492.385, "dur": 2.382, + "args": { + "External id": 709744,"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": 6305206332496.518, "dur": 1.001, + "args": { + "External id": 709745,"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": 6305206332498.853, "dur": 0.971, + "args": { + "External id": 709746,"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": 6305206332501.689, "dur": 0.630, + "args": { + "External id": 709747,"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": 6305206332538.314, "dur": 192.159, + "args": { + "External id": 709748,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305206332572.999, "dur": 151.757, + "args": { + "External id": 709749,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305206332591.431, "dur": 17.439, + "args": { + "External id": 709750,"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": 6305206332613.059, "dur": 80.453, + "args": { + "External id": 709751,"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": 6305206332615.680, "dur": 77.453, + "args": { + "External id": 709752,"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": 6305206332630.472, "dur": 5.842, + "args": { + "External id": 709753,"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": 6305206332638.362, "dur": 54.055, + "args": { + "External id": 709754,"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": 6305206332846.656, "dur": 627.850, + "args": { + "External id": 709755,"Record function id": 0, "Ev Idx": 3706 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.11)", "pid": 2338707, "tid": 2379456, + "ts": 6305206332865.490, "dur": 596.268, + "args": { + "External id": 709756,"Record function id": 0, "Ev Idx": 3707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305206332924.827, "dur": 4.993, + "args": { + "External id": 709757,"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": 6305206332944.726, "dur": 30.968, + "args": { + "External id": 709758,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206332950.101, "dur": 1.829, + "args": { + "External id": 709759,"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": 6305206332953.727, "dur": 0.735, + "args": { + "External id": 709760,"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": 6305206332955.960, "dur": 0.608, + "args": { + "External id": 709761,"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": 6305206332958.274, "dur": 0.400, + "args": { + "External id": 709762,"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": 6305206332960.162, "dur": 0.529, + "args": { + "External id": 709763,"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": 6305206332962.254, "dur": 2.313, + "args": { + "External id": 709764,"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": 6305206332966.047, "dur": 0.447, + "args": { + "External id": 709765,"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": 6305206332968.103, "dur": 0.551, + "args": { + "External id": 709766,"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": 6305206332970.229, "dur": 0.487, + "args": { + "External id": 709767,"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": 6305206332984.833, "dur": 41.397, + "args": { + "External id": 709768,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305206333100.528, "dur": 123.472, + "args": { + "External id": 709769,"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": 6305206333113.193, "dur": 5.202, + "args": { + "External id": 709770,"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": 6305206333124.601, "dur": 11.588, + "args": { + "External id": 709771,"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": 6305206333129.353, "dur": 6.430, + "args": { + "External id": 709772,"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": 6305206333133.145, "dur": 0.676, + "args": { + "External id": 709773,"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": 6305206333144.007, "dur": 25.662, + "args": { + "External id": 709774,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206333146.314, "dur": 0.492, + "args": { + "External id": 709775,"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": 6305206333148.558, "dur": 0.459, + "args": { + "External id": 709776,"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": 6305206333150.661, "dur": 2.399, + "args": { + "External id": 709777,"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": 6305206333154.588, "dur": 0.553, + "args": { + "External id": 709778,"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": 6305206333156.574, "dur": 0.427, + "args": { + "External id": 709779,"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": 6305206333158.589, "dur": 0.372, + "args": { + "External id": 709780,"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": 6305206333160.728, "dur": 0.470, + "args": { + "External id": 709781,"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": 6305206333162.901, "dur": 0.287, + "args": { + "External id": 709782,"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": 6305206333164.838, "dur": 0.519, + "args": { + "External id": 709783,"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": 6305206333183.404, "dur": 32.610, + "args": { + "External id": 709784,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305206333269.934, "dur": 116.964, + "args": { + "External id": 709785,"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": 6305206333294.281, "dur": 89.122, + "args": { + "External id": 709786,"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": 6305206333304.201, "dur": 74.759, + "args": { + "External id": 709787,"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": 6305206333407.133, "dur": 1.855, + "args": { + "External id": 709788,"Record function id": 0, "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": 6305206333490.566, "dur": 1821.981, + "args": { + "External id": 709789,"Sequence number": 7674416, "Fwd thread 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": 6305206333490.566, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6305206333626.832, "dur": 113.725, + "args": { + "External id": 709790,"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": 6305206333782.626, "dur": 43.980, + "args": { + "External id": 709791,"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": 6305206333843.522, "dur": 53.205, + "args": { + "External id": 709792,"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": 6305206333908.950, "dur": 34.600, + "args": { + "External id": 709793,"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": 6305206333950.042, "dur": 36.121, + "args": { + "External id": 709794,"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": 6305206333992.815, "dur": 27.285, + "args": { + "External id": 709795,"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": 6305206334027.309, "dur": 65.215, + "args": { + "External id": 709796,"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": 6305206334126.324, "dur": 25.590, + "args": { + "External id": 709797,"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": 6305206334173.819, "dur": 32.301, + "args": { + "External id": 709798,"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": 6305206334227.811, "dur": 22.626, + "args": { + "External id": 709799,"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": 6305206334264.834, "dur": 14.918, + "args": { + "External id": 709800,"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": 6305206334289.711, "dur": 45.257, + "args": { + "External id": 709801,"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": 6305206334339.091, "dur": 35.639, + "args": { + "External id": 709802,"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": 6305206334412.658, "dur": 272.735, + "args": { + "External id": 709803,"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": 6305206334492.642, "dur": 6.069, + "args": { + "External id": 709804,"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": 6305206334500.580, "dur": 2.484, + "args": { + "External id": 709805,"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": 6305206334504.269, "dur": 18.652, + "args": { + "External id": 709806,"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": 6305206334525.236, "dur": 2.410, + "args": { + "External id": 709807,"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": 6305206334573.036, "dur": 7.186, + "args": { + "External id": 709808,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206334577.091, "dur": 2.955, + "args": { + "External id": 709809,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206334581.947, "dur": 38.071, + "args": { + "External id": 709810,"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": 6305206334588.688, "dur": 3.393, + "args": { + "External id": 709811,"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": 6305206334621.568, "dur": 1.777, + "args": { + "External id": 709812,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206334622.799, "dur": 0.467, + "args": { + "External id": 709813,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206334624.758, "dur": 13.520, + "args": { + "External id": 709814,"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": 6305206334626.627, "dur": 0.418, + "args": { + "External id": 709815,"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": 6305206334719.501, "dur": 27.224, + "args": { + "External id": 709816,"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": 6305206334762.979, "dur": 17.252, + "args": { + "External id": 709817,"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": 6305206334788.582, "dur": 47.324, + "args": { + "External id": 709818,"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": 6305206334843.584, "dur": 39.532, + "args": { + "External id": 709819,"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": 6305206334895.026, "dur": 20.782, + "args": { + "External id": 709820,"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": 6305206334922.686, "dur": 30.589, + "args": { + "External id": 709821,"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": 6305206334961.042, "dur": 42.573, + "args": { + "External id": 709822,"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": 6305206335018.887, "dur": 75.104, + "args": { + "External id": 709823,"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": 6305206335120.015, "dur": 29.174, + "args": { + "External id": 709824,"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": 6305206335164.536, "dur": 24.091, + "args": { + "External id": 709825,"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": 6305206335202.485, "dur": 20.506, + "args": { + "External id": 709826,"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": 6305206335238.947, "dur": 14.240, + "args": { + "External id": 709827,"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": 6305206335265.638, "dur": 15.230, + "args": { + "External id": 709828,"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": 6305206335355.948, "dur": 15.233, + "args": { + "External id": 709829,"Record function id": 0, "Ev Idx": 3780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206335359.319, "dur": 10.959, + "args": { + "External id": 709830,"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": 6305206335363.709, "dur": 5.660, + "args": { + "External id": 709831,"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": 6305206335365.062, "dur": 4.182, + "args": { + "External id": 709832,"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": 6305206335375.040, "dur": 4.909, + "args": { + "External id": 709833,"Record function id": 0, "Ev Idx": 3784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206335376.522, "dur": 3.003, + "args": { + "External id": 709834,"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": 6305206335377.405, "dur": 1.628, + "args": { + "External id": 709835,"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": 6305206335377.828, "dur": 1.088, + "args": { + "External id": 709836,"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": 6305206335383.207, "dur": 6.302, + "args": { + "External id": 709837,"Record function id": 0, "Ev Idx": 3788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206335384.647, "dur": 4.429, + "args": { + "External id": 709838,"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": 6305206335385.188, "dur": 3.369, + "args": { + "External id": 709839,"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": 6305206335385.613, "dur": 2.875, + "args": { + "External id": 709840,"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": 6305206335392.811, "dur": 4.904, + "args": { + "External id": 709841,"Record function id": 0, "Ev Idx": 3792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206335394.375, "dur": 2.892, + "args": { + "External id": 709842,"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": 6305206335395.188, "dur": 1.603, + "args": { + "External id": 709843,"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": 6305206335395.861, "dur": 0.815, + "args": { + "External id": 709844,"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": 6305206335401.150, "dur": 4.075, + "args": { + "External id": 709845,"Record function id": 0, "Ev Idx": 3796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206335402.310, "dur": 2.448, + "args": { + "External id": 709846,"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": 6305206335403.029, "dur": 1.320, + "args": { + "External id": 709847,"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": 6305206335403.641, "dur": 0.602, + "args": { + "External id": 709848,"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": 6305206335408.571, "dur": 3.558, + "args": { + "External id": 709849,"Record function id": 0, "Ev Idx": 3800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206335409.865, "dur": 1.850, + "args": { + "External id": 709850,"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": 6305206335410.354, "dur": 0.931, + "args": { + "External id": 709851,"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": 6305206335410.595, "dur": 0.592, + "args": { + "External id": 709852,"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": 6305206335415.414, "dur": 4.377, + "args": { + "External id": 709853,"Record function id": 0, "Ev Idx": 3804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206335416.571, "dur": 2.767, + "args": { + "External id": 709854,"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": 6305206335417.015, "dur": 1.857, + "args": { + "External id": 709855,"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": 6305206335418.158, "dur": 0.609, + "args": { + "External id": 709856,"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": 6305206335422.957, "dur": 3.303, + "args": { + "External id": 709857,"Record function id": 0, "Ev Idx": 3808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206335424.000, "dur": 1.835, + "args": { + "External id": 709858,"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": 6305206335424.454, "dur": 0.960, + "args": { + "External id": 709859,"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": 6305206335424.777, "dur": 0.573, + "args": { + "External id": 709860,"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": 6305206335429.489, "dur": 3.843, + "args": { + "External id": 709861,"Record function id": 0, "Ev Idx": 3812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206335430.733, "dur": 2.162, + "args": { + "External id": 709862,"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": 6305206335431.189, "dur": 1.302, + "args": { + "External id": 709863,"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": 6305206335431.639, "dur": 0.790, + "args": { + "External id": 709864,"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": 6305206335437.252, "dur": 59927.583, + "args": { + "External id": 709865,"Record function id": 0, "Sequence number": 7674415, "Fwd thread id": 1, "Ev Idx": 3816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305206335438.808, "dur": 59916.875, + "args": { + "External id": 709866,"Sequence number": 7674415, "Fwd thread 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": 6305206335438.808, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.12)", "pid": 2338707, "tid": 2379456, + "ts": 6305206335467.881, "dur": 52.696, + "args": { + "External id": 709867,"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": 6305206335531.963, "dur": 73.814, + "args": { + "External id": 709868,"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": 6305206335612.138, "dur": 59735.979, + "args": { + "External id": 709869,"Record function id": 0, "Ev Idx": 3820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305206335705.011, "dur": 7.773, + "args": { + "External id": 709870,"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": 6305206335723.576, "dur": 7.018, + "args": { + "External id": 709871,"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": 6305206335745.749, "dur": 58704.788, + "args": { + "External id": 709872,"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": 6305206335759.936, "dur": 58676.898, + "args": { + "External id": 709873,"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": 6305206335855.312, "dur": 21.440, + "args": { + "External id": 709874,"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": 6305206335899.191, "dur": 58489.495, + "args": { + "External id": 709875,"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": 6305206335902.014, "dur": 58485.536, + "args": { + "External id": 709876,"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": 6305206335907.076, "dur": 10.542, + "args": { + "External id": 709877,"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": 6305206335919.572, "dur": 58462.531, + "args": { + "External id": 709878,"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": 6305206394583.407, "dur": 13.584, + "args": { + "External id": 709879,"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": 6305206394587.110, "dur": 9.323, + "args": { + "External id": 709880,"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": 6305206394629.038, "dur": 384.092, + "args": { + "External id": 709881,"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": 6305206394664.254, "dur": 344.151, + "args": { + "External id": 709882,"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": 6305206394676.400, "dur": 327.062, + "args": { + "External id": 709883,"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": 6305206395035.888, "dur": 2.121, + "args": { + "External id": 709884,"Record function id": 0, "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": 6305206395139.022, "dur": 7.316, + "args": { + "External id": 709885,"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": 6305206395191.822, "dur": 1.318, + "args": { + "External id": 709886,"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": 6305206395208.972, "dur": 3.803, + "args": { + "External id": 709887,"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": 6305206395225.187, "dur": 0.895, + "args": { + "External id": 709888,"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": 6305206395236.916, "dur": 0.940, + "args": { + "External id": 709889,"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": 6305206395248.179, "dur": 1.232, + "args": { + "External id": 709890,"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": 6305206395261.510, "dur": 3.170, + "args": { + "External id": 709891,"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": 6305206395274.481, "dur": 2.225, + "args": { + "External id": 709892,"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": 6305206395286.188, "dur": 0.655, + "args": { + "External id": 709893,"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": 6305206395380.619, "dur": 3027.363, + "args": { + "External id": 709894,"Record function id": 0, "Ev Idx": 3845 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.11)", "pid": 2338707, "tid": 2379456, + "ts": 6305206395400.302, "dur": 1166.325, + "args": { + "External id": 709895,"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": 6305206395415.428, "dur": 368.314, + "args": { + "External id": 709896,"Record function id": 0, "Ev Idx": 3847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6305206395501.433, "dur": 20.826, + "args": { + "External id": 709897,"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": 6305206395527.921, "dur": 1.173, + "args": { + "External id": 709898,"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": 6305206395530.878, "dur": 2.617, + "args": { + "External id": 709899,"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": 6305206395535.283, "dur": 0.606, + "args": { + "External id": 709900,"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": 6305206395537.544, "dur": 0.829, + "args": { + "External id": 709901,"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": 6305206395542.790, "dur": 0.700, + "args": { + "External id": 709902,"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": 6305206395544.983, "dur": 2.090, + "args": { + "External id": 709903,"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": 6305206395548.550, "dur": 0.576, + "args": { + "External id": 709904,"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": 6305206395550.508, "dur": 0.858, + "args": { + "External id": 709905,"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": 6305206395555.089, "dur": 0.694, + "args": { + "External id": 709906,"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": 6305206395575.730, "dur": 175.636, + "args": { + "External id": 709907,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305206395592.457, "dur": 153.795, + "args": { + "External id": 709908,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305206395622.395, "dur": 18.856, + "args": { + "External id": 709909,"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": 6305206395645.025, "dur": 69.445, + "args": { + "External id": 709910,"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": 6305206395647.810, "dur": 66.407, + "args": { + "External id": 709911,"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": 6305206395652.641, "dur": 6.334, + "args": { + "External id": 709912,"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": 6305206395660.665, "dur": 52.903, + "args": { + "External id": 709913,"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": 6305206395864.794, "dur": 693.558, + "args": { + "External id": 709914,"Record function id": 0, "Ev Idx": 3865 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.10)", "pid": 2338707, "tid": 2379456, + "ts": 6305206395882.464, "dur": 661.776, + "args": { + "External id": 709915,"Record function id": 0, "Ev Idx": 3866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305206395939.430, "dur": 5.315, + "args": { + "External id": 709916,"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": 6305206395959.646, "dur": 32.681, + "args": { + "External id": 709917,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206395964.837, "dur": 1.786, + "args": { + "External id": 709918,"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": 6305206395968.724, "dur": 1.567, + "args": { + "External id": 709919,"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": 6305206395971.771, "dur": 0.379, + "args": { + "External id": 709920,"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": 6305206395974.079, "dur": 0.502, + "args": { + "External id": 709921,"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": 6305206395977.075, "dur": 0.506, + "args": { + "External id": 709922,"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": 6305206395978.959, "dur": 3.123, + "args": { + "External id": 709923,"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": 6305206395983.798, "dur": 0.276, + "args": { + "External id": 709924,"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": 6305206395985.877, "dur": 0.405, + "args": { + "External id": 709925,"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": 6305206395987.522, "dur": 0.279, + "args": { + "External id": 709926,"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": 6305206396002.292, "dur": 106.343, + "args": { + "External id": 709927,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305206396147.392, "dur": 130.932, + "args": { + "External id": 709928,"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": 6305206396158.926, "dur": 5.211, + "args": { + "External id": 709929,"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": 6305206396169.336, "dur": 10.898, + "args": { + "External id": 709930,"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": 6305206396173.406, "dur": 6.428, + "args": { + "External id": 709931,"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": 6305206396177.209, "dur": 0.816, + "args": { + "External id": 709932,"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": 6305206396187.765, "dur": 34.157, + "args": { + "External id": 709933,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206396190.239, "dur": 0.615, + "args": { + "External id": 709934,"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": 6305206396196.751, "dur": 0.557, + "args": { + "External id": 709935,"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": 6305206396203.306, "dur": 2.800, + "args": { + "External id": 709936,"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": 6305206396207.877, "dur": 0.510, + "args": { + "External id": 709937,"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": 6305206396210.564, "dur": 0.447, + "args": { + "External id": 709938,"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": 6305206396212.431, "dur": 0.332, + "args": { + "External id": 709939,"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": 6305206396214.484, "dur": 0.319, + "args": { + "External id": 709940,"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": 6305206396216.309, "dur": 0.336, + "args": { + "External id": 709941,"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": 6305206396217.830, "dur": 0.394, + "args": { + "External id": 709942,"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": 6305206396234.095, "dur": 36.190, + "args": { + "External id": 709943,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305206396325.267, "dur": 130.041, + "args": { + "External id": 709944,"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": 6305206396359.662, "dur": 91.931, + "args": { + "External id": 709945,"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": 6305206396369.799, "dur": 76.933, + "args": { + "External id": 709946,"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": 6305206396474.105, "dur": 1.757, + "args": { + "External id": 709947,"Record function id": 0, "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": 6305206396574.171, "dur": 1813.855, + "args": { + "External id": 709948,"Sequence number": 7674414, "Fwd thread 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": 6305206396574.171, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6305206396687.900, "dur": 111.671, + "args": { + "External id": 709949,"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": 6305206396842.074, "dur": 40.535, + "args": { + "External id": 709950,"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": 6305206396897.889, "dur": 51.112, + "args": { + "External id": 709951,"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": 6305206396960.503, "dur": 32.188, + "args": { + "External id": 709952,"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": 6305206396999.171, "dur": 32.059, + "args": { + "External id": 709953,"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": 6305206397037.938, "dur": 68.062, + "args": { + "External id": 709954,"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": 6305206397117.626, "dur": 32.863, + "args": { + "External id": 709955,"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": 6305206397180.078, "dur": 26.511, + "args": { + "External id": 709956,"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": 6305206397225.151, "dur": 29.124, + "args": { + "External id": 709957,"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": 6305206397276.191, "dur": 18.056, + "args": { + "External id": 709958,"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": 6305206397308.669, "dur": 13.900, + "args": { + "External id": 709959,"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": 6305206397329.976, "dur": 38.141, + "args": { + "External id": 709960,"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": 6305206397371.675, "dur": 31.932, + "args": { + "External id": 709961,"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": 6305206397434.495, "dur": 272.595, + "args": { + "External id": 709962,"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": 6305206397526.757, "dur": 7.300, + "args": { + "External id": 709963,"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": 6305206397536.709, "dur": 2.228, + "args": { + "External id": 709964,"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": 6305206397540.620, "dur": 1.806, + "args": { + "External id": 709965,"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": 6305206397543.709, "dur": 1.694, + "args": { + "External id": 709966,"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": 6305206397595.777, "dur": 6.266, + "args": { + "External id": 709967,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206397597.804, "dur": 4.071, + "args": { + "External id": 709968,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206397603.983, "dur": 37.720, + "args": { + "External id": 709969,"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": 6305206397611.229, "dur": 3.678, + "args": { + "External id": 709970,"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": 6305206397642.984, "dur": 1.826, + "args": { + "External id": 709971,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206397643.943, "dur": 0.794, + "args": { + "External id": 709972,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206397645.949, "dur": 14.094, + "args": { + "External id": 709973,"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": 6305206397648.254, "dur": 0.570, + "args": { + "External id": 709974,"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": 6305206397744.156, "dur": 29.029, + "args": { + "External id": 709975,"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": 6305206397793.743, "dur": 18.770, + "args": { + "External id": 709976,"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": 6305206397820.804, "dur": 51.159, + "args": { + "External id": 709977,"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": 6305206397878.003, "dur": 40.755, + "args": { + "External id": 709978,"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": 6305206397932.031, "dur": 22.024, + "args": { + "External id": 709979,"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": 6305206397959.747, "dur": 31.214, + "args": { + "External id": 709980,"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": 6305206397998.113, "dur": 46.781, + "args": { + "External id": 709981,"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": 6305206398112.122, "dur": 39.325, + "args": { + "External id": 709982,"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": 6305206398183.719, "dur": 27.260, + "args": { + "External id": 709983,"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": 6305206398231.855, "dur": 24.540, + "args": { + "External id": 709984,"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": 6305206398273.284, "dur": 18.355, + "args": { + "External id": 709985,"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": 6305206398310.756, "dur": 15.936, + "args": { + "External id": 709986,"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": 6305206398340.338, "dur": 17.817, + "args": { + "External id": 709987,"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": 6305206398430.817, "dur": 16.899, + "args": { + "External id": 709988,"Record function id": 0, "Ev Idx": 3939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206398434.131, "dur": 12.723, + "args": { + "External id": 709989,"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": 6305206398438.924, "dur": 6.934, + "args": { + "External id": 709990,"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": 6305206398440.516, "dur": 5.243, + "args": { + "External id": 709991,"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": 6305206398451.933, "dur": 4.941, + "args": { + "External id": 709992,"Record function id": 0, "Ev Idx": 3943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206398453.596, "dur": 2.800, + "args": { + "External id": 709993,"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": 6305206398454.583, "dur": 1.392, + "args": { + "External id": 709994,"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": 6305206398455.082, "dur": 0.788, + "args": { + "External id": 709995,"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": 6305206398460.298, "dur": 6.855, + "args": { + "External id": 709996,"Record function id": 0, "Ev Idx": 3947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206398461.484, "dur": 5.205, + "args": { + "External id": 709997,"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": 6305206398461.969, "dur": 4.331, + "args": { + "External id": 709998,"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": 6305206398462.873, "dur": 3.354, + "args": { + "External id": 709999,"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": 6305206398470.472, "dur": 3.900, + "args": { + "External id": 710000,"Record function id": 0, "Ev Idx": 3951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206398471.892, "dur": 2.017, + "args": { + "External id": 710001,"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": 6305206398472.477, "dur": 1.046, + "args": { + "External id": 710002,"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": 6305206398472.766, "dur": 0.692, + "args": { + "External id": 710003,"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": 6305206398477.509, "dur": 3.865, + "args": { + "External id": 710004,"Record function id": 0, "Ev Idx": 3955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206398478.778, "dur": 2.177, + "args": { + "External id": 710005,"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": 6305206398479.428, "dur": 1.071, + "args": { + "External id": 710006,"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": 6305206398479.708, "dur": 0.724, + "args": { + "External id": 710007,"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": 6305206398485.273, "dur": 3.890, + "args": { + "External id": 710008,"Record function id": 0, "Ev Idx": 3959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206398486.589, "dur": 2.126, + "args": { + "External id": 710009,"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": 6305206398487.116, "dur": 1.204, + "args": { + "External id": 710010,"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": 6305206398487.622, "dur": 0.633, + "args": { + "External id": 710011,"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": 6305206398492.482, "dur": 31.158, + "args": { + "External id": 710012,"Record function id": 0, "Ev Idx": 3963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206398493.620, "dur": 28.976, + "args": { + "External id": 710013,"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": 6305206398494.403, "dur": 27.244, + "args": { + "External id": 710014,"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": 6305206398519.690, "dur": 1.643, + "args": { + "External id": 710015,"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": 6305206398533.020, "dur": 5.016, + "args": { + "External id": 710016,"Record function id": 0, "Ev Idx": 3967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206398534.823, "dur": 2.790, + "args": { + "External id": 710017,"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": 6305206398535.882, "dur": 1.351, + "args": { + "External id": 710018,"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": 6305206398536.333, "dur": 0.833, + "args": { + "External id": 710019,"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": 6305206398541.283, "dur": 4.233, + "args": { + "External id": 710020,"Record function id": 0, "Ev Idx": 3971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206398542.543, "dur": 2.575, + "args": { + "External id": 710021,"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": 6305206398543.196, "dur": 1.527, + "args": { + "External id": 710022,"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": 6305206398543.683, "dur": 0.971, + "args": { + "External id": 710023,"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": 6305206398549.823, "dur": 61719.590, + "args": { + "External id": 710024,"Record function id": 0, "Sequence number": 7674413, "Fwd thread id": 1, "Ev Idx": 3975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305206398551.573, "dur": 61708.715, + "args": { + "External id": 710025,"Sequence number": 7674413, "Fwd thread 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": 6305206398551.573, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.11)", "pid": 2338707, "tid": 2379456, + "ts": 6305206398582.746, "dur": 43.674, + "args": { + "External id": 710026,"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": 6305206398634.440, "dur": 71.307, + "args": { + "External id": 710027,"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": 6305206398712.111, "dur": 61540.203, + "args": { + "External id": 710028,"Record function id": 0, "Ev Idx": 3979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305206398807.327, "dur": 7.687, + "args": { + "External id": 710029,"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": 6305206398824.687, "dur": 6.668, + "args": { + "External id": 710030,"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": 6305206398847.968, "dur": 60488.761, + "args": { + "External id": 710031,"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": 6305206398861.794, "dur": 60461.581, + "args": { + "External id": 710032,"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": 6305206398950.227, "dur": 18.074, + "args": { + "External id": 710033,"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": 6305206398988.633, "dur": 60286.668, + "args": { + "External id": 710034,"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": 6305206398991.634, "dur": 60282.515, + "args": { + "External id": 710035,"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": 6305206398996.598, "dur": 11.541, + "args": { + "External id": 710036,"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": 6305206399010.169, "dur": 60258.744, + "args": { + "External id": 710037,"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": 6305206459447.193, "dur": 12.347, + "args": { + "External id": 710038,"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": 6305206459450.784, "dur": 8.388, + "args": { + "External id": 710039,"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": 6305206459493.758, "dur": 401.831, + "args": { + "External id": 710040,"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": 6305206459541.028, "dur": 349.184, + "args": { + "External id": 710041,"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": 6305206459556.113, "dur": 328.418, + "args": { + "External id": 710042,"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": 6305206459921.553, "dur": 2.316, + "args": { + "External id": 710043,"Record function id": 0, "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": 6305206459985.756, "dur": 7.042, + "args": { + "External id": 710044,"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": 6305206460038.286, "dur": 1.356, + "args": { + "External id": 710045,"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": 6305206460103.078, "dur": 5.143, + "args": { + "External id": 710046,"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": 6305206460123.755, "dur": 1.060, + "args": { + "External id": 710047,"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": 6305206460136.635, "dur": 0.834, + "args": { + "External id": 710048,"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": 6305206460148.016, "dur": 0.742, + "args": { + "External id": 710049,"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": 6305206460158.870, "dur": 2.783, + "args": { + "External id": 710050,"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": 6305206460172.585, "dur": 2.208, + "args": { + "External id": 710051,"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": 6305206460187.880, "dur": 0.871, + "args": { + "External id": 710052,"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": 6305206460285.740, "dur": 3040.638, + "args": { + "External id": 710053,"Record function id": 0, "Ev Idx": 4004 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.10)", "pid": 2338707, "tid": 2379456, + "ts": 6305206460305.360, "dur": 1137.178, + "args": { + "External id": 710054,"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": 6305206460319.973, "dur": 369.288, + "args": { + "External id": 710055,"Record function id": 0, "Ev Idx": 4006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6305206460405.139, "dur": 4.156, + "args": { + "External id": 710056,"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": 6305206460415.954, "dur": 0.948, + "args": { + "External id": 710057,"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": 6305206460419.182, "dur": 3.347, + "args": { + "External id": 710058,"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": 6305206460424.574, "dur": 0.489, + "args": { + "External id": 710059,"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": 6305206460426.615, "dur": 0.903, + "args": { + "External id": 710060,"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": 6305206460429.000, "dur": 0.845, + "args": { + "External id": 710061,"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": 6305206460431.420, "dur": 2.052, + "args": { + "External id": 710062,"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": 6305206460436.738, "dur": 0.726, + "args": { + "External id": 710063,"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": 6305206460439.209, "dur": 0.757, + "args": { + "External id": 710064,"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": 6305206460441.416, "dur": 1.078, + "args": { + "External id": 710065,"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": 6305206460460.700, "dur": 193.420, + "args": { + "External id": 710066,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305206460480.841, "dur": 167.769, + "args": { + "External id": 710067,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305206460528.161, "dur": 18.077, + "args": { + "External id": 710068,"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": 6305206460550.289, "dur": 68.108, + "args": { + "External id": 710069,"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": 6305206460553.038, "dur": 64.996, + "args": { + "External id": 710070,"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": 6305206460557.478, "dur": 5.857, + "args": { + "External id": 710071,"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": 6305206460565.070, "dur": 52.485, + "args": { + "External id": 710072,"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": 6305206460767.311, "dur": 667.408, + "args": { + "External id": 710073,"Record function id": 0, "Ev Idx": 4024 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.9)", "pid": 2338707, "tid": 2379456, + "ts": 6305206460783.809, "dur": 638.054, + "args": { + "External id": 710074,"Record function id": 0, "Ev Idx": 4025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305206460844.391, "dur": 5.203, + "args": { + "External id": 710075,"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": 6305206460865.174, "dur": 36.849, + "args": { + "External id": 710076,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206460870.788, "dur": 3.171, + "args": { + "External id": 710077,"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": 6305206460875.948, "dur": 0.368, + "args": { + "External id": 710078,"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": 6305206460878.036, "dur": 0.286, + "args": { + "External id": 710079,"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": 6305206460882.009, "dur": 0.421, + "args": { + "External id": 710080,"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": 6305206460884.276, "dur": 0.360, + "args": { + "External id": 710081,"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": 6305206460886.426, "dur": 2.812, + "args": { + "External id": 710082,"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": 6305206460891.164, "dur": 0.312, + "args": { + "External id": 710083,"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": 6305206460893.522, "dur": 0.395, + "args": { + "External id": 710084,"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": 6305206460895.460, "dur": 1.539, + "args": { + "External id": 710085,"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": 6305206460912.699, "dur": 47.203, + "args": { + "External id": 710086,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305206460993.407, "dur": 174.137, + "args": { + "External id": 710087,"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": 6305206461003.583, "dur": 3.642, + "args": { + "External id": 710088,"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": 6305206461012.465, "dur": 9.895, + "args": { + "External id": 710089,"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": 6305206461016.500, "dur": 5.447, + "args": { + "External id": 710090,"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": 6305206461020.019, "dur": 0.604, + "args": { + "External id": 710091,"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": 6305206461028.737, "dur": 71.339, + "args": { + "External id": 710092,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206461031.270, "dur": 0.533, + "args": { + "External id": 710093,"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": 6305206461033.807, "dur": 0.523, + "args": { + "External id": 710094,"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": 6305206461035.963, "dur": 3.639, + "args": { + "External id": 710095,"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": 6305206461041.250, "dur": 0.538, + "args": { + "External id": 710096,"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": 6305206461043.574, "dur": 0.477, + "args": { + "External id": 710097,"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": 6305206461046.396, "dur": 0.338, + "args": { + "External id": 710098,"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": 6305206461048.553, "dur": 0.366, + "args": { + "External id": 710099,"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": 6305206461050.862, "dur": 0.365, + "args": { + "External id": 710100,"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": 6305206461094.127, "dur": 0.644, + "args": { + "External id": 710101,"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": 6305206461119.253, "dur": 39.817, + "args": { + "External id": 710102,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305206461218.630, "dur": 128.169, + "args": { + "External id": 710103,"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": 6305206461252.583, "dur": 90.531, + "args": { + "External id": 710104,"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": 6305206461263.722, "dur": 74.363, + "args": { + "External id": 710105,"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": 6305206461365.498, "dur": 1.729, + "args": { + "External id": 710106,"Record function id": 0, "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": 6305206461450.265, "dur": 1855.339, + "args": { + "External id": 710107,"Sequence number": 7674412, "Fwd thread 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": 6305206461450.265, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6305206461583.762, "dur": 113.448, + "args": { + "External id": 710108,"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": 6305206461741.326, "dur": 41.505, + "args": { + "External id": 710109,"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": 6305206461799.646, "dur": 51.817, + "args": { + "External id": 710110,"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": 6305206461863.346, "dur": 31.373, + "args": { + "External id": 710111,"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": 6305206461901.339, "dur": 33.618, + "args": { + "External id": 710112,"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": 6305206461941.271, "dur": 27.914, + "args": { + "External id": 710113,"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": 6305206461976.927, "dur": 29.808, + "args": { + "External id": 710114,"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": 6305206462037.934, "dur": 68.382, + "args": { + "External id": 710115,"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": 6305206462128.126, "dur": 31.529, + "args": { + "External id": 710116,"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": 6305206462185.313, "dur": 19.050, + "args": { + "External id": 710117,"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": 6305206462217.776, "dur": 14.864, + "args": { + "External id": 710118,"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": 6305206462241.990, "dur": 42.737, + "args": { + "External id": 710119,"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": 6305206462288.756, "dur": 33.104, + "args": { + "External id": 710120,"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": 6305206462355.565, "dur": 273.892, + "args": { + "External id": 710121,"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": 6305206462432.637, "dur": 6.419, + "args": { + "External id": 710122,"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": 6305206462441.347, "dur": 4.218, + "args": { + "External id": 710123,"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": 6305206462447.155, "dur": 2.012, + "args": { + "External id": 710124,"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": 6305206462450.393, "dur": 2.244, + "args": { + "External id": 710125,"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": 6305206462501.414, "dur": 23.180, + "args": { + "External id": 710126,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206462503.394, "dur": 20.649, + "args": { + "External id": 710127,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206462527.435, "dur": 36.882, + "args": { + "External id": 710128,"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": 6305206462533.849, "dur": 4.572, + "args": { + "External id": 710129,"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": 6305206462565.819, "dur": 1.908, + "args": { + "External id": 710130,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206462567.066, "dur": 0.581, + "args": { + "External id": 710131,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206462568.848, "dur": 17.117, + "args": { + "External id": 710132,"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": 6305206462572.379, "dur": 1.661, + "args": { + "External id": 710133,"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": 6305206462668.368, "dur": 26.605, + "args": { + "External id": 710134,"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": 6305206462714.485, "dur": 16.828, + "args": { + "External id": 710135,"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": 6305206462738.983, "dur": 44.974, + "args": { + "External id": 710136,"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": 6305206462790.765, "dur": 37.989, + "args": { + "External id": 710137,"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": 6305206462838.244, "dur": 24.624, + "args": { + "External id": 710138,"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": 6305206462867.933, "dur": 31.229, + "args": { + "External id": 710139,"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": 6305206462906.294, "dur": 31.706, + "args": { + "External id": 710140,"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": 6305206462944.380, "dur": 29.972, + "args": { + "External id": 710141,"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": 6305206462994.593, "dur": 42.990, + "args": { + "External id": 710142,"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": 6305206463097.976, "dur": 28.112, + "args": { + "External id": 710143,"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": 6305206463145.287, "dur": 18.703, + "args": { + "External id": 710144,"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": 6305206463214.443, "dur": 19.317, + "args": { + "External id": 710145,"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": 6305206463250.856, "dur": 20.027, + "args": { + "External id": 710146,"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": 6305206463349.670, "dur": 15.329, + "args": { + "External id": 710147,"Record function id": 0, "Ev Idx": 4098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206463353.080, "dur": 10.935, + "args": { + "External id": 710148,"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": 6305206463357.471, "dur": 5.594, + "args": { + "External id": 710149,"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": 6305206463358.989, "dur": 3.975, + "args": { + "External id": 710150,"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": 6305206463368.814, "dur": 4.531, + "args": { + "External id": 710151,"Record function id": 0, "Ev Idx": 4102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206463370.512, "dur": 2.374, + "args": { + "External id": 710152,"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": 6305206463371.154, "dur": 1.250, + "args": { + "External id": 710153,"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": 6305206463371.595, "dur": 0.697, + "args": { + "External id": 710154,"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": 6305206463376.737, "dur": 7.016, + "args": { + "External id": 710155,"Record function id": 0, "Ev Idx": 4106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206463378.079, "dur": 5.156, + "args": { + "External id": 710156,"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": 6305206463378.678, "dur": 4.124, + "args": { + "External id": 710157,"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": 6305206463379.459, "dur": 3.233, + "args": { + "External id": 710158,"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": 6305206463386.928, "dur": 3.939, + "args": { + "External id": 710159,"Record function id": 0, "Ev Idx": 4110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206463388.243, "dur": 2.213, + "args": { + "External id": 710160,"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": 6305206463388.829, "dur": 1.159, + "args": { + "External id": 710161,"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": 6305206463389.111, "dur": 0.814, + "args": { + "External id": 710162,"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": 6305206463394.029, "dur": 4.232, + "args": { + "External id": 710163,"Record function id": 0, "Ev Idx": 4114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206463395.434, "dur": 2.406, + "args": { + "External id": 710164,"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": 6305206463395.903, "dur": 1.463, + "args": { + "External id": 710165,"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": 6305206463396.624, "dur": 0.668, + "args": { + "External id": 710166,"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": 6305206463401.442, "dur": 4.088, + "args": { + "External id": 710167,"Record function id": 0, "Ev Idx": 4118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206463402.904, "dur": 2.213, + "args": { + "External id": 710168,"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": 6305206463403.501, "dur": 1.176, + "args": { + "External id": 710169,"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": 6305206463403.877, "dur": 0.725, + "args": { + "External id": 710170,"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": 6305206463408.924, "dur": 3.631, + "args": { + "External id": 710171,"Record function id": 0, "Ev Idx": 4122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206463410.167, "dur": 1.995, + "args": { + "External id": 710172,"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": 6305206463410.646, "dur": 1.105, + "args": { + "External id": 710173,"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": 6305206463411.007, "dur": 0.681, + "args": { + "External id": 710174,"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": 6305206463415.651, "dur": 5.498, + "args": { + "External id": 710175,"Record function id": 0, "Ev Idx": 4126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206463416.919, "dur": 3.803, + "args": { + "External id": 710176,"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": 6305206463417.495, "dur": 2.791, + "args": { + "External id": 710177,"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": 6305206463419.597, "dur": 0.597, + "args": { + "External id": 710178,"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": 6305206463424.277, "dur": 3.648, + "args": { + "External id": 710179,"Record function id": 0, "Ev Idx": 4130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206463425.543, "dur": 1.985, + "args": { + "External id": 710180,"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": 6305206463425.982, "dur": 1.110, + "args": { + "External id": 710181,"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": 6305206463426.517, "dur": 0.511, + "args": { + "External id": 710182,"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": 6305206463432.051, "dur": 62072.293, + "args": { + "External id": 710183,"Record function id": 0, "Sequence number": 7674411, "Fwd thread id": 1, "Ev Idx": 4134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305206463433.871, "dur": 62061.795, + "args": { + "External id": 710184,"Sequence number": 7674411, "Fwd thread 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": 6305206463433.871, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.10)", "pid": 2338707, "tid": 2379456, + "ts": 6305206463462.846, "dur": 38.305, + "args": { + "External id": 710185,"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": 6305206463525.181, "dur": 66.378, + "args": { + "External id": 710186,"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": 6305206463598.273, "dur": 61889.100, + "args": { + "External id": 710187,"Record function id": 0, "Ev Idx": 4138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305206463690.997, "dur": 7.327, + "args": { + "External id": 710188,"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": 6305206463709.504, "dur": 7.067, + "args": { + "External id": 710189,"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": 6305206463731.910, "dur": 60832.399, + "args": { + "External id": 710190,"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": 6305206463746.159, "dur": 60804.315, + "args": { + "External id": 710191,"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": 6305206463834.224, "dur": 17.431, + "args": { + "External id": 710192,"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": 6305206463874.612, "dur": 60615.863, + "args": { + "External id": 710193,"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": 6305206463879.577, "dur": 60609.805, + "args": { + "External id": 710194,"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": 6305206463884.444, "dur": 9.532, + "args": { + "External id": 710195,"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": 6305206463896.134, "dur": 60588.195, + "args": { + "External id": 710196,"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": 6305206524676.982, "dur": 12.696, + "args": { + "External id": 710197,"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": 6305206524680.483, "dur": 8.675, + "args": { + "External id": 710198,"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": 6305206524720.555, "dur": 458.662, + "args": { + "External id": 710199,"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": 6305206524754.828, "dur": 418.344, + "args": { + "External id": 710200,"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": 6305206524766.679, "dur": 399.822, + "args": { + "External id": 710201,"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": 6305206525207.030, "dur": 2.526, + "args": { + "External id": 710202,"Record function id": 0, "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": 6305206525275.175, "dur": 7.350, + "args": { + "External id": 710203,"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": 6305206525329.105, "dur": 1.700, + "args": { + "External id": 710204,"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": 6305206525345.838, "dur": 3.671, + "args": { + "External id": 710205,"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": 6305206525361.705, "dur": 1.014, + "args": { + "External id": 710206,"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": 6305206525375.390, "dur": 0.800, + "args": { + "External id": 710207,"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": 6305206525386.631, "dur": 0.965, + "args": { + "External id": 710208,"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": 6305206525398.500, "dur": 3.125, + "args": { + "External id": 710209,"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": 6305206525412.470, "dur": 2.574, + "args": { + "External id": 710210,"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": 6305206525425.125, "dur": 0.967, + "args": { + "External id": 710211,"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": 6305206525537.343, "dur": 2957.670, + "args": { + "External id": 710212,"Record function id": 0, "Ev Idx": 4163 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.9)", "pid": 2338707, "tid": 2379456, + "ts": 6305206525560.438, "dur": 1112.337, + "args": { + "External id": 710213,"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": 6305206525576.193, "dur": 354.728, + "args": { + "External id": 710214,"Record function id": 0, "Ev Idx": 4165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6305206525668.940, "dur": 4.720, + "args": { + "External id": 710215,"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": 6305206525677.240, "dur": 0.817, + "args": { + "External id": 710216,"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": 6305206525680.167, "dur": 3.392, + "args": { + "External id": 710217,"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": 6305206525685.539, "dur": 0.959, + "args": { + "External id": 710218,"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": 6305206525688.375, "dur": 0.746, + "args": { + "External id": 710219,"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": 6305206525690.526, "dur": 0.873, + "args": { + "External id": 710220,"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": 6305206525692.966, "dur": 2.048, + "args": { + "External id": 710221,"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": 6305206525698.666, "dur": 0.919, + "args": { + "External id": 710222,"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": 6305206525707.557, "dur": 0.580, + "args": { + "External id": 710223,"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": 6305206525709.510, "dur": 0.873, + "args": { + "External id": 710224,"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": 6305206525728.369, "dur": 170.839, + "args": { + "External id": 710225,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305206525744.704, "dur": 149.607, + "args": { + "External id": 710226,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305206525771.699, "dur": 17.711, + "args": { + "External id": 710227,"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": 6305206525795.343, "dur": 68.914, + "args": { + "External id": 710228,"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": 6305206525798.466, "dur": 65.324, + "args": { + "External id": 710229,"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": 6305206525803.193, "dur": 5.540, + "args": { + "External id": 710230,"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": 6305206525810.338, "dur": 52.689, + "args": { + "External id": 710231,"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": 6305206526008.377, "dur": 656.729, + "args": { + "External id": 710232,"Record function id": 0, "Ev Idx": 4183 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.8)", "pid": 2338707, "tid": 2379456, + "ts": 6305206526025.509, "dur": 627.150, + "args": { + "External id": 710233,"Record function id": 0, "Ev Idx": 4184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305206526120.330, "dur": 6.804, + "args": { + "External id": 710234,"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": 6305206526143.703, "dur": 34.851, + "args": { + "External id": 710235,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206526148.897, "dur": 1.797, + "args": { + "External id": 710236,"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": 6305206526152.890, "dur": 1.769, + "args": { + "External id": 710237,"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": 6305206526156.305, "dur": 0.590, + "args": { + "External id": 710238,"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": 6305206526158.859, "dur": 0.396, + "args": { + "External id": 710239,"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": 6305206526162.528, "dur": 0.383, + "args": { + "External id": 710240,"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": 6305206526164.526, "dur": 2.644, + "args": { + "External id": 710241,"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": 6305206526168.452, "dur": 0.326, + "args": { + "External id": 710242,"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": 6305206526171.408, "dur": 0.290, + "args": { + "External id": 710243,"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": 6305206526173.056, "dur": 0.263, + "args": { + "External id": 710244,"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": 6305206526189.955, "dur": 45.278, + "args": { + "External id": 710245,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305206526267.020, "dur": 114.822, + "args": { + "External id": 710246,"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": 6305206526277.475, "dur": 3.987, + "args": { + "External id": 710247,"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": 6305206526286.477, "dur": 10.575, + "args": { + "External id": 710248,"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": 6305206526290.852, "dur": 5.759, + "args": { + "External id": 710249,"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": 6305206526294.637, "dur": 0.668, + "args": { + "External id": 710250,"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": 6305206526304.295, "dur": 28.527, + "args": { + "External id": 710251,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206526306.791, "dur": 0.408, + "args": { + "External id": 710252,"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": 6305206526309.615, "dur": 0.607, + "args": { + "External id": 710253,"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": 6305206526311.587, "dur": 2.248, + "args": { + "External id": 710254,"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": 6305206526315.614, "dur": 1.865, + "args": { + "External id": 710255,"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": 6305206526319.242, "dur": 0.326, + "args": { + "External id": 710256,"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": 6305206526321.395, "dur": 0.304, + "args": { + "External id": 710257,"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": 6305206526324.473, "dur": 0.262, + "args": { + "External id": 710258,"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": 6305206526326.086, "dur": 0.250, + "args": { + "External id": 710259,"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": 6305206526327.722, "dur": 0.439, + "args": { + "External id": 710260,"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": 6305206526343.961, "dur": 29.898, + "args": { + "External id": 710261,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305206526427.575, "dur": 146.994, + "args": { + "External id": 710262,"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": 6305206526457.054, "dur": 113.447, + "args": { + "External id": 710263,"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": 6305206526472.151, "dur": 93.435, + "args": { + "External id": 710264,"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": 6305206526596.603, "dur": 1.693, + "args": { + "External id": 710265,"Record function id": 0, "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": 6305206526680.388, "dur": 1795.065, + "args": { + "External id": 710266,"Sequence number": 7674410, "Fwd thread 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": 6305206526680.388, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6305206526798.494, "dur": 111.661, + "args": { + "External id": 710267,"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": 6305206526954.675, "dur": 40.989, + "args": { + "External id": 710268,"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": 6305206527012.557, "dur": 92.631, + "args": { + "External id": 710269,"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": 6305206527122.248, "dur": 38.407, + "args": { + "External id": 710270,"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": 6305206527166.998, "dur": 32.770, + "args": { + "External id": 710271,"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": 6305206527206.687, "dur": 28.399, + "args": { + "External id": 710272,"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": 6305206527242.037, "dur": 32.634, + "args": { + "External id": 710273,"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": 6305206527306.621, "dur": 30.646, + "args": { + "External id": 710274,"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": 6305206527354.942, "dur": 31.213, + "args": { + "External id": 710275,"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": 6305206527409.091, "dur": 19.506, + "args": { + "External id": 710276,"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": 6305206527443.057, "dur": 16.618, + "args": { + "External id": 710277,"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": 6305206527466.929, "dur": 35.697, + "args": { + "External id": 710278,"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": 6305206527520.676, "dur": 37.470, + "args": { + "External id": 710279,"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": 6305206527596.068, "dur": 252.276, + "args": { + "External id": 710280,"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": 6305206527679.382, "dur": 6.389, + "args": { + "External id": 710281,"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": 6305206527687.858, "dur": 2.838, + "args": { + "External id": 710282,"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": 6305206527692.307, "dur": 1.933, + "args": { + "External id": 710283,"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": 6305206527695.395, "dur": 2.038, + "args": { + "External id": 710284,"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": 6305206527741.361, "dur": 6.794, + "args": { + "External id": 710285,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206527743.579, "dur": 4.369, + "args": { + "External id": 710286,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206527752.308, "dur": 33.589, + "args": { + "External id": 710287,"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": 6305206527758.019, "dur": 3.858, + "args": { + "External id": 710288,"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": 6305206527787.469, "dur": 2.006, + "args": { + "External id": 710289,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206527788.773, "dur": 0.605, + "args": { + "External id": 710290,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206527790.473, "dur": 15.678, + "args": { + "External id": 710291,"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": 6305206527793.708, "dur": 0.685, + "args": { + "External id": 710292,"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": 6305206527885.116, "dur": 24.490, + "args": { + "External id": 710293,"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": 6305206527928.315, "dur": 15.604, + "args": { + "External id": 710294,"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": 6305206527951.525, "dur": 39.465, + "args": { + "External id": 710295,"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": 6305206527996.974, "dur": 37.430, + "args": { + "External id": 710296,"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": 6305206528044.421, "dur": 59.060, + "args": { + "External id": 710297,"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": 6305206528113.153, "dur": 33.542, + "args": { + "External id": 710298,"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": 6305206528154.203, "dur": 27.798, + "args": { + "External id": 710299,"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": 6305206528188.084, "dur": 30.150, + "args": { + "External id": 710300,"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": 6305206528241.583, "dur": 24.209, + "args": { + "External id": 710301,"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": 6305206528296.974, "dur": 32.407, + "args": { + "External id": 710302,"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": 6305206528347.478, "dur": 16.348, + "args": { + "External id": 710303,"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": 6305206528391.737, "dur": 13.490, + "args": { + "External id": 710304,"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": 6305206528425.893, "dur": 15.346, + "args": { + "External id": 710305,"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": 6305206528538.276, "dur": 18.027, + "args": { + "External id": 710306,"Record function id": 0, "Ev Idx": 4257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206528542.022, "dur": 13.026, + "args": { + "External id": 710307,"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": 6305206528546.404, "dur": 7.479, + "args": { + "External id": 710308,"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": 6305206528547.752, "dur": 5.897, + "args": { + "External id": 710309,"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": 6305206528560.515, "dur": 4.450, + "args": { + "External id": 710310,"Record function id": 0, "Ev Idx": 4261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206528562.136, "dur": 2.331, + "args": { + "External id": 710311,"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": 6305206528562.729, "dur": 1.287, + "args": { + "External id": 710312,"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": 6305206528563.218, "dur": 0.702, + "args": { + "External id": 710313,"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": 6305206528568.314, "dur": 5.882, + "args": { + "External id": 710314,"Record function id": 0, "Ev Idx": 4265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206528569.476, "dur": 4.279, + "args": { + "External id": 710315,"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": 6305206528570.110, "dur": 3.232, + "args": { + "External id": 710316,"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": 6305206528570.742, "dur": 2.490, + "args": { + "External id": 710317,"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": 6305206528577.583, "dur": 3.825, + "args": { + "External id": 710318,"Record function id": 0, "Ev Idx": 4269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206528579.115, "dur": 1.898, + "args": { + "External id": 710319,"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": 6305206528579.567, "dur": 1.013, + "args": { + "External id": 710320,"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": 6305206528579.849, "dur": 0.620, + "args": { + "External id": 710321,"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": 6305206528584.631, "dur": 3.901, + "args": { + "External id": 710322,"Record function id": 0, "Ev Idx": 4273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206528586.064, "dur": 2.052, + "args": { + "External id": 710323,"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": 6305206528586.515, "dur": 1.140, + "args": { + "External id": 710324,"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": 6305206528587.017, "dur": 0.565, + "args": { + "External id": 710325,"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": 6305206528591.780, "dur": 3.840, + "args": { + "External id": 710326,"Record function id": 0, "Ev Idx": 4277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206528593.162, "dur": 2.015, + "args": { + "External id": 710327,"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": 6305206528593.639, "dur": 1.132, + "args": { + "External id": 710328,"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": 6305206528594.044, "dur": 0.630, + "args": { + "External id": 710329,"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": 6305206528598.798, "dur": 4.398, + "args": { + "External id": 710330,"Record function id": 0, "Ev Idx": 4281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206528600.269, "dur": 2.532, + "args": { + "External id": 710331,"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": 6305206528600.816, "dur": 1.592, + "args": { + "External id": 710332,"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": 6305206528601.550, "dur": 0.788, + "args": { + "External id": 710333,"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": 6305206528606.338, "dur": 3.945, + "args": { + "External id": 710334,"Record function id": 0, "Ev Idx": 4285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206528607.562, "dur": 2.327, + "args": { + "External id": 710335,"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": 6305206528608.423, "dur": 1.070, + "args": { + "External id": 710336,"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": 6305206528608.702, "dur": 0.726, + "args": { + "External id": 710337,"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": 6305206528613.409, "dur": 5.546, + "args": { + "External id": 710338,"Record function id": 0, "Ev Idx": 4289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206528614.561, "dur": 3.992, + "args": { + "External id": 710339,"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": 6305206528615.010, "dur": 3.133, + "args": { + "External id": 710340,"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": 6305206528617.409, "dur": 0.667, + "args": { + "External id": 710341,"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": 6305206528623.247, "dur": 64360.296, + "args": { + "External id": 710342,"Record function id": 0, "Sequence number": 7674409, "Fwd thread id": 1, "Ev Idx": 4293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305206528625.327, "dur": 64348.665, + "args": { + "External id": 710343,"Sequence number": 7674409, "Fwd thread 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": 6305206528625.327, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.9)", "pid": 2338707, "tid": 2379456, + "ts": 6305206528656.249, "dur": 40.711, + "args": { + "External id": 710344,"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": 6305206528705.036, "dur": 63.775, + "args": { + "External id": 710345,"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": 6305206528777.110, "dur": 64189.210, + "args": { + "External id": 710346,"Record function id": 0, "Ev Idx": 4297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305206528868.271, "dur": 7.569, + "args": { + "External id": 710347,"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": 6305206528885.517, "dur": 7.446, + "args": { + "External id": 710348,"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": 6305206528907.345, "dur": 63188.267, + "args": { + "External id": 710349,"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": 6305206528921.993, "dur": 63159.949, + "args": { + "External id": 710350,"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": 6305206529010.489, "dur": 16.954, + "args": { + "External id": 710351,"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": 6305206529047.744, "dur": 62961.114, + "args": { + "External id": 710352,"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": 6305206529050.349, "dur": 62957.130, + "args": { + "External id": 710353,"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": 6305206529097.331, "dur": 14.688, + "args": { + "External id": 710354,"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": 6305206529116.996, "dur": 62885.045, + "args": { + "External id": 710355,"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": 6305206592207.125, "dur": 13.563, + "args": { + "External id": 710356,"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": 6305206592210.791, "dur": 9.355, + "args": { + "External id": 710357,"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": 6305206592253.775, "dur": 407.476, + "args": { + "External id": 710358,"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": 6305206592288.835, "dur": 366.415, + "args": { + "External id": 710359,"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": 6305206592302.770, "dur": 346.234, + "args": { + "External id": 710360,"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": 6305206592687.916, "dur": 2.356, + "args": { + "External id": 710361,"Record function id": 0, "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": 6305206592754.511, "dur": 6.936, + "args": { + "External id": 710362,"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": 6305206592808.408, "dur": 1.855, + "args": { + "External id": 710363,"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": 6305206592825.461, "dur": 3.518, + "args": { + "External id": 710364,"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": 6305206592840.904, "dur": 1.057, + "args": { + "External id": 710365,"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": 6305206592853.134, "dur": 0.940, + "args": { + "External id": 710366,"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": 6305206592864.558, "dur": 0.933, + "args": { + "External id": 710367,"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": 6305206592878.342, "dur": 3.108, + "args": { + "External id": 710368,"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": 6305206592892.617, "dur": 2.482, + "args": { + "External id": 710369,"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": 6305206592904.075, "dur": 0.895, + "args": { + "External id": 710370,"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": 6305206592999.389, "dur": 3047.855, + "args": { + "External id": 710371,"Record function id": 0, "Ev Idx": 4322 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.8)", "pid": 2338707, "tid": 2379456, + "ts": 6305206593020.218, "dur": 1186.764, + "args": { + "External id": 710372,"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": 6305206593034.732, "dur": 399.414, + "args": { + "External id": 710373,"Record function id": 0, "Ev Idx": 4324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6305206593163.812, "dur": 5.302, + "args": { + "External id": 710374,"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": 6305206593172.966, "dur": 0.896, + "args": { + "External id": 710375,"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": 6305206593175.579, "dur": 3.206, + "args": { + "External id": 710376,"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": 6305206593180.627, "dur": 1.036, + "args": { + "External id": 710377,"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": 6305206593185.100, "dur": 0.963, + "args": { + "External id": 710378,"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": 6305206593187.966, "dur": 0.904, + "args": { + "External id": 710379,"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": 6305206593190.581, "dur": 2.138, + "args": { + "External id": 710380,"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": 6305206593194.239, "dur": 1.043, + "args": { + "External id": 710381,"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": 6305206593199.146, "dur": 0.767, + "args": { + "External id": 710382,"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": 6305206593201.363, "dur": 0.583, + "args": { + "External id": 710383,"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": 6305206593221.776, "dur": 176.775, + "args": { + "External id": 710384,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305206593238.698, "dur": 155.123, + "args": { + "External id": 710385,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305206593268.400, "dur": 17.667, + "args": { + "External id": 710386,"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": 6305206593290.012, "dur": 73.899, + "args": { + "External id": 710387,"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": 6305206593292.830, "dur": 70.755, + "args": { + "External id": 710388,"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": 6305206593296.914, "dur": 6.345, + "args": { + "External id": 710389,"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": 6305206593306.896, "dur": 56.077, + "args": { + "External id": 710390,"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": 6305206593535.669, "dur": 663.852, + "args": { + "External id": 710391,"Record function id": 0, "Ev Idx": 4342 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.7)", "pid": 2338707, "tid": 2379456, + "ts": 6305206593554.149, "dur": 632.705, + "args": { + "External id": 710392,"Record function id": 0, "Ev Idx": 4343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305206593618.950, "dur": 6.735, + "args": { + "External id": 710393,"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": 6305206593641.474, "dur": 37.860, + "args": { + "External id": 710394,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206593647.001, "dur": 3.502, + "args": { + "External id": 710395,"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": 6305206593652.427, "dur": 0.582, + "args": { + "External id": 710396,"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": 6305206593654.629, "dur": 0.801, + "args": { + "External id": 710397,"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": 6305206593658.721, "dur": 0.595, + "args": { + "External id": 710398,"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": 6305206593661.299, "dur": 0.283, + "args": { + "External id": 710399,"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": 6305206593662.878, "dur": 2.503, + "args": { + "External id": 710400,"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": 6305206593668.136, "dur": 0.478, + "args": { + "External id": 710401,"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": 6305206593670.019, "dur": 0.667, + "args": { + "External id": 710402,"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": 6305206593672.412, "dur": 1.997, + "args": { + "External id": 710403,"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": 6305206593690.454, "dur": 48.389, + "args": { + "External id": 710404,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305206593770.995, "dur": 122.552, + "args": { + "External id": 710405,"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": 6305206593781.296, "dur": 3.667, + "args": { + "External id": 710406,"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": 6305206593790.258, "dur": 10.765, + "args": { + "External id": 710407,"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": 6305206593794.373, "dur": 6.228, + "args": { + "External id": 710408,"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": 6305206593798.480, "dur": 0.894, + "args": { + "External id": 710409,"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": 6305206593807.995, "dur": 32.392, + "args": { + "External id": 710410,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206593810.756, "dur": 0.332, + "args": { + "External id": 710411,"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": 6305206593812.945, "dur": 0.369, + "args": { + "External id": 710412,"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": 6305206593818.408, "dur": 3.528, + "args": { + "External id": 710413,"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": 6305206593823.716, "dur": 0.528, + "args": { + "External id": 710414,"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": 6305206593825.860, "dur": 0.256, + "args": { + "External id": 710415,"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": 6305206593828.819, "dur": 0.337, + "args": { + "External id": 710416,"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": 6305206593831.068, "dur": 0.512, + "args": { + "External id": 710417,"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": 6305206593833.066, "dur": 0.254, + "args": { + "External id": 710418,"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": 6305206593835.565, "dur": 0.543, + "args": { + "External id": 710419,"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": 6305206593852.536, "dur": 33.354, + "args": { + "External id": 710420,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305206593936.648, "dur": 169.301, + "args": { + "External id": 710421,"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": 6305206593972.457, "dur": 129.287, + "args": { + "External id": 710422,"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": 6305206593982.184, "dur": 113.009, + "args": { + "External id": 710423,"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": 6305206594126.971, "dur": 2.557, + "args": { + "External id": 710424,"Record function id": 0, "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": 6305206594215.001, "dur": 1811.347, + "args": { + "External id": 710425,"Sequence number": 7674408, "Fwd thread 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": 6305206594215.001, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6305206594336.795, "dur": 111.119, + "args": { + "External id": 710426,"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": 6305206594498.506, "dur": 55.800, + "args": { + "External id": 710427,"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": 6305206594574.965, "dur": 57.259, + "args": { + "External id": 710428,"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": 6305206594645.270, "dur": 32.204, + "args": { + "External id": 710429,"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": 6305206594683.530, "dur": 32.805, + "args": { + "External id": 710430,"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": 6305206594722.369, "dur": 28.160, + "args": { + "External id": 710431,"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": 6305206594757.168, "dur": 28.853, + "args": { + "External id": 710432,"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": 6305206594815.452, "dur": 23.925, + "args": { + "External id": 710433,"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": 6305206594860.802, "dur": 28.239, + "args": { + "External id": 710434,"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": 6305206594912.239, "dur": 18.519, + "args": { + "External id": 710435,"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": 6305206594945.786, "dur": 14.725, + "args": { + "External id": 710436,"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": 6305206594967.745, "dur": 39.967, + "args": { + "External id": 710437,"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": 6305206595011.316, "dur": 37.232, + "args": { + "External id": 710438,"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": 6305206595122.481, "dur": 261.735, + "args": { + "External id": 710439,"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": 6305206595206.187, "dur": 6.471, + "args": { + "External id": 710440,"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": 6305206595215.459, "dur": 2.860, + "args": { + "External id": 710441,"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": 6305206595219.486, "dur": 2.309, + "args": { + "External id": 710442,"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": 6305206595223.027, "dur": 3.356, + "args": { + "External id": 710443,"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": 6305206595277.520, "dur": 5.622, + "args": { + "External id": 710444,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206595279.999, "dur": 2.971, + "args": { + "External id": 710445,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206595285.139, "dur": 35.674, + "args": { + "External id": 710446,"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": 6305206595290.966, "dur": 3.455, + "args": { + "External id": 710447,"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": 6305206595322.251, "dur": 2.022, + "args": { + "External id": 710448,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206595323.456, "dur": 0.751, + "args": { + "External id": 710449,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206595325.283, "dur": 16.501, + "args": { + "External id": 710450,"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": 6305206595327.653, "dur": 0.484, + "args": { + "External id": 710451,"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": 6305206595420.616, "dur": 28.638, + "args": { + "External id": 710452,"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": 6305206595469.198, "dur": 19.143, + "args": { + "External id": 710453,"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": 6305206595496.428, "dur": 65.505, + "args": { + "External id": 710454,"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": 6305206595571.227, "dur": 42.256, + "args": { + "External id": 710455,"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": 6305206595624.777, "dur": 37.088, + "args": { + "External id": 710456,"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": 6305206595676.027, "dur": 37.926, + "args": { + "External id": 710457,"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": 6305206595721.364, "dur": 28.857, + "args": { + "External id": 710458,"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": 6305206595756.475, "dur": 29.194, + "args": { + "External id": 710459,"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": 6305206595811.946, "dur": 30.861, + "args": { + "External id": 710460,"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": 6305206595860.620, "dur": 28.830, + "args": { + "External id": 710461,"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": 6305206595907.615, "dur": 17.353, + "args": { + "External id": 710462,"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": 6305206595948.864, "dur": 13.486, + "args": { + "External id": 710463,"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": 6305206595975.775, "dur": 18.696, + "args": { + "External id": 710464,"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": 6305206596107.527, "dur": 17.257, + "args": { + "External id": 710465,"Record function id": 0, "Ev Idx": 4416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206596111.455, "dur": 12.161, + "args": { + "External id": 710466,"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": 6305206596115.930, "dur": 6.263, + "args": { + "External id": 710467,"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": 6305206596117.524, "dur": 4.468, + "args": { + "External id": 710468,"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": 6305206596128.887, "dur": 4.423, + "args": { + "External id": 710469,"Record function id": 0, "Ev Idx": 4420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206596130.318, "dur": 2.599, + "args": { + "External id": 710470,"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": 6305206596130.933, "dur": 1.458, + "args": { + "External id": 710471,"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": 6305206596131.403, "dur": 0.886, + "args": { + "External id": 710472,"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": 6305206596137.167, "dur": 6.982, + "args": { + "External id": 710473,"Record function id": 0, "Ev Idx": 4424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206596138.614, "dur": 5.146, + "args": { + "External id": 710474,"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": 6305206596139.381, "dur": 3.885, + "args": { + "External id": 710475,"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": 6305206596140.225, "dur": 2.979, + "args": { + "External id": 710476,"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": 6305206596147.530, "dur": 4.341, + "args": { + "External id": 710477,"Record function id": 0, "Ev Idx": 4428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206596148.686, "dur": 2.798, + "args": { + "External id": 710478,"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": 6305206596149.729, "dur": 1.333, + "args": { + "External id": 710479,"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": 6305206596150.268, "dur": 0.733, + "args": { + "External id": 710480,"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": 6305206596155.161, "dur": 3.921, + "args": { + "External id": 710481,"Record function id": 0, "Ev Idx": 4432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206596156.504, "dur": 2.198, + "args": { + "External id": 710482,"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": 6305206596157.040, "dur": 1.171, + "args": { + "External id": 710483,"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": 6305206596157.515, "dur": 0.629, + "args": { + "External id": 710484,"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": 6305206596162.147, "dur": 3.670, + "args": { + "External id": 710485,"Record function id": 0, "Ev Idx": 4436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206596163.442, "dur": 1.996, + "args": { + "External id": 710486,"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": 6305206596163.865, "dur": 1.154, + "args": { + "External id": 710487,"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": 6305206596164.244, "dur": 0.710, + "args": { + "External id": 710488,"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": 6305206596168.995, "dur": 5.892, + "args": { + "External id": 710489,"Record function id": 0, "Ev Idx": 4440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206596170.097, "dur": 4.412, + "args": { + "External id": 710490,"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": 6305206596170.672, "dur": 3.403, + "args": { + "External id": 710491,"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": 6305206596173.359, "dur": 0.654, + "args": { + "External id": 710492,"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": 6305206596178.000, "dur": 3.695, + "args": { + "External id": 710493,"Record function id": 0, "Ev Idx": 4444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206596179.317, "dur": 1.978, + "args": { + "External id": 710494,"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": 6305206596179.753, "dur": 1.122, + "args": { + "External id": 710495,"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": 6305206596180.034, "dur": 0.770, + "args": { + "External id": 710496,"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": 6305206596185.519, "dur": 3.920, + "args": { + "External id": 710497,"Record function id": 0, "Ev Idx": 4448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206596186.876, "dur": 2.153, + "args": { + "External id": 710498,"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": 6305206596187.291, "dur": 1.324, + "args": { + "External id": 710499,"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": 6305206596187.717, "dur": 0.835, + "args": { + "External id": 710500,"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": 6305206596193.913, "dur": 62416.317, + "args": { + "External id": 710501,"Record function id": 0, "Sequence number": 7674407, "Fwd thread id": 1, "Ev Idx": 4452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305206596195.879, "dur": 62405.007, + "args": { + "External id": 710502,"Sequence number": 7674407, "Fwd thread 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": 6305206596195.879, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.8)", "pid": 2338707, "tid": 2379456, + "ts": 6305206596226.717, "dur": 39.033, + "args": { + "External id": 710503,"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": 6305206596273.958, "dur": 65.526, + "args": { + "External id": 710504,"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": 6305206596345.849, "dur": 62246.884, + "args": { + "External id": 710505,"Record function id": 0, "Ev Idx": 4456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305206596438.091, "dur": 7.136, + "args": { + "External id": 710506,"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": 6305206596459.100, "dur": 6.953, + "args": { + "External id": 710507,"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": 6305206596483.596, "dur": 61491.213, + "args": { + "External id": 710508,"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": 6305206596497.425, "dur": 61463.411, + "args": { + "External id": 710509,"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": 6305206596605.640, "dur": 19.249, + "args": { + "External id": 710510,"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": 6305206596645.897, "dur": 61268.676, + "args": { + "External id": 710511,"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": 6305206596648.800, "dur": 61264.594, + "args": { + "External id": 710512,"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": 6305206596654.417, "dur": 11.633, + "args": { + "External id": 710513,"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": 6305206596668.128, "dur": 61240.171, + "args": { + "External id": 710514,"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": 6305206658111.186, "dur": 12.896, + "args": { + "External id": 710515,"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": 6305206658114.706, "dur": 8.680, + "args": { + "External id": 710516,"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": 6305206658156.542, "dur": 146.581, + "args": { + "External id": 710517,"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": 6305206658190.783, "dur": 108.328, + "args": { + "External id": 710518,"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": 6305206658204.732, "dur": 89.823, + "args": { + "External id": 710519,"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": 6305206658321.079, "dur": 2.215, + "args": { + "External id": 710520,"Record function id": 0, "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": 6305206658369.710, "dur": 6.092, + "args": { + "External id": 710521,"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": 6305206658418.711, "dur": 1.471, + "args": { + "External id": 710522,"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": 6305206658435.511, "dur": 3.560, + "args": { + "External id": 710523,"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": 6305206658450.858, "dur": 0.740, + "args": { + "External id": 710524,"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": 6305206658464.820, "dur": 0.937, + "args": { + "External id": 710525,"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": 6305206658475.284, "dur": 0.884, + "args": { + "External id": 710526,"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": 6305206658486.058, "dur": 3.179, + "args": { + "External id": 710527,"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": 6305206658499.729, "dur": 2.350, + "args": { + "External id": 710528,"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": 6305206658529.784, "dur": 1.218, + "args": { + "External id": 710529,"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": 6305206658624.889, "dur": 2983.123, + "args": { + "External id": 710530,"Record function id": 0, "Ev Idx": 4481 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.7)", "pid": 2338707, "tid": 2379456, + "ts": 6305206658646.249, "dur": 1092.011, + "args": { + "External id": 710531,"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": 6305206658659.968, "dur": 335.647, + "args": { + "External id": 710532,"Record function id": 0, "Ev Idx": 4483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6305206658744.884, "dur": 4.340, + "args": { + "External id": 710533,"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": 6305206658752.849, "dur": 1.242, + "args": { + "External id": 710534,"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": 6305206658756.041, "dur": 2.774, + "args": { + "External id": 710535,"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": 6305206658760.670, "dur": 0.928, + "args": { + "External id": 710536,"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": 6305206658766.988, "dur": 0.846, + "args": { + "External id": 710537,"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": 6305206658769.308, "dur": 0.886, + "args": { + "External id": 710538,"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": 6305206658772.014, "dur": 2.115, + "args": { + "External id": 710539,"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": 6305206658777.854, "dur": 0.991, + "args": { + "External id": 710540,"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": 6305206658780.435, "dur": 0.811, + "args": { + "External id": 710541,"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": 6305206658782.661, "dur": 0.818, + "args": { + "External id": 710542,"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": 6305206658801.749, "dur": 165.257, + "args": { + "External id": 710543,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305206658817.292, "dur": 145.354, + "args": { + "External id": 710544,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305206658846.002, "dur": 18.756, + "args": { + "External id": 710545,"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": 6305206658870.379, "dur": 64.729, + "args": { + "External id": 710546,"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": 6305206658872.934, "dur": 61.768, + "args": { + "External id": 710547,"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": 6305206658877.078, "dur": 5.250, + "args": { + "External id": 710548,"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": 6305206658884.481, "dur": 49.119, + "args": { + "External id": 710549,"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": 6305206659116.086, "dur": 614.586, + "args": { + "External id": 710550,"Record function id": 0, "Ev Idx": 4501 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.6)", "pid": 2338707, "tid": 2379456, + "ts": 6305206659133.947, "dur": 584.647, + "args": { + "External id": 710551,"Record function id": 0, "Ev Idx": 4502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305206659196.921, "dur": 5.699, + "args": { + "External id": 710552,"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": 6305206659218.408, "dur": 38.606, + "args": { + "External id": 710553,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206659224.278, "dur": 2.670, + "args": { + "External id": 710554,"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": 6305206659228.957, "dur": 0.483, + "args": { + "External id": 710555,"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": 6305206659230.960, "dur": 0.652, + "args": { + "External id": 710556,"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": 6305206659234.907, "dur": 0.468, + "args": { + "External id": 710557,"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": 6305206659236.845, "dur": 0.575, + "args": { + "External id": 710558,"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": 6305206659239.042, "dur": 2.524, + "args": { + "External id": 710559,"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": 6305206659244.049, "dur": 0.573, + "args": { + "External id": 710560,"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": 6305206659246.081, "dur": 0.288, + "args": { + "External id": 710561,"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": 6305206659247.592, "dur": 1.357, + "args": { + "External id": 710562,"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": 6305206659267.540, "dur": 44.712, + "args": { + "External id": 710563,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305206659343.494, "dur": 116.728, + "args": { + "External id": 710564,"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": 6305206659354.208, "dur": 3.758, + "args": { + "External id": 710565,"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": 6305206659363.278, "dur": 10.205, + "args": { + "External id": 710566,"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": 6305206659367.511, "dur": 5.563, + "args": { + "External id": 710567,"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": 6305206659371.391, "dur": 0.430, + "args": { + "External id": 710568,"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": 6305206659380.382, "dur": 28.634, + "args": { + "External id": 710569,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206659383.000, "dur": 0.607, + "args": { + "External id": 710570,"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": 6305206659385.434, "dur": 0.479, + "args": { + "External id": 710571,"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": 6305206659387.487, "dur": 2.739, + "args": { + "External id": 710572,"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": 6305206659392.124, "dur": 0.428, + "args": { + "External id": 710573,"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": 6305206659394.310, "dur": 0.475, + "args": { + "External id": 710574,"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": 6305206659398.571, "dur": 0.499, + "args": { + "External id": 710575,"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": 6305206659400.468, "dur": 0.253, + "args": { + "External id": 710576,"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": 6305206659402.283, "dur": 0.249, + "args": { + "External id": 710577,"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": 6305206659404.919, "dur": 0.586, + "args": { + "External id": 710578,"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": 6305206659419.379, "dur": 33.325, + "args": { + "External id": 710579,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305206659504.544, "dur": 139.804, + "args": { + "External id": 710580,"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": 6305206659551.105, "dur": 89.710, + "args": { + "External id": 710581,"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": 6305206659561.367, "dur": 75.404, + "args": { + "External id": 710582,"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": 6305206659664.574, "dur": 1.905, + "args": { + "External id": 710583,"Record function id": 0, "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": 6305206659745.203, "dur": 1840.685, + "args": { + "External id": 710584,"Sequence number": 7674406, "Fwd thread 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": 6305206659745.203, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6305206659857.713, "dur": 109.916, + "args": { + "External id": 710585,"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": 6305206660011.370, "dur": 39.044, + "args": { + "External id": 710586,"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": 6305206660123.471, "dur": 61.459, + "args": { + "External id": 710587,"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": 6305206660198.358, "dur": 33.447, + "args": { + "External id": 710588,"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": 6305206660238.438, "dur": 32.267, + "args": { + "External id": 710589,"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": 6305206660277.119, "dur": 26.848, + "args": { + "External id": 710590,"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": 6305206660310.107, "dur": 37.687, + "args": { + "External id": 710591,"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": 6305206660380.824, "dur": 30.508, + "args": { + "External id": 710592,"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": 6305206660432.749, "dur": 27.699, + "args": { + "External id": 710593,"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": 6305206660482.143, "dur": 20.604, + "args": { + "External id": 710594,"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": 6305206660536.106, "dur": 18.459, + "args": { + "External id": 710595,"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": 6305206660562.633, "dur": 42.261, + "args": { + "External id": 710596,"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": 6305206660608.684, "dur": 33.416, + "args": { + "External id": 710597,"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": 6305206660673.758, "dur": 263.135, + "args": { + "External id": 710598,"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": 6305206660755.107, "dur": 6.073, + "args": { + "External id": 710599,"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": 6305206660763.259, "dur": 2.704, + "args": { + "External id": 710600,"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": 6305206660767.262, "dur": 2.017, + "args": { + "External id": 710601,"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": 6305206660770.795, "dur": 3.354, + "args": { + "External id": 710602,"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": 6305206660825.356, "dur": 10.376, + "args": { + "External id": 710603,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206660832.659, "dur": 2.766, + "args": { + "External id": 710604,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206660837.720, "dur": 35.299, + "args": { + "External id": 710605,"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": 6305206660843.706, "dur": 3.768, + "args": { + "External id": 710606,"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": 6305206660874.566, "dur": 1.650, + "args": { + "External id": 710607,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206660875.503, "dur": 0.613, + "args": { + "External id": 710608,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206660877.178, "dur": 18.011, + "args": { + "External id": 710609,"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": 6305206660881.576, "dur": 0.540, + "args": { + "External id": 710610,"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": 6305206660976.674, "dur": 26.901, + "args": { + "External id": 710611,"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": 6305206661026.096, "dur": 18.980, + "args": { + "External id": 710612,"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": 6305206661093.016, "dur": 55.804, + "args": { + "External id": 710613,"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": 6305206661157.340, "dur": 40.227, + "args": { + "External id": 710614,"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": 6305206661208.762, "dur": 21.437, + "args": { + "External id": 710615,"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": 6305206661235.845, "dur": 31.821, + "args": { + "External id": 710616,"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": 6305206661274.780, "dur": 27.526, + "args": { + "External id": 710617,"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": 6305206661310.267, "dur": 30.827, + "args": { + "External id": 710618,"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": 6305206661363.870, "dur": 25.609, + "args": { + "External id": 710619,"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": 6305206661407.319, "dur": 23.612, + "args": { + "External id": 710620,"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": 6305206661446.900, "dur": 19.681, + "args": { + "External id": 710621,"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": 6305206661486.108, "dur": 15.326, + "args": { + "External id": 710622,"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": 6305206661531.743, "dur": 20.139, + "args": { + "External id": 710623,"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": 6305206661641.313, "dur": 21.081, + "args": { + "External id": 710624,"Record function id": 0, "Ev Idx": 4575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206661647.788, "dur": 13.376, + "args": { + "External id": 710625,"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": 6305206661652.938, "dur": 6.126, + "args": { + "External id": 710626,"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": 6305206661654.432, "dur": 4.404, + "args": { + "External id": 710627,"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": 6305206661667.461, "dur": 4.720, + "args": { + "External id": 710628,"Record function id": 0, "Ev Idx": 4579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206661669.068, "dur": 2.660, + "args": { + "External id": 710629,"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": 6305206661669.725, "dur": 1.498, + "args": { + "External id": 710630,"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": 6305206661670.261, "dur": 0.881, + "args": { + "External id": 710631,"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": 6305206661675.513, "dur": 7.401, + "args": { + "External id": 710632,"Record function id": 0, "Ev Idx": 4583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206661676.818, "dur": 5.605, + "args": { + "External id": 710633,"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": 6305206661677.601, "dur": 4.391, + "args": { + "External id": 710634,"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": 6305206661678.679, "dur": 3.180, + "args": { + "External id": 710635,"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": 6305206661686.142, "dur": 4.290, + "args": { + "External id": 710636,"Record function id": 0, "Ev Idx": 4587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206661687.770, "dur": 2.270, + "args": { + "External id": 710637,"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": 6305206661688.387, "dur": 1.271, + "args": { + "External id": 710638,"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": 6305206661688.847, "dur": 0.748, + "args": { + "External id": 710639,"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": 6305206661693.568, "dur": 4.301, + "args": { + "External id": 710640,"Record function id": 0, "Ev Idx": 4591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206661694.853, "dur": 2.619, + "args": { + "External id": 710641,"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": 6305206661695.413, "dur": 1.578, + "args": { + "External id": 710642,"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": 6305206661696.143, "dur": 0.784, + "args": { + "External id": 710643,"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": 6305206661700.989, "dur": 3.808, + "args": { + "External id": 710644,"Record function id": 0, "Ev Idx": 4595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206661702.188, "dur": 2.202, + "args": { + "External id": 710645,"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": 6305206661702.633, "dur": 1.157, + "args": { + "External id": 710646,"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": 6305206661702.972, "dur": 0.752, + "args": { + "External id": 710647,"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": 6305206661707.879, "dur": 5.911, + "args": { + "External id": 710648,"Record function id": 0, "Ev Idx": 4599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206661709.016, "dur": 4.380, + "args": { + "External id": 710649,"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": 6305206661709.584, "dur": 3.426, + "args": { + "External id": 710650,"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": 6305206661712.252, "dur": 0.664, + "args": { + "External id": 710651,"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": 6305206661716.803, "dur": 3.701, + "args": { + "External id": 710652,"Record function id": 0, "Ev Idx": 4603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206661717.973, "dur": 2.134, + "args": { + "External id": 710653,"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": 6305206661718.658, "dur": 1.063, + "args": { + "External id": 710654,"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": 6305206661719.073, "dur": 0.566, + "args": { + "External id": 710655,"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": 6305206661723.770, "dur": 34.760, + "args": { + "External id": 710656,"Record function id": 0, "Ev Idx": 4607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206661756.014, "dur": 2.074, + "args": { + "External id": 710657,"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": 6305206661756.702, "dur": 0.951, + "args": { + "External id": 710658,"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": 6305206661756.963, "dur": 0.620, + "args": { + "External id": 710659,"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": 6305206661770.302, "dur": 61444.116, + "args": { + "External id": 710660,"Record function id": 0, "Sequence number": 7674405, "Fwd thread id": 1, "Ev Idx": 4611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305206661772.109, "dur": 61433.088, + "args": { + "External id": 710661,"Sequence number": 7674405, "Fwd thread 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": 6305206661772.109, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.7)", "pid": 2338707, "tid": 2379456, + "ts": 6305206661809.954, "dur": 38.390, + "args": { + "External id": 710662,"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": 6305206661856.723, "dur": 64.301, + "args": { + "External id": 710663,"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": 6305206661927.032, "dur": 61269.636, + "args": { + "External id": 710664,"Record function id": 0, "Ev Idx": 4615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305206662018.976, "dur": 7.331, + "args": { + "External id": 710665,"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": 6305206662036.372, "dur": 6.651, + "args": { + "External id": 710666,"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": 6305206662101.170, "dur": 60158.255, + "args": { + "External id": 710667,"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": 6305206662116.966, "dur": 60129.011, + "args": { + "External id": 710668,"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": 6305206662209.427, "dur": 21.324, + "args": { + "External id": 710669,"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": 6305206662251.390, "dur": 59945.908, + "args": { + "External id": 710670,"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": 6305206662254.085, "dur": 59942.080, + "args": { + "External id": 710671,"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": 6305206662258.994, "dur": 13.083, + "args": { + "External id": 710672,"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": 6305206662273.924, "dur": 59917.109, + "args": { + "External id": 710673,"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": 6305206722369.312, "dur": 12.067, + "args": { + "External id": 710674,"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": 6305206722372.826, "dur": 8.180, + "args": { + "External id": 710675,"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": 6305206722414.192, "dur": 441.226, + "args": { + "External id": 710676,"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": 6305206722448.709, "dur": 400.551, + "args": { + "External id": 710677,"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": 6305206722461.873, "dur": 381.367, + "args": { + "External id": 710678,"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": 6305206722880.847, "dur": 2.472, + "args": { + "External id": 710679,"Record function id": 0, "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": 6305206722944.968, "dur": 7.203, + "args": { + "External id": 710680,"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": 6305206722997.755, "dur": 1.327, + "args": { + "External id": 710681,"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": 6305206723013.847, "dur": 3.827, + "args": { + "External id": 710682,"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": 6305206723029.261, "dur": 0.967, + "args": { + "External id": 710683,"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": 6305206723043.133, "dur": 0.854, + "args": { + "External id": 710684,"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": 6305206723090.704, "dur": 1.538, + "args": { + "External id": 710685,"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": 6305206723106.390, "dur": 3.368, + "args": { + "External id": 710686,"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": 6305206723120.305, "dur": 2.170, + "args": { + "External id": 710687,"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": 6305206723132.375, "dur": 0.838, + "args": { + "External id": 710688,"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": 6305206723230.838, "dur": 3007.229, + "args": { + "External id": 710689,"Record function id": 0, "Ev Idx": 4640 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.6)", "pid": 2338707, "tid": 2379456, + "ts": 6305206723252.865, "dur": 1106.345, + "args": { + "External id": 710690,"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": 6305206723269.529, "dur": 365.629, + "args": { + "External id": 710691,"Record function id": 0, "Ev Idx": 4642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6305206723356.398, "dur": 4.172, + "args": { + "External id": 710692,"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": 6305206723363.930, "dur": 0.856, + "args": { + "External id": 710693,"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": 6305206723366.707, "dur": 2.851, + "args": { + "External id": 710694,"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": 6305206723371.822, "dur": 0.689, + "args": { + "External id": 710695,"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": 6305206723374.169, "dur": 0.782, + "args": { + "External id": 710696,"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": 6305206723376.549, "dur": 0.551, + "args": { + "External id": 710697,"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": 6305206723378.590, "dur": 1.706, + "args": { + "External id": 710698,"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": 6305206723383.918, "dur": 0.732, + "args": { + "External id": 710699,"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": 6305206723386.154, "dur": 0.658, + "args": { + "External id": 710700,"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": 6305206723388.391, "dur": 0.648, + "args": { + "External id": 710701,"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": 6305206723407.499, "dur": 191.688, + "args": { + "External id": 710702,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305206723424.334, "dur": 169.841, + "args": { + "External id": 710703,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305206723456.399, "dur": 19.122, + "args": { + "External id": 710704,"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": 6305206723479.263, "dur": 82.750, + "args": { + "External id": 710705,"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": 6305206723481.788, "dur": 79.863, + "args": { + "External id": 710706,"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": 6305206723485.931, "dur": 5.571, + "args": { + "External id": 710707,"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": 6305206723493.314, "dur": 67.241, + "args": { + "External id": 710708,"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": 6305206723719.037, "dur": 632.599, + "args": { + "External id": 710709,"Record function id": 0, "Ev Idx": 4660 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.5)", "pid": 2338707, "tid": 2379456, + "ts": 6305206723735.708, "dur": 603.946, + "args": { + "External id": 710710,"Record function id": 0, "Ev Idx": 4661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305206723794.237, "dur": 5.837, + "args": { + "External id": 710711,"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": 6305206723815.750, "dur": 35.183, + "args": { + "External id": 710712,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206723821.550, "dur": 2.539, + "args": { + "External id": 710713,"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": 6305206723826.057, "dur": 0.582, + "args": { + "External id": 710714,"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": 6305206723828.558, "dur": 0.592, + "args": { + "External id": 710715,"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": 6305206723832.033, "dur": 0.284, + "args": { + "External id": 710716,"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": 6305206723833.897, "dur": 0.402, + "args": { + "External id": 710717,"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": 6305206723836.004, "dur": 2.603, + "args": { + "External id": 710718,"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": 6305206723841.614, "dur": 0.341, + "args": { + "External id": 710719,"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": 6305206723843.203, "dur": 0.447, + "args": { + "External id": 710720,"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": 6305206723844.981, "dur": 1.607, + "args": { + "External id": 710721,"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": 6305206723861.862, "dur": 42.920, + "args": { + "External id": 710722,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305206723934.467, "dur": 115.403, + "args": { + "External id": 710723,"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": 6305206723945.043, "dur": 3.395, + "args": { + "External id": 710724,"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": 6305206723953.531, "dur": 10.143, + "args": { + "External id": 710725,"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": 6305206723957.776, "dur": 5.509, + "args": { + "External id": 710726,"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": 6305206723961.374, "dur": 0.656, + "args": { + "External id": 710727,"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": 6305206723970.971, "dur": 28.692, + "args": { + "External id": 710728,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206723973.257, "dur": 0.486, + "args": { + "External id": 710729,"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": 6305206723975.395, "dur": 0.524, + "args": { + "External id": 710730,"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": 6305206723977.318, "dur": 3.779, + "args": { + "External id": 710731,"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": 6305206723983.037, "dur": 0.503, + "args": { + "External id": 710732,"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": 6305206723985.364, "dur": 0.559, + "args": { + "External id": 710733,"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": 6305206723988.507, "dur": 0.493, + "args": { + "External id": 710734,"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": 6305206723990.518, "dur": 0.320, + "args": { + "External id": 710735,"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": 6305206723992.221, "dur": 0.486, + "args": { + "External id": 710736,"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": 6305206723995.011, "dur": 0.560, + "args": { + "External id": 710737,"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": 6305206724012.283, "dur": 30.204, + "args": { + "External id": 710738,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305206724135.745, "dur": 131.516, + "args": { + "External id": 710739,"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": 6305206724167.541, "dur": 96.173, + "args": { + "External id": 710740,"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": 6305206724179.696, "dur": 79.671, + "args": { + "External id": 710741,"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": 6305206724285.684, "dur": 1.790, + "args": { + "External id": 710742,"Record function id": 0, "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": 6305206724366.795, "dur": 1849.556, + "args": { + "External id": 710743,"Sequence number": 7674404, "Fwd thread 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": 6305206724366.795, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6305206724479.266, "dur": 130.274, + "args": { + "External id": 710744,"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": 6305206724658.050, "dur": 41.180, + "args": { + "External id": 710745,"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": 6305206724716.949, "dur": 54.727, + "args": { + "External id": 710746,"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": 6305206724784.418, "dur": 32.408, + "args": { + "External id": 710747,"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": 6305206724833.929, "dur": 34.798, + "args": { + "External id": 710748,"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": 6305206724875.578, "dur": 27.756, + "args": { + "External id": 710749,"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": 6305206724911.059, "dur": 29.209, + "args": { + "External id": 710750,"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": 6305206724969.894, "dur": 23.802, + "args": { + "External id": 710751,"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": 6305206725017.173, "dur": 30.495, + "args": { + "External id": 710752,"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": 6305206725111.021, "dur": 24.141, + "args": { + "External id": 710753,"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": 6305206725149.522, "dur": 14.675, + "args": { + "External id": 710754,"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": 6305206725173.443, "dur": 42.637, + "args": { + "External id": 710755,"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": 6305206725219.639, "dur": 33.555, + "args": { + "External id": 710756,"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": 6305206725283.056, "dur": 262.691, + "args": { + "External id": 710757,"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": 6305206725360.406, "dur": 6.350, + "args": { + "External id": 710758,"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": 6305206725368.913, "dur": 2.476, + "args": { + "External id": 710759,"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": 6305206725372.976, "dur": 3.509, + "args": { + "External id": 710760,"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": 6305206725378.214, "dur": 2.298, + "args": { + "External id": 710761,"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": 6305206725424.182, "dur": 7.438, + "args": { + "External id": 710762,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206725428.356, "dur": 3.096, + "args": { + "External id": 710763,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206725433.426, "dur": 32.913, + "args": { + "External id": 710764,"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": 6305206725439.283, "dur": 3.774, + "args": { + "External id": 710765,"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": 6305206725467.852, "dur": 2.024, + "args": { + "External id": 710766,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206725469.130, "dur": 0.678, + "args": { + "External id": 710767,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206725470.970, "dur": 16.184, + "args": { + "External id": 710768,"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": 6305206725474.925, "dur": 0.566, + "args": { + "External id": 710769,"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": 6305206725587.523, "dur": 28.680, + "args": { + "External id": 710770,"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": 6305206725635.859, "dur": 16.853, + "args": { + "External id": 710771,"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": 6305206725664.546, "dur": 46.277, + "args": { + "External id": 710772,"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": 6305206725717.190, "dur": 42.578, + "args": { + "External id": 710773,"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": 6305206725769.726, "dur": 24.340, + "args": { + "External id": 710774,"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": 6305206725799.062, "dur": 31.108, + "args": { + "External id": 710775,"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": 6305206725840.306, "dur": 41.618, + "args": { + "External id": 710776,"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": 6305206725898.163, "dur": 35.290, + "args": { + "External id": 710777,"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": 6305206725957.605, "dur": 24.729, + "args": { + "External id": 710778,"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": 6305206726002.957, "dur": 23.066, + "args": { + "External id": 710779,"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": 6305206726042.081, "dur": 68.506, + "args": { + "External id": 710780,"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": 6305206726137.071, "dur": 15.593, + "args": { + "External id": 710781,"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": 6305206726166.238, "dur": 16.955, + "args": { + "External id": 710782,"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": 6305206726261.128, "dur": 15.434, + "args": { + "External id": 710783,"Record function id": 0, "Ev Idx": 4734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206726264.334, "dur": 11.251, + "args": { + "External id": 710784,"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": 6305206726268.782, "dur": 5.942, + "args": { + "External id": 710785,"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": 6305206726270.579, "dur": 4.014, + "args": { + "External id": 710786,"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": 6305206726280.519, "dur": 4.904, + "args": { + "External id": 710787,"Record function id": 0, "Ev Idx": 4738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206726282.152, "dur": 2.822, + "args": { + "External id": 710788,"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": 6305206726283.063, "dur": 1.468, + "args": { + "External id": 710789,"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": 6305206726283.734, "dur": 0.733, + "args": { + "External id": 710790,"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": 6305206726288.930, "dur": 6.396, + "args": { + "External id": 710791,"Record function id": 0, "Ev Idx": 4742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206726290.373, "dur": 4.513, + "args": { + "External id": 710792,"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": 6305206726291.011, "dur": 3.431, + "args": { + "External id": 710793,"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": 6305206726291.599, "dur": 2.720, + "args": { + "External id": 710794,"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": 6305206726298.646, "dur": 4.653, + "args": { + "External id": 710795,"Record function id": 0, "Ev Idx": 4746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206726300.395, "dur": 2.473, + "args": { + "External id": 710796,"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": 6305206726300.968, "dur": 1.517, + "args": { + "External id": 710797,"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": 6305206726301.509, "dur": 0.913, + "args": { + "External id": 710798,"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": 6305206726306.454, "dur": 3.688, + "args": { + "External id": 710799,"Record function id": 0, "Ev Idx": 4750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206726307.762, "dur": 1.982, + "args": { + "External id": 710800,"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": 6305206726308.302, "dur": 1.036, + "args": { + "External id": 710801,"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": 6305206726308.743, "dur": 0.529, + "args": { + "External id": 710802,"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": 6305206726313.268, "dur": 4.450, + "args": { + "External id": 710803,"Record function id": 0, "Ev Idx": 4754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206726314.744, "dur": 2.548, + "args": { + "External id": 710804,"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": 6305206726315.454, "dur": 1.418, + "args": { + "External id": 710805,"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": 6305206726315.980, "dur": 0.828, + "args": { + "External id": 710806,"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": 6305206726320.924, "dur": 5.849, + "args": { + "External id": 710807,"Record function id": 0, "Ev Idx": 4758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206726322.282, "dur": 4.046, + "args": { + "External id": 710808,"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": 6305206726322.848, "dur": 3.076, + "args": { + "External id": 710809,"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": 6305206726325.199, "dur": 0.639, + "args": { + "External id": 710810,"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": 6305206726329.971, "dur": 3.884, + "args": { + "External id": 710811,"Record function id": 0, "Ev Idx": 4762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206726331.262, "dur": 2.187, + "args": { + "External id": 710812,"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": 6305206726331.847, "dur": 1.204, + "args": { + "External id": 710813,"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": 6305206726332.265, "dur": 0.706, + "args": { + "External id": 710814,"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": 6305206726337.472, "dur": 3.550, + "args": { + "External id": 710815,"Record function id": 0, "Ev Idx": 4766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206726338.715, "dur": 1.882, + "args": { + "External id": 710816,"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": 6305206726339.173, "dur": 0.996, + "args": { + "External id": 710817,"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": 6305206726339.426, "dur": 0.646, + "args": { + "External id": 710818,"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": 6305206726345.447, "dur": 66404.834, + "args": { + "External id": 710819,"Record function id": 0, "Sequence number": 7674403, "Fwd thread id": 1, "Ev Idx": 4770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305206726347.327, "dur": 66393.165, + "args": { + "External id": 710820,"Sequence number": 7674403, "Fwd thread 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": 6305206726347.327, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.6)", "pid": 2338707, "tid": 2379456, + "ts": 6305206726378.673, "dur": 40.273, + "args": { + "External id": 710821,"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": 6305206726427.425, "dur": 61.221, + "args": { + "External id": 710822,"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": 6305206726494.655, "dur": 66237.853, + "args": { + "External id": 710823,"Record function id": 0, "Ev Idx": 4774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305206726603.011, "dur": 7.306, + "args": { + "External id": 710824,"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": 6305206726621.360, "dur": 7.319, + "args": { + "External id": 710825,"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": 6305206726647.029, "dur": 65191.649, + "args": { + "External id": 710826,"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": 6305206726663.677, "dur": 65161.743, + "args": { + "External id": 710827,"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": 6305206726753.317, "dur": 17.782, + "args": { + "External id": 710828,"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": 6305206726791.072, "dur": 64989.318, + "args": { + "External id": 710829,"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": 6305206726793.692, "dur": 64985.593, + "args": { + "External id": 710830,"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": 6305206726798.508, "dur": 10.553, + "args": { + "External id": 710831,"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": 6305206726811.367, "dur": 64963.122, + "args": { + "External id": 710832,"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": 6305206791947.161, "dur": 11.976, + "args": { + "External id": 710833,"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": 6305206791950.596, "dur": 8.156, + "args": { + "External id": 710834,"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": 6305206791991.562, "dur": 421.943, + "args": { + "External id": 710835,"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": 6305206792026.696, "dur": 381.427, + "args": { + "External id": 710836,"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": 6305206792040.370, "dur": 361.522, + "args": { + "External id": 710837,"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": 6305206792438.759, "dur": 2.147, + "args": { + "External id": 710838,"Record function id": 0, "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": 6305206792504.321, "dur": 21.862, + "args": { + "External id": 710839,"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": 6305206792574.883, "dur": 1.529, + "args": { + "External id": 710840,"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": 6305206792591.301, "dur": 3.459, + "args": { + "External id": 710841,"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": 6305206792606.861, "dur": 1.002, + "args": { + "External id": 710842,"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": 6305206792621.630, "dur": 0.872, + "args": { + "External id": 710843,"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": 6305206792632.954, "dur": 0.806, + "args": { + "External id": 710844,"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": 6305206792644.003, "dur": 2.881, + "args": { + "External id": 710845,"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": 6305206792657.134, "dur": 2.242, + "args": { + "External id": 710846,"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": 6305206792669.182, "dur": 0.651, + "args": { + "External id": 710847,"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": 6305206792766.404, "dur": 3068.434, + "args": { + "External id": 710848,"Record function id": 0, "Ev Idx": 4799 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.5)", "pid": 2338707, "tid": 2379456, + "ts": 6305206792789.139, "dur": 1121.012, + "args": { + "External id": 710849,"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": 6305206792805.557, "dur": 390.444, + "args": { + "External id": 710850,"Record function id": 0, "Ev Idx": 4801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6305206792892.273, "dur": 4.130, + "args": { + "External id": 710851,"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": 6305206792899.945, "dur": 0.841, + "args": { + "External id": 710852,"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": 6305206792902.548, "dur": 2.756, + "args": { + "External id": 710853,"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": 6305206792907.254, "dur": 0.796, + "args": { + "External id": 710854,"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": 6305206792909.652, "dur": 0.791, + "args": { + "External id": 710855,"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": 6305206792911.974, "dur": 0.707, + "args": { + "External id": 710856,"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": 6305206792914.263, "dur": 2.323, + "args": { + "External id": 710857,"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": 6305206792920.154, "dur": 0.800, + "args": { + "External id": 710858,"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": 6305206792922.348, "dur": 0.615, + "args": { + "External id": 710859,"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": 6305206792924.547, "dur": 0.588, + "args": { + "External id": 710860,"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": 6305206792943.345, "dur": 217.684, + "args": { + "External id": 710861,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305206792959.635, "dur": 195.464, + "args": { + "External id": 710862,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305206792990.534, "dur": 20.688, + "args": { + "External id": 710863,"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": 6305206793015.241, "dur": 107.074, + "args": { + "External id": 710864,"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": 6305206793017.895, "dur": 104.103, + "args": { + "External id": 710865,"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": 6305206793021.803, "dur": 5.425, + "args": { + "External id": 710866,"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": 6305206793028.842, "dur": 92.138, + "args": { + "External id": 710867,"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": 6305206793287.839, "dur": 614.443, + "args": { + "External id": 710868,"Record function id": 0, "Ev Idx": 4819 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.4)", "pid": 2338707, "tid": 2379456, + "ts": 6305206793305.357, "dur": 585.182, + "args": { + "External id": 710869,"Record function id": 0, "Ev Idx": 4820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305206793364.258, "dur": 5.675, + "args": { + "External id": 710870,"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": 6305206793385.330, "dur": 35.861, + "args": { + "External id": 710871,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206793390.665, "dur": 3.619, + "args": { + "External id": 710872,"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": 6305206793396.438, "dur": 0.425, + "args": { + "External id": 710873,"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": 6305206793397.963, "dur": 0.514, + "args": { + "External id": 710874,"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": 6305206793402.043, "dur": 0.305, + "args": { + "External id": 710875,"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": 6305206793403.808, "dur": 0.451, + "args": { + "External id": 710876,"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": 6305206793405.920, "dur": 2.596, + "args": { + "External id": 710877,"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": 6305206793411.793, "dur": 0.334, + "args": { + "External id": 710878,"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": 6305206793413.532, "dur": 0.359, + "args": { + "External id": 710879,"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": 6305206793415.299, "dur": 1.851, + "args": { + "External id": 710880,"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": 6305206793432.065, "dur": 41.266, + "args": { + "External id": 710881,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305206793520.551, "dur": 124.900, + "args": { + "External id": 710882,"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": 6305206793533.917, "dur": 4.935, + "args": { + "External id": 710883,"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": 6305206793544.871, "dur": 11.397, + "args": { + "External id": 710884,"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": 6305206793549.177, "dur": 6.667, + "args": { + "External id": 710885,"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": 6305206793553.364, "dur": 0.695, + "args": { + "External id": 710886,"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": 6305206793563.764, "dur": 28.714, + "args": { + "External id": 710887,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206793566.290, "dur": 0.485, + "args": { + "External id": 710888,"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": 6305206793568.692, "dur": 0.483, + "args": { + "External id": 710889,"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": 6305206793570.446, "dur": 4.126, + "args": { + "External id": 710890,"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": 6305206793576.344, "dur": 0.527, + "args": { + "External id": 710891,"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": 6305206793578.127, "dur": 0.404, + "args": { + "External id": 710892,"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": 6305206793581.356, "dur": 0.624, + "args": { + "External id": 710893,"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": 6305206793583.224, "dur": 0.406, + "args": { + "External id": 710894,"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": 6305206793585.293, "dur": 0.412, + "args": { + "External id": 710895,"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": 6305206793588.350, "dur": 0.366, + "args": { + "External id": 710896,"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": 6305206793603.450, "dur": 31.383, + "args": { + "External id": 710897,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305206793691.177, "dur": 128.653, + "args": { + "External id": 710898,"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": 6305206793725.735, "dur": 90.507, + "args": { + "External id": 710899,"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": 6305206793736.786, "dur": 74.130, + "args": { + "External id": 710900,"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": 6305206793838.219, "dur": 2.238, + "args": { + "External id": 710901,"Record function id": 0, "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": 6305206793917.770, "dur": 1894.098, + "args": { + "External id": 710902,"Sequence number": 7674402, "Fwd thread 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": 6305206793917.770, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6305206794030.298, "dur": 153.657, + "args": { + "External id": 710903,"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": 6305206794253.915, "dur": 41.886, + "args": { + "External id": 710904,"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": 6305206794314.595, "dur": 56.498, + "args": { + "External id": 710905,"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": 6305206794384.193, "dur": 31.917, + "args": { + "External id": 710906,"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": 6305206794422.194, "dur": 33.931, + "args": { + "External id": 710907,"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": 6305206794462.746, "dur": 27.394, + "args": { + "External id": 710908,"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": 6305206794499.001, "dur": 48.863, + "args": { + "External id": 710909,"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": 6305206794582.677, "dur": 26.254, + "args": { + "External id": 710910,"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": 6305206794629.077, "dur": 31.226, + "args": { + "External id": 710911,"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": 6305206794683.702, "dur": 20.229, + "args": { + "External id": 710912,"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": 6305206794719.087, "dur": 15.267, + "args": { + "External id": 710913,"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": 6305206794741.899, "dur": 39.681, + "args": { + "External id": 710914,"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": 6305206794785.172, "dur": 34.929, + "args": { + "External id": 710915,"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": 6305206794850.471, "dur": 306.424, + "args": { + "External id": 710916,"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": 6305206794932.186, "dur": 6.254, + "args": { + "External id": 710917,"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": 6305206794940.688, "dur": 3.317, + "args": { + "External id": 710918,"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": 6305206794945.421, "dur": 2.409, + "args": { + "External id": 710919,"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": 6305206794949.080, "dur": 3.264, + "args": { + "External id": 710920,"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": 6305206794995.528, "dur": 7.436, + "args": { + "External id": 710921,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206794999.799, "dur": 2.958, + "args": { + "External id": 710922,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206795004.992, "dur": 33.188, + "args": { + "External id": 710923,"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": 6305206795010.562, "dur": 3.711, + "args": { + "External id": 710924,"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": 6305206795039.740, "dur": 1.833, + "args": { + "External id": 710925,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206795040.924, "dur": 0.556, + "args": { + "External id": 710926,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206795042.782, "dur": 66.051, + "args": { + "External id": 710927,"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": 6305206795045.056, "dur": 0.499, + "args": { + "External id": 710928,"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": 6305206795196.172, "dur": 27.601, + "args": { + "External id": 710929,"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": 6305206795243.429, "dur": 15.877, + "args": { + "External id": 710930,"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": 6305206795267.572, "dur": 53.004, + "args": { + "External id": 710931,"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": 6305206795326.818, "dur": 43.025, + "args": { + "External id": 710932,"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": 6305206795380.523, "dur": 37.113, + "args": { + "External id": 710933,"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": 6305206795431.806, "dur": 38.359, + "args": { + "External id": 710934,"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": 6305206795477.578, "dur": 42.212, + "args": { + "External id": 710935,"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": 6305206795529.315, "dur": 38.705, + "args": { + "External id": 710936,"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": 6305206795598.570, "dur": 26.440, + "args": { + "External id": 710937,"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": 6305206795643.042, "dur": 26.243, + "args": { + "External id": 710938,"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": 6305206795686.040, "dur": 22.202, + "args": { + "External id": 710939,"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": 6305206795725.867, "dur": 16.645, + "args": { + "External id": 710940,"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": 6305206795758.591, "dur": 21.361, + "args": { + "External id": 710941,"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": 6305206795858.372, "dur": 14.996, + "args": { + "External id": 710942,"Record function id": 0, "Ev Idx": 4893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206795861.536, "dur": 10.882, + "args": { + "External id": 710943,"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": 6305206795865.392, "dur": 5.957, + "args": { + "External id": 710944,"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": 6305206795867.011, "dur": 4.247, + "args": { + "External id": 710945,"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": 6305206795877.315, "dur": 5.267, + "args": { + "External id": 710946,"Record function id": 0, "Ev Idx": 4897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206795878.801, "dur": 3.344, + "args": { + "External id": 710947,"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": 6305206795879.786, "dur": 1.859, + "args": { + "External id": 710948,"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": 6305206795880.726, "dur": 0.835, + "args": { + "External id": 710949,"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": 6305206795886.098, "dur": 7.065, + "args": { + "External id": 710950,"Record function id": 0, "Ev Idx": 4901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206795887.612, "dur": 5.066, + "args": { + "External id": 710951,"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": 6305206795888.123, "dur": 4.147, + "args": { + "External id": 710952,"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": 6305206795888.946, "dur": 3.232, + "args": { + "External id": 710953,"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": 6305206795896.385, "dur": 4.747, + "args": { + "External id": 710954,"Record function id": 0, "Ev Idx": 4905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206795898.089, "dur": 2.625, + "args": { + "External id": 710955,"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": 6305206795898.636, "dur": 1.675, + "args": { + "External id": 710956,"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": 6305206795899.353, "dur": 0.896, + "args": { + "External id": 710957,"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": 6305206795904.256, "dur": 4.473, + "args": { + "External id": 710958,"Record function id": 0, "Ev Idx": 4909 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206795905.887, "dur": 2.409, + "args": { + "External id": 710959,"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": 6305206795906.542, "dur": 1.293, + "args": { + "External id": 710960,"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": 6305206795907.015, "dur": 0.751, + "args": { + "External id": 710961,"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": 6305206795911.942, "dur": 4.036, + "args": { + "External id": 710962,"Record function id": 0, "Ev Idx": 4913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206795913.215, "dur": 2.370, + "args": { + "External id": 710963,"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": 6305206795913.844, "dur": 1.307, + "args": { + "External id": 710964,"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": 6305206795914.401, "dur": 0.673, + "args": { + "External id": 710965,"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": 6305206795919.162, "dur": 3.909, + "args": { + "External id": 710966,"Record function id": 0, "Ev Idx": 4917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206795920.520, "dur": 2.142, + "args": { + "External id": 710967,"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": 6305206795920.985, "dur": 1.260, + "args": { + "External id": 710968,"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": 6305206795921.522, "dur": 0.657, + "args": { + "External id": 710969,"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": 6305206795926.202, "dur": 5.903, + "args": { + "External id": 710970,"Record function id": 0, "Ev Idx": 4921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206795927.462, "dur": 4.228, + "args": { + "External id": 710971,"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": 6305206795928.089, "dur": 3.152, + "args": { + "External id": 710972,"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": 6305206795930.478, "dur": 0.698, + "args": { + "External id": 710973,"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": 6305206795935.216, "dur": 3.534, + "args": { + "External id": 710974,"Record function id": 0, "Ev Idx": 4925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206795936.497, "dur": 1.861, + "args": { + "External id": 710975,"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": 6305206795936.945, "dur": 0.986, + "args": { + "External id": 710976,"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": 6305206795937.253, "dur": 0.616, + "args": { + "External id": 710977,"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": 6305206795943.158, "dur": 75222.612, + "args": { + "External id": 710978,"Record function id": 0, "Sequence number": 7674401, "Fwd thread id": 1, "Ev Idx": 4929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305206795944.706, "dur": 75210.745, + "args": { + "External id": 710979,"Sequence number": 7674401, "Fwd thread 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": 6305206795944.706, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.5)", "pid": 2338707, "tid": 2379456, + "ts": 6305206795974.629, "dur": 38.770, + "args": { + "External id": 710980,"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": 6305206796021.382, "dur": 106.617, + "args": { + "External id": 710981,"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": 6305206796137.350, "dur": 75009.081, + "args": { + "External id": 710982,"Record function id": 0, "Ev Idx": 4933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305206796231.823, "dur": 7.737, + "args": { + "External id": 710983,"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": 6305206796250.530, "dur": 7.004, + "args": { + "External id": 710984,"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": 6305206796274.581, "dur": 73930.870, + "args": { + "External id": 710985,"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": 6305206796288.770, "dur": 73903.097, + "args": { + "External id": 710986,"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": 6305206796374.283, "dur": 17.879, + "args": { + "External id": 710987,"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": 6305206796411.933, "dur": 73731.718, + "args": { + "External id": 710988,"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": 6305206796417.200, "dur": 73725.465, + "args": { + "External id": 710989,"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": 6305206796423.306, "dur": 9.766, + "args": { + "External id": 710990,"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": 6305206796434.999, "dur": 73702.612, + "args": { + "External id": 710991,"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": 6305206870311.754, "dur": 11.978, + "args": { + "External id": 710992,"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": 6305206870315.223, "dur": 8.097, + "args": { + "External id": 710993,"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": 6305206870353.767, "dur": 444.587, + "args": { + "External id": 710994,"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": 6305206870386.428, "dur": 406.120, + "args": { + "External id": 710995,"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": 6305206870398.856, "dur": 387.649, + "args": { + "External id": 710996,"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": 6305206870824.715, "dur": 2.403, + "args": { + "External id": 710997,"Record function id": 0, "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": 6305206870891.374, "dur": 7.278, + "args": { + "External id": 710998,"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": 6305206870943.601, "dur": 1.273, + "args": { + "External id": 710999,"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": 6305206870959.508, "dur": 3.435, + "args": { + "External id": 711000,"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": 6305206870975.252, "dur": 1.016, + "args": { + "External id": 711001,"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": 6305206870987.320, "dur": 0.901, + "args": { + "External id": 711002,"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": 6305206870998.469, "dur": 0.913, + "args": { + "External id": 711003,"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": 6305206871011.192, "dur": 3.046, + "args": { + "External id": 711004,"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": 6305206871024.592, "dur": 2.242, + "args": { + "External id": 711005,"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": 6305206871036.355, "dur": 0.890, + "args": { + "External id": 711006,"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": 6305206871183.643, "dur": 2955.205, + "args": { + "External id": 711007,"Record function id": 0, "Ev Idx": 4958 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.4)", "pid": 2338707, "tid": 2379456, + "ts": 6305206871203.484, "dur": 1111.784, + "args": { + "External id": 711008,"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": 6305206871217.763, "dur": 366.994, + "args": { + "External id": 711009,"Record function id": 0, "Ev Idx": 4960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6305206871306.362, "dur": 4.974, + "args": { + "External id": 711010,"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": 6305206871314.676, "dur": 1.008, + "args": { + "External id": 711011,"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": 6305206871317.993, "dur": 2.981, + "args": { + "External id": 711012,"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": 6305206871324.908, "dur": 1.060, + "args": { + "External id": 711013,"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": 6305206871327.591, "dur": 0.829, + "args": { + "External id": 711014,"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": 6305206871329.985, "dur": 0.764, + "args": { + "External id": 711015,"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": 6305206871332.378, "dur": 2.031, + "args": { + "External id": 711016,"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": 6305206871337.627, "dur": 0.736, + "args": { + "External id": 711017,"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": 6305206871339.641, "dur": 1.038, + "args": { + "External id": 711018,"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": 6305206871342.194, "dur": 0.953, + "args": { + "External id": 711019,"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": 6305206871361.174, "dur": 189.644, + "args": { + "External id": 711020,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305206871377.816, "dur": 167.365, + "args": { + "External id": 711021,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305206871408.591, "dur": 17.823, + "args": { + "External id": 711022,"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": 6305206871432.666, "dur": 65.896, + "args": { + "External id": 711023,"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": 6305206871435.380, "dur": 62.776, + "args": { + "External id": 711024,"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": 6305206871439.949, "dur": 5.883, + "args": { + "External id": 711025,"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": 6305206871447.343, "dur": 50.269, + "args": { + "External id": 711026,"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": 6305206871666.351, "dur": 640.929, + "args": { + "External id": 711027,"Record function id": 0, "Ev Idx": 4978 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.3)", "pid": 2338707, "tid": 2379456, + "ts": 6305206871683.200, "dur": 611.324, + "args": { + "External id": 711028,"Record function id": 0, "Ev Idx": 4979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305206871742.792, "dur": 5.536, + "args": { + "External id": 711029,"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": 6305206871763.014, "dur": 34.206, + "args": { + "External id": 711030,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206871768.581, "dur": 2.624, + "args": { + "External id": 711031,"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": 6305206871773.352, "dur": 0.538, + "args": { + "External id": 711032,"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": 6305206871775.297, "dur": 0.438, + "args": { + "External id": 711033,"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": 6305206871778.678, "dur": 0.503, + "args": { + "External id": 711034,"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": 6305206871780.505, "dur": 0.293, + "args": { + "External id": 711035,"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": 6305206871782.313, "dur": 2.463, + "args": { + "External id": 711036,"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": 6305206871787.706, "dur": 0.265, + "args": { + "External id": 711037,"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": 6305206871789.397, "dur": 0.413, + "args": { + "External id": 711038,"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": 6305206871791.011, "dur": 1.805, + "args": { + "External id": 711039,"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": 6305206871807.179, "dur": 47.666, + "args": { + "External id": 711040,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305206871885.558, "dur": 113.966, + "args": { + "External id": 711041,"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": 6305206871896.153, "dur": 3.724, + "args": { + "External id": 711042,"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": 6305206871905.064, "dur": 10.648, + "args": { + "External id": 711043,"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": 6305206871909.382, "dur": 5.926, + "args": { + "External id": 711044,"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": 6305206871913.362, "dur": 0.763, + "args": { + "External id": 711045,"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": 6305206871922.392, "dur": 25.914, + "args": { + "External id": 711046,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206871924.405, "dur": 0.811, + "args": { + "External id": 711047,"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": 6305206871927.079, "dur": 0.447, + "args": { + "External id": 711048,"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": 6305206871929.118, "dur": 2.426, + "args": { + "External id": 711049,"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": 6305206871933.125, "dur": 0.419, + "args": { + "External id": 711050,"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": 6305206871934.938, "dur": 0.574, + "args": { + "External id": 711051,"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": 6305206871938.240, "dur": 0.304, + "args": { + "External id": 711052,"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": 6305206871940.007, "dur": 0.289, + "args": { + "External id": 711053,"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": 6305206871941.579, "dur": 0.459, + "args": { + "External id": 711054,"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": 6305206871944.697, "dur": 0.297, + "args": { + "External id": 711055,"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": 6305206871960.612, "dur": 31.723, + "args": { + "External id": 711056,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305206872044.059, "dur": 168.847, + "args": { + "External id": 711057,"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": 6305206872115.111, "dur": 93.502, + "args": { + "External id": 711058,"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": 6305206872126.010, "dur": 78.189, + "args": { + "External id": 711059,"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": 6305206872234.739, "dur": 1.856, + "args": { + "External id": 711060,"Record function id": 0, "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": 6305206872322.421, "dur": 1794.424, + "args": { + "External id": 711061,"Sequence number": 7674400, "Fwd thread 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": 6305206872322.421, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6305206872436.077, "dur": 130.808, + "args": { + "External id": 711062,"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": 6305206872614.684, "dur": 42.331, + "args": { + "External id": 711063,"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": 6305206872674.664, "dur": 53.835, + "args": { + "External id": 711064,"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": 6305206872741.572, "dur": 31.623, + "args": { + "External id": 711065,"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": 6305206872779.921, "dur": 31.472, + "args": { + "External id": 711066,"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": 6305206872817.370, "dur": 27.876, + "args": { + "External id": 711067,"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": 6305206872851.997, "dur": 28.456, + "args": { + "External id": 711068,"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": 6305206872911.802, "dur": 24.330, + "args": { + "External id": 711069,"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": 6305206872968.959, "dur": 27.198, + "args": { + "External id": 711070,"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": 6305206873020.775, "dur": 19.274, + "args": { + "External id": 711071,"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": 6305206873091.431, "dur": 18.978, + "args": { + "External id": 711072,"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": 6305206873120.409, "dur": 43.667, + "args": { + "External id": 711073,"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": 6305206873168.288, "dur": 33.169, + "args": { + "External id": 711074,"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": 6305206873232.973, "dur": 254.731, + "args": { + "External id": 711075,"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": 6305206873316.649, "dur": 6.817, + "args": { + "External id": 711076,"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": 6305206873325.930, "dur": 5.891, + "args": { + "External id": 711077,"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": 6305206873332.957, "dur": 3.082, + "args": { + "External id": 711078,"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": 6305206873337.176, "dur": 1.910, + "args": { + "External id": 711079,"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": 6305206873382.236, "dur": 5.061, + "args": { + "External id": 711080,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206873384.506, "dur": 2.636, + "args": { + "External id": 711081,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206873391.617, "dur": 34.493, + "args": { + "External id": 711082,"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": 6305206873399.118, "dur": 3.166, + "args": { + "External id": 711083,"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": 6305206873427.568, "dur": 1.819, + "args": { + "External id": 711084,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206873428.670, "dur": 0.605, + "args": { + "External id": 711085,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206873430.556, "dur": 15.734, + "args": { + "External id": 711086,"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": 6305206873434.617, "dur": 0.398, + "args": { + "External id": 711087,"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": 6305206873541.892, "dur": 27.269, + "args": { + "External id": 711088,"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": 6305206873589.806, "dur": 16.506, + "args": { + "External id": 711089,"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": 6305206873614.138, "dur": 44.451, + "args": { + "External id": 711090,"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": 6305206873664.843, "dur": 38.953, + "args": { + "External id": 711091,"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": 6305206873714.004, "dur": 20.587, + "args": { + "External id": 711092,"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": 6305206873739.976, "dur": 30.439, + "args": { + "External id": 711093,"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": 6305206873777.369, "dur": 26.862, + "args": { + "External id": 711094,"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": 6305206873810.478, "dur": 29.133, + "args": { + "External id": 711095,"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": 6305206873873.865, "dur": 30.133, + "args": { + "External id": 711096,"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": 6305206873924.205, "dur": 21.034, + "args": { + "External id": 711097,"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": 6305206873962.993, "dur": 15.952, + "args": { + "External id": 711098,"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": 6305206874000.051, "dur": 13.845, + "args": { + "External id": 711099,"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": 6305206874031.125, "dur": 19.191, + "args": { + "External id": 711100,"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": 6305206874163.179, "dur": 15.293, + "args": { + "External id": 711101,"Record function id": 0, "Ev Idx": 5052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206874166.470, "dur": 10.989, + "args": { + "External id": 711102,"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": 6305206874170.916, "dur": 5.644, + "args": { + "External id": 711103,"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": 6305206874172.457, "dur": 4.012, + "args": { + "External id": 711104,"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": 6305206874182.386, "dur": 4.666, + "args": { + "External id": 711105,"Record function id": 0, "Ev Idx": 5056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206874183.932, "dur": 2.634, + "args": { + "External id": 711106,"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": 6305206874184.614, "dur": 1.418, + "args": { + "External id": 711107,"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": 6305206874185.095, "dur": 0.850, + "args": { + "External id": 711108,"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": 6305206874190.490, "dur": 6.869, + "args": { + "External id": 711109,"Record function id": 0, "Ev Idx": 5060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206874191.770, "dur": 5.090, + "args": { + "External id": 711110,"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": 6305206874192.499, "dur": 3.919, + "args": { + "External id": 711111,"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": 6305206874193.215, "dur": 3.104, + "args": { + "External id": 711112,"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": 6305206874200.726, "dur": 4.945, + "args": { + "External id": 711113,"Record function id": 0, "Ev Idx": 5064 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206874202.210, "dur": 3.027, + "args": { + "External id": 711114,"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": 6305206874202.846, "dur": 1.961, + "args": { + "External id": 711115,"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": 6305206874203.641, "dur": 1.056, + "args": { + "External id": 711116,"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": 6305206874208.777, "dur": 4.044, + "args": { + "External id": 711117,"Record function id": 0, "Ev Idx": 5068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206874210.291, "dur": 2.080, + "args": { + "External id": 711118,"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": 6305206874210.902, "dur": 0.991, + "args": { + "External id": 711119,"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": 6305206874211.166, "dur": 0.663, + "args": { + "External id": 711120,"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": 6305206874215.889, "dur": 4.535, + "args": { + "External id": 711121,"Record function id": 0, "Ev Idx": 5072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206874217.322, "dur": 2.661, + "args": { + "External id": 711122,"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": 6305206874217.859, "dur": 1.684, + "args": { + "External id": 711123,"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": 6305206874218.665, "dur": 0.814, + "args": { + "External id": 711124,"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": 6305206874223.806, "dur": 3.584, + "args": { + "External id": 711125,"Record function id": 0, "Ev Idx": 5076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206874225.075, "dur": 1.873, + "args": { + "External id": 711126,"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": 6305206874225.541, "dur": 0.965, + "args": { + "External id": 711127,"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": 6305206874225.805, "dur": 0.639, + "args": { + "External id": 711128,"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": 6305206874230.482, "dur": 4.200, + "args": { + "External id": 711129,"Record function id": 0, "Ev Idx": 5080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206874231.692, "dur": 2.456, + "args": { + "External id": 711130,"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": 6305206874232.427, "dur": 1.299, + "args": { + "External id": 711131,"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": 6305206874232.830, "dur": 0.828, + "args": { + "External id": 711132,"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": 6305206874238.072, "dur": 5.787, + "args": { + "External id": 711133,"Record function id": 0, "Ev Idx": 5084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206874239.317, "dur": 4.106, + "args": { + "External id": 711134,"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": 6305206874239.887, "dur": 3.097, + "args": { + "External id": 711135,"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": 6305206874242.307, "dur": 0.611, + "args": { + "External id": 711136,"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": 6305206874248.446, "dur": 71930.864, + "args": { + "External id": 711137,"Record function id": 0, "Sequence number": 7674399, "Fwd thread id": 1, "Ev Idx": 5088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305206874250.348, "dur": 71918.741, + "args": { + "External id": 711138,"Sequence number": 7674399, "Fwd thread 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": 6305206874250.348, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.4)", "pid": 2338707, "tid": 2379456, + "ts": 6305206874280.269, "dur": 39.725, + "args": { + "External id": 711139,"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": 6305206874327.969, "dur": 63.049, + "args": { + "External id": 711140,"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": 6305206874397.702, "dur": 71762.361, + "args": { + "External id": 711141,"Record function id": 0, "Ev Idx": 5092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305206874486.607, "dur": 7.380, + "args": { + "External id": 711142,"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": 6305206874522.229, "dur": 7.470, + "args": { + "External id": 711143,"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": 6305206874545.944, "dur": 70692.283, + "args": { + "External id": 711144,"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": 6305206874560.540, "dur": 70664.328, + "args": { + "External id": 711145,"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": 6305206874657.482, "dur": 19.371, + "args": { + "External id": 711146,"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": 6305206874697.004, "dur": 70473.024, + "args": { + "External id": 711147,"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": 6305206874700.169, "dur": 70468.600, + "args": { + "External id": 711148,"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": 6305206874704.974, "dur": 13.386, + "args": { + "External id": 711149,"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": 6305206874720.269, "dur": 70442.823, + "args": { + "External id": 711150,"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": 6305206945350.778, "dur": 12.878, + "args": { + "External id": 711151,"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": 6305206945354.287, "dur": 8.912, + "args": { + "External id": 711152,"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": 6305206945394.994, "dur": 411.948, + "args": { + "External id": 711153,"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": 6305206945429.113, "dur": 372.277, + "args": { + "External id": 711154,"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": 6305206945442.660, "dur": 352.611, + "args": { + "External id": 711155,"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": 6305206945831.718, "dur": 2.303, + "args": { + "External id": 711156,"Record function id": 0, "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": 6305206945896.392, "dur": 7.038, + "args": { + "External id": 711157,"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": 6305206945948.699, "dur": 1.405, + "args": { + "External id": 711158,"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": 6305206945965.977, "dur": 3.313, + "args": { + "External id": 711159,"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": 6305206945981.672, "dur": 0.900, + "args": { + "External id": 711160,"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": 6305206945994.153, "dur": 1.091, + "args": { + "External id": 711161,"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": 6305206946006.030, "dur": 0.759, + "args": { + "External id": 711162,"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": 6305206946019.150, "dur": 3.696, + "args": { + "External id": 711163,"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": 6305206946033.453, "dur": 2.273, + "args": { + "External id": 711164,"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": 6305206946045.146, "dur": 0.944, + "args": { + "External id": 711165,"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": 6305206946196.567, "dur": 3056.929, + "args": { + "External id": 711166,"Record function id": 0, "Ev Idx": 5117 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.3)", "pid": 2338707, "tid": 2379456, + "ts": 6305206946218.056, "dur": 1164.941, + "args": { + "External id": 711167,"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": 6305206946234.411, "dur": 401.489, + "args": { + "External id": 711168,"Record function id": 0, "Ev Idx": 5119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6305206946354.251, "dur": 4.899, + "args": { + "External id": 711169,"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": 6305206946363.041, "dur": 0.902, + "args": { + "External id": 711170,"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": 6305206946365.859, "dur": 3.011, + "args": { + "External id": 711171,"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": 6305206946372.618, "dur": 0.530, + "args": { + "External id": 711172,"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": 6305206946374.754, "dur": 0.527, + "args": { + "External id": 711173,"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": 6305206946376.893, "dur": 0.695, + "args": { + "External id": 711174,"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": 6305206946379.267, "dur": 1.620, + "args": { + "External id": 711175,"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": 6305206946383.925, "dur": 0.559, + "args": { + "External id": 711176,"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": 6305206946385.830, "dur": 0.775, + "args": { + "External id": 711177,"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": 6305206946387.995, "dur": 0.481, + "args": { + "External id": 711178,"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": 6305206946406.504, "dur": 192.505, + "args": { + "External id": 711179,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305206946423.074, "dur": 170.422, + "args": { + "External id": 711180,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305206946452.421, "dur": 15.774, + "args": { + "External id": 711181,"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": 6305206946472.155, "dur": 86.766, + "args": { + "External id": 711182,"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": 6305206946474.517, "dur": 83.984, + "args": { + "External id": 711183,"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": 6305206946478.902, "dur": 5.804, + "args": { + "External id": 711184,"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": 6305206946486.330, "dur": 71.044, + "args": { + "External id": 711185,"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": 6305206946726.006, "dur": 648.546, + "args": { + "External id": 711186,"Record function id": 0, "Ev Idx": 5137 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.2)", "pid": 2338707, "tid": 2379456, + "ts": 6305206946743.271, "dur": 618.983, + "args": { + "External id": 711187,"Record function id": 0, "Ev Idx": 5138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305206946804.722, "dur": 5.787, + "args": { + "External id": 711188,"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": 6305206946825.944, "dur": 34.307, + "args": { + "External id": 711189,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206946831.231, "dur": 1.733, + "args": { + "External id": 711190,"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": 6305206946835.441, "dur": 1.554, + "args": { + "External id": 711191,"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": 6305206946838.650, "dur": 0.302, + "args": { + "External id": 711192,"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": 6305206946841.005, "dur": 0.405, + "args": { + "External id": 711193,"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": 6305206946844.650, "dur": 0.294, + "args": { + "External id": 711194,"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": 6305206946846.882, "dur": 2.749, + "args": { + "External id": 711195,"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": 6305206946851.266, "dur": 0.394, + "args": { + "External id": 711196,"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": 6305206946853.882, "dur": 0.254, + "args": { + "External id": 711197,"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": 6305206946855.362, "dur": 0.230, + "args": { + "External id": 711198,"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": 6305206946869.662, "dur": 41.712, + "args": { + "External id": 711199,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305206946941.933, "dur": 167.745, + "args": { + "External id": 711200,"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": 6305206946952.195, "dur": 3.503, + "args": { + "External id": 711201,"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": 6305206946960.910, "dur": 10.246, + "args": { + "External id": 711202,"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": 6305206946965.118, "dur": 5.655, + "args": { + "External id": 711203,"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": 6305206946969.000, "dur": 0.521, + "args": { + "External id": 711204,"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": 6305206946977.865, "dur": 26.925, + "args": { + "External id": 711205,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206946980.262, "dur": 0.432, + "args": { + "External id": 711206,"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": 6305206946983.442, "dur": 0.287, + "args": { + "External id": 711207,"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": 6305206946985.201, "dur": 2.483, + "args": { + "External id": 711208,"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": 6305206946988.964, "dur": 1.499, + "args": { + "External id": 711209,"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": 6305206946991.886, "dur": 0.256, + "args": { + "External id": 711210,"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": 6305206946993.453, "dur": 0.356, + "args": { + "External id": 711211,"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": 6305206946996.681, "dur": 0.635, + "args": { + "External id": 711212,"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": 6305206946998.942, "dur": 0.440, + "args": { + "External id": 711213,"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": 6305206947000.547, "dur": 0.589, + "args": { + "External id": 711214,"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": 6305206947019.334, "dur": 32.175, + "args": { + "External id": 711215,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305206947159.423, "dur": 129.517, + "args": { + "External id": 711216,"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": 6305206947193.496, "dur": 91.966, + "args": { + "External id": 711217,"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": 6305206947204.614, "dur": 76.649, + "args": { + "External id": 711218,"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": 6305206947306.402, "dur": 1.954, + "args": { + "External id": 711219,"Record function id": 0, "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": 6305206947391.104, "dur": 1841.432, + "args": { + "External id": 711220,"Sequence number": 7674398, "Fwd thread 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": 6305206947391.104, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6305206947504.208, "dur": 125.863, + "args": { + "External id": 711221,"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": 6305206947678.227, "dur": 39.227, + "args": { + "External id": 711222,"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": 6305206947735.349, "dur": 49.761, + "args": { + "External id": 711223,"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": 6305206947797.960, "dur": 30.992, + "args": { + "External id": 711224,"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": 6305206947835.078, "dur": 32.507, + "args": { + "External id": 711225,"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": 6305206947874.239, "dur": 27.663, + "args": { + "External id": 711226,"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": 6305206947909.365, "dur": 29.374, + "args": { + "External id": 711227,"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": 6305206947964.814, "dur": 24.939, + "args": { + "External id": 711228,"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": 6305206948009.338, "dur": 28.978, + "args": { + "External id": 711229,"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": 6305206948115.340, "dur": 23.195, + "args": { + "External id": 711230,"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": 6305206948154.886, "dur": 16.452, + "args": { + "External id": 711231,"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": 6305206948187.406, "dur": 44.763, + "args": { + "External id": 711232,"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": 6305206948235.861, "dur": 33.279, + "args": { + "External id": 711233,"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": 6305206948301.182, "dur": 273.446, + "args": { + "External id": 711234,"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": 6305206948382.929, "dur": 6.452, + "args": { + "External id": 711235,"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": 6305206948391.820, "dur": 2.374, + "args": { + "External id": 711236,"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": 6305206948395.631, "dur": 2.418, + "args": { + "External id": 711237,"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": 6305206948399.178, "dur": 2.332, + "args": { + "External id": 711238,"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": 6305206948447.716, "dur": 5.081, + "args": { + "External id": 711239,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206948449.853, "dur": 2.774, + "args": { + "External id": 711240,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206948454.704, "dur": 35.896, + "args": { + "External id": 711241,"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": 6305206948460.500, "dur": 4.760, + "args": { + "External id": 711242,"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": 6305206948492.334, "dur": 3.806, + "args": { + "External id": 711243,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206948495.461, "dur": 0.526, + "args": { + "External id": 711244,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305206948497.394, "dur": 33.171, + "args": { + "External id": 711245,"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": 6305206948501.347, "dur": 0.438, + "args": { + "External id": 711246,"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": 6305206948617.196, "dur": 31.819, + "args": { + "External id": 711247,"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": 6305206948667.309, "dur": 17.613, + "args": { + "External id": 711248,"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": 6305206948693.438, "dur": 45.959, + "args": { + "External id": 711249,"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": 6305206948745.809, "dur": 38.858, + "args": { + "External id": 711250,"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": 6305206948795.380, "dur": 21.919, + "args": { + "External id": 711251,"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": 6305206948822.337, "dur": 31.241, + "args": { + "External id": 711252,"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": 6305206948860.346, "dur": 27.383, + "args": { + "External id": 711253,"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": 6305206948894.047, "dur": 50.642, + "args": { + "External id": 711254,"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": 6305206948976.556, "dur": 27.422, + "args": { + "External id": 711255,"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": 6305206949023.907, "dur": 24.234, + "args": { + "External id": 711256,"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": 6305206949105.291, "dur": 23.669, + "args": { + "External id": 711257,"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": 6305206949150.042, "dur": 15.898, + "args": { + "External id": 711258,"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": 6305206949185.525, "dur": 17.353, + "args": { + "External id": 711259,"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": 6305206949276.276, "dur": 15.129, + "args": { + "External id": 711260,"Record function id": 0, "Ev Idx": 5211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206949279.787, "dur": 10.522, + "args": { + "External id": 711261,"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": 6305206949283.758, "dur": 5.663, + "args": { + "External id": 711262,"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": 6305206949285.207, "dur": 4.129, + "args": { + "External id": 711263,"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": 6305206949295.212, "dur": 4.512, + "args": { + "External id": 711264,"Record function id": 0, "Ev Idx": 5215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206949296.562, "dur": 2.709, + "args": { + "External id": 711265,"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": 6305206949297.276, "dur": 1.507, + "args": { + "External id": 711266,"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": 6305206949297.643, "dur": 1.019, + "args": { + "External id": 711267,"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": 6305206949303.247, "dur": 4.071, + "args": { + "External id": 711268,"Record function id": 0, "Ev Idx": 5219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206949304.616, "dur": 2.278, + "args": { + "External id": 711269,"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": 6305206949305.136, "dur": 1.278, + "args": { + "External id": 711270,"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": 6305206949305.734, "dur": 0.591, + "args": { + "External id": 711271,"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": 6305206949310.590, "dur": 6.083, + "args": { + "External id": 711272,"Record function id": 0, "Ev Idx": 5223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206949311.850, "dur": 4.424, + "args": { + "External id": 711273,"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": 6305206949312.497, "dur": 3.368, + "args": { + "External id": 711274,"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": 6305206949312.906, "dur": 2.891, + "args": { + "External id": 711275,"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": 6305206949319.800, "dur": 3.986, + "args": { + "External id": 711276,"Record function id": 0, "Ev Idx": 5227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206949321.128, "dur": 2.270, + "args": { + "External id": 711277,"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": 6305206949321.677, "dur": 1.286, + "args": { + "External id": 711278,"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": 6305206949322.170, "dur": 0.720, + "args": { + "External id": 711279,"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": 6305206949326.915, "dur": 3.928, + "args": { + "External id": 711280,"Record function id": 0, "Ev Idx": 5231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206949328.041, "dur": 2.396, + "args": { + "External id": 711281,"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": 6305206949328.536, "dur": 1.481, + "args": { + "External id": 711282,"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": 6305206949329.374, "dur": 0.578, + "args": { + "External id": 711283,"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": 6305206949334.033, "dur": 3.857, + "args": { + "External id": 711284,"Record function id": 0, "Ev Idx": 5235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206949335.465, "dur": 2.019, + "args": { + "External id": 711285,"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": 6305206949335.946, "dur": 1.137, + "args": { + "External id": 711286,"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": 6305206949336.394, "dur": 0.626, + "args": { + "External id": 711287,"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": 6305206949340.950, "dur": 4.520, + "args": { + "External id": 711288,"Record function id": 0, "Ev Idx": 5239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206949342.214, "dur": 2.865, + "args": { + "External id": 711289,"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": 6305206949342.918, "dur": 1.725, + "args": { + "External id": 711290,"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": 6305206949343.609, "dur": 0.962, + "args": { + "External id": 711291,"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": 6305206949348.823, "dur": 5.895, + "args": { + "External id": 711292,"Record function id": 0, "Ev Idx": 5243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305206949349.950, "dur": 4.372, + "args": { + "External id": 711293,"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": 6305206949350.418, "dur": 3.472, + "args": { + "External id": 711294,"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": 6305206949353.134, "dur": 0.683, + "args": { + "External id": 711295,"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": 6305206949359.572, "dur": 66641.157, + "args": { + "External id": 711296,"Record function id": 0, "Sequence number": 7674397, "Fwd thread id": 1, "Ev Idx": 5247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305206949361.737, "dur": 66629.938, + "args": { + "External id": 711297,"Sequence number": 7674397, "Fwd thread 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": 6305206949361.737, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.3)", "pid": 2338707, "tid": 2379456, + "ts": 6305206949392.571, "dur": 42.652, + "args": { + "External id": 711298,"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": 6305206949443.143, "dur": 78.611, + "args": { + "External id": 711299,"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": 6305206949531.251, "dur": 66452.899, + "args": { + "External id": 711300,"Record function id": 0, "Ev Idx": 5251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305206949625.637, "dur": 7.200, + "args": { + "External id": 711301,"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": 6305206949645.798, "dur": 4.967, + "args": { + "External id": 711302,"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": 6305206949665.454, "dur": 65458.915, + "args": { + "External id": 711303,"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": 6305206949679.135, "dur": 65431.562, + "args": { + "External id": 711304,"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": 6305206949770.820, "dur": 20.219, + "args": { + "External id": 711305,"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": 6305206949811.805, "dur": 65227.893, + "args": { + "External id": 711306,"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": 6305206949814.643, "dur": 65223.870, + "args": { + "External id": 711307,"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": 6305206949819.078, "dur": 11.964, + "args": { + "External id": 711308,"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": 6305206949833.262, "dur": 65200.113, + "args": { + "External id": 711309,"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": 6305207015231.377, "dur": 12.014, + "args": { + "External id": 711310,"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": 6305207015234.694, "dur": 8.251, + "args": { + "External id": 711311,"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": 6305207015274.128, "dur": 405.396, + "args": { + "External id": 711312,"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": 6305207015309.133, "dur": 364.718, + "args": { + "External id": 711313,"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": 6305207015322.046, "dur": 345.929, + "args": { + "External id": 711314,"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": 6305207015709.209, "dur": 2.386, + "args": { + "External id": 711315,"Record function id": 0, "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": 6305207015776.197, "dur": 7.172, + "args": { + "External id": 711316,"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": 6305207015828.110, "dur": 1.239, + "args": { + "External id": 711317,"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": 6305207015844.286, "dur": 1.226, + "args": { + "External id": 711318,"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": 6305207015860.319, "dur": 0.779, + "args": { + "External id": 711319,"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": 6305207015873.202, "dur": 0.914, + "args": { + "External id": 711320,"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": 6305207015884.522, "dur": 0.699, + "args": { + "External id": 711321,"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": 6305207015895.326, "dur": 0.988, + "args": { + "External id": 711322,"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": 6305207015908.306, "dur": 2.325, + "args": { + "External id": 711323,"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": 6305207015922.230, "dur": 0.639, + "args": { + "External id": 711324,"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": 6305207016015.824, "dur": 3074.906, + "args": { + "External id": 711325,"Record function id": 0, "Ev Idx": 5276 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.2)", "pid": 2338707, "tid": 2379456, + "ts": 6305207016036.126, "dur": 1180.618, + "args": { + "External id": 711326,"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": 6305207016051.835, "dur": 393.415, + "args": { + "External id": 711327,"Record function id": 0, "Ev Idx": 5278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6305207016183.846, "dur": 5.066, + "args": { + "External id": 711328,"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": 6305207016192.753, "dur": 1.022, + "args": { + "External id": 711329,"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": 6305207016195.714, "dur": 0.898, + "args": { + "External id": 711330,"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": 6305207016198.447, "dur": 2.915, + "args": { + "External id": 711331,"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": 6305207016202.715, "dur": 0.889, + "args": { + "External id": 711332,"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": 6305207016205.031, "dur": 0.798, + "args": { + "External id": 711333,"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": 6305207016209.567, "dur": 1.882, + "args": { + "External id": 711334,"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": 6305207016213.073, "dur": 0.684, + "args": { + "External id": 711335,"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": 6305207016215.435, "dur": 0.838, + "args": { + "External id": 711336,"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": 6305207016217.762, "dur": 0.893, + "args": { + "External id": 711337,"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": 6305207016241.138, "dur": 171.283, + "args": { + "External id": 711338,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305207016258.113, "dur": 149.502, + "args": { + "External id": 711339,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305207016287.457, "dur": 16.055, + "args": { + "External id": 711340,"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": 6305207016307.295, "dur": 69.260, + "args": { + "External id": 711341,"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": 6305207016310.125, "dur": 66.095, + "args": { + "External id": 711342,"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": 6305207016314.067, "dur": 7.928, + "args": { + "External id": 711343,"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": 6305207016324.019, "dur": 51.428, + "args": { + "External id": 711344,"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": 6305207016546.284, "dur": 662.319, + "args": { + "External id": 711345,"Record function id": 0, "Ev Idx": 5296 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.1)", "pid": 2338707, "tid": 2379456, + "ts": 6305207016564.940, "dur": 630.081, + "args": { + "External id": 711346,"Record function id": 0, "Ev Idx": 5297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305207016627.271, "dur": 6.182, + "args": { + "External id": 711347,"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": 6305207016649.105, "dur": 40.069, + "args": { + "External id": 711348,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305207016654.988, "dur": 3.041, + "args": { + "External id": 711349,"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": 6305207016665.093, "dur": 0.394, + "args": { + "External id": 711350,"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": 6305207016667.493, "dur": 0.188, + "args": { + "External id": 711351,"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": 6305207016670.153, "dur": 0.297, + "args": { + "External id": 711352,"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": 6305207016672.028, "dur": 0.357, + "args": { + "External id": 711353,"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": 6305207016673.741, "dur": 2.021, + "args": { + "External id": 711354,"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": 6305207016677.415, "dur": 2.568, + "args": { + "External id": 711355,"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": 6305207016681.271, "dur": 0.435, + "args": { + "External id": 711356,"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": 6305207016684.351, "dur": 0.471, + "args": { + "External id": 711357,"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": 6305207016699.839, "dur": 44.664, + "args": { + "External id": 711358,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305207016774.123, "dur": 116.333, + "args": { + "External id": 711359,"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": 6305207016784.471, "dur": 3.299, + "args": { + "External id": 711360,"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": 6305207016792.880, "dur": 10.703, + "args": { + "External id": 711361,"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": 6305207016797.162, "dur": 6.003, + "args": { + "External id": 711362,"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": 6305207016801.224, "dur": 0.683, + "args": { + "External id": 711363,"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": 6305207016810.700, "dur": 26.961, + "args": { + "External id": 711364,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305207016813.400, "dur": 0.318, + "args": { + "External id": 711365,"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": 6305207016815.579, "dur": 0.350, + "args": { + "External id": 711366,"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": 6305207016819.191, "dur": 0.372, + "args": { + "External id": 711367,"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": 6305207016821.252, "dur": 2.583, + "args": { + "External id": 711368,"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": 6305207016825.126, "dur": 0.314, + "args": { + "External id": 711369,"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": 6305207016827.705, "dur": 0.264, + "args": { + "External id": 711370,"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": 6305207016829.427, "dur": 0.287, + "args": { + "External id": 711371,"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": 6305207016831.099, "dur": 1.097, + "args": { + "External id": 711372,"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": 6305207016833.836, "dur": 0.388, + "args": { + "External id": 711373,"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": 6305207016852.617, "dur": 30.272, + "args": { + "External id": 711374,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305207016934.146, "dur": 176.465, + "args": { + "External id": 711375,"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": 6305207016964.918, "dur": 140.927, + "args": { + "External id": 711376,"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": 6305207016974.185, "dur": 75.183, + "args": { + "External id": 711377,"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": 6305207017130.708, "dur": 2.668, + "args": { + "External id": 711378,"Record function id": 0, "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": 6305207017224.765, "dur": 1810.231, + "args": { + "External id": 711379,"Sequence number": 7674396, "Fwd thread 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": 6305207017224.765, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6305207017339.350, "dur": 114.764, + "args": { + "External id": 711380,"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": 6305207017501.563, "dur": 65.128, + "args": { + "External id": 711381,"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": 6305207017587.515, "dur": 58.601, + "args": { + "External id": 711382,"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": 6305207017656.498, "dur": 32.545, + "args": { + "External id": 711383,"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": 6305207017697.007, "dur": 33.606, + "args": { + "External id": 711384,"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": 6305207017737.321, "dur": 28.124, + "args": { + "External id": 711385,"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": 6305207017772.987, "dur": 30.274, + "args": { + "External id": 711386,"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": 6305207017830.747, "dur": 26.076, + "args": { + "External id": 711387,"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": 6305207017880.227, "dur": 28.496, + "args": { + "External id": 711388,"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": 6305207017930.596, "dur": 20.018, + "args": { + "External id": 711389,"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": 6305207017965.558, "dur": 15.234, + "args": { + "External id": 711390,"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": 6305207017989.025, "dur": 37.361, + "args": { + "External id": 711391,"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": 6305207018030.168, "dur": 70.858, + "args": { + "External id": 711392,"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": 6305207018145.286, "dur": 263.573, + "args": { + "External id": 711393,"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": 6305207018226.909, "dur": 10.275, + "args": { + "External id": 711394,"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": 6305207018239.447, "dur": 3.886, + "args": { + "External id": 711395,"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": 6305207018244.866, "dur": 2.539, + "args": { + "External id": 711396,"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": 6305207018248.659, "dur": 2.475, + "args": { + "External id": 711397,"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": 6305207018296.847, "dur": 4.647, + "args": { + "External id": 711398,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305207018298.699, "dur": 2.608, + "args": { + "External id": 711399,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305207018303.423, "dur": 34.064, + "args": { + "External id": 711400,"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": 6305207018309.661, "dur": 1.820, + "args": { + "External id": 711401,"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": 6305207018338.979, "dur": 4.164, + "args": { + "External id": 711402,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305207018342.297, "dur": 0.764, + "args": { + "External id": 711403,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305207018344.199, "dur": 22.047, + "args": { + "External id": 711404,"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": 6305207018348.841, "dur": 4.188, + "args": { + "External id": 711405,"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": 6305207018450.258, "dur": 28.414, + "args": { + "External id": 711406,"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": 6305207018497.150, "dur": 33.029, + "args": { + "External id": 711407,"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": 6305207018541.179, "dur": 51.195, + "args": { + "External id": 711408,"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": 6305207018600.034, "dur": 41.181, + "args": { + "External id": 711409,"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": 6305207018652.164, "dur": 19.917, + "args": { + "External id": 711410,"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": 6305207018678.063, "dur": 32.714, + "args": { + "External id": 711411,"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": 6305207018718.195, "dur": 27.434, + "args": { + "External id": 711412,"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": 6305207018754.686, "dur": 49.760, + "args": { + "External id": 711413,"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": 6305207018835.405, "dur": 25.138, + "args": { + "External id": 711414,"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": 6305207018881.530, "dur": 22.338, + "args": { + "External id": 711415,"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": 6305207018919.824, "dur": 16.969, + "args": { + "External id": 711416,"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": 6305207018956.923, "dur": 13.860, + "args": { + "External id": 711417,"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": 6305207018985.652, "dur": 15.830, + "args": { + "External id": 711418,"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": 6305207019115.128, "dur": 16.058, + "args": { + "External id": 711419,"Record function id": 0, "Ev Idx": 5370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305207019118.791, "dur": 11.333, + "args": { + "External id": 711420,"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": 6305207019123.323, "dur": 5.565, + "args": { + "External id": 711421,"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": 6305207019124.739, "dur": 3.996, + "args": { + "External id": 711422,"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": 6305207019135.413, "dur": 4.909, + "args": { + "External id": 711423,"Record function id": 0, "Ev Idx": 5374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305207019136.937, "dur": 2.902, + "args": { + "External id": 711424,"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": 6305207019137.851, "dur": 1.476, + "args": { + "External id": 711425,"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": 6305207019138.330, "dur": 0.898, + "args": { + "External id": 711426,"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": 6305207019143.811, "dur": 4.305, + "args": { + "External id": 711427,"Record function id": 0, "Ev Idx": 5378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305207019145.230, "dur": 2.453, + "args": { + "External id": 711428,"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": 6305207019145.786, "dur": 1.437, + "args": { + "External id": 711429,"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": 6305207019146.470, "dur": 0.673, + "args": { + "External id": 711430,"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": 6305207019151.379, "dur": 5.802, + "args": { + "External id": 711431,"Record function id": 0, "Ev Idx": 5382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305207019152.635, "dur": 4.115, + "args": { + "External id": 711432,"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": 6305207019153.159, "dur": 3.140, + "args": { + "External id": 711433,"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": 6305207019153.461, "dur": 2.769, + "args": { + "External id": 711434,"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": 6305207019160.270, "dur": 4.222, + "args": { + "External id": 711435,"Record function id": 0, "Ev Idx": 5386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305207019161.628, "dur": 2.439, + "args": { + "External id": 711436,"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": 6305207019162.333, "dur": 1.112, + "args": { + "External id": 711437,"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": 6305207019162.607, "dur": 0.767, + "args": { + "External id": 711438,"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": 6305207019167.691, "dur": 5.767, + "args": { + "External id": 711439,"Record function id": 0, "Ev Idx": 5390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305207019168.977, "dur": 4.083, + "args": { + "External id": 711440,"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": 6305207019169.425, "dur": 3.174, + "args": { + "External id": 711441,"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": 6305207019171.837, "dur": 0.688, + "args": { + "External id": 711442,"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": 6305207019176.749, "dur": 4.709, + "args": { + "External id": 711443,"Record function id": 0, "Ev Idx": 5394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305207019178.068, "dur": 2.868, + "args": { + "External id": 711444,"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": 6305207019178.930, "dur": 1.494, + "args": { + "External id": 711445,"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": 6305207019179.629, "dur": 0.735, + "args": { + "External id": 711446,"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": 6305207019184.728, "dur": 3.891, + "args": { + "External id": 711447,"Record function id": 0, "Ev Idx": 5398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305207019185.882, "dur": 2.317, + "args": { + "External id": 711448,"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": 6305207019186.668, "dur": 1.100, + "args": { + "External id": 711449,"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": 6305207019187.133, "dur": 0.561, + "args": { + "External id": 711450,"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": 6305207019191.670, "dur": 3.965, + "args": { + "External id": 711451,"Record function id": 0, "Ev Idx": 5402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305207019193.066, "dur": 2.124, + "args": { + "External id": 711452,"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": 6305207019193.550, "dur": 1.187, + "args": { + "External id": 711453,"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": 6305207019194.084, "dur": 0.587, + "args": { + "External id": 711454,"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": 6305207019200.639, "dur": 64295.908, + "args": { + "External id": 711455,"Record function id": 0, "Sequence number": 7674395, "Fwd thread id": 1, "Ev Idx": 5406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305207019202.407, "dur": 64285.532, + "args": { + "External id": 711456,"Sequence number": 7674395, "Fwd thread 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": 6305207019202.407, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.2)", "pid": 2338707, "tid": 2379456, + "ts": 6305207019236.028, "dur": 41.667, + "args": { + "External id": 711457,"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": 6305207019286.555, "dur": 64.391, + "args": { + "External id": 711458,"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": 6305207019357.051, "dur": 64123.293, + "args": { + "External id": 711459,"Record function id": 0, "Ev Idx": 5410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305207019449.615, "dur": 7.561, + "args": { + "External id": 711460,"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": 6305207019467.474, "dur": 4.938, + "args": { + "External id": 711461,"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": 6305207019486.849, "dur": 63055.037, + "args": { + "External id": 711462,"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": 6305207019503.091, "dur": 63024.640, + "args": { + "External id": 711463,"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": 6305207019610.708, "dur": 21.511, + "args": { + "External id": 711464,"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": 6305207019653.050, "dur": 62818.076, + "args": { + "External id": 711465,"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": 6305207019657.423, "dur": 62812.726, + "args": { + "External id": 711466,"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": 6305207019662.019, "dur": 11.273, + "args": { + "External id": 711467,"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": 6305207019675.125, "dur": 62789.678, + "args": { + "External id": 711468,"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": 6305207082647.803, "dur": 15.164, + "args": { + "External id": 711469,"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": 6305207082651.447, "dur": 11.123, + "args": { + "External id": 711470,"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": 6305207082693.087, "dur": 480.312, + "args": { + "External id": 711471,"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": 6305207082731.614, "dur": 435.964, + "args": { + "External id": 711472,"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": 6305207082744.253, "dur": 416.758, + "args": { + "External id": 711473,"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": 6305207083202.100, "dur": 2.527, + "args": { + "External id": 711474,"Record function id": 0, "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": 6305207083271.315, "dur": 7.529, + "args": { + "External id": 711475,"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": 6305207083325.166, "dur": 1.253, + "args": { + "External id": 711476,"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": 6305207083341.793, "dur": 1.306, + "args": { + "External id": 711477,"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": 6305207083356.928, "dur": 1.107, + "args": { + "External id": 711478,"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": 6305207083369.239, "dur": 0.660, + "args": { + "External id": 711479,"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": 6305207083380.843, "dur": 0.694, + "args": { + "External id": 711480,"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": 6305207083392.284, "dur": 0.944, + "args": { + "External id": 711481,"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": 6305207083405.435, "dur": 2.011, + "args": { + "External id": 711482,"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": 6305207083419.382, "dur": 0.670, + "args": { + "External id": 711483,"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": 6305207083526.658, "dur": 3073.912, + "args": { + "External id": 711484,"Record function id": 0, "Ev Idx": 5435 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.1)", "pid": 2338707, "tid": 2379456, + "ts": 6305207083550.925, "dur": 1141.724, + "args": { + "External id": 711485,"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": 6305207083567.220, "dur": 369.094, + "args": { + "External id": 711486,"Record function id": 0, "Ev Idx": 5437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6305207083659.475, "dur": 5.105, + "args": { + "External id": 711487,"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": 6305207083668.287, "dur": 0.843, + "args": { + "External id": 711488,"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": 6305207083671.143, "dur": 1.046, + "args": { + "External id": 711489,"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": 6305207083674.157, "dur": 2.996, + "args": { + "External id": 711490,"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": 6305207083678.995, "dur": 0.723, + "args": { + "External id": 711491,"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": 6305207083683.646, "dur": 0.827, + "args": { + "External id": 711492,"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": 6305207083686.193, "dur": 1.898, + "args": { + "External id": 711493,"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": 6305207083689.693, "dur": 0.709, + "args": { + "External id": 711494,"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": 6305207083692.144, "dur": 0.656, + "args": { + "External id": 711495,"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": 6305207083696.086, "dur": 0.582, + "args": { + "External id": 711496,"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": 6305207083715.273, "dur": 188.189, + "args": { + "External id": 711497,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305207083741.168, "dur": 157.314, + "args": { + "External id": 711498,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305207083770.747, "dur": 16.766, + "args": { + "External id": 711499,"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": 6305207083791.166, "dur": 73.789, + "args": { + "External id": 711500,"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": 6305207083793.843, "dur": 70.696, + "args": { + "External id": 711501,"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": 6305207083798.184, "dur": 9.603, + "args": { + "External id": 711502,"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": 6305207083809.280, "dur": 54.612, + "args": { + "External id": 711503,"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": 6305207084021.585, "dur": 663.166, + "args": { + "External id": 711504,"Record function id": 0, "Ev Idx": 5455 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.0)", "pid": 2338707, "tid": 2379456, + "ts": 6305207084037.624, "dur": 634.269, + "args": { + "External id": 711505,"Record function id": 0, "Ev Idx": 5456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305207084145.175, "dur": 6.961, + "args": { + "External id": 711506,"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": 6305207084169.015, "dur": 33.989, + "args": { + "External id": 711507,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305207084174.704, "dur": 1.940, + "args": { + "External id": 711508,"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": 6305207084178.848, "dur": 1.387, + "args": { + "External id": 711509,"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": 6305207084182.048, "dur": 0.407, + "args": { + "External id": 711510,"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": 6305207084184.000, "dur": 0.324, + "args": { + "External id": 711511,"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": 6305207084187.014, "dur": 0.424, + "args": { + "External id": 711512,"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": 6305207084188.900, "dur": 0.440, + "args": { + "External id": 711513,"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": 6305207084190.524, "dur": 2.632, + "args": { + "External id": 711514,"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": 6305207084195.494, "dur": 0.503, + "args": { + "External id": 711515,"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": 6305207084197.728, "dur": 0.367, + "args": { + "External id": 711516,"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": 6305207084214.448, "dur": 50.003, + "args": { + "External id": 711517,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305207084296.096, "dur": 111.957, + "args": { + "External id": 711518,"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": 6305207084309.407, "dur": 2.756, + "args": { + "External id": 711519,"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": 6305207084317.082, "dur": 10.028, + "args": { + "External id": 711520,"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": 6305207084321.233, "dur": 5.471, + "args": { + "External id": 711521,"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": 6305207084324.869, "dur": 0.643, + "args": { + "External id": 711522,"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": 6305207084334.236, "dur": 25.938, + "args": { + "External id": 711523,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305207084336.509, "dur": 0.405, + "args": { + "External id": 711524,"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": 6305207084339.385, "dur": 0.285, + "args": { + "External id": 711525,"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": 6305207084341.468, "dur": 0.276, + "args": { + "External id": 711526,"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": 6305207084343.465, "dur": 3.910, + "args": { + "External id": 711527,"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": 6305207084349.064, "dur": 0.356, + "args": { + "External id": 711528,"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": 6305207084350.806, "dur": 0.296, + "args": { + "External id": 711529,"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": 6305207084353.577, "dur": 0.342, + "args": { + "External id": 711530,"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": 6305207084355.442, "dur": 0.256, + "args": { + "External id": 711531,"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": 6305207084356.524, "dur": 0.358, + "args": { + "External id": 711532,"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": 6305207084371.444, "dur": 28.795, + "args": { + "External id": 711533,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305207084452.769, "dur": 141.219, + "args": { + "External id": 711534,"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": 6305207084482.661, "dur": 107.138, + "args": { + "External id": 711535,"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": 6305207084491.877, "dur": 93.037, + "args": { + "External id": 711536,"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": 6305207084615.505, "dur": 1.865, + "args": { + "External id": 711537,"Record function id": 0, "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": 6305207084703.907, "dur": 1874.696, + "args": { + "External id": 711538,"Sequence number": 7674394, "Fwd thread 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": 6305207084703.907, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6305207084818.478, "dur": 109.930, + "args": { + "External id": 711539,"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": 6305207084973.384, "dur": 40.305, + "args": { + "External id": 711540,"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": 6305207085030.284, "dur": 96.976, + "args": { + "External id": 711541,"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": 6305207085142.143, "dur": 36.288, + "args": { + "External id": 711542,"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": 6305207085187.681, "dur": 33.372, + "args": { + "External id": 711543,"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": 6305207085227.718, "dur": 27.832, + "args": { + "External id": 711544,"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": 6305207085262.731, "dur": 29.181, + "args": { + "External id": 711545,"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": 6305207085319.623, "dur": 27.833, + "args": { + "External id": 711546,"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": 6305207085368.353, "dur": 28.931, + "args": { + "External id": 711547,"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": 6305207085425.292, "dur": 20.566, + "args": { + "External id": 711548,"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": 6305207085460.954, "dur": 19.867, + "args": { + "External id": 711549,"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": 6305207085488.284, "dur": 56.838, + "args": { + "External id": 711550,"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": 6305207085550.787, "dur": 35.766, + "args": { + "External id": 711551,"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": 6305207085632.969, "dur": 263.483, + "args": { + "External id": 711552,"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": 6305207085721.674, "dur": 7.080, + "args": { + "External id": 711553,"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": 6305207085731.034, "dur": 2.356, + "args": { + "External id": 711554,"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": 6305207085734.849, "dur": 2.427, + "args": { + "External id": 711555,"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": 6305207085738.748, "dur": 2.095, + "args": { + "External id": 711556,"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": 6305207085786.752, "dur": 6.275, + "args": { + "External id": 711557,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305207085789.156, "dur": 3.671, + "args": { + "External id": 711558,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305207085795.354, "dur": 32.740, + "args": { + "External id": 711559,"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": 6305207085800.932, "dur": 1.767, + "args": { + "External id": 711560,"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": 6305207085832.032, "dur": 1.775, + "args": { + "External id": 711561,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305207085833.085, "dur": 0.610, + "args": { + "External id": 711562,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305207085834.806, "dur": 19.655, + "args": { + "External id": 711563,"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": 6305207085837.965, "dur": 2.599, + "args": { + "External id": 711564,"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": 6305207085935.241, "dur": 28.808, + "args": { + "External id": 711565,"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": 6305207085981.614, "dur": 19.454, + "args": { + "External id": 711566,"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": 6305207086008.616, "dur": 92.807, + "args": { + "External id": 711567,"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": 6305207086112.178, "dur": 46.859, + "args": { + "External id": 711568,"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": 6305207086170.721, "dur": 21.408, + "args": { + "External id": 711569,"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": 6305207086197.949, "dur": 42.458, + "args": { + "External id": 711570,"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": 6305207086256.104, "dur": 37.317, + "args": { + "External id": 711571,"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": 6305207086300.235, "dur": 34.054, + "args": { + "External id": 711572,"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": 6305207086363.106, "dur": 25.091, + "args": { + "External id": 711573,"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": 6305207086406.829, "dur": 26.062, + "args": { + "External id": 711574,"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": 6305207086448.179, "dur": 17.546, + "args": { + "External id": 711575,"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": 6305207086481.276, "dur": 14.501, + "args": { + "External id": 711576,"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": 6305207086527.796, "dur": 18.253, + "args": { + "External id": 711577,"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": 6305207086623.668, "dur": 16.980, + "args": { + "External id": 711578,"Record function id": 0, "Ev Idx": 5529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305207086627.039, "dur": 12.584, + "args": { + "External id": 711579,"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": 6305207086631.149, "dur": 7.410, + "args": { + "External id": 711580,"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": 6305207086632.751, "dur": 5.674, + "args": { + "External id": 711581,"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": 6305207086644.790, "dur": 4.509, + "args": { + "External id": 711582,"Record function id": 0, "Ev Idx": 5533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305207086646.358, "dur": 2.466, + "args": { + "External id": 711583,"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": 6305207086646.979, "dur": 1.393, + "args": { + "External id": 711584,"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": 6305207086647.461, "dur": 0.789, + "args": { + "External id": 711585,"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": 6305207086652.701, "dur": 4.195, + "args": { + "External id": 711586,"Record function id": 0, "Ev Idx": 5537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305207086653.843, "dur": 2.633, + "args": { + "External id": 711587,"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": 6305207086654.408, "dur": 1.617, + "args": { + "External id": 711588,"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": 6305207086655.082, "dur": 0.866, + "args": { + "External id": 711589,"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": 6305207086660.176, "dur": 5.583, + "args": { + "External id": 711590,"Record function id": 0, "Ev Idx": 5541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305207086661.425, "dur": 3.912, + "args": { + "External id": 711591,"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": 6305207086661.919, "dur": 2.989, + "args": { + "External id": 711592,"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": 6305207086662.230, "dur": 2.608, + "args": { + "External id": 711593,"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": 6305207086668.896, "dur": 3.716, + "args": { + "External id": 711594,"Record function id": 0, "Ev Idx": 5545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305207086670.036, "dur": 2.147, + "args": { + "External id": 711595,"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": 6305207086670.515, "dur": 1.237, + "args": { + "External id": 711596,"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": 6305207086670.983, "dur": 0.705, + "args": { + "External id": 711597,"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": 6305207086675.737, "dur": 6.068, + "args": { + "External id": 711598,"Record function id": 0, "Ev Idx": 5549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305207086676.782, "dur": 4.608, + "args": { + "External id": 711599,"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": 6305207086677.297, "dur": 3.655, + "args": { + "External id": 711600,"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": 6305207086680.099, "dur": 0.778, + "args": { + "External id": 711601,"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": 6305207086685.184, "dur": 3.528, + "args": { + "External id": 711602,"Record function id": 0, "Ev Idx": 5553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305207086686.288, "dur": 2.024, + "args": { + "External id": 711603,"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": 6305207086686.789, "dur": 1.110, + "args": { + "External id": 711604,"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": 6305207086687.222, "dur": 0.610, + "args": { + "External id": 711605,"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": 6305207086691.920, "dur": 3.512, + "args": { + "External id": 711606,"Record function id": 0, "Ev Idx": 5557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305207086692.949, "dur": 2.087, + "args": { + "External id": 711607,"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": 6305207086693.452, "dur": 1.149, + "args": { + "External id": 711608,"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": 6305207086693.873, "dur": 0.665, + "args": { + "External id": 711609,"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": 6305207086698.856, "dur": 3.656, + "args": { + "External id": 711610,"Record function id": 0, "Ev Idx": 5561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305207086700.074, "dur": 2.026, + "args": { + "External id": 711611,"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": 6305207086700.507, "dur": 1.178, + "args": { + "External id": 711612,"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": 6305207086700.974, "dur": 0.648, + "args": { + "External id": 711613,"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": 6305207086707.056, "dur": 65774.000, + "args": { + "External id": 711614,"Record function id": 0, "Sequence number": 7674393, "Fwd thread id": 1, "Ev Idx": 5565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305207086708.761, "dur": 65763.053, + "args": { + "External id": 711615,"Sequence number": 7674393, "Fwd thread 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": 6305207086708.761, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.1)", "pid": 2338707, "tid": 2379456, + "ts": 6305207086739.388, "dur": 37.914, + "args": { + "External id": 711616,"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": 6305207086785.443, "dur": 66.482, + "args": { + "External id": 711617,"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": 6305207086858.788, "dur": 65604.912, + "args": { + "External id": 711618,"Record function id": 0, "Ev Idx": 5569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305207086949.403, "dur": 7.517, + "args": { + "External id": 711619,"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": 6305207086967.479, "dur": 4.706, + "args": { + "External id": 711620,"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": 6305207086986.276, "dur": 64675.527, + "args": { + "External id": 711621,"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": 6305207087000.199, "dur": 64648.090, + "args": { + "External id": 711622,"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": 6305207087140.028, "dur": 23.429, + "args": { + "External id": 711623,"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": 6305207087186.645, "dur": 64416.270, + "args": { + "External id": 711624,"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": 6305207087192.775, "dur": 64409.076, + "args": { + "External id": 711625,"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": 6305207087197.273, "dur": 16.347, + "args": { + "External id": 711626,"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": 6305207087215.481, "dur": 64381.276, + "args": { + "External id": 711627,"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": 6305207151767.313, "dur": 14.366, + "args": { + "External id": 711628,"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": 6305207151770.683, "dur": 10.621, + "args": { + "External id": 711629,"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": 6305207151811.806, "dur": 352.870, + "args": { + "External id": 711630,"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": 6305207151845.371, "dur": 313.895, + "args": { + "External id": 711631,"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": 6305207151858.330, "dur": 295.205, + "args": { + "External id": 711632,"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": 6305207152189.443, "dur": 2.346, + "args": { + "External id": 711633,"Record function id": 0, "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": 6305207152253.163, "dur": 7.105, + "args": { + "External id": 711634,"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": 6305207152305.493, "dur": 1.576, + "args": { + "External id": 711635,"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": 6305207152323.348, "dur": 1.339, + "args": { + "External id": 711636,"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": 6305207152336.296, "dur": 0.906, + "args": { + "External id": 711637,"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": 6305207152351.913, "dur": 0.994, + "args": { + "External id": 711638,"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": 6305207152364.050, "dur": 0.807, + "args": { + "External id": 711639,"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": 6305207152377.604, "dur": 0.877, + "args": { + "External id": 711640,"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": 6305207152388.975, "dur": 2.262, + "args": { + "External id": 711641,"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": 6305207152403.015, "dur": 0.654, + "args": { + "External id": 711642,"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": 6305207152495.479, "dur": 2345.519, + "args": { + "External id": 711643,"Record function id": 0, "Ev Idx": 5594 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.0)", "pid": 2338707, "tid": 2379456, + "ts": 6305207152531.765, "dur": 447.013, + "args": { + "External id": 711644,"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": 6305207152548.176, "dur": 339.602, + "args": { + "External id": 711645,"Record function id": 0, "Ev Idx": 5596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6305207152638.104, "dur": 4.920, + "args": { + "External id": 711646,"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": 6305207152646.564, "dur": 1.013, + "args": { + "External id": 711647,"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": 6305207152651.889, "dur": 0.655, + "args": { + "External id": 711648,"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": 6305207152653.988, "dur": 0.836, + "args": { + "External id": 711649,"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": 6305207152656.205, "dur": 0.668, + "args": { + "External id": 711650,"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": 6305207152658.360, "dur": 2.551, + "args": { + "External id": 711651,"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": 6305207152664.893, "dur": 1.860, + "args": { + "External id": 711652,"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": 6305207152668.204, "dur": 1.020, + "args": { + "External id": 711653,"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": 6305207152670.576, "dur": 0.742, + "args": { + "External id": 711654,"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": 6305207152672.904, "dur": 0.699, + "args": { + "External id": 711655,"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": 6305207152693.829, "dur": 162.461, + "args": { + "External id": 711656,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305207152709.829, "dur": 140.876, + "args": { + "External id": 711657,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305207152737.452, "dur": 15.382, + "args": { + "External id": 711658,"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": 6305207152756.409, "dur": 66.609, + "args": { + "External id": 711659,"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": 6305207152758.943, "dur": 63.681, + "args": { + "External id": 711660,"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": 6305207152762.783, "dur": 6.854, + "args": { + "External id": 711661,"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": 6305207152771.296, "dur": 50.775, + "args": { + "External id": 711662,"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": 6305207152986.485, "dur": 1832.462, + "args": { + "External id": 711663,"Sequence number": 7674392, "Fwd thread 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": 6305207152986.485, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6305207153139.071, "dur": 110.796, + "args": { + "External id": 711664,"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": 6305207153295.437, "dur": 39.849, + "args": { + "External id": 711665,"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": 6305207153352.664, "dur": 50.349, + "args": { + "External id": 711666,"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": 6305207153415.723, "dur": 30.920, + "args": { + "External id": 711667,"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": 6305207153454.228, "dur": 32.646, + "args": { + "External id": 711668,"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": 6305207153494.127, "dur": 48.015, + "args": { + "External id": 711669,"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": 6305207153553.019, "dur": 35.044, + "args": { + "External id": 711670,"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": 6305207153618.452, "dur": 26.162, + "args": { + "External id": 711671,"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": 6305207153663.187, "dur": 29.987, + "args": { + "External id": 711672,"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": 6305207153716.682, "dur": 23.432, + "args": { + "External id": 711673,"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": 6305207153754.815, "dur": 15.745, + "args": { + "External id": 711674,"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": 6305207153777.801, "dur": 40.380, + "args": { + "External id": 711675,"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": 6305207153821.786, "dur": 36.029, + "args": { + "External id": 711676,"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": 6305207153889.354, "dur": 343.351, + "args": { + "External id": 711677,"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": 6305207153972.374, "dur": 6.326, + "args": { + "External id": 711678,"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": 6305207153980.787, "dur": 2.608, + "args": { + "External id": 711679,"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": 6305207153984.594, "dur": 2.140, + "args": { + "External id": 711680,"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": 6305207154026.925, "dur": 9.634, + "args": { + "External id": 711681,"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": 6305207154119.896, "dur": 6.651, + "args": { + "External id": 711682,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305207154123.121, "dur": 3.018, + "args": { + "External id": 711683,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305207154128.709, "dur": 34.057, + "args": { + "External id": 711684,"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": 6305207154135.065, "dur": 3.607, + "args": { + "External id": 711685,"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": 6305207154166.241, "dur": 1.610, + "args": { + "External id": 711686,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305207154167.248, "dur": 0.523, + "args": { + "External id": 711687,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305207154168.909, "dur": 14.660, + "args": { + "External id": 711688,"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": 6305207154171.861, "dur": 0.454, + "args": { + "External id": 711689,"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": 6305207154273.753, "dur": 30.083, + "args": { + "External id": 711690,"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": 6305207154322.958, "dur": 17.473, + "args": { + "External id": 711691,"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": 6305207154351.374, "dur": 49.930, + "args": { + "External id": 711692,"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": 6305207154408.292, "dur": 39.931, + "args": { + "External id": 711693,"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": 6305207154458.572, "dur": 20.369, + "args": { + "External id": 711694,"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": 6305207154484.103, "dur": 44.373, + "args": { + "External id": 711695,"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": 6305207154538.776, "dur": 30.116, + "args": { + "External id": 711696,"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": 6305207154576.833, "dur": 29.645, + "args": { + "External id": 711697,"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": 6305207154630.020, "dur": 24.484, + "args": { + "External id": 711698,"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": 6305207154674.217, "dur": 22.512, + "args": { + "External id": 711699,"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": 6305207154711.217, "dur": 15.786, + "args": { + "External id": 711700,"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": 6305207154744.295, "dur": 13.298, + "args": { + "External id": 711701,"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": 6305207154773.187, "dur": 15.434, + "args": { + "External id": 711702,"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": 6305207154864.479, "dur": 14.345, + "args": { + "External id": 711703,"Record function id": 0, "Ev Idx": 5654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305207154867.776, "dur": 10.058, + "args": { + "External id": 711704,"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": 6305207154871.789, "dur": 5.132, + "args": { + "External id": 711705,"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": 6305207154873.011, "dur": 3.814, + "args": { + "External id": 711706,"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": 6305207154882.925, "dur": 4.860, + "args": { + "External id": 711707,"Record function id": 0, "Ev Idx": 5658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305207154884.698, "dur": 2.630, + "args": { + "External id": 711708,"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": 6305207154885.358, "dur": 1.459, + "args": { + "External id": 711709,"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": 6305207154885.836, "dur": 0.895, + "args": { + "External id": 711710,"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": 6305207154891.153, "dur": 4.255, + "args": { + "External id": 711711,"Record function id": 0, "Ev Idx": 5662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305207154892.600, "dur": 2.375, + "args": { + "External id": 711712,"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": 6305207154893.134, "dur": 1.399, + "args": { + "External id": 711713,"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": 6305207154893.659, "dur": 0.806, + "args": { + "External id": 711714,"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": 6305207154898.661, "dur": 6.501, + "args": { + "External id": 711715,"Record function id": 0, "Ev Idx": 5666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305207154900.310, "dur": 4.428, + "args": { + "External id": 711716,"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": 6305207154900.871, "dur": 3.478, + "args": { + "External id": 711717,"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": 6305207154901.307, "dur": 2.981, + "args": { + "External id": 711718,"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": 6305207154908.277, "dur": 4.427, + "args": { + "External id": 711719,"Record function id": 0, "Ev Idx": 5670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305207154909.938, "dur": 2.356, + "args": { + "External id": 711720,"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": 6305207154910.753, "dur": 1.113, + "args": { + "External id": 711721,"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": 6305207154911.045, "dur": 0.747, + "args": { + "External id": 711722,"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": 6305207154915.875, "dur": 6.042, + "args": { + "External id": 711723,"Record function id": 0, "Ev Idx": 5674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305207154917.219, "dur": 4.282, + "args": { + "External id": 711724,"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": 6305207154917.697, "dur": 3.271, + "args": { + "External id": 711725,"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": 6305207154920.212, "dur": 0.680, + "args": { + "External id": 711726,"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": 6305207154925.422, "dur": 3.835, + "args": { + "External id": 711727,"Record function id": 0, "Ev Idx": 5678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305207154926.697, "dur": 2.161, + "args": { + "External id": 711728,"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": 6305207154927.191, "dur": 1.274, + "args": { + "External id": 711729,"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": 6305207154927.699, "dur": 0.699, + "args": { + "External id": 711730,"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": 6305207154932.704, "dur": 3.998, + "args": { + "External id": 711731,"Record function id": 0, "Ev Idx": 5682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305207154933.954, "dur": 2.307, + "args": { + "External id": 711732,"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": 6305207154934.778, "dur": 1.103, + "args": { + "External id": 711733,"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": 6305207154935.213, "dur": 0.600, + "args": { + "External id": 711734,"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": 6305207154940.028, "dur": 3.485, + "args": { + "External id": 711735,"Record function id": 0, "Ev Idx": 5686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305207154941.241, "dur": 1.863, + "args": { + "External id": 711736,"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": 6305207154941.773, "dur": 0.951, + "args": { + "External id": 711737,"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": 6305207154942.093, "dur": 0.561, + "args": { + "External id": 711738,"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": 6305207154947.773, "dur": 65312.837, + "args": { + "External id": 711739,"Record function id": 0, "Sequence number": 7674391, "Fwd thread id": 1, "Ev Idx": 5690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305207154949.406, "dur": 65302.211, + "args": { + "External id": 711740,"Sequence number": 7674391, "Fwd thread 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": 6305207154949.406, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.0)", "pid": 2338707, "tid": 2379456, + "ts": 6305207154981.259, "dur": 44.670, + "args": { + "External id": 711741,"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": 6305207155033.678, "dur": 115.065, + "args": { + "External id": 711742,"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": 6305207155157.264, "dur": 65086.443, + "args": { + "External id": 711743,"Record function id": 0, "Ev Idx": 5694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305207155270.559, "dur": 10.820, + "args": { + "External id": 711744,"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": 6305207155293.851, "dur": 5.673, + "args": { + "External id": 711745,"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": 6305207155314.559, "dur": 64026.277, + "args": { + "External id": 711746,"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": 6305207155328.460, "dur": 63999.277, + "args": { + "External id": 711747,"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": 6305207155427.954, "dur": 18.786, + "args": { + "External id": 711748,"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": 6305207155471.017, "dur": 63809.847, + "args": { + "External id": 711749,"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": 6305207155478.107, "dur": 63801.767, + "args": { + "External id": 711750,"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": 6305207155482.750, "dur": 10.915, + "args": { + "External id": 711751,"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": 6305207155495.564, "dur": 63779.424, + "args": { + "External id": 711752,"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": 6305207219450.252, "dur": 10.993, + "args": { + "External id": 711753,"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": 6305207219453.628, "dur": 7.218, + "args": { + "External id": 711754,"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": 6305207219491.624, "dur": 401.805, + "args": { + "External id": 711755,"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": 6305207219540.400, "dur": 347.680, + "args": { + "External id": 711756,"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": 6305207219555.982, "dur": 327.014, + "args": { + "External id": 711757,"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": 6305207219920.532, "dur": 2.386, + "args": { + "External id": 711758,"Record function id": 0, "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": 6305207219985.729, "dur": 6.860, + "args": { + "External id": 711759,"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": 6305207220039.349, "dur": 1.264, + "args": { + "External id": 711760,"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": 6305207220091.583, "dur": 2.233, + "args": { + "External id": 711761,"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": 6305207220109.361, "dur": 3.089, + "args": { + "External id": 711762,"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": 6305207220125.490, "dur": 0.826, + "args": { + "External id": 711763,"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": 6305207220137.101, "dur": 0.915, + "args": { + "External id": 711764,"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": 6305207220147.969, "dur": 0.714, + "args": { + "External id": 711765,"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": 6305207220160.657, "dur": 3.956, + "args": { + "External id": 711766,"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": 6305207220174.904, "dur": 0.741, + "args": { + "External id": 711767,"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": 6305207220280.789, "dur": 302.649, + "args": { + "External id": 711768,"Record function id": 0, "Sequence number": 7674390, "Fwd thread id": 1, "Ev Idx": 5719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305207220283.740, "dur": 290.150, + "args": { + "External id": 711769,"Sequence number": 7674390, "Fwd thread 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": 6305207220283.740, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_embedding_dense_backward_0", "pid": 2338707, "tid": 2379456, + "ts": 6305207220399.780, "dur": 50.996, + "args": { + "External id": 711770,"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": 6305207220469.409, "dur": 24.549, + "args": { + "External id": 711771,"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": 6305207220531.510, "dur": 24.648, + "args": { + "External id": 711772,"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": 6305207220596.687, "dur": 14.471, + "args": { + "External id": 711773,"Record function id": 0, "Ev Idx": 5724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305207220599.646, "dur": 10.673, + "args": { + "External id": 711774,"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": 6305207220603.594, "dur": 5.942, + "args": { + "External id": 711775,"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": 6305207220605.158, "dur": 4.240, + "args": { + "External id": 711776,"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": 6305207220634.627, "dur": 15097.986, + "args": { + "External id": 711777,"Record function id": 0, "Ev Idx": 5728 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate", "pid": 2338707, "tid": 2379456, + "ts": 6305207220654.111, "dur": 38.843, + "args": { + "External id": 711778,"Record function id": 0, "Ev Idx": 5729 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard", "pid": 2338707, "tid": 2379456, + "ts": 6305207220698.983, "dur": 225.248, + "args": { + "External id": 711779,"Record function id": 0, "Ev Idx": 5730 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce", "pid": 2338707, "tid": 2379456, + "ts": 6305207220929.934, "dur": 14539.537, + "args": { + "External id": 711780,"Record function id": 0, "Ev Idx": 5731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305207221049.491, "dur": 44.832, + "args": { + "External id": 711781,"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": 6305207221108.690, "dur": 7.906, + "args": { + "External id": 711782,"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": 6305207221140.207, "dur": 13149.142, + "args": { + "External id": 711783,"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": 6305207221158.689, "dur": 13115.267, + "args": { + "External id": 711784,"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": 6305207221977.869, "dur": 23.976, + "args": { + "External id": 711785,"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": 6305207222276.338, "dur": 11941.234, + "args": { + "External id": 711786,"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": 6305207222280.518, "dur": 11935.616, + "args": { + "External id": 711787,"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": 6305207222288.024, "dur": 18.450, + "args": { + "External id": 711788,"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": 6305207222309.986, "dur": 11899.481, + "args": { + "External id": 711789,"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": 6305207234433.751, "dur": 11.497, + "args": { + "External id": 711790,"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": 6305207234437.186, "dur": 7.650, + "args": { + "External id": 711791,"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": 6305207234476.166, "dur": 289.275, + "args": { + "External id": 711792,"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": 6305207234520.975, "dur": 239.483, + "args": { + "External id": 711793,"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": 6305207234535.118, "dur": 220.313, + "args": { + "External id": 711794,"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": 6305207234788.533, "dur": 2.282, + "args": { + "External id": 711795,"Record function id": 0, "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": 6305207234847.020, "dur": 6.836, + "args": { + "External id": 711796,"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": 6305207234897.494, "dur": 0.970, + "args": { + "External id": 711797,"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": 6305207234912.851, "dur": 1.392, + "args": { + "External id": 711798,"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": 6305207234929.995, "dur": 0.976, + "args": { + "External id": 711799,"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": 6305207234941.464, "dur": 1.016, + "args": { + "External id": 711800,"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": 6305207234955.126, "dur": 0.999, + "args": { + "External id": 711801,"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": 6305207234967.032, "dur": 1.761, + "args": { + "External id": 711802,"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": 6305207234981.077, "dur": 0.795, + "args": { + "External id": 711803,"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": 6305207234991.677, "dur": 0.978, + "args": { + "External id": 711804,"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": 6305207235002.651, "dur": 0.556, + "args": { + "External id": 711805,"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": 6305207235015.621, "dur": 0.734, + "args": { + "External id": 711806,"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": 6305207235032.862, "dur": 0.758, + "args": { + "External id": 711807,"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": 6305207235043.325, "dur": 1.083, + "args": { + "External id": 711808,"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": 6305207235089.204, "dur": 1.881, + "args": { + "External id": 711809,"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": 6305207235104.868, "dur": 0.906, + "args": { + "External id": 711810,"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": 6305207235119.672, "dur": 0.760, + "args": { + "External id": 711811,"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": 6305207235133.076, "dur": 0.789, + "args": { + "External id": 711812,"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": 6305207235143.437, "dur": 0.736, + "args": { + "External id": 711813,"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": 6305207235153.588, "dur": 1.124, + "args": { + "External id": 711814,"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": 6305207235167.597, "dur": 1.335, + "args": { + "External id": 711815,"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": 6305207235178.930, "dur": 2.675, + "args": { + "External id": 711816,"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": 6305207235193.990, "dur": 1.066, + "args": { + "External id": 711817,"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": 6305207235205.229, "dur": 0.801, + "args": { + "External id": 711818,"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": 6305207235228.371, "dur": 0.988, + "args": { + "External id": 711819,"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": 6305207235241.397, "dur": 1.092, + "args": { + "External id": 711820,"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": 6305207235252.293, "dur": 0.879, + "args": { + "External id": 711821,"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": 6305207235264.493, "dur": 0.678, + "args": { + "External id": 711822,"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": 6305207235277.279, "dur": 0.770, + "args": { + "External id": 711823,"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": 6305207235287.084, "dur": 1.925, + "args": { + "External id": 711824,"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": 6305207235298.096, "dur": 0.971, + "args": { + "External id": 711825,"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": 6305207235307.803, "dur": 1.127, + "args": { + "External id": 711826,"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": 6305207235321.806, "dur": 0.856, + "args": { + "External id": 711827,"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": 6305207235332.045, "dur": 1.173, + "args": { + "External id": 711828,"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": 6305207235342.568, "dur": 1.031, + "args": { + "External id": 711829,"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": 6305207235352.660, "dur": 1.946, + "args": { + "External id": 711830,"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": 6305207235366.215, "dur": 1.132, + "args": { + "External id": 711831,"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": 6305207235379.238, "dur": 0.874, + "args": { + "External id": 711832,"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": 6305207235388.706, "dur": 1.224, + "args": { + "External id": 711833,"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": 6305207235400.164, "dur": 1.216, + "args": { + "External id": 711834,"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": 6305208407331.175, "dur": 103.821, + "args": { + "External id": 711835,"Record function id": 0, "Sequence number": 7674845, "Fwd thread id": 1, "Ev Idx": 5786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "DivBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208407340.863, "dur": 84.630, + "args": { + "External id": 711836,"Sequence number": 7674845, "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": 6305208407340.863, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::div", "pid": 2338707, "tid": 2379456, + "ts": 6305208407348.549, "dur": 75.234, + "args": { + "External id": 711837,"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": 6305208407443.528, "dur": 263.624, + "args": { + "External id": 711838,"Record function id": 0, "Ev Idx": 5789 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward", "pid": 2338707, "tid": 2379456, + "ts": 6305208407538.695, "dur": 93.098, + "args": { + "External id": 711839,"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": 6305208407571.559, "dur": 48.449, + "args": { + "External id": 711840,"Record function id": 0, "Ev Idx": 5791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208407637.842, "dur": 2.033, + "args": { + "External id": 711841,"Sequence number": 7674844, "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": 6305208407637.842, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338707, "tid": 2379456, + "ts": 6305208407644.873, "dur": 56.653, + "args": { + "External id": 711842,"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": 6305208407651.044, "dur": 49.746, + "args": { + "External id": 711843,"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": 6305208407662.941, "dur": 3.095, + "args": { + "External id": 711844,"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": 6305208407719.592, "dur": 38767.928, + "args": { + "External id": 711845,"Record function id": 0, "Sequence number": 7674842, "Fwd thread id": 1, "Ev Idx": 5796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305208407721.881, "dur": 38750.879, + "args": { + "External id": 711846,"Sequence number": 7674842, "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": 6305208407721.881, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305208407762.897, "dur": 4.068, + "args": { + "External id": 711847,"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": 6305208407771.857, "dur": 38416.081, + "args": { + "External id": 711848,"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": 6305208407773.979, "dur": 38413.560, + "args": { + "External id": 711849,"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": 6305208407778.637, "dur": 7.789, + "args": { + "External id": 711850,"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": 6305208407788.501, "dur": 38397.023, + "args": { + "External id": 711851,"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": 6305208446193.417, "dur": 0.487, + "args": { + "External id": 711852,"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": 6305208446196.290, "dur": 3.203, + "args": { + "External id": 711853,"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": 6305208446198.204, "dur": 1.108, + "args": { + "External id": 711854,"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": 6305208446206.915, "dur": 32.123, + "args": { + "External id": 711855,"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": 6305208446248.798, "dur": 48.598, + "args": { + "External id": 711856,"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": 6305208446250.482, "dur": 46.713, + "args": { + "External id": 711857,"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": 6305208446252.486, "dur": 44.080, + "args": { + "External id": 711858,"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": 6305208446502.551, "dur": 35.503, + "args": { + "External id": 711859,"Record function id": 0, "Sequence number": 7674841, "Fwd thread id": 1, "Ev Idx": 5810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208446504.903, "dur": 29.435, + "args": { + "External id": 711860,"Sequence number": 7674841, "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": 6305208446504.903, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208446523.243, "dur": 10.797, + "args": { + "External id": 711861,"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": 6305208446526.509, "dur": 7.266, + "args": { + "External id": 711862,"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": 6305208446543.773, "dur": 111.596, + "args": { + "External id": 711863,"Record function id": 0, "Sequence number": 7674840, "Fwd thread id": 1, "Ev Idx": 5814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208446545.106, "dur": 102.858, + "args": { + "External id": 711864,"Sequence number": 7674840, "Fwd thread 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": 6305208446545.106, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338707, "tid": 2379456, + "ts": 6305208446549.653, "dur": 97.760, + "args": { + "External id": 711865,"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": 6305208446555.723, "dur": 37.890, + "args": { + "External id": 711866,"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": 6305208446560.814, "dur": 6.418, + "args": { + "External id": 711867,"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": 6305208446569.031, "dur": 24.214, + "args": { + "External id": 711868,"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": 6305208446573.199, "dur": 19.552, + "args": { + "External id": 711869,"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": 6305208446596.196, "dur": 7.024, + "args": { + "External id": 711870,"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": 6305208446601.027, "dur": 1.847, + "args": { + "External id": 711871,"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": 6305208446604.501, "dur": 41.824, + "args": { + "External id": 711872,"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": 6305208446660.887, "dur": 68.003, + "args": { + "External id": 711873,"Record function id": 0, "Sequence number": 7674839, "Fwd thread id": 1, "Ev Idx": 5824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SelectBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208446662.870, "dur": 63.130, + "args": { + "External id": 711874,"Sequence number": 7674839, "Fwd thread 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": 6305208446662.870, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select_backward", "pid": 2338707, "tid": 2379456, + "ts": 6305208446667.037, "dur": 58.650, + "args": { + "External id": 711875,"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": 6305208446670.869, "dur": 21.554, + "args": { + "External id": 711876,"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": 6305208446672.866, "dur": 2.514, + "args": { + "External id": 711877,"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": 6305208446676.218, "dur": 15.965, + "args": { + "External id": 711878,"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": 6305208446681.169, "dur": 10.448, + "args": { + "External id": 711879,"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": 6305208446693.824, "dur": 12.456, + "args": { + "External id": 711880,"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": 6305208446700.012, "dur": 5.490, + "args": { + "External id": 711881,"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": 6305208446707.480, "dur": 17.567, + "args": { + "External id": 711882,"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": 6305208446733.177, "dur": 234.106, + "args": { + "External id": 711883,"Record function id": 0, "Sequence number": 7674838, "Fwd thread id": 1, "Ev Idx": 5834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208446734.372, "dur": 229.168, + "args": { + "External id": 711884,"Sequence number": 7674838, "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": 6305208446734.372, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338707, "tid": 2379456, + "ts": 6305208446737.017, "dur": 226.096, + "args": { + "External id": 711885,"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": 6305208446739.011, "dur": 21.302, + "args": { + "External id": 711886,"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": 6305208446740.324, "dur": 2.279, + "args": { + "External id": 711887,"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": 6305208446743.351, "dur": 16.716, + "args": { + "External id": 711888,"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": 6305208446748.398, "dur": 11.335, + "args": { + "External id": 711889,"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": 6305208446761.486, "dur": 4.207, + "args": { + "External id": 711890,"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": 6305208446764.488, "dur": 1.028, + "args": { + "External id": 711891,"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": 6305208446766.648, "dur": 195.480, + "args": { + "External id": 711892,"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": 6305208446972.482, "dur": 126.109, + "args": { + "External id": 711893,"Record function id": 0, "Sequence number": 7674837, "Fwd thread id": 1, "Ev Idx": 5844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208446973.463, "dur": 119.698, + "args": { + "External id": 711894,"Sequence number": 7674837, "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": 6305208446973.463, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338707, "tid": 2379456, + "ts": 6305208446976.317, "dur": 116.452, + "args": { + "External id": 711895,"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": 6305208446977.914, "dur": 19.458, + "args": { + "External id": 711896,"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": 6305208446979.860, "dur": 2.306, + "args": { + "External id": 711897,"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": 6305208446983.109, "dur": 14.009, + "args": { + "External id": 711898,"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": 6305208446985.198, "dur": 11.546, + "args": { + "External id": 711899,"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": 6305208446999.869, "dur": 4.522, + "args": { + "External id": 711900,"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": 6305208447003.471, "dur": 0.739, + "args": { + "External id": 711901,"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": 6305208447013.399, "dur": 77.802, + "args": { + "External id": 711902,"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": 6305208447110.423, "dur": 39.929, + "args": { + "External id": 711903,"Record function id": 0, "Sequence number": 7674836, "Fwd thread id": 1, "Ev Idx": 5854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208447111.863, "dur": 1.299, + "args": { + "External id": 711904,"Sequence number": 7674836, "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": 6305208447111.863, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338707, "tid": 2379456, + "ts": 6305208447116.243, "dur": 31.067, + "args": { + "External id": 711905,"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": 6305208447119.402, "dur": 27.479, + "args": { + "External id": 711906,"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": 6305208447126.529, "dur": 0.886, + "args": { + "External id": 711907,"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": 6305208447155.809, "dur": 2418.910, + "args": { + "External id": 711908,"Record function id": 0, "Sequence number": 7674834, "Fwd thread id": 1, "Ev Idx": 5859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305208447158.226, "dur": 2375.256, + "args": { + "External id": 711909,"Sequence number": 7674834, "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": 6305208447158.226, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305208447198.415, "dur": 5.371, + "args": { + "External id": 711910,"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": 6305208447206.981, "dur": 2073.416, + "args": { + "External id": 711911,"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": 6305208447209.155, "dur": 2070.924, + "args": { + "External id": 711912,"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": 6305208447213.078, "dur": 4.106, + "args": { + "External id": 711913,"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": 6305208447218.186, "dur": 2060.862, + "args": { + "External id": 711914,"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": 6305208449284.647, "dur": 0.673, + "args": { + "External id": 711915,"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": 6305208449287.463, "dur": 6.184, + "args": { + "External id": 711916,"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": 6305208449292.240, "dur": 1.270, + "args": { + "External id": 711917,"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": 6305208449298.707, "dur": 29.283, + "args": { + "External id": 711918,"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": 6305208449334.441, "dur": 47.791, + "args": { + "External id": 711919,"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": 6305208449336.186, "dur": 45.681, + "args": { + "External id": 711920,"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": 6305208449338.081, "dur": 43.398, + "args": { + "External id": 711921,"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": 6305208449548.275, "dur": 21.442, + "args": { + "External id": 711922,"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": 6305208449586.499, "dur": 15.947, + "args": { + "External id": 711923,"Record function id": 0, "Sequence number": 7674833, "Fwd thread id": 1, "Ev Idx": 5874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208449588.333, "dur": 11.680, + "args": { + "External id": 711924,"Sequence number": 7674833, "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": 6305208449588.333, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208449592.756, "dur": 7.031, + "args": { + "External id": 711925,"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": 6305208449594.816, "dur": 4.804, + "args": { + "External id": 711926,"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": 6305208449605.906, "dur": 83.655, + "args": { + "External id": 711927,"Record function id": 0, "Sequence number": 7674832, "Fwd thread id": 1, "Ev Idx": 5878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208449607.189, "dur": 77.426, + "args": { + "External id": 711928,"Sequence number": 7674832, "Fwd thread 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": 6305208449607.189, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338707, "tid": 2379456, + "ts": 6305208449609.874, "dur": 74.324, + "args": { + "External id": 711929,"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": 6305208449616.970, "dur": 24.649, + "args": { + "External id": 711930,"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": 6305208449619.622, "dur": 3.944, + "args": { + "External id": 711931,"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": 6305208449624.884, "dur": 16.450, + "args": { + "External id": 711932,"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": 6305208449627.966, "dur": 12.940, + "args": { + "External id": 711933,"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": 6305208449643.471, "dur": 6.356, + "args": { + "External id": 711934,"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": 6305208449647.891, "dur": 1.612, + "args": { + "External id": 711935,"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": 6305208449651.234, "dur": 32.119, + "args": { + "External id": 711936,"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": 6305208449693.806, "dur": 60.274, + "args": { + "External id": 711937,"Record function id": 0, "Sequence number": 7674831, "Fwd thread id": 1, "Ev Idx": 5888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SelectBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208449695.086, "dur": 56.353, + "args": { + "External id": 711938,"Sequence number": 7674831, "Fwd thread 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": 6305208449695.086, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select_backward", "pid": 2338707, "tid": 2379456, + "ts": 6305208449698.850, "dur": 52.347, + "args": { + "External id": 711939,"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": 6305208449701.514, "dur": 19.153, + "args": { + "External id": 711940,"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": 6305208449703.006, "dur": 2.301, + "args": { + "External id": 711941,"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": 6305208449709.162, "dur": 11.240, + "args": { + "External id": 711942,"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": 6305208449710.258, "dur": 9.693, + "args": { + "External id": 711943,"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": 6305208449728.059, "dur": 6.481, + "args": { + "External id": 711944,"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": 6305208449732.913, "dur": 1.077, + "args": { + "External id": 711945,"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": 6305208449735.296, "dur": 15.301, + "args": { + "External id": 711946,"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": 6305208449757.955, "dur": 141.779, + "args": { + "External id": 711947,"Record function id": 0, "Sequence number": 7674830, "Fwd thread id": 1, "Ev Idx": 5898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208449759.073, "dur": 136.964, + "args": { + "External id": 711948,"Sequence number": 7674830, "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": 6305208449759.073, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338707, "tid": 2379456, + "ts": 6305208449761.827, "dur": 133.879, + "args": { + "External id": 711949,"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": 6305208449763.639, "dur": 19.733, + "args": { + "External id": 711950,"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": 6305208449765.444, "dur": 2.154, + "args": { + "External id": 711951,"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": 6305208449772.288, "dur": 10.811, + "args": { + "External id": 711952,"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": 6305208449773.150, "dur": 9.643, + "args": { + "External id": 711953,"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": 6305208449784.388, "dur": 5.266, + "args": { + "External id": 711954,"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": 6305208449788.430, "dur": 0.974, + "args": { + "External id": 711955,"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": 6305208449790.552, "dur": 104.186, + "args": { + "External id": 711956,"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": 6305208449908.407, "dur": 104.547, + "args": { + "External id": 711957,"Record function id": 0, "Sequence number": 7674829, "Fwd thread id": 1, "Ev Idx": 5908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208449909.347, "dur": 84.940, + "args": { + "External id": 711958,"Sequence number": 7674829, "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": 6305208449909.347, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338707, "tid": 2379456, + "ts": 6305208449912.110, "dur": 81.827, + "args": { + "External id": 711959,"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": 6305208449913.663, "dur": 22.403, + "args": { + "External id": 711960,"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": 6305208449915.124, "dur": 2.026, + "args": { + "External id": 711961,"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": 6305208449917.961, "dur": 17.849, + "args": { + "External id": 711962,"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": 6305208449922.161, "dur": 13.089, + "args": { + "External id": 711963,"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": 6305208449937.186, "dur": 3.921, + "args": { + "External id": 711964,"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": 6305208449940.346, "dur": 0.494, + "args": { + "External id": 711965,"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": 6305208449942.103, "dur": 51.108, + "args": { + "External id": 711966,"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": 6305208449998.987, "dur": 12.659, + "args": { + "External id": 711967,"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": 6305208450017.816, "dur": 74.453, + "args": { + "External id": 711968,"Record function id": 0, "Sequence number": 7674828, "Fwd thread id": 1, "Ev Idx": 5919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208450019.264, "dur": 1.128, + "args": { + "External id": 711969,"Sequence number": 7674828, "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": 6305208450019.264, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338707, "tid": 2379456, + "ts": 6305208450023.016, "dur": 66.214, + "args": { + "External id": 711970,"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": 6305208450025.797, "dur": 62.477, + "args": { + "External id": 711971,"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": 6305208450035.171, "dur": 0.675, + "args": { + "External id": 711972,"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": 6305208450100.449, "dur": 3419.383, + "args": { + "External id": 711973,"Record function id": 0, "Sequence number": 7674826, "Fwd thread id": 1, "Ev Idx": 5924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305208450102.665, "dur": 3374.029, + "args": { + "External id": 711974,"Sequence number": 7674826, "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": 6305208450102.665, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305208450138.779, "dur": 3.012, + "args": { + "External id": 711975,"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": 6305208450144.546, "dur": 3118.032, + "args": { + "External id": 711976,"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": 6305208450146.421, "dur": 3115.908, + "args": { + "External id": 711977,"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": 6305208450150.423, "dur": 4.654, + "args": { + "External id": 711978,"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": 6305208450158.278, "dur": 3102.858, + "args": { + "External id": 711979,"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": 6305208453266.617, "dur": 0.408, + "args": { + "External id": 711980,"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": 6305208453268.838, "dur": 2.631, + "args": { + "External id": 711981,"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": 6305208453270.186, "dur": 1.161, + "args": { + "External id": 711982,"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": 6305208453276.807, "dur": 24.091, + "args": { + "External id": 711983,"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": 6305208453307.090, "dur": 43.133, + "args": { + "External id": 711984,"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": 6305208453308.281, "dur": 41.680, + "args": { + "External id": 711985,"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": 6305208453309.922, "dur": 39.687, + "args": { + "External id": 711986,"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": 6305208453487.402, "dur": 16.527, + "args": { + "External id": 711987,"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": 6305208453532.057, "dur": 18.398, + "args": { + "External id": 711988,"Record function id": 0, "Sequence number": 7674825, "Fwd thread id": 1, "Ev Idx": 5939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208453537.040, "dur": 11.163, + "args": { + "External id": 711989,"Sequence number": 7674825, "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": 6305208453537.040, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208453541.298, "dur": 6.663, + "args": { + "External id": 711990,"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": 6305208453543.369, "dur": 4.406, + "args": { + "External id": 711991,"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": 6305208453554.282, "dur": 79.330, + "args": { + "External id": 711992,"Record function id": 0, "Sequence number": 7674824, "Fwd thread id": 1, "Ev Idx": 5943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208453555.279, "dur": 73.884, + "args": { + "External id": 711993,"Sequence number": 7674824, "Fwd thread 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": 6305208453555.279, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338707, "tid": 2379456, + "ts": 6305208453558.664, "dur": 70.063, + "args": { + "External id": 711994,"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": 6305208453562.196, "dur": 28.734, + "args": { + "External id": 711995,"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": 6305208453564.751, "dur": 3.954, + "args": { + "External id": 711996,"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": 6305208453569.999, "dur": 20.528, + "args": { + "External id": 711997,"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": 6305208453571.512, "dur": 18.424, + "args": { + "External id": 711998,"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": 6305208453592.568, "dur": 5.606, + "args": { + "External id": 711999,"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": 6305208453596.650, "dur": 1.255, + "args": { + "External id": 712000,"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": 6305208453602.378, "dur": 25.514, + "args": { + "External id": 712001,"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": 6305208453637.714, "dur": 54.267, + "args": { + "External id": 712002,"Record function id": 0, "Sequence number": 7674823, "Fwd thread id": 1, "Ev Idx": 5953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SelectBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208453639.084, "dur": 50.426, + "args": { + "External id": 712003,"Sequence number": 7674823, "Fwd thread 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": 6305208453639.084, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select_backward", "pid": 2338707, "tid": 2379456, + "ts": 6305208453641.882, "dur": 47.334, + "args": { + "External id": 712004,"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": 6305208453644.770, "dur": 17.573, + "args": { + "External id": 712005,"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": 6305208453646.540, "dur": 2.787, + "args": { + "External id": 712006,"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": 6305208453650.223, "dur": 11.857, + "args": { + "External id": 712007,"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": 6305208453651.340, "dur": 10.310, + "args": { + "External id": 712008,"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": 6305208453663.698, "dur": 9.742, + "args": { + "External id": 712009,"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": 6305208453671.714, "dur": 1.066, + "args": { + "External id": 712010,"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": 6305208453674.122, "dur": 14.568, + "args": { + "External id": 712011,"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": 6305208453695.525, "dur": 122.828, + "args": { + "External id": 712012,"Record function id": 0, "Sequence number": 7674822, "Fwd thread id": 1, "Ev Idx": 5963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208453696.819, "dur": 117.534, + "args": { + "External id": 712013,"Sequence number": 7674822, "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": 6305208453696.819, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338707, "tid": 2379456, + "ts": 6305208453699.066, "dur": 114.787, + "args": { + "External id": 712014,"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": 6305208453700.719, "dur": 18.488, + "args": { + "External id": 712015,"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": 6305208453702.374, "dur": 5.276, + "args": { + "External id": 712016,"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": 6305208453708.255, "dur": 10.687, + "args": { + "External id": 712017,"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": 6305208453709.419, "dur": 9.235, + "args": { + "External id": 712018,"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": 6305208453720.146, "dur": 4.025, + "args": { + "External id": 712019,"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": 6305208453723.286, "dur": 0.662, + "args": { + "External id": 712020,"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": 6305208453728.273, "dur": 84.454, + "args": { + "External id": 712021,"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": 6305208453822.887, "dur": 106.138, + "args": { + "External id": 712022,"Record function id": 0, "Sequence number": 7674821, "Fwd thread id": 1, "Ev Idx": 5973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208453823.850, "dur": 86.959, + "args": { + "External id": 712023,"Sequence number": 7674821, "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": 6305208453823.850, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338707, "tid": 2379456, + "ts": 6305208453826.155, "dur": 84.259, + "args": { + "External id": 712024,"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": 6305208453828.043, "dur": 19.681, + "args": { + "External id": 712025,"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": 6305208453829.030, "dur": 2.114, + "args": { + "External id": 712026,"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": 6305208453831.963, "dur": 15.506, + "args": { + "External id": 712027,"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": 6305208453832.813, "dur": 14.360, + "args": { + "External id": 712028,"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": 6305208453848.832, "dur": 3.657, + "args": { + "External id": 712029,"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": 6305208453851.823, "dur": 0.442, + "args": { + "External id": 712030,"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": 6305208453855.735, "dur": 53.841, + "args": { + "External id": 712031,"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": 6305208453915.815, "dur": 11.912, + "args": { + "External id": 712032,"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": 6305208453934.010, "dur": 35.338, + "args": { + "External id": 712033,"Record function id": 0, "Sequence number": 7674820, "Fwd thread id": 1, "Ev Idx": 5984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208453935.460, "dur": 1.129, + "args": { + "External id": 712034,"Sequence number": 7674820, "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": 6305208453935.460, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 2338707, "tid": 2379456, + "ts": 6305208453938.573, "dur": 26.073, + "args": { + "External id": 712035,"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": 6305208453940.811, "dur": 23.289, + "args": { + "External id": 712036,"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": 6305208453946.607, "dur": 0.560, + "args": { + "External id": 712037,"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": 6305208453973.988, "dur": 3483.537, + "args": { + "External id": 712038,"Record function id": 0, "Sequence number": 7674819, "Fwd thread id": 1, "Ev Idx": 5989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305208453986.014, "dur": 3440.360, + "args": { + "External id": 712039,"Sequence number": 7674819, "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": 6305208453986.014, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305208454015.177, "dur": 2.452, + "args": { + "External id": 712040,"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": 6305208454020.230, "dur": 3195.339, + "args": { + "External id": 712041,"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": 6305208454021.908, "dur": 3193.334, + "args": { + "External id": 712042,"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": 6305208454026.020, "dur": 3.635, + "args": { + "External id": 712043,"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": 6305208454030.596, "dur": 3183.687, + "args": { + "External id": 712044,"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": 6305208457219.596, "dur": 0.401, + "args": { + "External id": 712045,"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": 6305208457224.046, "dur": 2.897, + "args": { + "External id": 712046,"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": 6305208457225.571, "dur": 1.122, + "args": { + "External id": 712047,"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": 6305208457232.044, "dur": 22.180, + "args": { + "External id": 712048,"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": 6305208457260.031, "dur": 43.855, + "args": { + "External id": 712049,"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": 6305208457261.101, "dur": 42.582, + "args": { + "External id": 712050,"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": 6305208457263.024, "dur": 40.312, + "args": { + "External id": 712051,"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": 6305208457438.589, "dur": 14.576, + "args": { + "External id": 712052,"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": 6305208457472.209, "dur": 13.570, + "args": { + "External id": 712053,"Record function id": 0, "Ev Idx": 6004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208457475.133, "dur": 9.034, + "args": { + "External id": 712054,"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": 6305208457478.698, "dur": 4.598, + "args": { + "External id": 712055,"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": 6305208457479.805, "dur": 3.380, + "args": { + "External id": 712056,"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": 6305208457489.795, "dur": 28.977, + "args": { + "External id": 712057,"Record function id": 0, "Sequence number": 7674818, "Fwd thread id": 1, "Ev Idx": 6008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208457494.308, "dur": 9.270, + "args": { + "External id": 712058,"Sequence number": 7674818, "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": 6305208457494.308, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208457497.769, "dur": 5.570, + "args": { + "External id": 712059,"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": 6305208457499.752, "dur": 3.450, + "args": { + "External id": 712060,"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": 6305208457524.586, "dur": 76.814, + "args": { + "External id": 712061,"Record function id": 0, "Sequence number": 7674817, "Fwd thread id": 1, "Ev Idx": 6012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208457525.655, "dur": 69.537, + "args": { + "External id": 712062,"Sequence number": 7674817, "Fwd thread 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": 6305208457525.655, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338707, "tid": 2379456, + "ts": 6305208457529.294, "dur": 65.493, + "args": { + "External id": 712063,"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": 6305208457533.133, "dur": 25.186, + "args": { + "External id": 712064,"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": 6305208457535.518, "dur": 4.168, + "args": { + "External id": 712065,"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": 6305208457540.848, "dur": 17.176, + "args": { + "External id": 712066,"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": 6305208457542.788, "dur": 14.864, + "args": { + "External id": 712067,"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": 6305208457560.113, "dur": 4.855, + "args": { + "External id": 712068,"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": 6305208457563.215, "dur": 1.412, + "args": { + "External id": 712069,"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": 6305208457569.276, "dur": 24.731, + "args": { + "External id": 712070,"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": 6305208457605.558, "dur": 57.230, + "args": { + "External id": 712071,"Record function id": 0, "Sequence number": 7674816, "Fwd thread id": 1, "Ev Idx": 6022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SelectBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208457607.012, "dur": 53.119, + "args": { + "External id": 712072,"Sequence number": 7674816, "Fwd thread 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": 6305208457607.012, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select_backward", "pid": 2338707, "tid": 2379456, + "ts": 6305208457610.236, "dur": 49.607, + "args": { + "External id": 712073,"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": 6305208457613.645, "dur": 20.814, + "args": { + "External id": 712074,"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": 6305208457615.562, "dur": 2.840, + "args": { + "External id": 712075,"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": 6305208457619.211, "dur": 15.000, + "args": { + "External id": 712076,"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": 6305208457620.356, "dur": 13.476, + "args": { + "External id": 712077,"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": 6305208457635.630, "dur": 8.164, + "args": { + "External id": 712078,"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": 6305208457642.100, "dur": 1.048, + "args": { + "External id": 712079,"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": 6305208457644.596, "dur": 14.665, + "args": { + "External id": 712080,"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": 6305208457666.689, "dur": 130.151, + "args": { + "External id": 712081,"Record function id": 0, "Sequence number": 7674815, "Fwd thread id": 1, "Ev Idx": 6032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208457667.618, "dur": 125.557, + "args": { + "External id": 712082,"Sequence number": 7674815, "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": 6305208457667.618, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338707, "tid": 2379456, + "ts": 6305208457670.025, "dur": 122.595, + "args": { + "External id": 712083,"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": 6305208457671.769, "dur": 23.491, + "args": { + "External id": 712084,"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": 6305208457673.280, "dur": 1.857, + "args": { + "External id": 712085,"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": 6305208457681.664, "dur": 13.321, + "args": { + "External id": 712086,"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": 6305208457685.099, "dur": 9.492, + "args": { + "External id": 712087,"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": 6305208457699.199, "dur": 5.300, + "args": { + "External id": 712088,"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": 6305208457701.333, "dur": 2.930, + "args": { + "External id": 712089,"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": 6305208457705.283, "dur": 86.465, + "args": { + "External id": 712090,"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": 6305208457804.718, "dur": 101.715, + "args": { + "External id": 712091,"Record function id": 0, "Sequence number": 7674814, "Fwd thread id": 1, "Ev Idx": 6042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208457805.812, "dur": 80.309, + "args": { + "External id": 712092,"Sequence number": 7674814, "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": 6305208457805.812, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 2338707, "tid": 2379456, + "ts": 6305208457807.354, "dur": 78.415, + "args": { + "External id": 712093,"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": 6305208457808.811, "dur": 15.788, + "args": { + "External id": 712094,"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": 6305208457809.815, "dur": 2.256, + "args": { + "External id": 712095,"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": 6305208457812.894, "dur": 11.439, + "args": { + "External id": 712096,"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": 6305208457814.200, "dur": 9.742, + "args": { + "External id": 712097,"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": 6305208457825.567, "dur": 3.031, + "args": { + "External id": 712098,"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": 6305208457827.658, "dur": 0.762, + "args": { + "External id": 712099,"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": 6305208457831.791, "dur": 53.234, + "args": { + "External id": 712100,"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": 6305208457890.646, "dur": 13.919, + "args": { + "External id": 712101,"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": 6305208457912.805, "dur": 407.514, + "args": { + "External id": 712102,"Record function id": 0, "Sequence number": 7674813, "Fwd thread id": 1, "Ev Idx": 6053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305208457914.381, "dur": 396.775, + "args": { + "External id": 712103,"Sequence number": 7674813, "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": 6305208457914.381, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 2338707, "tid": 2379456, + "ts": 6305208458134.196, "dur": 45.491, + "args": { + "External id": 712104,"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": 6305208458219.311, "dur": 27.893, + "args": { + "External id": 712105,"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": 6305208458264.731, "dur": 22.091, + "args": { + "External id": 712106,"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": 6305208458335.061, "dur": 15.860, + "args": { + "External id": 712107,"Record function id": 0, "Ev Idx": 6058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208458337.505, "dur": 12.500, + "args": { + "External id": 712108,"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": 6305208458340.817, "dur": 8.270, + "args": { + "External id": 712109,"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": 6305208458342.261, "dur": 6.725, + "args": { + "External id": 712110,"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": 6305208458354.858, "dur": 36.688, + "args": { + "External id": 712111,"Record function id": 0, "Sequence number": 7674812, "Fwd thread id": 1, "Ev Idx": 6062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "StackBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208458355.852, "dur": 29.331, + "args": { + "External id": 712112,"Sequence number": 7674812, "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": 6305208458355.852, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 2338707, "tid": 2379456, + "ts": 6305208458358.300, "dur": 10.158, + "args": { + "External id": 712113,"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": 6305208458365.169, "dur": 1.257, + "args": { + "External id": 712114,"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": 6305208458369.191, "dur": 4.177, + "args": { + "External id": 712115,"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": 6305208458371.740, "dur": 0.662, + "args": { + "External id": 712116,"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": 6305208458373.922, "dur": 6.366, + "args": { + "External id": 712117,"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": 6305208458378.726, "dur": 0.507, + "args": { + "External id": 712118,"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": 6305208458380.861, "dur": 3.482, + "args": { + "External id": 712119,"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": 6305208458382.807, "dur": 0.519, + "args": { + "External id": 712120,"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": 6305208458395.434, "dur": 5.626, + "args": { + "External id": 712121,"Record function id": 0, "Sequence number": 7674811, "Fwd thread id": 1, "Ev Idx": 6072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208458396.740, "dur": 1.144, + "args": { + "External id": 712122,"Sequence number": 7674811, "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": 6305208458396.740, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SwiGLULinearFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305208458405.678, "dur": 571.709, + "args": { + "External id": 712123,"Record function id": 0, "Sequence number": 7674810, "Fwd thread id": 1, "Ev Idx": 6074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305208458407.721, "dur": 555.522, + "args": { + "External id": 712124,"Sequence number": 7674810, "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": 6305208458407.721, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208458447.332, "dur": 12.246, + "args": { + "External id": 712125,"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": 6305208458454.211, "dur": 5.018, + "args": { + "External id": 712126,"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": 6305208458463.941, "dur": 7.860, + "args": { + "External id": 712127,"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": 6305208458466.561, "dur": 3.767, + "args": { + "External id": 712128,"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": 6305208458468.753, "dur": 1.364, + "args": { + "External id": 712129,"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": 6305208458475.777, "dur": 161.365, + "args": { + "External id": 712130,"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": 6305208458479.366, "dur": 3.990, + "args": { + "External id": 712131,"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": 6305208458480.134, "dur": 2.129, + "args": { + "External id": 712132,"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": 6305208458481.561, "dur": 0.608, + "args": { + "External id": 712133,"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": 6305208458489.408, "dur": 146.900, + "args": { + "External id": 712134,"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": 6305208458491.286, "dur": 143.523, + "args": { + "External id": 712135,"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": 6305208458644.218, "dur": 5.671, + "args": { + "External id": 712136,"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": 6305208458646.438, "dur": 3.308, + "args": { + "External id": 712137,"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": 6305208458688.224, "dur": 6.081, + "args": { + "External id": 712138,"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": 6305208458696.074, "dur": 2.857, + "args": { + "External id": 712139,"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": 6305208458700.320, "dur": 5.781, + "args": { + "External id": 712140,"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": 6305208458746.333, "dur": 2.851, + "args": { + "External id": 712141,"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": 6305208458747.687, "dur": 1.347, + "args": { + "External id": 712142,"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": 6305208458780.388, "dur": 158.111, + "args": { + "External id": 712143,"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": 6305208458788.921, "dur": 7.926, + "args": { + "External id": 712144,"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": 6305208458794.036, "dur": 1.245, + "args": { + "External id": 712145,"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": 6305208458799.632, "dur": 9.245, + "args": { + "External id": 712146,"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": 6305208458806.851, "dur": 0.813, + "args": { + "External id": 712147,"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": 6305208458810.704, "dur": 5.418, + "args": { + "External id": 712148,"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": 6305208458812.614, "dur": 3.100, + "args": { + "External id": 712149,"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": 6305208458817.361, "dur": 3.329, + "args": { + "External id": 712150,"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": 6305208458819.329, "dur": 0.589, + "args": { + "External id": 712151,"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": 6305208458825.623, "dur": 3.754, + "args": { + "External id": 712152,"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": 6305208458828.185, "dur": 0.900, + "args": { + "External id": 712153,"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": 6305208458831.162, "dur": 7.108, + "args": { + "External id": 712154,"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": 6305208458835.509, "dur": 2.598, + "args": { + "External id": 712155,"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": 6305208458843.197, "dur": 2.786, + "args": { + "External id": 712156,"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": 6305208458845.097, "dur": 0.559, + "args": { + "External id": 712157,"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": 6305208458847.297, "dur": 3.149, + "args": { + "External id": 712158,"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": 6305208458848.390, "dur": 1.971, + "args": { + "External id": 712159,"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": 6305208458852.442, "dur": 70.272, + "args": { + "External id": 712160,"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": 6305208458925.031, "dur": 1.084, + "args": { + "External id": 712161,"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": 6305208458927.795, "dur": 5.761, + "args": { + "External id": 712162,"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": 6305208458929.801, "dur": 3.019, + "args": { + "External id": 712163,"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": 6305208458935.966, "dur": 1.021, + "args": { + "External id": 712164,"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": 6305208458991.043, "dur": 11.071, + "args": { + "External id": 712165,"Record function id": 0, "Ev Idx": 6116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208458993.311, "dur": 7.987, + "args": { + "External id": 712166,"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": 6305208458995.958, "dur": 4.304, + "args": { + "External id": 712167,"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": 6305208458997.204, "dur": 2.940, + "args": { + "External id": 712168,"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": 6305208459006.426, "dur": 7.979, + "args": { + "External id": 712169,"Record function id": 0, "Sequence number": 7674809, "Fwd thread id": 1, "Ev Idx": 6120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208459007.987, "dur": 4.000, + "args": { + "External id": 712170,"Sequence number": 7674809, "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": 6305208459007.987, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208459009.833, "dur": 1.930, + "args": { + "External id": 712171,"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": 6305208459010.821, "dur": 0.802, + "args": { + "External id": 712172,"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": 6305208459018.415, "dur": 202.662, + "args": { + "External id": 712173,"Record function id": 0, "Sequence number": 7674808, "Fwd thread id": 1, "Ev Idx": 6124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208459019.230, "dur": 192.315, + "args": { + "External id": 712174,"Sequence number": 7674808, "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": 6305208459019.230, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305208459022.952, "dur": 7.945, + "args": { + "External id": 712175,"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": 6305208459027.579, "dur": 2.744, + "args": { + "External id": 712176,"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": 6305208459029.447, "dur": 0.655, + "args": { + "External id": 712177,"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": 6305208459031.961, "dur": 109.418, + "args": { + "External id": 712178,"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": 6305208459144.154, "dur": 6.318, + "args": { + "External id": 712179,"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": 6305208459145.529, "dur": 3.978, + "args": { + "External id": 712180,"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": 6305208459148.012, "dur": 1.333, + "args": { + "External id": 712181,"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": 6305208459154.841, "dur": 3.804, + "args": { + "External id": 712182,"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": 6305208459155.861, "dur": 2.279, + "args": { + "External id": 712183,"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": 6305208459157.491, "dur": 0.526, + "args": { + "External id": 712184,"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": 6305208459159.257, "dur": 51.453, + "args": { + "External id": 712185,"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": 6305208459228.318, "dur": 11.325, + "args": { + "External id": 712186,"Record function id": 0, "Sequence number": 7674807, "Fwd thread id": 1, "Ev Idx": 6137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208459229.522, "dur": 8.585, + "args": { + "External id": 712187,"Sequence number": 7674807, "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": 6305208459229.522, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208459231.747, "dur": 6.200, + "args": { + "External id": 712188,"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": 6305208459233.271, "dur": 4.541, + "args": { + "External id": 712189,"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": 6305208459243.391, "dur": 90.927, + "args": { + "External id": 712190,"Record function id": 0, "Sequence number": 7674806, "Fwd thread id": 1, "Ev Idx": 6141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208459244.497, "dur": 86.977, + "args": { + "External id": 712191,"Sequence number": 7674806, "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": 6305208459244.497, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305208459247.491, "dur": 83.764, + "args": { + "External id": 712192,"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": 6305208459328.246, "dur": 2.412, + "args": { + "External id": 716801,"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": 6305208459329.954, "dur": 0.589, + "args": { + "External id": 716802,"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": 6305208459339.288, "dur": 7.257, + "args": { + "External id": 716803,"Record function id": 0, "Ev Idx": 6146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208459340.878, "dur": 5.056, + "args": { + "External id": 716804,"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": 6305208459342.598, "dur": 2.902, + "args": { + "External id": 716805,"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": 6305208459343.512, "dur": 1.893, + "args": { + "External id": 716806,"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": 6305208459350.254, "dur": 8.529, + "args": { + "External id": 716807,"Record function id": 0, "Sequence number": 7674805, "Fwd thread id": 1, "Ev Idx": 6150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208459351.474, "dur": 5.236, + "args": { + "External id": 716808,"Sequence number": 7674805, "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": 6305208459351.474, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208459352.255, "dur": 4.312, + "args": { + "External id": 716809,"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": 6305208459355.664, "dur": 0.762, + "args": { + "External id": 716810,"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": 6305208459362.218, "dur": 124.607, + "args": { + "External id": 716811,"Record function id": 0, "Sequence number": 7674804, "Fwd thread id": 1, "Ev Idx": 6154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208459362.995, "dur": 115.186, + "args": { + "External id": 716812,"Sequence number": 7674804, "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": 6305208459362.995, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305208459364.904, "dur": 2.634, + "args": { + "External id": 716813,"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": 6305208459365.327, "dur": 1.767, + "args": { + "External id": 716814,"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": 6305208459366.583, "dur": 0.376, + "args": { + "External id": 716815,"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": 6305208459368.198, "dur": 46.854, + "args": { + "External id": 716816,"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": 6305208459418.863, "dur": 3.402, + "args": { + "External id": 716817,"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": 6305208459419.374, "dur": 2.387, + "args": { + "External id": 716818,"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": 6305208459420.759, "dur": 0.853, + "args": { + "External id": 716819,"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": 6305208459423.410, "dur": 2.961, + "args": { + "External id": 716820,"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": 6305208459424.210, "dur": 1.623, + "args": { + "External id": 716821,"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": 6305208459425.309, "dur": 0.449, + "args": { + "External id": 716822,"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": 6305208459429.737, "dur": 47.678, + "args": { + "External id": 716823,"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": 6305208459491.721, "dur": 52.766, + "args": { + "External id": 716824,"Record function id": 0, "Sequence number": 7674803, "Fwd thread id": 1, "Ev Idx": 6167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208459492.877, "dur": 3.853, + "args": { + "External id": 716825,"Sequence number": 7674803, "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": 6305208459492.877, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208459494.558, "dur": 2.019, + "args": { + "External id": 716826,"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": 6305208459495.438, "dur": 1.004, + "args": { + "External id": 716827,"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": 6305208459500.199, "dur": 41.051, + "args": { + "External id": 716828,"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": 6305208459550.317, "dur": 12.450, + "args": { + "External id": 716829,"Record function id": 0, "Sequence number": 7674802, "Fwd thread id": 1, "Ev Idx": 6172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208459551.683, "dur": 8.360, + "args": { + "External id": 716830,"Sequence number": 7674802, "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": 6305208459551.683, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305208459552.797, "dur": 7.017, + "args": { + "External id": 716831,"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": 6305208459553.857, "dur": 5.231, + "args": { + "External id": 716832,"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": 6305208459558.166, "dur": 0.842, + "args": { + "External id": 716833,"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": 6305208459567.076, "dur": 6.773, + "args": { + "External id": 716834,"Record function id": 0, "Ev Idx": 6177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208459569.259, "dur": 4.047, + "args": { + "External id": 716835,"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": 6305208459570.707, "dur": 2.059, + "args": { + "External id": 716836,"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": 6305208459571.222, "dur": 1.407, + "args": { + "External id": 716837,"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": 6305208459578.498, "dur": 448.335, + "args": { + "External id": 716838,"Record function id": 0, "Sequence number": 7674801, "Fwd thread id": 1, "Ev Idx": 6181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305208459580.056, "dur": 433.077, + "args": { + "External id": 716839,"Sequence number": 7674801, "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": 6305208459580.056, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338707, "tid": 2379456, + "ts": 6305208459608.135, "dur": 38.797, + "args": { + "External id": 716840,"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": 6305208459609.697, "dur": 37.022, + "args": { + "External id": 716841,"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": 6305208459612.819, "dur": 7.055, + "args": { + "External id": 716842,"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": 6305208459615.498, "dur": 3.823, + "args": { + "External id": 716843,"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": 6305208459621.314, "dur": 24.749, + "args": { + "External id": 716844,"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": 6305208459659.978, "dur": 5.105, + "args": { + "External id": 716845,"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": 6305208459663.551, "dur": 1.398, + "args": { + "External id": 716846,"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": 6305208459669.379, "dur": 1.718, + "args": { + "External id": 716847,"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": 6305208459670.352, "dur": 0.656, + "args": { + "External id": 716848,"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": 6305208459684.632, "dur": 5.049, + "args": { + "External id": 716849,"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": 6305208459701.321, "dur": 2.303, + "args": { + "External id": 716850,"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": 6305208459892.242, "dur": 1.994, + "args": { + "External id": 716851,"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": 6305208459898.773, "dur": 41.212, + "args": { + "External id": 716852,"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": 6305208459914.073, "dur": 0.820, + "args": { + "External id": 716853,"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": 6305208459945.941, "dur": 32.954, + "args": { + "External id": 716854,"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": 6305208459947.772, "dur": 30.869, + "args": { + "External id": 716855,"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": 6305208459952.693, "dur": 4.661, + "args": { + "External id": 716856,"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": 6305208459958.805, "dur": 19.356, + "args": { + "External id": 716857,"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": 6305208459983.533, "dur": 5.256, + "args": { + "External id": 716858,"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": 6305208459987.552, "dur": 1.100, + "args": { + "External id": 716859,"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": 6305208459996.401, "dur": 2.512, + "args": { + "External id": 716860,"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": 6305208459997.659, "dur": 1.164, + "args": { + "External id": 716861,"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": 6305208460001.852, "dur": 2.614, + "args": { + "External id": 716862,"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": 6305208460003.283, "dur": 1.095, + "args": { + "External id": 716863,"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": 6305208460037.274, "dur": 10.435, + "args": { + "External id": 716864,"Record function id": 0, "Ev Idx": 6207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208460039.632, "dur": 7.430, + "args": { + "External id": 716865,"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": 6305208460041.343, "dur": 4.770, + "args": { + "External id": 716866,"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": 6305208460044.507, "dur": 1.492, + "args": { + "External id": 716867,"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": 6305208460086.747, "dur": 12.432, + "args": { + "External id": 716868,"Record function id": 0, "Sequence number": 7674800, "Fwd thread id": 1, "Ev Idx": 6211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208460089.710, "dur": 5.720, + "args": { + "External id": 716869,"Sequence number": 7674800, "Fwd thread 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": 6305208460089.710, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208460091.971, "dur": 3.239, + "args": { + "External id": 716870,"Record 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": 6305208460092.951, "dur": 2.022, + "args": { + "External id": 716871,"Record 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": 6305208460104.672, "dur": 182.194, + "args": { + "External id": 716872,"Record function id": 0, "Sequence number": 7674799, "Fwd thread id": 1, "Ev Idx": 6215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208460105.789, "dur": 176.123, + "args": { + "External id": 716873,"Sequence number": 7674799, "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": 6305208460105.789, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305208460109.277, "dur": 7.785, + "args": { + "External id": 716874,"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": 6305208460113.023, "dur": 3.375, + "args": { + "External id": 716875,"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": 6305208460115.220, "dur": 0.914, + "args": { + "External id": 716876,"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": 6305208460118.380, "dur": 89.000, + "args": { + "External id": 716877,"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": 6305208460208.834, "dur": 8.196, + "args": { + "External id": 716878,"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": 6305208460209.769, "dur": 6.624, + "args": { + "External id": 716879,"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": 6305208460215.441, "dur": 0.831, + "args": { + "External id": 716880,"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": 6305208460218.670, "dur": 8.571, + "args": { + "External id": 716881,"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": 6305208460222.261, "dur": 4.525, + "args": { + "External id": 716882,"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": 6305208460223.710, "dur": 2.949, + "args": { + "External id": 716883,"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": 6305208460228.128, "dur": 52.831, + "args": { + "External id": 716884,"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": 6305208460291.932, "dur": 7.074, + "args": { + "External id": 716885,"Record function id": 0, "Sequence number": 7674798, "Fwd thread id": 1, "Ev Idx": 6228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208460293.137, "dur": 3.966, + "args": { + "External id": 716886,"Sequence number": 7674798, "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": 6305208460293.137, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208460294.816, "dur": 2.141, + "args": { + "External id": 716887,"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": 6305208460295.741, "dur": 1.093, + "args": { + "External id": 716888,"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": 6305208460302.314, "dur": 9.953, + "args": { + "External id": 716889,"Record function id": 0, "Sequence number": 7674797, "Fwd thread id": 1, "Ev Idx": 6232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208460303.171, "dur": 6.969, + "args": { + "External id": 716890,"Sequence number": 7674797, "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": 6305208460303.171, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305208460304.170, "dur": 5.772, + "args": { + "External id": 716891,"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": 6305208460307.295, "dur": 2.166, + "args": { + "External id": 716892,"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": 6305208460308.777, "dur": 0.564, + "args": { + "External id": 716893,"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": 6305208460316.637, "dur": 7.342, + "args": { + "External id": 716894,"Record function id": 0, "Ev Idx": 6237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208460318.510, "dur": 4.913, + "args": { + "External id": 716895,"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": 6305208460320.311, "dur": 2.746, + "args": { + "External id": 716896,"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": 6305208460321.328, "dur": 1.633, + "args": { + "External id": 716897,"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": 6305208460327.354, "dur": 6.687, + "args": { + "External id": 716898,"Record function id": 0, "Sequence number": 7674796, "Fwd thread id": 1, "Ev Idx": 6241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208460328.396, "dur": 4.165, + "args": { + "External id": 716899,"Sequence number": 7674796, "Fwd thread 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": 6305208460328.396, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208460329.692, "dur": 2.707, + "args": { + "External id": 716900,"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": 6305208460331.074, "dur": 1.231, + "args": { + "External id": 716901,"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": 6305208460339.577, "dur": 434.505, + "args": { + "External id": 716902,"Record function id": 0, "Sequence number": 7674795, "Fwd thread id": 1, "Ev Idx": 6245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFuncBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305208460340.954, "dur": 413.175, + "args": { + "External id": 716903,"Sequence number": 7674795, "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": 6305208460340.954, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338707, "tid": 2379456, + "ts": 6305208460358.857, "dur": 8.449, + "args": { + "External id": 716904,"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": 6305208460362.291, "dur": 4.330, + "args": { + "External id": 716905,"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": 6305208460369.517, "dur": 4.229, + "args": { + "External id": 716906,"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": 6305208460371.516, "dur": 2.055, + "args": { + "External id": 716907,"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": 6305208460375.208, "dur": 7.086, + "args": { + "External id": 716908,"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": 6305208460376.769, "dur": 5.361, + "args": { + "External id": 716909,"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": 6305208460419.746, "dur": 308.243, + "args": { + "External id": 716910,"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": 6305208460534.719, "dur": 7.854, + "args": { + "External id": 716911,"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": 6305208460544.941, "dur": 2.747, + "args": { + "External id": 716912,"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": 6305208460549.124, "dur": 2.741, + "args": { + "External id": 716913,"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": 6305208460553.188, "dur": 3.274, + "args": { + "External id": 716914,"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": 6305208460618.519, "dur": 5.682, + "args": { + "External id": 716915,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305208460622.175, "dur": 1.911, + "args": { + "External id": 716916,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305208460626.406, "dur": 30.955, + "args": { + "External id": 716917,"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": 6305208460632.124, "dur": 1.184, + "args": { + "External id": 716918,"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": 6305208460659.140, "dur": 2.395, + "args": { + "External id": 716919,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305208460661.021, "dur": 0.429, + "args": { + "External id": 716920,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305208460662.504, "dur": 20.200, + "args": { + "External id": 716921,"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": 6305208460669.025, "dur": 0.458, + "args": { + "External id": 716922,"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": 6305208460741.185, "dur": 4.066, + "args": { + "External id": 716923,"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": 6305208460748.561, "dur": 0.558, + "args": { + "External id": 716924,"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": 6305208460750.851, "dur": 0.662, + "args": { + "External id": 716925,"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": 6305208460784.834, "dur": 239.943, + "args": { + "External id": 716926,"Record function id": 0, "Sequence number": 7674794, "Fwd thread id": 1, "Ev Idx": 6269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305208460786.542, "dur": 231.934, + "args": { + "External id": 716927,"Sequence number": 7674794, "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": 6305208460786.542, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338707, "tid": 2379456, + "ts": 6305208460807.964, "dur": 49.846, + "args": { + "External id": 716928,"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": 6305208460812.657, "dur": 2.964, + "args": { + "External id": 716929,"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": 6305208460817.264, "dur": 39.943, + "args": { + "External id": 716930,"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": 6305208460868.685, "dur": 5.104, + "args": { + "External id": 716931,"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": 6305208460871.332, "dur": 2.103, + "args": { + "External id": 716932,"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": 6305208461032.218, "dur": 235.906, + "args": { + "External id": 716933,"Record function id": 0, "Sequence number": 7674793, "Fwd thread id": 1, "Ev Idx": 6276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305208461034.340, "dur": 225.648, + "args": { + "External id": 716934,"Sequence number": 7674793, "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": 6305208461034.340, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338707, "tid": 2379456, + "ts": 6305208461045.193, "dur": 94.395, + "args": { + "External id": 716935,"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": 6305208461048.183, "dur": 3.003, + "args": { + "External id": 716936,"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": 6305208461089.412, "dur": 49.374, + "args": { + "External id": 716937,"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": 6305208461148.568, "dur": 6.718, + "args": { + "External id": 716938,"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": 6305208461151.022, "dur": 3.935, + "args": { + "External id": 716939,"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": 6305208461276.922, "dur": 13.660, + "args": { + "External id": 716940,"Record function id": 0, "Sequence number": 7674792, "Fwd thread id": 1, "Ev Idx": 6283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208461278.351, "dur": 9.753, + "args": { + "External id": 716941,"Sequence number": 7674792, "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": 6305208461278.351, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208461280.973, "dur": 6.800, + "args": { + "External id": 716942,"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": 6305208461282.657, "dur": 4.867, + "args": { + "External id": 716943,"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": 6305208461294.232, "dur": 9.483, + "args": { + "External id": 716944,"Record function id": 0, "Sequence number": 7674791, "Fwd thread id": 1, "Ev Idx": 6287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208461298.561, "dur": 3.363, + "args": { + "External id": 716945,"Sequence number": 7674791, "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": 6305208461298.561, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208461299.882, "dur": 1.917, + "args": { + "External id": 716946,"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": 6305208461300.860, "dur": 0.823, + "args": { + "External id": 716947,"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": 6305208461307.359, "dur": 10.647, + "args": { + "External id": 716948,"Record function id": 0, "Sequence number": 7674790, "Fwd thread id": 1, "Ev Idx": 6291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208461313.222, "dur": 3.453, + "args": { + "External id": 716949,"Sequence number": 7674790, "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": 6305208461313.222, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208461314.806, "dur": 1.718, + "args": { + "External id": 716950,"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": 6305208461315.564, "dur": 0.870, + "args": { + "External id": 716951,"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": 6305208461321.802, "dur": 12.164, + "args": { + "External id": 716952,"Record function id": 0, "Sequence number": 7674789, "Fwd thread id": 1, "Ev Idx": 6295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208461322.916, "dur": 9.075, + "args": { + "External id": 716953,"Sequence number": 7674789, "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": 6305208461322.916, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208461324.051, "dur": 7.782, + "args": { + "External id": 716954,"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": 6305208461328.141, "dur": 3.567, + "args": { + "External id": 716955,"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": 6305208461337.663, "dur": 159.909, + "args": { + "External id": 716956,"Record function id": 0, "Sequence number": 7674788, "Fwd thread id": 1, "Ev Idx": 6299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208461338.567, "dur": 152.398, + "args": { + "External id": 716957,"Sequence number": 7674788, "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": 6305208461338.567, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305208461342.262, "dur": 6.836, + "args": { + "External id": 716958,"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": 6305208461344.153, "dur": 4.238, + "args": { + "External id": 716959,"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": 6305208461346.424, "dur": 1.717, + "args": { + "External id": 716960,"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": 6305208461350.853, "dur": 75.649, + "args": { + "External id": 716961,"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": 6305208461430.852, "dur": 4.266, + "args": { + "External id": 716962,"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": 6305208461431.638, "dur": 2.856, + "args": { + "External id": 716963,"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": 6305208461433.358, "dur": 1.018, + "args": { + "External id": 716964,"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": 6305208461436.938, "dur": 3.495, + "args": { + "External id": 716965,"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": 6305208461437.908, "dur": 2.096, + "args": { + "External id": 716966,"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": 6305208461439.355, "dur": 0.539, + "args": { + "External id": 716967,"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": 6305208461443.691, "dur": 46.377, + "args": { + "External id": 716968,"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": 6305208461503.112, "dur": 24.972, + "args": { + "External id": 716969,"Record function id": 0, "Sequence number": 7674787, "Fwd thread id": 1, "Ev Idx": 6312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208461504.065, "dur": 21.803, + "args": { + "External id": 716970,"Sequence number": 7674787, "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": 6305208461504.065, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208461522.274, "dur": 3.410, + "args": { + "External id": 716971,"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": 6305208461523.353, "dur": 2.081, + "args": { + "External id": 716972,"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": 6305208461532.959, "dur": 11.125, + "args": { + "External id": 716973,"Record function id": 0, "Sequence number": 7674786, "Fwd thread id": 1, "Ev Idx": 6316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208461534.000, "dur": 7.663, + "args": { + "External id": 716974,"Sequence number": 7674786, "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": 6305208461534.000, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305208461535.082, "dur": 6.428, + "args": { + "External id": 716975,"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": 6305208461535.960, "dur": 4.998, + "args": { + "External id": 716976,"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": 6305208461540.194, "dur": 0.641, + "args": { + "External id": 716977,"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": 6305208461549.943, "dur": 12.411, + "args": { + "External id": 716978,"Record function id": 0, "Ev Idx": 6321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208461551.759, "dur": 9.771, + "args": { + "External id": 716979,"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": 6305208461554.644, "dur": 6.462, + "args": { + "External id": 716980,"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": 6305208461555.857, "dur": 5.138, + "args": { + "External id": 716981,"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": 6305208461565.963, "dur": 6.401, + "args": { + "External id": 716982,"Record function id": 0, "Sequence number": 7674785, "Fwd thread id": 1, "Ev Idx": 6325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208461567.482, "dur": 3.060, + "args": { + "External id": 716983,"Sequence number": 7674785, "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": 6305208461567.482, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208461568.580, "dur": 1.819, + "args": { + "External id": 716984,"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": 6305208461569.415, "dur": 0.869, + "args": { + "External id": 716985,"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": 6305208461575.765, "dur": 109.860, + "args": { + "External id": 716986,"Record function id": 0, "Sequence number": 7674784, "Fwd thread id": 1, "Ev Idx": 6329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208461579.194, "dur": 99.760, + "args": { + "External id": 716987,"Sequence number": 7674784, "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": 6305208461579.194, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305208461581.790, "dur": 3.421, + "args": { + "External id": 716988,"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": 6305208461582.445, "dur": 2.299, + "args": { + "External id": 716989,"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": 6305208461583.948, "dur": 0.691, + "args": { + "External id": 716990,"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": 6305208461585.935, "dur": 33.750, + "args": { + "External id": 716991,"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": 6305208461620.819, "dur": 12.336, + "args": { + "External id": 716992,"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": 6305208461621.532, "dur": 11.089, + "args": { + "External id": 716993,"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": 6305208461628.197, "dur": 4.267, + "args": { + "External id": 716994,"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": 6305208461634.544, "dur": 3.754, + "args": { + "External id": 716995,"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": 6305208461635.437, "dur": 2.394, + "args": { + "External id": 716996,"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": 6305208461637.213, "dur": 0.522, + "args": { + "External id": 716997,"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": 6305208461638.905, "dur": 39.207, + "args": { + "External id": 716998,"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": 6305208461690.606, "dur": 38.205, + "args": { + "External id": 716999,"Record function id": 0, "Sequence number": 7674783, "Fwd thread id": 1, "Ev Idx": 6342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208461691.708, "dur": 6.919, + "args": { + "External id": 717000,"Sequence number": 7674783, "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": 6305208461691.708, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208461693.645, "dur": 4.843, + "args": { + "External id": 717001,"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": 6305208461697.085, "dur": 1.263, + "args": { + "External id": 717002,"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": 6305208461702.179, "dur": 24.059, + "args": { + "External id": 717003,"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": 6305208461732.586, "dur": 7.672, + "args": { + "External id": 717004,"Record function id": 0, "Sequence number": 7674782, "Fwd thread id": 1, "Ev Idx": 6347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208461733.601, "dur": 4.743, + "args": { + "External id": 717005,"Sequence number": 7674782, "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": 6305208461733.601, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305208461734.277, "dur": 3.867, + "args": { + "External id": 717006,"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": 6305208461734.958, "dur": 2.500, + "args": { + "External id": 717007,"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": 6305208461736.871, "dur": 0.465, + "args": { + "External id": 717008,"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": 6305208461744.340, "dur": 7.694, + "args": { + "External id": 717009,"Record function id": 0, "Ev Idx": 6352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208461745.621, "dur": 5.894, + "args": { + "External id": 717010,"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": 6305208461746.809, "dur": 4.392, + "args": { + "External id": 717011,"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": 6305208461749.963, "dur": 1.135, + "args": { + "External id": 717012,"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": 6305208461755.692, "dur": 6.852, + "args": { + "External id": 717013,"Record function id": 0, "Sequence number": 7674781, "Fwd thread id": 1, "Ev Idx": 6356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208461757.058, "dur": 2.903, + "args": { + "External id": 717014,"Sequence number": 7674781, "Fwd thread 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": 6305208461757.058, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208461758.120, "dur": 1.682, + "args": { + "External id": 717015,"Record 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": 6305208461758.935, "dur": 0.762, + "args": { + "External id": 717016,"Record 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": 6305208461765.970, "dur": 100.923, + "args": { + "External id": 717017,"Record function id": 0, "Sequence number": 7674780, "Fwd thread id": 1, "Ev Idx": 6360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208461766.675, "dur": 92.380, + "args": { + "External id": 717018,"Sequence number": 7674780, "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": 6305208461766.675, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305208461769.066, "dur": 5.748, + "args": { + "External id": 717019,"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": 6305208461772.381, "dur": 1.998, + "args": { + "External id": 717020,"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": 6305208461773.764, "dur": 0.505, + "args": { + "External id": 717021,"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": 6305208461775.432, "dur": 35.445, + "args": { + "External id": 717022,"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": 6305208461811.998, "dur": 3.781, + "args": { + "External id": 717023,"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": 6305208461812.651, "dur": 2.498, + "args": { + "External id": 717024,"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": 6305208461814.063, "dur": 0.965, + "args": { + "External id": 717025,"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": 6305208461816.869, "dur": 5.723, + "args": { + "External id": 717026,"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": 6305208461820.146, "dur": 1.933, + "args": { + "External id": 717027,"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": 6305208461821.560, "dur": 0.392, + "args": { + "External id": 717028,"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": 6305208461823.072, "dur": 35.320, + "args": { + "External id": 717029,"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": 6305208461872.077, "dur": 23.864, + "args": { + "External id": 717030,"Record function id": 0, "Sequence number": 7674779, "Fwd thread id": 1, "Ev Idx": 6373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208461873.059, "dur": 4.276, + "args": { + "External id": 717031,"Sequence number": 7674779, "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": 6305208461873.059, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208461874.796, "dur": 2.393, + "args": { + "External id": 717032,"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": 6305208461875.980, "dur": 1.066, + "args": { + "External id": 717033,"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": 6305208461879.755, "dur": 14.213, + "args": { + "External id": 717034,"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": 6305208461899.578, "dur": 11.261, + "args": { + "External id": 717035,"Record function id": 0, "Sequence number": 7674778, "Fwd thread id": 1, "Ev Idx": 6378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208461903.538, "dur": 5.249, + "args": { + "External id": 717036,"Sequence number": 7674778, "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": 6305208461903.538, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305208461904.406, "dur": 4.186, + "args": { + "External id": 717037,"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": 6305208461905.273, "dur": 2.714, + "args": { + "External id": 717038,"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": 6305208461907.241, "dur": 0.626, + "args": { + "External id": 717039,"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": 6305208461914.838, "dur": 5.260, + "args": { + "External id": 717040,"Record function id": 0, "Ev Idx": 6383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208461916.586, "dur": 3.052, + "args": { + "External id": 717041,"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": 6305208461917.399, "dur": 1.829, + "args": { + "External id": 717042,"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": 6305208461917.831, "dur": 1.322, + "args": { + "External id": 717043,"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": 6305208461924.456, "dur": 433.986, + "args": { + "External id": 717044,"Record function id": 0, "Sequence number": 7674777, "Fwd thread id": 1, "Ev Idx": 6387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305208461926.224, "dur": 395.610, + "args": { + "External id": 717045,"Sequence number": 7674777, "Fwd thread 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": 6305208461926.224, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208461959.142, "dur": 4.128, + "args": { + "External id": 717046,"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": 6305208461962.136, "dur": 0.988, + "args": { + "External id": 717047,"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": 6305208461977.529, "dur": 4.131, + "args": { + "External id": 717048,"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": 6305208461994.128, "dur": 2.012, + "args": { + "External id": 717049,"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": 6305208462198.800, "dur": 3.386, + "args": { + "External id": 717050,"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": 6305208462206.794, "dur": 45.841, + "args": { + "External id": 717051,"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": 6305208462221.980, "dur": 3.260, + "args": { + "External id": 717052,"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": 6305208462259.271, "dur": 36.818, + "args": { + "External id": 717053,"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": 6305208462263.968, "dur": 31.879, + "args": { + "External id": 717054,"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": 6305208462268.711, "dur": 5.197, + "args": { + "External id": 717055,"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": 6305208462275.532, "dur": 19.716, + "args": { + "External id": 717056,"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": 6305208462301.390, "dur": 2.700, + "args": { + "External id": 717057,"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": 6305208462302.767, "dur": 1.196, + "args": { + "External id": 717058,"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": 6305208462311.744, "dur": 2.383, + "args": { + "External id": 717059,"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": 6305208462312.958, "dur": 0.995, + "args": { + "External id": 717060,"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": 6305208462334.155, "dur": 17.136, + "args": { + "External id": 717061,"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": 6305208462372.100, "dur": 12.786, + "args": { + "External id": 717062,"Record function id": 0, "Ev Idx": 6405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208462374.689, "dur": 9.332, + "args": { + "External id": 717063,"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": 6305208462377.143, "dur": 5.845, + "args": { + "External id": 717064,"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": 6305208462380.799, "dur": 2.056, + "args": { + "External id": 717065,"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": 6305208462389.124, "dur": 6.721, + "args": { + "External id": 717066,"Record function id": 0, "Sequence number": 7674776, "Fwd thread id": 1, "Ev Idx": 6409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208462390.558, "dur": 1.660, + "args": { + "External id": 717067,"Sequence number": 7674776, "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": 6305208462390.558, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SwiGLULinearFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305208462399.623, "dur": 468.879, + "args": { + "External id": 717068,"Record function id": 0, "Sequence number": 7674775, "Fwd thread id": 1, "Ev Idx": 6411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305208462401.121, "dur": 455.879, + "args": { + "External id": 717069,"Sequence number": 7674775, "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": 6305208462401.121, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208462433.976, "dur": 9.414, + "args": { + "External id": 717070,"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": 6305208462439.536, "dur": 3.532, + "args": { + "External id": 717071,"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": 6305208462446.544, "dur": 8.135, + "args": { + "External id": 717072,"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": 6305208462450.758, "dur": 3.047, + "args": { + "External id": 717073,"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": 6305208462452.718, "dur": 0.877, + "args": { + "External id": 717074,"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": 6305208462458.434, "dur": 118.941, + "args": { + "External id": 717075,"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": 6305208462459.278, "dur": 3.466, + "args": { + "External id": 717076,"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": 6305208462459.913, "dur": 2.348, + "args": { + "External id": 717077,"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": 6305208462461.567, "dur": 0.601, + "args": { + "External id": 717078,"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": 6305208462466.419, "dur": 110.301, + "args": { + "External id": 717079,"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": 6305208462467.936, "dur": 107.327, + "args": { + "External id": 717080,"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": 6305208462582.943, "dur": 4.225, + "args": { + "External id": 717081,"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": 6305208462585.053, "dur": 1.991, + "args": { + "External id": 717082,"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": 6305208462621.618, "dur": 7.115, + "args": { + "External id": 717083,"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": 6305208462629.880, "dur": 2.898, + "args": { + "External id": 717084,"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": 6305208462633.937, "dur": 2.290, + "args": { + "External id": 717085,"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": 6305208462678.298, "dur": 2.222, + "args": { + "External id": 717086,"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": 6305208462679.278, "dur": 1.093, + "args": { + "External id": 717087,"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": 6305208462703.915, "dur": 133.987, + "args": { + "External id": 717088,"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": 6305208462709.918, "dur": 6.275, + "args": { + "External id": 717089,"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": 6305208462714.329, "dur": 1.037, + "args": { + "External id": 717090,"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": 6305208462717.977, "dur": 7.994, + "args": { + "External id": 717091,"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": 6305208462724.678, "dur": 0.424, + "args": { + "External id": 717092,"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": 6305208462727.400, "dur": 2.628, + "args": { + "External id": 717093,"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": 6305208462729.350, "dur": 0.321, + "args": { + "External id": 717094,"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": 6305208462730.927, "dur": 3.555, + "args": { + "External id": 717095,"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": 6305208462733.275, "dur": 0.467, + "args": { + "External id": 717096,"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": 6305208462741.415, "dur": 5.394, + "args": { + "External id": 717097,"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": 6305208462743.616, "dur": 2.873, + "args": { + "External id": 717098,"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": 6305208462748.369, "dur": 6.502, + "args": { + "External id": 717099,"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": 6305208462752.259, "dur": 2.399, + "args": { + "External id": 717100,"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": 6305208462756.101, "dur": 2.903, + "args": { + "External id": 717101,"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": 6305208462758.207, "dur": 0.455, + "args": { + "External id": 717102,"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": 6305208462760.019, "dur": 2.645, + "args": { + "External id": 717103,"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": 6305208462761.130, "dur": 1.450, + "args": { + "External id": 717104,"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": 6305208462763.991, "dur": 59.490, + "args": { + "External id": 717105,"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": 6305208462828.601, "dur": 0.743, + "args": { + "External id": 717106,"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": 6305208462830.209, "dur": 3.517, + "args": { + "External id": 717107,"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": 6305208462832.438, "dur": 0.760, + "args": { + "External id": 717108,"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": 6305208462835.939, "dur": 0.957, + "args": { + "External id": 717109,"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": 6305208462880.924, "dur": 9.545, + "args": { + "External id": 717110,"Record function id": 0, "Ev Idx": 6453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208462883.053, "dur": 6.631, + "args": { + "External id": 717111,"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": 6305208462885.181, "dur": 3.289, + "args": { + "External id": 717112,"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": 6305208462886.200, "dur": 2.123, + "args": { + "External id": 717113,"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": 6305208462894.557, "dur": 9.780, + "args": { + "External id": 717114,"Record function id": 0, "Sequence number": 7674774, "Fwd thread id": 1, "Ev Idx": 6457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208462895.818, "dur": 6.331, + "args": { + "External id": 717115,"Sequence number": 7674774, "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": 6305208462895.818, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208462897.600, "dur": 4.303, + "args": { + "External id": 717116,"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": 6305208462900.808, "dur": 0.962, + "args": { + "External id": 717117,"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": 6305208462907.878, "dur": 114.300, + "args": { + "External id": 717118,"Record function id": 0, "Sequence number": 7674773, "Fwd thread id": 1, "Ev Idx": 6461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208462908.727, "dur": 106.166, + "args": { + "External id": 717119,"Sequence number": 7674773, "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": 6305208462908.727, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305208462912.108, "dur": 4.401, + "args": { + "External id": 717120,"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": 6305208462913.587, "dur": 2.328, + "args": { + "External id": 717121,"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": 6305208462915.179, "dur": 0.565, + "args": { + "External id": 717122,"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": 6305208462920.200, "dur": 42.766, + "args": { + "External id": 717123,"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": 6305208462964.281, "dur": 4.108, + "args": { + "External id": 717124,"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": 6305208462964.980, "dur": 2.750, + "args": { + "External id": 717125,"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": 6305208462966.526, "dur": 1.039, + "args": { + "External id": 717126,"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": 6305208462969.918, "dur": 8.462, + "args": { + "External id": 717127,"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": 6305208462970.816, "dur": 7.097, + "args": { + "External id": 717128,"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": 6305208462975.059, "dur": 2.789, + "args": { + "External id": 717129,"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": 6305208462978.976, "dur": 35.007, + "args": { + "External id": 717130,"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": 6305208463027.243, "dur": 6.824, + "args": { + "External id": 717131,"Record function id": 0, "Sequence number": 7674772, "Fwd thread id": 1, "Ev Idx": 6474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208463028.286, "dur": 4.317, + "args": { + "External id": 717132,"Sequence number": 7674772, "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": 6305208463028.286, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208463030.016, "dur": 2.431, + "args": { + "External id": 717133,"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": 6305208463031.353, "dur": 0.958, + "args": { + "External id": 717134,"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": 6305208463037.336, "dur": 9.866, + "args": { + "External id": 717135,"Record function id": 0, "Sequence number": 7674771, "Fwd thread id": 1, "Ev Idx": 6478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208463038.291, "dur": 6.679, + "args": { + "External id": 717136,"Sequence number": 7674771, "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": 6305208463038.291, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305208463039.160, "dur": 5.596, + "args": { + "External id": 717137,"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": 6305208463039.804, "dur": 4.458, + "args": { + "External id": 717138,"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": 6305208463043.654, "dur": 0.526, + "args": { + "External id": 717139,"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": 6305208463051.434, "dur": 43.928, + "args": { + "External id": 717140,"Record function id": 0, "Ev Idx": 6483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208463052.793, "dur": 41.080, + "args": { + "External id": 717141,"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": 6305208463053.840, "dur": 39.343, + "args": { + "External id": 717142,"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": 6305208463054.496, "dur": 38.102, + "args": { + "External id": 717143,"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": 6305208463101.338, "dur": 7.846, + "args": { + "External id": 717144,"Record function id": 0, "Sequence number": 7674770, "Fwd thread id": 1, "Ev Idx": 6487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208463103.021, "dur": 3.867, + "args": { + "External id": 717145,"Sequence number": 7674770, "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": 6305208463103.021, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208463104.382, "dur": 2.318, + "args": { + "External id": 717146,"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": 6305208463105.315, "dur": 1.269, + "args": { + "External id": 717147,"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": 6305208463112.557, "dur": 113.419, + "args": { + "External id": 717148,"Record function id": 0, "Sequence number": 7674769, "Fwd thread id": 1, "Ev Idx": 6491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208463116.329, "dur": 99.446, + "args": { + "External id": 717149,"Sequence number": 7674769, "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": 6305208463116.329, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305208463118.578, "dur": 3.451, + "args": { + "External id": 717150,"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": 6305208463119.418, "dur": 2.140, + "args": { + "External id": 717151,"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": 6305208463120.770, "dur": 0.686, + "args": { + "External id": 717152,"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": 6305208463122.747, "dur": 42.095, + "args": { + "External id": 717153,"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": 6305208463165.881, "dur": 8.917, + "args": { + "External id": 717154,"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": 6305208463166.743, "dur": 7.386, + "args": { + "External id": 717155,"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": 6305208463170.649, "dur": 3.324, + "args": { + "External id": 717156,"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": 6305208463176.013, "dur": 3.910, + "args": { + "External id": 717157,"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": 6305208463177.255, "dur": 2.068, + "args": { + "External id": 717158,"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": 6305208463178.709, "dur": 0.540, + "args": { + "External id": 717159,"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": 6305208463180.542, "dur": 34.376, + "args": { + "External id": 717160,"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": 6305208463230.695, "dur": 33.328, + "args": { + "External id": 717161,"Record function id": 0, "Sequence number": 7674768, "Fwd thread id": 1, "Ev Idx": 6504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208463231.700, "dur": 6.516, + "args": { + "External id": 717162,"Sequence number": 7674768, "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": 6305208463231.700, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208463235.843, "dur": 2.237, + "args": { + "External id": 717163,"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": 6305208463236.769, "dur": 1.191, + "args": { + "External id": 717164,"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": 6305208463240.976, "dur": 20.188, + "args": { + "External id": 717165,"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": 6305208463267.958, "dur": 7.767, + "args": { + "External id": 717166,"Record function id": 0, "Sequence number": 7674767, "Fwd thread id": 1, "Ev Idx": 6509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208463268.891, "dur": 4.765, + "args": { + "External id": 717167,"Sequence number": 7674767, "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": 6305208463268.891, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305208463269.846, "dur": 3.634, + "args": { + "External id": 717168,"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": 6305208463270.692, "dur": 2.176, + "args": { + "External id": 717169,"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": 6305208463272.309, "dur": 0.429, + "args": { + "External id": 717170,"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": 6305208463279.996, "dur": 8.508, + "args": { + "External id": 717171,"Record function id": 0, "Ev Idx": 6514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208463281.390, "dur": 6.553, + "args": { + "External id": 717172,"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": 6305208463282.638, "dur": 4.825, + "args": { + "External id": 717173,"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": 6305208463286.080, "dur": 1.278, + "args": { + "External id": 717174,"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": 6305208463292.615, "dur": 441.978, + "args": { + "External id": 717175,"Record function id": 0, "Sequence number": 7674766, "Fwd thread id": 1, "Ev Idx": 6518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305208463294.541, "dur": 405.293, + "args": { + "External id": 717176,"Sequence number": 7674766, "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": 6305208463294.541, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338707, "tid": 2379456, + "ts": 6305208463318.659, "dur": 34.328, + "args": { + "External id": 717177,"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": 6305208463320.211, "dur": 32.568, + "args": { + "External id": 717178,"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": 6305208463323.258, "dur": 5.971, + "args": { + "External id": 717179,"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": 6305208463325.877, "dur": 2.825, + "args": { + "External id": 717180,"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": 6305208463330.876, "dur": 21.392, + "args": { + "External id": 717181,"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": 6305208463363.567, "dur": 5.031, + "args": { + "External id": 717182,"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": 6305208463364.593, "dur": 3.863, + "args": { + "External id": 717183,"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": 6305208463372.300, "dur": 3.993, + "args": { + "External id": 717184,"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": 6305208463375.433, "dur": 0.776, + "args": { + "External id": 717185,"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": 6305208463388.707, "dur": 2.854, + "args": { + "External id": 717186,"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": 6305208463402.511, "dur": 1.903, + "args": { + "External id": 717187,"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": 6305208463584.430, "dur": 5.516, + "args": { + "External id": 717188,"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": 6305208463594.217, "dur": 34.415, + "args": { + "External id": 717189,"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": 6305208463605.489, "dur": 1.103, + "args": { + "External id": 717190,"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": 6305208463637.432, "dur": 26.843, + "args": { + "External id": 717191,"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": 6305208463639.474, "dur": 24.607, + "args": { + "External id": 717192,"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": 6305208463643.718, "dur": 4.080, + "args": { + "External id": 717193,"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": 6305208463649.272, "dur": 14.260, + "args": { + "External id": 717194,"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": 6305208463668.590, "dur": 3.070, + "args": { + "External id": 717195,"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": 6305208463670.328, "dur": 1.199, + "args": { + "External id": 717196,"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": 6305208463678.898, "dur": 4.727, + "args": { + "External id": 717197,"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": 6305208463682.477, "dur": 1.000, + "args": { + "External id": 717198,"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": 6305208463685.663, "dur": 4.453, + "args": { + "External id": 717199,"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": 6305208463686.731, "dur": 3.302, + "args": { + "External id": 717200,"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": 6305208463715.883, "dur": 17.144, + "args": { + "External id": 717201,"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": 6305208463747.927, "dur": 11.772, + "args": { + "External id": 717202,"Record function id": 0, "Ev Idx": 6545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208463750.447, "dur": 8.609, + "args": { + "External id": 717203,"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": 6305208463752.481, "dur": 5.762, + "args": { + "External id": 717204,"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": 6305208463755.933, "dur": 2.080, + "args": { + "External id": 717205,"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": 6305208463763.376, "dur": 8.490, + "args": { + "External id": 717206,"Record function id": 0, "Sequence number": 7674765, "Fwd thread id": 1, "Ev Idx": 6549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208463764.514, "dur": 4.315, + "args": { + "External id": 717207,"Sequence number": 7674765, "Fwd thread 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": 6305208463764.514, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208463766.416, "dur": 2.167, + "args": { + "External id": 717208,"Record 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": 6305208463767.299, "dur": 1.110, + "args": { + "External id": 717209,"Record 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": 6305208463775.340, "dur": 145.412, + "args": { + "External id": 717210,"Record function id": 0, "Sequence number": 7674764, "Fwd thread id": 1, "Ev Idx": 6553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208463776.434, "dur": 136.780, + "args": { + "External id": 717211,"Sequence number": 7674764, "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": 6305208463776.434, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305208463779.766, "dur": 7.882, + "args": { + "External id": 717212,"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": 6305208463781.505, "dur": 5.556, + "args": { + "External id": 717213,"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": 6305208463785.939, "dur": 0.950, + "args": { + "External id": 717214,"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": 6305208463788.871, "dur": 70.151, + "args": { + "External id": 717215,"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": 6305208463860.470, "dur": 6.542, + "args": { + "External id": 717216,"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": 6305208463861.186, "dur": 5.053, + "args": { + "External id": 717217,"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": 6305208463862.779, "dur": 3.314, + "args": { + "External id": 717218,"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": 6305208463868.730, "dur": 5.449, + "args": { + "External id": 717219,"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": 6305208463869.827, "dur": 3.857, + "args": { + "External id": 717220,"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": 6305208463873.091, "dur": 0.493, + "args": { + "External id": 717221,"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": 6305208463874.732, "dur": 37.732, + "args": { + "External id": 717222,"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": 6305208463925.641, "dur": 6.489, + "args": { + "External id": 717223,"Record function id": 0, "Sequence number": 7674763, "Fwd thread id": 1, "Ev Idx": 6566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208463926.720, "dur": 3.448, + "args": { + "External id": 717224,"Sequence number": 7674763, "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": 6305208463926.720, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208463928.063, "dur": 1.949, + "args": { + "External id": 717225,"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": 6305208463928.831, "dur": 1.065, + "args": { + "External id": 717226,"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": 6305208463935.474, "dur": 9.543, + "args": { + "External id": 717227,"Record function id": 0, "Sequence number": 7674762, "Fwd thread id": 1, "Ev Idx": 6570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208463936.302, "dur": 6.839, + "args": { + "External id": 717228,"Sequence number": 7674762, "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": 6305208463936.302, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305208463937.267, "dur": 5.621, + "args": { + "External id": 717229,"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": 6305208463937.875, "dur": 4.451, + "args": { + "External id": 717230,"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": 6305208463941.819, "dur": 0.415, + "args": { + "External id": 717231,"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": 6305208463948.950, "dur": 7.336, + "args": { + "External id": 717232,"Record function id": 0, "Ev Idx": 6575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208463950.300, "dur": 5.391, + "args": { + "External id": 717233,"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": 6305208463951.340, "dur": 4.057, + "args": { + "External id": 717234,"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": 6305208463951.979, "dur": 3.330, + "args": { + "External id": 717235,"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": 6305208463959.933, "dur": 6.567, + "args": { + "External id": 717236,"Record function id": 0, "Sequence number": 7674761, "Fwd thread id": 1, "Ev Idx": 6579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208463960.916, "dur": 3.756, + "args": { + "External id": 717237,"Sequence number": 7674761, "Fwd thread 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": 6305208463960.916, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208463962.466, "dur": 2.045, + "args": { + "External id": 717238,"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": 6305208463963.039, "dur": 1.341, + "args": { + "External id": 717239,"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": 6305208463971.279, "dur": 416.986, + "args": { + "External id": 717240,"Record function id": 0, "Sequence number": 7674760, "Fwd thread id": 1, "Ev Idx": 6583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFuncBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305208463972.785, "dur": 395.680, + "args": { + "External id": 717241,"Sequence number": 7674760, "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": 6305208463972.785, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338707, "tid": 2379456, + "ts": 6305208463988.338, "dur": 7.541, + "args": { + "External id": 717242,"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": 6305208463991.725, "dur": 3.607, + "args": { + "External id": 717243,"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": 6305208463998.029, "dur": 3.278, + "args": { + "External id": 717244,"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": 6305208463999.812, "dur": 1.275, + "args": { + "External id": 717245,"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": 6305208464002.821, "dur": 3.478, + "args": { + "External id": 717246,"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": 6305208464004.282, "dur": 1.839, + "args": { + "External id": 717247,"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": 6305208464030.854, "dur": 311.977, + "args": { + "External id": 717248,"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": 6305208464166.068, "dur": 4.817, + "args": { + "External id": 717249,"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": 6305208464173.548, "dur": 3.121, + "args": { + "External id": 717250,"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": 6305208464177.943, "dur": 2.963, + "args": { + "External id": 717251,"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": 6305208464182.492, "dur": 7.068, + "args": { + "External id": 717252,"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": 6305208464238.443, "dur": 3.531, + "args": { + "External id": 717253,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305208464239.986, "dur": 1.869, + "args": { + "External id": 717254,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305208464243.611, "dur": 32.192, + "args": { + "External id": 717255,"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": 6305208464249.487, "dur": 3.325, + "args": { + "External id": 717256,"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": 6305208464279.447, "dur": 1.897, + "args": { + "External id": 717257,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305208464280.672, "dur": 0.595, + "args": { + "External id": 717258,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305208464281.945, "dur": 16.115, + "args": { + "External id": 717259,"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": 6305208464284.500, "dur": 0.541, + "args": { + "External id": 717260,"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": 6305208464355.326, "dur": 4.190, + "args": { + "External id": 717261,"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": 6305208464362.449, "dur": 0.796, + "args": { + "External id": 717262,"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": 6305208464365.216, "dur": 0.638, + "args": { + "External id": 717263,"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": 6305208464399.652, "dur": 243.299, + "args": { + "External id": 717264,"Record function id": 0, "Sequence number": 7674759, "Fwd thread id": 1, "Ev Idx": 6607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305208464401.355, "dur": 233.562, + "args": { + "External id": 717265,"Sequence number": 7674759, "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": 6305208464401.355, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338707, "tid": 2379456, + "ts": 6305208464422.483, "dur": 42.841, + "args": { + "External id": 717266,"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": 6305208464426.401, "dur": 3.253, + "args": { + "External id": 717267,"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": 6305208464430.855, "dur": 33.854, + "args": { + "External id": 717268,"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": 6305208464475.506, "dur": 5.232, + "args": { + "External id": 717269,"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": 6305208464478.151, "dur": 2.278, + "args": { + "External id": 717270,"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": 6305208464653.510, "dur": 173.924, + "args": { + "External id": 717271,"Record function id": 0, "Sequence number": 7674758, "Fwd thread id": 1, "Ev Idx": 6614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305208464655.283, "dur": 164.558, + "args": { + "External id": 717272,"Sequence number": 7674758, "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": 6305208464655.283, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338707, "tid": 2379456, + "ts": 6305208464668.269, "dur": 52.209, + "args": { + "External id": 717273,"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": 6305208464671.536, "dur": 4.445, + "args": { + "External id": 717274,"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": 6305208464676.966, "dur": 42.929, + "args": { + "External id": 717275,"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": 6305208464728.636, "dur": 4.837, + "args": { + "External id": 717276,"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": 6305208464731.004, "dur": 2.092, + "args": { + "External id": 717277,"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": 6305208464833.639, "dur": 12.823, + "args": { + "External id": 717278,"Record function id": 0, "Sequence number": 7674757, "Fwd thread id": 1, "Ev Idx": 6621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208464835.106, "dur": 9.038, + "args": { + "External id": 717279,"Sequence number": 7674757, "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": 6305208464835.106, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208464837.659, "dur": 6.117, + "args": { + "External id": 717280,"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": 6305208464839.243, "dur": 4.290, + "args": { + "External id": 717281,"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": 6305208464849.951, "dur": 9.210, + "args": { + "External id": 717282,"Record function id": 0, "Sequence number": 7674756, "Fwd thread id": 1, "Ev Idx": 6625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208464853.131, "dur": 4.088, + "args": { + "External id": 717283,"Sequence number": 7674756, "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": 6305208464853.131, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208464854.406, "dur": 2.626, + "args": { + "External id": 717284,"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": 6305208464855.877, "dur": 1.013, + "args": { + "External id": 717285,"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": 6305208464862.754, "dur": 6.365, + "args": { + "External id": 717286,"Record function id": 0, "Sequence number": 7674755, "Fwd thread id": 1, "Ev Idx": 6629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208464863.607, "dur": 3.629, + "args": { + "External id": 717287,"Sequence number": 7674755, "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": 6305208464863.607, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208464865.128, "dur": 1.946, + "args": { + "External id": 717288,"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": 6305208464866.141, "dur": 0.804, + "args": { + "External id": 717289,"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": 6305208464872.706, "dur": 11.687, + "args": { + "External id": 717290,"Record function id": 0, "Sequence number": 7674754, "Fwd thread id": 1, "Ev Idx": 6633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208464873.816, "dur": 8.301, + "args": { + "External id": 717291,"Sequence number": 7674754, "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": 6305208464873.816, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208464875.221, "dur": 6.743, + "args": { + "External id": 717292,"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": 6305208464878.182, "dur": 3.687, + "args": { + "External id": 717293,"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": 6305208464888.009, "dur": 160.987, + "args": { + "External id": 717294,"Record function id": 0, "Sequence number": 7674753, "Fwd thread id": 1, "Ev Idx": 6637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208464889.200, "dur": 153.115, + "args": { + "External id": 717295,"Sequence number": 7674753, "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": 6305208464889.200, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305208464892.875, "dur": 6.759, + "args": { + "External id": 717296,"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": 6305208464895.135, "dur": 3.778, + "args": { + "External id": 717297,"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": 6305208464897.394, "dur": 1.231, + "args": { + "External id": 717298,"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": 6305208464901.429, "dur": 71.534, + "args": { + "External id": 717299,"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": 6305208464976.359, "dur": 10.237, + "args": { + "External id": 717300,"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": 6305208464977.414, "dur": 8.431, + "args": { + "External id": 717301,"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": 6305208464982.745, "dur": 2.919, + "args": { + "External id": 717302,"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": 6305208464988.322, "dur": 4.097, + "args": { + "External id": 717303,"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": 6305208464989.683, "dur": 2.171, + "args": { + "External id": 717304,"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": 6305208464991.327, "dur": 0.413, + "args": { + "External id": 717305,"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": 6305208464996.089, "dur": 45.346, + "args": { + "External id": 717306,"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": 6305208465054.083, "dur": 47.491, + "args": { + "External id": 717307,"Record function id": 0, "Sequence number": 7674752, "Fwd thread id": 1, "Ev Idx": 6650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208465055.191, "dur": 43.189, + "args": { + "External id": 717308,"Sequence number": 7674752, "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": 6305208465055.191, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208465094.525, "dur": 3.688, + "args": { + "External id": 717309,"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": 6305208465095.652, "dur": 2.312, + "args": { + "External id": 717310,"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": 6305208465107.508, "dur": 66.462, + "args": { + "External id": 717311,"Record function id": 0, "Sequence number": 7674751, "Fwd thread id": 1, "Ev Idx": 6654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208465108.762, "dur": 62.640, + "args": { + "External id": 717312,"Sequence number": 7674751, "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": 6305208465108.762, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305208465158.653, "dur": 12.537, + "args": { + "External id": 717313,"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": 6305208465160.203, "dur": 10.378, + "args": { + "External id": 717314,"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": 6305208465169.939, "dur": 0.537, + "args": { + "External id": 717315,"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": 6305208465180.471, "dur": 11.226, + "args": { + "External id": 717316,"Record function id": 0, "Ev Idx": 6659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208465182.064, "dur": 8.946, + "args": { + "External id": 717317,"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": 6305208465184.712, "dur": 5.873, + "args": { + "External id": 717318,"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": 6305208465186.102, "dur": 4.349, + "args": { + "External id": 717319,"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": 6305208465195.140, "dur": 6.421, + "args": { + "External id": 717320,"Record function id": 0, "Sequence number": 7674750, "Fwd thread id": 1, "Ev Idx": 6663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208465196.090, "dur": 3.167, + "args": { + "External id": 717321,"Sequence number": 7674750, "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": 6305208465196.090, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208465197.214, "dur": 1.883, + "args": { + "External id": 717322,"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": 6305208465198.012, "dur": 0.941, + "args": { + "External id": 717323,"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": 6305208465205.470, "dur": 107.923, + "args": { + "External id": 717324,"Record function id": 0, "Sequence number": 7674749, "Fwd thread id": 1, "Ev Idx": 6667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208465208.412, "dur": 97.266, + "args": { + "External id": 717325,"Sequence number": 7674749, "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": 6305208465208.412, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305208465210.763, "dur": 2.937, + "args": { + "External id": 717326,"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": 6305208465211.243, "dur": 1.980, + "args": { + "External id": 717327,"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": 6305208465212.578, "dur": 0.496, + "args": { + "External id": 717328,"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": 6305208465214.515, "dur": 40.722, + "args": { + "External id": 717329,"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": 6305208465256.469, "dur": 6.128, + "args": { + "External id": 717330,"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": 6305208465257.070, "dur": 4.952, + "args": { + "External id": 717331,"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": 6305208465261.235, "dur": 0.664, + "args": { + "External id": 717332,"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": 6305208465263.774, "dur": 3.082, + "args": { + "External id": 717333,"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": 6305208465264.639, "dur": 1.780, + "args": { + "External id": 717334,"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": 6305208465266.085, "dur": 0.263, + "args": { + "External id": 717335,"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": 6305208465267.267, "dur": 37.570, + "args": { + "External id": 717336,"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": 6305208465318.339, "dur": 37.385, + "args": { + "External id": 717337,"Record function id": 0, "Sequence number": 7674748, "Fwd thread id": 1, "Ev Idx": 6680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208465319.128, "dur": 6.029, + "args": { + "External id": 717338,"Sequence number": 7674748, "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": 6305208465319.128, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208465320.599, "dur": 4.396, + "args": { + "External id": 717339,"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": 6305208465323.912, "dur": 0.985, + "args": { + "External id": 717340,"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": 6305208465328.531, "dur": 24.852, + "args": { + "External id": 717341,"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": 6305208465359.922, "dur": 6.905, + "args": { + "External id": 717342,"Record function id": 0, "Sequence number": 7674747, "Fwd thread id": 1, "Ev Idx": 6685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208465360.850, "dur": 3.974, + "args": { + "External id": 717343,"Sequence number": 7674747, "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": 6305208465360.850, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305208465361.504, "dur": 3.095, + "args": { + "External id": 717344,"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": 6305208465362.164, "dur": 1.810, + "args": { + "External id": 717345,"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": 6305208465363.437, "dur": 0.374, + "args": { + "External id": 717346,"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": 6305208465370.782, "dur": 7.710, + "args": { + "External id": 717347,"Record function id": 0, "Ev Idx": 6690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208465372.063, "dur": 5.883, + "args": { + "External id": 717348,"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": 6305208465373.039, "dur": 4.334, + "args": { + "External id": 717349,"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": 6305208465376.211, "dur": 1.001, + "args": { + "External id": 717350,"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": 6305208465381.832, "dur": 6.146, + "args": { + "External id": 717351,"Record function id": 0, "Sequence number": 7674746, "Fwd thread id": 1, "Ev Idx": 6694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208465383.054, "dur": 2.863, + "args": { + "External id": 717352,"Sequence number": 7674746, "Fwd thread 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": 6305208465383.054, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208465384.283, "dur": 1.488, + "args": { + "External id": 717353,"Record 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": 6305208465384.838, "dur": 0.841, + "args": { + "External id": 717354,"Record 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": 6305208465391.375, "dur": 100.995, + "args": { + "External id": 717355,"Record function id": 0, "Sequence number": 7674745, "Fwd thread id": 1, "Ev Idx": 6698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208465392.157, "dur": 91.871, + "args": { + "External id": 717356,"Sequence number": 7674745, "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": 6305208465392.157, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305208465394.061, "dur": 5.504, + "args": { + "External id": 717357,"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": 6305208465394.519, "dur": 4.592, + "args": { + "External id": 717358,"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": 6305208465398.494, "dur": 0.510, + "args": { + "External id": 717359,"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": 6305208465400.128, "dur": 34.949, + "args": { + "External id": 717360,"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": 6305208465436.143, "dur": 3.494, + "args": { + "External id": 717361,"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": 6305208465436.677, "dur": 2.382, + "args": { + "External id": 717362,"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": 6305208465438.246, "dur": 0.703, + "args": { + "External id": 717363,"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": 6305208465440.717, "dur": 6.564, + "args": { + "External id": 717364,"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": 6305208465444.474, "dur": 2.111, + "args": { + "External id": 717365,"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": 6305208465446.151, "dur": 0.362, + "args": { + "External id": 717366,"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": 6305208465447.657, "dur": 35.446, + "args": { + "External id": 717367,"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": 6305208465496.885, "dur": 44.076, + "args": { + "External id": 717368,"Record function id": 0, "Sequence number": 7674744, "Fwd thread id": 1, "Ev Idx": 6711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208465497.654, "dur": 3.496, + "args": { + "External id": 717369,"Sequence number": 7674744, "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": 6305208465497.654, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208465498.994, "dur": 2.001, + "args": { + "External id": 717370,"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": 6305208465499.831, "dur": 1.022, + "args": { + "External id": 717371,"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": 6305208465503.554, "dur": 34.469, + "args": { + "External id": 717372,"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": 6305208465547.139, "dur": 11.340, + "args": { + "External id": 717373,"Record function id": 0, "Sequence number": 7674743, "Fwd thread id": 1, "Ev Idx": 6716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208465548.261, "dur": 8.047, + "args": { + "External id": 717374,"Sequence number": 7674743, "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": 6305208465548.261, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305208465551.658, "dur": 4.416, + "args": { + "External id": 717375,"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": 6305208465552.417, "dur": 2.942, + "args": { + "External id": 717376,"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": 6305208465554.308, "dur": 0.916, + "args": { + "External id": 717377,"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": 6305208465562.765, "dur": 5.594, + "args": { + "External id": 717378,"Record function id": 0, "Ev Idx": 6721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208465563.950, "dur": 3.925, + "args": { + "External id": 717379,"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": 6305208465565.254, "dur": 2.248, + "args": { + "External id": 717380,"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": 6305208465565.885, "dur": 1.512, + "args": { + "External id": 717381,"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": 6305208465572.768, "dur": 411.231, + "args": { + "External id": 717382,"Record function id": 0, "Sequence number": 7674742, "Fwd thread id": 1, "Ev Idx": 6725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305208465573.858, "dur": 372.336, + "args": { + "External id": 717383,"Sequence number": 7674742, "Fwd thread 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": 6305208465573.858, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208465609.582, "dur": 16.929, + "args": { + "External id": 717384,"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": 6305208465623.486, "dur": 2.560, + "args": { + "External id": 717385,"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": 6305208465647.662, "dur": 7.050, + "args": { + "External id": 717386,"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": 6305208465665.335, "dur": 2.459, + "args": { + "External id": 717387,"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": 6305208465835.098, "dur": 2.117, + "args": { + "External id": 717388,"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": 6305208465841.621, "dur": 40.809, + "args": { + "External id": 717389,"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": 6305208465855.637, "dur": 0.977, + "args": { + "External id": 717390,"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": 6305208465888.879, "dur": 34.749, + "args": { + "External id": 717391,"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": 6305208465890.790, "dur": 32.582, + "args": { + "External id": 717392,"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": 6305208465897.950, "dur": 4.460, + "args": { + "External id": 717393,"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": 6305208465904.301, "dur": 18.503, + "args": { + "External id": 717394,"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": 6305208465928.132, "dur": 2.727, + "args": { + "External id": 717395,"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": 6305208465929.644, "dur": 1.066, + "args": { + "External id": 717396,"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": 6305208465937.317, "dur": 2.196, + "args": { + "External id": 717397,"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": 6305208465938.451, "dur": 0.969, + "args": { + "External id": 717398,"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": 6305208465961.425, "dur": 18.134, + "args": { + "External id": 717399,"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": 6305208465998.150, "dur": 9.838, + "args": { + "External id": 717400,"Record function id": 0, "Ev Idx": 6743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208466000.894, "dur": 6.400, + "args": { + "External id": 717401,"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": 6305208466003.057, "dur": 3.216, + "args": { + "External id": 717402,"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": 6305208466004.144, "dur": 2.027, + "args": { + "External id": 717403,"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": 6305208466012.058, "dur": 6.308, + "args": { + "External id": 717404,"Record function id": 0, "Sequence number": 7674741, "Fwd thread id": 1, "Ev Idx": 6747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208466013.450, "dur": 1.617, + "args": { + "External id": 717405,"Sequence number": 7674741, "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": 6305208466013.450, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SwiGLULinearFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305208466022.270, "dur": 504.786, + "args": { + "External id": 717406,"Record function id": 0, "Sequence number": 7674740, "Fwd thread id": 1, "Ev Idx": 6749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305208466026.780, "dur": 468.153, + "args": { + "External id": 717407,"Sequence number": 7674740, "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": 6305208466026.780, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208466097.116, "dur": 10.350, + "args": { + "External id": 717408,"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": 6305208466102.636, "dur": 4.390, + "args": { + "External id": 717409,"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": 6305208466111.266, "dur": 5.739, + "args": { + "External id": 717410,"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": 6305208466113.093, "dur": 3.153, + "args": { + "External id": 717411,"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": 6305208466114.954, "dur": 1.102, + "args": { + "External id": 717412,"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": 6305208466122.524, "dur": 105.226, + "args": { + "External id": 717413,"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": 6305208466123.520, "dur": 2.946, + "args": { + "External id": 717414,"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": 6305208466124.031, "dur": 1.909, + "args": { + "External id": 717415,"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": 6305208466125.397, "dur": 0.464, + "args": { + "External id": 717416,"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": 6305208466127.804, "dur": 99.204, + "args": { + "External id": 717417,"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": 6305208466129.540, "dur": 96.596, + "args": { + "External id": 717418,"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": 6305208466232.230, "dur": 6.587, + "args": { + "External id": 717419,"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": 6305208466236.703, "dur": 1.961, + "args": { + "External id": 717420,"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": 6305208466272.184, "dur": 4.610, + "args": { + "External id": 717421,"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": 6305208466278.116, "dur": 5.830, + "args": { + "External id": 717422,"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": 6305208466285.142, "dur": 2.012, + "args": { + "External id": 717423,"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": 6305208466321.117, "dur": 2.526, + "args": { + "External id": 717424,"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": 6305208466322.601, "dur": 0.897, + "args": { + "External id": 717425,"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": 6305208466348.359, "dur": 125.449, + "args": { + "External id": 717426,"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": 6305208466354.294, "dur": 6.143, + "args": { + "External id": 717427,"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": 6305208466358.407, "dur": 1.164, + "args": { + "External id": 717428,"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": 6305208466362.085, "dur": 7.149, + "args": { + "External id": 717429,"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": 6305208466367.755, "dur": 0.649, + "args": { + "External id": 717430,"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": 6305208466370.588, "dur": 3.051, + "args": { + "External id": 717431,"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": 6305208466372.881, "dur": 0.367, + "args": { + "External id": 717432,"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": 6305208466374.760, "dur": 3.240, + "args": { + "External id": 717433,"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": 6305208466376.872, "dur": 0.532, + "args": { + "External id": 717434,"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": 6305208466382.035, "dur": 3.791, + "args": { + "External id": 717435,"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": 6305208466384.880, "dur": 0.641, + "args": { + "External id": 717436,"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": 6305208466388.921, "dur": 8.375, + "args": { + "External id": 717437,"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": 6305208466392.610, "dur": 4.524, + "args": { + "External id": 717438,"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": 6305208466398.181, "dur": 3.273, + "args": { + "External id": 717439,"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": 6305208466400.773, "dur": 0.393, + "args": { + "External id": 717440,"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": 6305208466402.807, "dur": 2.831, + "args": { + "External id": 717441,"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": 6305208466404.018, "dur": 1.536, + "args": { + "External id": 717442,"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": 6305208466406.880, "dur": 55.306, + "args": { + "External id": 717443,"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": 6305208466463.930, "dur": 1.064, + "args": { + "External id": 717444,"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": 6305208466466.149, "dur": 3.069, + "args": { + "External id": 717445,"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": 6305208466468.205, "dur": 0.448, + "args": { + "External id": 717446,"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": 6305208466471.759, "dur": 0.961, + "args": { + "External id": 717447,"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": 6305208466542.026, "dur": 10.920, + "args": { + "External id": 717448,"Record function id": 0, "Ev Idx": 6791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208466544.441, "dur": 7.700, + "args": { + "External id": 717449,"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": 6305208466547.054, "dur": 3.814, + "args": { + "External id": 717450,"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": 6305208466548.015, "dur": 2.734, + "args": { + "External id": 717451,"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": 6305208466556.842, "dur": 6.855, + "args": { + "External id": 717452,"Record function id": 0, "Sequence number": 7674739, "Fwd thread id": 1, "Ev Idx": 6795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208466557.980, "dur": 3.866, + "args": { + "External id": 717453,"Sequence number": 7674739, "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": 6305208466557.980, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208466559.514, "dur": 2.105, + "args": { + "External id": 717454,"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": 6305208466560.547, "dur": 0.982, + "args": { + "External id": 717455,"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": 6305208466567.328, "dur": 121.846, + "args": { + "External id": 717456,"Record function id": 0, "Sequence number": 7674738, "Fwd thread id": 1, "Ev Idx": 6799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208466570.330, "dur": 111.217, + "args": { + "External id": 717457,"Sequence number": 7674738, "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": 6305208466570.330, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305208466573.680, "dur": 4.606, + "args": { + "External id": 717458,"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": 6305208466575.124, "dur": 2.459, + "args": { + "External id": 717459,"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": 6305208466576.873, "dur": 0.557, + "args": { + "External id": 717460,"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": 6305208466579.368, "dur": 50.106, + "args": { + "External id": 717461,"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": 6305208466630.567, "dur": 7.041, + "args": { + "External id": 717462,"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": 6305208466631.379, "dur": 5.556, + "args": { + "External id": 717463,"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": 6305208466635.863, "dur": 0.892, + "args": { + "External id": 717464,"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": 6305208466639.178, "dur": 5.452, + "args": { + "External id": 717465,"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": 6305208466640.184, "dur": 3.941, + "args": { + "External id": 717466,"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": 6305208466641.340, "dur": 2.666, + "args": { + "External id": 717467,"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": 6305208466645.324, "dur": 35.384, + "args": { + "External id": 717468,"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": 6305208466694.289, "dur": 8.895, + "args": { + "External id": 717469,"Record function id": 0, "Sequence number": 7674737, "Fwd thread id": 1, "Ev Idx": 6812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208466695.248, "dur": 6.608, + "args": { + "External id": 717470,"Sequence number": 7674737, "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": 6305208466695.248, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208466696.897, "dur": 4.801, + "args": { + "External id": 717471,"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": 6305208466700.443, "dur": 1.135, + "args": { + "External id": 717472,"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": 6305208466706.689, "dur": 7.813, + "args": { + "External id": 717473,"Record function id": 0, "Sequence number": 7674736, "Fwd thread id": 1, "Ev Idx": 6816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208466707.555, "dur": 4.631, + "args": { + "External id": 717474,"Sequence number": 7674736, "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": 6305208466707.555, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305208466708.275, "dur": 3.689, + "args": { + "External id": 717475,"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": 6305208466708.969, "dur": 2.437, + "args": { + "External id": 717476,"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": 6305208466710.615, "dur": 0.673, + "args": { + "External id": 717477,"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": 6305208466718.423, "dur": 5.351, + "args": { + "External id": 717478,"Record function id": 0, "Ev Idx": 6821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208466719.931, "dur": 3.255, + "args": { + "External id": 717479,"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": 6305208466720.942, "dur": 1.995, + "args": { + "External id": 717480,"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": 6305208466721.595, "dur": 1.216, + "args": { + "External id": 717481,"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": 6305208466727.230, "dur": 8.311, + "args": { + "External id": 717482,"Record function id": 0, "Sequence number": 7674735, "Fwd thread id": 1, "Ev Idx": 6825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208466728.360, "dur": 5.634, + "args": { + "External id": 717483,"Sequence number": 7674735, "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": 6305208466728.360, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208466731.854, "dur": 1.989, + "args": { + "External id": 717484,"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": 6305208466733.008, "dur": 0.747, + "args": { + "External id": 717485,"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": 6305208466738.657, "dur": 96.785, + "args": { + "External id": 717486,"Record function id": 0, "Sequence number": 7674734, "Fwd thread id": 1, "Ev Idx": 6829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208466739.328, "dur": 88.897, + "args": { + "External id": 717487,"Sequence number": 7674734, "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": 6305208466739.328, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305208466741.519, "dur": 5.168, + "args": { + "External id": 717488,"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": 6305208466741.966, "dur": 4.289, + "args": { + "External id": 717489,"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": 6305208466745.493, "dur": 0.657, + "args": { + "External id": 717490,"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": 6305208466747.477, "dur": 34.002, + "args": { + "External id": 717491,"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": 6305208466782.589, "dur": 6.379, + "args": { + "External id": 717492,"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": 6305208466783.435, "dur": 4.985, + "args": { + "External id": 717493,"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": 6305208466784.890, "dur": 3.379, + "args": { + "External id": 717494,"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": 6305208466790.037, "dur": 6.086, + "args": { + "External id": 717495,"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": 6305208466791.340, "dur": 4.180, + "args": { + "External id": 717496,"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": 6305208466795.090, "dur": 0.359, + "args": { + "External id": 717497,"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": 6305208466796.773, "dur": 30.705, + "args": { + "External id": 717498,"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": 6305208466840.055, "dur": 31.136, + "args": { + "External id": 717499,"Record function id": 0, "Sequence number": 7674733, "Fwd thread id": 1, "Ev Idx": 6842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208466840.975, "dur": 3.837, + "args": { + "External id": 717500,"Sequence number": 7674733, "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": 6305208466840.975, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208466842.617, "dur": 2.045, + "args": { + "External id": 717501,"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": 6305208466843.455, "dur": 1.061, + "args": { + "External id": 717502,"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": 6305208466847.694, "dur": 20.295, + "args": { + "External id": 717503,"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": 6305208466875.047, "dur": 10.576, + "args": { + "External id": 717504,"Record function id": 0, "Sequence number": 7674732, "Fwd thread id": 1, "Ev Idx": 6847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208466876.160, "dur": 7.409, + "args": { + "External id": 717505,"Sequence number": 7674732, "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": 6305208466876.160, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305208466879.595, "dur": 3.791, + "args": { + "External id": 717506,"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": 6305208466880.402, "dur": 2.387, + "args": { + "External id": 717507,"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": 6305208466882.173, "dur": 0.491, + "args": { + "External id": 717508,"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": 6305208466889.404, "dur": 5.107, + "args": { + "External id": 717509,"Record function id": 0, "Ev Idx": 6852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208466890.865, "dur": 3.154, + "args": { + "External id": 717510,"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": 6305208466891.806, "dur": 1.929, + "args": { + "External id": 717511,"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": 6305208466892.437, "dur": 1.179, + "args": { + "External id": 717512,"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": 6305208466898.462, "dur": 473.515, + "args": { + "External id": 717513,"Record function id": 0, "Sequence number": 7674731, "Fwd thread id": 1, "Ev Idx": 6856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305208466900.000, "dur": 437.248, + "args": { + "External id": 717514,"Sequence number": 7674731, "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": 6305208466900.000, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338707, "tid": 2379456, + "ts": 6305208466923.889, "dur": 39.295, + "args": { + "External id": 717515,"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": 6305208466925.674, "dur": 37.308, + "args": { + "External id": 717516,"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": 6305208466928.781, "dur": 11.055, + "args": { + "External id": 717517,"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": 6305208466936.091, "dur": 3.131, + "args": { + "External id": 717518,"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": 6305208466941.269, "dur": 21.181, + "args": { + "External id": 717519,"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": 6305208466977.215, "dur": 2.513, + "args": { + "External id": 717520,"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": 6305208466978.513, "dur": 1.084, + "args": { + "External id": 717521,"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": 6305208466983.158, "dur": 4.057, + "args": { + "External id": 717522,"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": 6305208466984.085, "dur": 3.038, + "args": { + "External id": 717523,"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": 6305208467001.615, "dur": 2.213, + "args": { + "External id": 717524,"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": 6305208467015.023, "dur": 2.059, + "args": { + "External id": 717525,"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": 6305208467221.330, "dur": 5.887, + "args": { + "External id": 717526,"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": 6305208467231.529, "dur": 34.115, + "args": { + "External id": 717527,"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": 6305208467242.144, "dur": 1.133, + "args": { + "External id": 717528,"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": 6305208467271.384, "dur": 30.778, + "args": { + "External id": 717529,"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": 6305208467273.350, "dur": 28.571, + "args": { + "External id": 717530,"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": 6305208467277.864, "dur": 4.376, + "args": { + "External id": 717531,"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": 6305208467286.182, "dur": 15.095, + "args": { + "External id": 717532,"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": 6305208467306.304, "dur": 2.921, + "args": { + "External id": 717533,"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": 6305208467307.770, "dur": 1.354, + "args": { + "External id": 717534,"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": 6305208467316.280, "dur": 2.870, + "args": { + "External id": 717535,"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": 6305208467317.679, "dur": 1.290, + "args": { + "External id": 717536,"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": 6305208467321.317, "dur": 4.009, + "args": { + "External id": 717537,"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": 6305208467322.239, "dur": 3.005, + "args": { + "External id": 717538,"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": 6305208467353.787, "dur": 16.681, + "args": { + "External id": 717539,"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": 6305208467385.633, "dur": 9.341, + "args": { + "External id": 717540,"Record function id": 0, "Ev Idx": 6883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208467387.890, "dur": 6.398, + "args": { + "External id": 717541,"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": 6305208467390.109, "dur": 3.321, + "args": { + "External id": 717542,"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": 6305208467391.181, "dur": 2.149, + "args": { + "External id": 717543,"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": 6305208467398.668, "dur": 7.763, + "args": { + "External id": 717544,"Record function id": 0, "Sequence number": 7674730, "Fwd thread id": 1, "Ev Idx": 6887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208467399.917, "dur": 3.770, + "args": { + "External id": 717545,"Sequence number": 7674730, "Fwd thread 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": 6305208467399.917, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208467401.585, "dur": 1.852, + "args": { + "External id": 717546,"Record 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": 6305208467402.224, "dur": 1.076, + "args": { + "External id": 717547,"Record 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": 6305208467410.014, "dur": 167.052, + "args": { + "External id": 717548,"Record function id": 0, "Sequence number": 7674729, "Fwd thread id": 1, "Ev Idx": 6891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208467413.235, "dur": 154.954, + "args": { + "External id": 717549,"Sequence number": 7674729, "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": 6305208467413.235, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305208467416.642, "dur": 5.526, + "args": { + "External id": 717550,"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": 6305208467418.357, "dur": 3.202, + "args": { + "External id": 717551,"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": 6305208467420.469, "dur": 0.886, + "args": { + "External id": 717552,"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": 6305208467423.341, "dur": 68.145, + "args": { + "External id": 717553,"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": 6305208467492.700, "dur": 7.957, + "args": { + "External id": 717554,"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": 6305208467493.457, "dur": 6.512, + "args": { + "External id": 717555,"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": 6305208467497.289, "dur": 2.488, + "args": { + "External id": 717556,"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": 6305208467502.160, "dur": 20.544, + "args": { + "External id": 717557,"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": 6305208467503.115, "dur": 18.618, + "args": { + "External id": 717558,"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": 6305208467520.510, "dur": 0.740, + "args": { + "External id": 717559,"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": 6305208467523.752, "dur": 43.462, + "args": { + "External id": 717560,"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": 6305208467583.805, "dur": 12.712, + "args": { + "External id": 717561,"Record function id": 0, "Sequence number": 7674728, "Fwd thread id": 1, "Ev Idx": 6904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208467585.002, "dur": 9.084, + "args": { + "External id": 717562,"Sequence number": 7674728, "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": 6305208467585.002, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208467586.649, "dur": 7.280, + "args": { + "External id": 717563,"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": 6305208467589.788, "dur": 3.998, + "args": { + "External id": 717564,"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": 6305208467600.309, "dur": 7.804, + "args": { + "External id": 717565,"Record function id": 0, "Sequence number": 7674727, "Fwd thread id": 1, "Ev Idx": 6908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208467601.311, "dur": 4.995, + "args": { + "External id": 717566,"Sequence number": 7674727, "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": 6305208467601.311, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305208467602.151, "dur": 3.951, + "args": { + "External id": 717567,"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": 6305208467603.085, "dur": 2.485, + "args": { + "External id": 717568,"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": 6305208467604.932, "dur": 0.516, + "args": { + "External id": 717569,"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": 6305208467612.305, "dur": 6.055, + "args": { + "External id": 717570,"Record function id": 0, "Ev Idx": 6913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208467613.711, "dur": 4.133, + "args": { + "External id": 717571,"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": 6305208467615.039, "dur": 2.482, + "args": { + "External id": 717572,"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": 6305208467615.811, "dur": 1.602, + "args": { + "External id": 717573,"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": 6305208467622.131, "dur": 9.522, + "args": { + "External id": 717574,"Record function id": 0, "Sequence number": 7674726, "Fwd thread id": 1, "Ev Idx": 6917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208467625.790, "dur": 3.612, + "args": { + "External id": 717575,"Sequence number": 7674726, "Fwd thread 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": 6305208467625.790, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208467626.944, "dur": 2.301, + "args": { + "External id": 717576,"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": 6305208467627.959, "dur": 1.146, + "args": { + "External id": 717577,"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": 6305208467636.265, "dur": 341.781, + "args": { + "External id": 717578,"Record function id": 0, "Sequence number": 7674725, "Fwd thread id": 1, "Ev Idx": 6921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFuncBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305208467637.764, "dur": 323.271, + "args": { + "External id": 717579,"Sequence number": 7674725, "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": 6305208467637.764, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338707, "tid": 2379456, + "ts": 6305208467654.602, "dur": 7.285, + "args": { + "External id": 717580,"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": 6305208467657.610, "dur": 3.759, + "args": { + "External id": 717581,"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": 6305208467664.290, "dur": 3.875, + "args": { + "External id": 717582,"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": 6305208467666.305, "dur": 1.703, + "args": { + "External id": 717583,"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": 6305208467669.912, "dur": 4.884, + "args": { + "External id": 717584,"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": 6305208467672.258, "dur": 2.385, + "args": { + "External id": 717585,"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": 6305208467698.635, "dur": 237.574, + "args": { + "External id": 717586,"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": 6305208467778.187, "dur": 3.199, + "args": { + "External id": 717587,"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": 6305208467783.475, "dur": 4.642, + "args": { + "External id": 717588,"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": 6305208467789.352, "dur": 2.756, + "args": { + "External id": 717589,"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": 6305208467795.550, "dur": 2.066, + "args": { + "External id": 717590,"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": 6305208467841.646, "dur": 3.033, + "args": { + "External id": 717591,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305208467843.206, "dur": 1.339, + "args": { + "External id": 717592,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305208467846.620, "dur": 27.819, + "args": { + "External id": 717593,"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": 6305208467852.254, "dur": 2.325, + "args": { + "External id": 717594,"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": 6305208467875.919, "dur": 1.746, + "args": { + "External id": 717595,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305208467877.022, "dur": 0.554, + "args": { + "External id": 717596,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305208467878.582, "dur": 13.944, + "args": { + "External id": 717597,"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": 6305208467880.785, "dur": 0.781, + "args": { + "External id": 717598,"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": 6305208467947.814, "dur": 3.687, + "args": { + "External id": 717599,"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": 6305208467954.832, "dur": 0.979, + "args": { + "External id": 717600,"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": 6305208467957.982, "dur": 0.479, + "args": { + "External id": 717601,"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": 6305208467985.686, "dur": 285.809, + "args": { + "External id": 717602,"Record function id": 0, "Sequence number": 7674724, "Fwd thread id": 1, "Ev Idx": 6945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305208467987.282, "dur": 275.701, + "args": { + "External id": 717603,"Sequence number": 7674724, "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": 6305208467987.282, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338707, "tid": 2379456, + "ts": 6305208468009.979, "dur": 92.773, + "args": { + "External id": 717604,"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": 6305208468013.157, "dur": 3.520, + "args": { + "External id": 717605,"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": 6305208468018.098, "dur": 83.633, + "args": { + "External id": 717606,"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": 6305208468115.153, "dur": 6.887, + "args": { + "External id": 717607,"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": 6305208468118.077, "dur": 3.603, + "args": { + "External id": 717608,"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": 6305208468280.979, "dur": 180.313, + "args": { + "External id": 717609,"Record function id": 0, "Sequence number": 7674723, "Fwd thread id": 1, "Ev Idx": 6952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305208468283.031, "dur": 171.783, + "args": { + "External id": 717610,"Sequence number": 7674723, "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": 6305208468283.031, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338707, "tid": 2379456, + "ts": 6305208468295.420, "dur": 58.659, + "args": { + "External id": 717611,"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": 6305208468304.473, "dur": 2.822, + "args": { + "External id": 717612,"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": 6305208468310.654, "dur": 43.013, + "args": { + "External id": 717613,"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": 6305208468361.933, "dur": 5.901, + "args": { + "External id": 717614,"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": 6305208468364.109, "dur": 3.456, + "args": { + "External id": 717615,"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": 6305208468470.544, "dur": 14.243, + "args": { + "External id": 717616,"Record function id": 0, "Sequence number": 7674722, "Fwd thread id": 1, "Ev Idx": 6959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208468471.925, "dur": 10.311, + "args": { + "External id": 717617,"Sequence number": 7674722, "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": 6305208468471.925, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208468474.325, "dur": 7.583, + "args": { + "External id": 717618,"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": 6305208468475.943, "dur": 5.771, + "args": { + "External id": 717619,"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": 6305208468488.459, "dur": 10.088, + "args": { + "External id": 717620,"Record function id": 0, "Sequence number": 7674721, "Fwd thread id": 1, "Ev Idx": 6963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208468489.347, "dur": 6.954, + "args": { + "External id": 717621,"Sequence number": 7674721, "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": 6305208468489.347, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208468491.079, "dur": 5.078, + "args": { + "External id": 717622,"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": 6305208468492.133, "dur": 3.881, + "args": { + "External id": 717623,"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": 6305208468501.641, "dur": 27.710, + "args": { + "External id": 717624,"Record function id": 0, "Sequence number": 7674720, "Fwd thread id": 1, "Ev Idx": 6967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208468502.771, "dur": 23.368, + "args": { + "External id": 717625,"Sequence number": 7674720, "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": 6305208468502.771, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208468522.614, "dur": 3.356, + "args": { + "External id": 717626,"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": 6305208468524.154, "dur": 1.566, + "args": { + "External id": 717627,"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": 6305208468534.700, "dur": 6.968, + "args": { + "External id": 717628,"Record function id": 0, "Sequence number": 7674719, "Fwd thread id": 1, "Ev Idx": 6971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208468535.880, "dur": 3.229, + "args": { + "External id": 717629,"Sequence number": 7674719, "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": 6305208468535.880, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208468537.112, "dur": 1.835, + "args": { + "External id": 717630,"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": 6305208468537.872, "dur": 0.947, + "args": { + "External id": 717631,"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": 6305208468544.868, "dur": 179.699, + "args": { + "External id": 717632,"Record function id": 0, "Sequence number": 7674718, "Fwd thread id": 1, "Ev Idx": 6975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208468545.917, "dur": 169.331, + "args": { + "External id": 717633,"Sequence number": 7674718, "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": 6305208468545.917, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305208468550.186, "dur": 10.149, + "args": { + "External id": 717634,"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": 6305208468555.313, "dur": 4.357, + "args": { + "External id": 717635,"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": 6305208468557.645, "dur": 1.763, + "args": { + "External id": 717636,"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": 6305208468561.944, "dur": 76.502, + "args": { + "External id": 717637,"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": 6305208468639.641, "dur": 5.094, + "args": { + "External id": 717638,"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": 6305208468640.438, "dur": 3.443, + "args": { + "External id": 717639,"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": 6305208468642.478, "dur": 1.250, + "args": { + "External id": 717640,"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": 6305208468646.549, "dur": 6.553, + "args": { + "External id": 717641,"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": 6305208468650.641, "dur": 1.980, + "args": { + "External id": 717642,"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": 6305208468651.986, "dur": 0.550, + "args": { + "External id": 717643,"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": 6305208468653.688, "dur": 60.566, + "args": { + "External id": 717644,"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": 6305208468730.534, "dur": 10.041, + "args": { + "External id": 717645,"Record function id": 0, "Sequence number": 7674717, "Fwd thread id": 1, "Ev Idx": 6988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208468731.558, "dur": 7.222, + "args": { + "External id": 717646,"Sequence number": 7674717, "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": 6305208468731.558, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208468733.344, "dur": 5.284, + "args": { + "External id": 717647,"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": 6305208468734.712, "dur": 3.755, + "args": { + "External id": 717648,"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": 6305208468744.155, "dur": 11.312, + "args": { + "External id": 717649,"Record function id": 0, "Sequence number": 7674716, "Fwd thread id": 1, "Ev Idx": 6992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208468745.109, "dur": 8.110, + "args": { + "External id": 717650,"Sequence number": 7674716, "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": 6305208468745.109, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305208468745.987, "dur": 7.012, + "args": { + "External id": 717651,"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": 6305208468749.724, "dur": 2.756, + "args": { + "External id": 717652,"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": 6305208468751.741, "dur": 0.632, + "args": { + "External id": 717653,"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": 6305208468761.511, "dur": 10.041, + "args": { + "External id": 717654,"Record function id": 0, "Ev Idx": 6997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208468763.230, "dur": 7.437, + "args": { + "External id": 717655,"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": 6305208468765.771, "dur": 4.479, + "args": { + "External id": 717656,"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": 6305208468767.098, "dur": 3.058, + "args": { + "External id": 717657,"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": 6305208468774.910, "dur": 6.112, + "args": { + "External id": 717658,"Record function id": 0, "Sequence number": 7674715, "Fwd thread id": 1, "Ev Idx": 7001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208468776.218, "dur": 2.998, + "args": { + "External id": 717659,"Sequence number": 7674715, "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": 6305208468776.218, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208468777.271, "dur": 1.791, + "args": { + "External id": 717660,"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": 6305208468777.926, "dur": 1.004, + "args": { + "External id": 717661,"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": 6305208468785.935, "dur": 112.736, + "args": { + "External id": 717662,"Record function id": 0, "Sequence number": 7674714, "Fwd thread id": 1, "Ev Idx": 7005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208468786.998, "dur": 104.821, + "args": { + "External id": 717663,"Sequence number": 7674714, "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": 6305208468786.998, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305208468788.936, "dur": 2.680, + "args": { + "External id": 717664,"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": 6305208468789.555, "dur": 1.609, + "args": { + "External id": 717665,"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": 6305208468790.762, "dur": 0.321, + "args": { + "External id": 717666,"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": 6305208468792.421, "dur": 27.121, + "args": { + "External id": 717667,"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": 6305208468820.335, "dur": 5.763, + "args": { + "External id": 717668,"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": 6305208468823.116, "dur": 2.495, + "args": { + "External id": 717669,"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": 6305208468824.639, "dur": 0.852, + "args": { + "External id": 717670,"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": 6305208468827.247, "dur": 4.068, + "args": { + "External id": 717671,"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": 6305208468828.612, "dur": 2.157, + "args": { + "External id": 717672,"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": 6305208468830.009, "dur": 0.625, + "args": { + "External id": 717673,"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": 6305208468831.852, "dur": 59.143, + "args": { + "External id": 717674,"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": 6305208468903.562, "dur": 33.909, + "args": { + "External id": 717675,"Record function id": 0, "Sequence number": 7674713, "Fwd thread id": 1, "Ev Idx": 7018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208468906.616, "dur": 4.141, + "args": { + "External id": 717676,"Sequence number": 7674713, "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": 6305208468906.616, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208468908.155, "dur": 2.440, + "args": { + "External id": 717677,"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": 6305208468909.300, "dur": 1.184, + "args": { + "External id": 717678,"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": 6305208468914.022, "dur": 21.211, + "args": { + "External id": 717679,"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": 6305208468941.335, "dur": 10.288, + "args": { + "External id": 717680,"Record function id": 0, "Sequence number": 7674712, "Fwd thread id": 1, "Ev Idx": 7023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208468942.574, "dur": 6.917, + "args": { + "External id": 717681,"Sequence number": 7674712, "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": 6305208468942.574, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305208468943.362, "dur": 5.874, + "args": { + "External id": 717682,"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": 6305208468944.049, "dur": 4.580, + "args": { + "External id": 717683,"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": 6305208468947.807, "dur": 0.691, + "args": { + "External id": 717684,"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": 6305208468955.470, "dur": 5.535, + "args": { + "External id": 717685,"Record function id": 0, "Ev Idx": 7028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208468956.862, "dur": 3.547, + "args": { + "External id": 717686,"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": 6305208468957.834, "dur": 2.280, + "args": { + "External id": 717687,"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": 6305208468958.763, "dur": 1.258, + "args": { + "External id": 717688,"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": 6305208468964.120, "dur": 5.769, + "args": { + "External id": 717689,"Record function id": 0, "Sequence number": 7674711, "Fwd thread id": 1, "Ev Idx": 7032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208468965.202, "dur": 2.463, + "args": { + "External id": 717690,"Sequence number": 7674711, "Fwd thread 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": 6305208468965.202, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208468966.045, "dur": 1.462, + "args": { + "External id": 717691,"Record 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": 6305208468966.721, "dur": 0.658, + "args": { + "External id": 717692,"Record 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": 6305208468973.032, "dur": 176.504, + "args": { + "External id": 717693,"Record function id": 0, "Sequence number": 7674710, "Fwd thread id": 1, "Ev Idx": 7036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208468973.700, "dur": 166.253, + "args": { + "External id": 717694,"Sequence number": 7674710, "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": 6305208468973.700, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305208468978.225, "dur": 2.715, + "args": { + "External id": 717695,"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": 6305208468978.654, "dur": 1.848, + "args": { + "External id": 717696,"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": 6305208468979.796, "dur": 0.598, + "args": { + "External id": 717697,"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": 6305208468981.884, "dur": 51.634, + "args": { + "External id": 717698,"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": 6305208469034.637, "dur": 8.479, + "args": { + "External id": 717699,"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": 6305208469035.238, "dur": 7.249, + "args": { + "External id": 717700,"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": 6305208469039.624, "dur": 2.745, + "args": { + "External id": 717701,"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": 6305208469044.310, "dur": 3.184, + "args": { + "External id": 717702,"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": 6305208469045.428, "dur": 1.627, + "args": { + "External id": 717703,"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": 6305208469046.609, "dur": 0.377, + "args": { + "External id": 717704,"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": 6305208469048.081, "dur": 90.451, + "args": { + "External id": 717705,"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": 6305208469157.199, "dur": 29.986, + "args": { + "External id": 717706,"Record function id": 0, "Sequence number": 7674709, "Fwd thread id": 1, "Ev Idx": 7049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208469158.482, "dur": 7.534, + "args": { + "External id": 717707,"Sequence number": 7674709, "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": 6305208469158.482, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208469160.713, "dur": 5.130, + "args": { + "External id": 717708,"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": 6305208469163.903, "dur": 1.853, + "args": { + "External id": 717709,"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": 6305208469168.961, "dur": 15.640, + "args": { + "External id": 717710,"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": 6305208469190.876, "dur": 7.875, + "args": { + "External id": 717711,"Record function id": 0, "Sequence number": 7674708, "Fwd thread id": 1, "Ev Idx": 7054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208469191.784, "dur": 5.102, + "args": { + "External id": 717712,"Sequence number": 7674708, "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": 6305208469191.784, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305208469192.531, "dur": 4.151, + "args": { + "External id": 717713,"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": 6305208469193.775, "dur": 2.223, + "args": { + "External id": 717714,"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": 6305208469195.245, "dur": 0.627, + "args": { + "External id": 717715,"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": 6305208469203.082, "dur": 6.472, + "args": { + "External id": 717716,"Record function id": 0, "Ev Idx": 7059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208469204.707, "dur": 4.271, + "args": { + "External id": 717717,"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": 6305208469206.023, "dur": 2.333, + "args": { + "External id": 717718,"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": 6305208469206.764, "dur": 1.489, + "args": { + "External id": 717719,"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": 6305208469213.870, "dur": 386.220, + "args": { + "External id": 717720,"Record function id": 0, "Sequence number": 7674707, "Fwd thread id": 1, "Ev Idx": 7063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305208469215.601, "dur": 354.124, + "args": { + "External id": 717721,"Sequence number": 7674707, "Fwd thread 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": 6305208469215.601, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208469255.072, "dur": 2.533, + "args": { + "External id": 717722,"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": 6305208469256.258, "dur": 1.189, + "args": { + "External id": 717723,"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": 6305208469273.071, "dur": 4.236, + "args": { + "External id": 717724,"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": 6305208469286.935, "dur": 3.926, + "args": { + "External id": 717725,"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": 6305208469442.317, "dur": 1.787, + "args": { + "External id": 717726,"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": 6305208469448.396, "dur": 34.535, + "args": { + "External id": 717727,"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": 6305208469459.774, "dur": 0.857, + "args": { + "External id": 717728,"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": 6305208469488.833, "dur": 51.308, + "args": { + "External id": 717729,"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": 6305208469493.570, "dur": 46.315, + "args": { + "External id": 717730,"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": 6305208469497.579, "dur": 4.419, + "args": { + "External id": 717731,"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": 6305208469503.850, "dur": 34.819, + "args": { + "External id": 717732,"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": 6305208469546.307, "dur": 3.567, + "args": { + "External id": 717733,"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": 6305208469547.957, "dur": 1.768, + "args": { + "External id": 717734,"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": 6305208469556.810, "dur": 5.101, + "args": { + "External id": 717735,"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": 6305208469560.796, "dur": 1.019, + "args": { + "External id": 717736,"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": 6305208469580.287, "dur": 15.838, + "args": { + "External id": 717737,"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": 6305208469611.997, "dur": 8.768, + "args": { + "External id": 717738,"Record function id": 0, "Ev Idx": 7081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208469614.175, "dur": 5.915, + "args": { + "External id": 717739,"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": 6305208469616.112, "dur": 2.851, + "args": { + "External id": 717740,"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": 6305208469617.071, "dur": 1.786, + "args": { + "External id": 717741,"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": 6305208469624.660, "dur": 7.697, + "args": { + "External id": 717742,"Record function id": 0, "Sequence number": 7674706, "Fwd thread id": 1, "Ev Idx": 7085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208469627.941, "dur": 1.620, + "args": { + "External id": 717743,"Sequence number": 7674706, "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": 6305208469627.941, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SwiGLULinearFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305208469636.218, "dur": 476.375, + "args": { + "External id": 717744,"Record function id": 0, "Sequence number": 7674705, "Fwd thread id": 1, "Ev Idx": 7087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305208469637.465, "dur": 460.888, + "args": { + "External id": 717745,"Sequence number": 7674705, "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": 6305208469637.465, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208469667.161, "dur": 8.464, + "args": { + "External id": 717746,"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": 6305208469672.190, "dur": 3.173, + "args": { + "External id": 717747,"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": 6305208469678.674, "dur": 7.119, + "args": { + "External id": 717748,"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": 6305208469679.829, "dur": 5.373, + "args": { + "External id": 717749,"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": 6305208469684.178, "dur": 0.892, + "args": { + "External id": 717750,"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": 6305208469689.311, "dur": 106.506, + "args": { + "External id": 717751,"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": 6305208469690.292, "dur": 3.549, + "args": { + "External id": 717752,"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": 6305208469690.974, "dur": 2.350, + "args": { + "External id": 717753,"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": 6305208469692.469, "dur": 0.776, + "args": { + "External id": 717754,"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": 6305208469694.818, "dur": 100.413, + "args": { + "External id": 717755,"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": 6305208469696.767, "dur": 97.634, + "args": { + "External id": 717756,"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": 6305208469802.026, "dur": 3.486, + "args": { + "External id": 717757,"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": 6305208469803.864, "dur": 1.523, + "args": { + "External id": 717758,"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": 6305208469841.409, "dur": 4.134, + "args": { + "External id": 717759,"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": 6305208469846.790, "dur": 2.851, + "args": { + "External id": 717760,"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": 6305208469850.823, "dur": 2.470, + "args": { + "External id": 717761,"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": 6305208469887.576, "dur": 2.117, + "args": { + "External id": 717762,"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": 6305208469888.219, "dur": 1.292, + "args": { + "External id": 717763,"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": 6305208469912.819, "dur": 126.331, + "args": { + "External id": 717764,"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": 6305208469918.011, "dur": 5.974, + "args": { + "External id": 717765,"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": 6305208469922.234, "dur": 0.860, + "args": { + "External id": 717766,"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": 6305208469925.752, "dur": 8.066, + "args": { + "External id": 717767,"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": 6305208469932.139, "dur": 0.705, + "args": { + "External id": 717768,"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": 6305208469935.205, "dur": 5.410, + "args": { + "External id": 717769,"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": 6305208469937.387, "dur": 2.880, + "args": { + "External id": 717770,"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": 6305208469941.410, "dur": 3.264, + "args": { + "External id": 717771,"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": 6305208469943.572, "dur": 0.623, + "args": { + "External id": 717772,"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": 6305208469948.705, "dur": 2.794, + "args": { + "External id": 717773,"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": 6305208469950.464, "dur": 0.715, + "args": { + "External id": 717774,"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": 6305208469954.906, "dur": 5.937, + "args": { + "External id": 717775,"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": 6305208469958.863, "dur": 1.828, + "args": { + "External id": 717776,"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": 6305208469962.195, "dur": 2.510, + "args": { + "External id": 717777,"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": 6305208469963.786, "dur": 0.584, + "args": { + "External id": 717778,"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": 6305208469965.539, "dur": 2.467, + "args": { + "External id": 717779,"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": 6305208469966.683, "dur": 1.228, + "args": { + "External id": 717780,"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": 6305208469969.061, "dur": 56.443, + "args": { + "External id": 717781,"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": 6305208470027.665, "dur": 1.323, + "args": { + "External id": 717782,"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": 6305208470029.714, "dur": 5.433, + "args": { + "External id": 717783,"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": 6305208470031.731, "dur": 2.872, + "args": { + "External id": 717784,"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": 6305208470037.220, "dur": 0.846, + "args": { + "External id": 717785,"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": 6305208470125.886, "dur": 10.441, + "args": { + "External id": 717786,"Record function id": 0, "Ev Idx": 7129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208470128.375, "dur": 7.220, + "args": { + "External id": 717787,"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": 6305208470131.179, "dur": 3.382, + "args": { + "External id": 717788,"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": 6305208470132.199, "dur": 2.238, + "args": { + "External id": 717789,"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": 6305208470140.511, "dur": 8.318, + "args": { + "External id": 717790,"Record function id": 0, "Sequence number": 7674704, "Fwd thread id": 1, "Ev Idx": 7133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208470141.458, "dur": 5.161, + "args": { + "External id": 717791,"Sequence number": 7674704, "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": 6305208470141.458, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208470143.943, "dur": 2.467, + "args": { + "External id": 717792,"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": 6305208470144.736, "dur": 1.524, + "args": { + "External id": 717793,"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": 6305208470152.565, "dur": 121.654, + "args": { + "External id": 717794,"Record function id": 0, "Sequence number": 7674703, "Fwd thread id": 1, "Ev Idx": 7137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208470156.279, "dur": 111.026, + "args": { + "External id": 717795,"Sequence number": 7674703, "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": 6305208470156.279, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305208470159.760, "dur": 4.497, + "args": { + "External id": 717796,"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": 6305208470161.236, "dur": 2.408, + "args": { + "External id": 717797,"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": 6305208470162.696, "dur": 0.669, + "args": { + "External id": 717798,"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": 6305208470165.351, "dur": 52.178, + "args": { + "External id": 717799,"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": 6305208470218.770, "dur": 6.255, + "args": { + "External id": 717800,"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": 6305208470219.324, "dur": 5.166, + "args": { + "External id": 717801,"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": 6305208470223.103, "dur": 1.193, + "args": { + "External id": 717802,"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": 6305208470226.373, "dur": 3.925, + "args": { + "External id": 717803,"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": 6305208470227.315, "dur": 2.504, + "args": { + "External id": 717804,"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": 6305208470229.083, "dur": 0.627, + "args": { + "External id": 717805,"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": 6305208470230.693, "dur": 35.693, + "args": { + "External id": 717806,"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": 6305208470278.963, "dur": 11.203, + "args": { + "External id": 717807,"Record function id": 0, "Sequence number": 7674702, "Fwd thread id": 1, "Ev Idx": 7150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208470280.213, "dur": 8.423, + "args": { + "External id": 717808,"Sequence number": 7674702, "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": 6305208470280.213, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208470281.572, "dur": 6.915, + "args": { + "External id": 717809,"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": 6305208470284.791, "dur": 3.561, + "args": { + "External id": 717810,"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": 6305208470293.883, "dur": 7.527, + "args": { + "External id": 717811,"Record function id": 0, "Sequence number": 7674701, "Fwd thread id": 1, "Ev Idx": 7154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208470294.743, "dur": 4.738, + "args": { + "External id": 717812,"Sequence number": 7674701, "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": 6305208470294.743, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305208470295.527, "dur": 3.718, + "args": { + "External id": 717813,"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": 6305208470296.282, "dur": 2.420, + "args": { + "External id": 717814,"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": 6305208470297.792, "dur": 0.744, + "args": { + "External id": 717815,"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": 6305208470305.894, "dur": 5.060, + "args": { + "External id": 717816,"Record function id": 0, "Ev Idx": 7159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208470307.207, "dur": 3.209, + "args": { + "External id": 717817,"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": 6305208470308.226, "dur": 1.937, + "args": { + "External id": 717818,"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": 6305208470308.983, "dur": 1.074, + "args": { + "External id": 717819,"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": 6305208470314.300, "dur": 8.394, + "args": { + "External id": 717820,"Record function id": 0, "Sequence number": 7674700, "Fwd thread id": 1, "Ev Idx": 7163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208470315.340, "dur": 5.633, + "args": { + "External id": 717821,"Sequence number": 7674700, "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": 6305208470315.340, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208470319.119, "dur": 1.694, + "args": { + "External id": 717822,"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": 6305208470319.994, "dur": 0.678, + "args": { + "External id": 717823,"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": 6305208470325.936, "dur": 152.679, + "args": { + "External id": 717824,"Record function id": 0, "Sequence number": 7674699, "Fwd thread id": 1, "Ev Idx": 7167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208470378.337, "dur": 92.657, + "args": { + "External id": 717825,"Sequence number": 7674699, "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": 6305208470378.337, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305208470380.257, "dur": 5.347, + "args": { + "External id": 717826,"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": 6305208470380.732, "dur": 4.377, + "args": { + "External id": 717827,"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": 6305208470384.590, "dur": 0.381, + "args": { + "External id": 717828,"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": 6305208470386.247, "dur": 36.015, + "args": { + "External id": 717829,"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": 6305208470423.531, "dur": 4.875, + "args": { + "External id": 717830,"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": 6305208470424.016, "dur": 3.847, + "args": { + "External id": 717831,"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": 6305208470425.270, "dur": 2.417, + "args": { + "External id": 717832,"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": 6305208470429.691, "dur": 5.481, + "args": { + "External id": 717833,"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": 6305208470430.692, "dur": 4.028, + "args": { + "External id": 717834,"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": 6305208470434.072, "dur": 0.575, + "args": { + "External id": 717835,"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": 6305208470435.584, "dur": 34.603, + "args": { + "External id": 717836,"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": 6305208470483.525, "dur": 51.076, + "args": { + "External id": 717837,"Record function id": 0, "Sequence number": 7674698, "Fwd thread id": 1, "Ev Idx": 7180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208470484.444, "dur": 3.928, + "args": { + "External id": 717838,"Sequence number": 7674698, "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": 6305208470484.444, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208470485.947, "dur": 2.268, + "args": { + "External id": 717839,"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": 6305208470486.839, "dur": 1.251, + "args": { + "External id": 717840,"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": 6305208470491.156, "dur": 39.476, + "args": { + "External id": 717841,"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": 6305208470540.961, "dur": 10.271, + "args": { + "External id": 717842,"Record function id": 0, "Sequence number": 7674697, "Fwd thread id": 1, "Ev Idx": 7185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208470542.234, "dur": 7.262, + "args": { + "External id": 717843,"Sequence number": 7674697, "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": 6305208470542.234, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305208470545.176, "dur": 4.094, + "args": { + "External id": 717844,"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": 6305208470546.201, "dur": 2.272, + "args": { + "External id": 717845,"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": 6305208470547.801, "dur": 0.551, + "args": { + "External id": 717846,"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": 6305208470555.714, "dur": 5.120, + "args": { + "External id": 717847,"Record function id": 0, "Ev Idx": 7190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208470556.774, "dur": 3.527, + "args": { + "External id": 717848,"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": 6305208470557.974, "dur": 1.982, + "args": { + "External id": 717849,"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": 6305208470558.516, "dur": 1.345, + "args": { + "External id": 717850,"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": 6305208470565.281, "dur": 431.490, + "args": { + "External id": 717851,"Record function id": 0, "Sequence number": 7674696, "Fwd thread id": 1, "Ev Idx": 7194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305208470569.788, "dur": 392.202, + "args": { + "External id": 717852,"Sequence number": 7674696, "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": 6305208470569.788, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338707, "tid": 2379456, + "ts": 6305208470595.066, "dur": 38.254, + "args": { + "External id": 717853,"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": 6305208470596.847, "dur": 36.183, + "args": { + "External id": 717854,"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": 6305208470599.789, "dur": 6.944, + "args": { + "External id": 717855,"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": 6305208470602.619, "dur": 3.542, + "args": { + "External id": 717856,"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": 6305208470608.118, "dur": 24.496, + "args": { + "External id": 717857,"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": 6305208470647.068, "dur": 2.205, + "args": { + "External id": 717858,"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": 6305208470647.650, "dur": 1.448, + "args": { + "External id": 717859,"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": 6305208470653.123, "dur": 1.049, + "args": { + "External id": 717860,"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": 6305208470653.452, "dur": 0.618, + "args": { + "External id": 717861,"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": 6305208470669.142, "dur": 4.793, + "args": { + "External id": 717862,"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": 6305208470684.596, "dur": 2.411, + "args": { + "External id": 717863,"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": 6305208470848.403, "dur": 4.133, + "args": { + "External id": 717864,"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": 6305208470857.088, "dur": 32.954, + "args": { + "External id": 717865,"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": 6305208470866.365, "dur": 0.991, + "args": { + "External id": 717866,"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": 6305208470895.487, "dur": 34.874, + "args": { + "External id": 717867,"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": 6305208470897.332, "dur": 32.772, + "args": { + "External id": 717868,"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": 6305208470905.511, "dur": 4.145, + "args": { + "External id": 717869,"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": 6305208470913.667, "dur": 15.899, + "args": { + "External id": 717870,"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": 6305208470934.432, "dur": 1.770, + "args": { + "External id": 717871,"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": 6305208470935.275, "dur": 0.797, + "args": { + "External id": 717872,"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": 6305208470944.227, "dur": 2.291, + "args": { + "External id": 717873,"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": 6305208470945.345, "dur": 1.072, + "args": { + "External id": 717874,"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": 6305208470948.963, "dur": 1.951, + "args": { + "External id": 717875,"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": 6305208470949.999, "dur": 0.826, + "args": { + "External id": 717876,"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": 6305208470978.107, "dur": 17.018, + "args": { + "External id": 717877,"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": 6305208471006.422, "dur": 7.344, + "args": { + "External id": 717878,"Record function id": 0, "Ev Idx": 7221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208471008.529, "dur": 4.631, + "args": { + "External id": 717879,"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": 6305208471010.161, "dur": 2.111, + "args": { + "External id": 717880,"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": 6305208471010.912, "dur": 1.257, + "args": { + "External id": 717881,"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": 6305208471017.472, "dur": 8.102, + "args": { + "External id": 717882,"Record function id": 0, "Sequence number": 7674695, "Fwd thread id": 1, "Ev Idx": 7225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208471018.613, "dur": 4.027, + "args": { + "External id": 717883,"Sequence number": 7674695, "Fwd thread 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": 6305208471018.613, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208471020.191, "dur": 2.225, + "args": { + "External id": 717884,"Record 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": 6305208471021.273, "dur": 1.019, + "args": { + "External id": 717885,"Record 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": 6305208471029.096, "dur": 186.671, + "args": { + "External id": 717886,"Record function id": 0, "Sequence number": 7674694, "Fwd thread id": 1, "Ev Idx": 7229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208471032.619, "dur": 175.176, + "args": { + "External id": 717887,"Sequence number": 7674694, "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": 6305208471032.619, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305208471035.392, "dur": 4.505, + "args": { + "External id": 717888,"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": 6305208471036.693, "dur": 2.679, + "args": { + "External id": 717889,"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": 6305208471038.462, "dur": 0.736, + "args": { + "External id": 717890,"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": 6305208471040.848, "dur": 106.805, + "args": { + "External id": 717891,"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": 6305208471150.232, "dur": 10.600, + "args": { + "External id": 717892,"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": 6305208471151.412, "dur": 8.419, + "args": { + "External id": 717893,"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": 6305208471156.336, "dur": 3.350, + "args": { + "External id": 717894,"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": 6305208471162.516, "dur": 3.699, + "args": { + "External id": 717895,"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": 6305208471163.729, "dur": 1.830, + "args": { + "External id": 717896,"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": 6305208471165.019, "dur": 0.470, + "args": { + "External id": 717897,"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": 6305208471167.010, "dur": 39.760, + "args": { + "External id": 717898,"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": 6305208471223.225, "dur": 10.010, + "args": { + "External id": 717899,"Record function id": 0, "Sequence number": 7674693, "Fwd thread id": 1, "Ev Idx": 7242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208471224.136, "dur": 6.801, + "args": { + "External id": 717900,"Sequence number": 7674693, "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": 6305208471224.136, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208471227.923, "dur": 2.871, + "args": { + "External id": 717901,"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": 6305208471229.304, "dur": 1.351, + "args": { + "External id": 717902,"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": 6305208471236.908, "dur": 7.303, + "args": { + "External id": 717903,"Record function id": 0, "Sequence number": 7674692, "Fwd thread id": 1, "Ev Idx": 7246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208471237.883, "dur": 4.556, + "args": { + "External id": 717904,"Sequence number": 7674692, "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": 6305208471237.883, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305208471238.894, "dur": 3.326, + "args": { + "External id": 717905,"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": 6305208471239.721, "dur": 2.027, + "args": { + "External id": 717906,"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": 6305208471241.130, "dur": 0.496, + "args": { + "External id": 717907,"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": 6305208471248.562, "dur": 9.070, + "args": { + "External id": 717908,"Record function id": 0, "Ev Idx": 7251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208471249.883, "dur": 7.223, + "args": { + "External id": 717909,"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": 6305208471251.687, "dur": 5.095, + "args": { + "External id": 717910,"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": 6305208471254.896, "dur": 1.754, + "args": { + "External id": 717911,"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": 6305208471260.787, "dur": 5.995, + "args": { + "External id": 717912,"Record function id": 0, "Sequence number": 7674691, "Fwd thread id": 1, "Ev Idx": 7255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208471261.789, "dur": 3.258, + "args": { + "External id": 717913,"Sequence number": 7674691, "Fwd thread 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": 6305208471261.789, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208471262.799, "dur": 2.086, + "args": { + "External id": 717914,"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": 6305208471263.657, "dur": 1.098, + "args": { + "External id": 717915,"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": 6305208471271.363, "dur": 378.767, + "args": { + "External id": 717916,"Record function id": 0, "Sequence number": 7674690, "Fwd thread id": 1, "Ev Idx": 7259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFuncBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305208471272.823, "dur": 357.943, + "args": { + "External id": 717917,"Sequence number": 7674690, "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": 6305208471272.823, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338707, "tid": 2379456, + "ts": 6305208471290.427, "dur": 10.315, + "args": { + "External id": 717918,"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": 6305208471293.880, "dur": 6.401, + "args": { + "External id": 717919,"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": 6305208471302.888, "dur": 3.826, + "args": { + "External id": 717920,"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": 6305208471304.321, "dur": 2.185, + "args": { + "External id": 717921,"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": 6305208471307.843, "dur": 3.842, + "args": { + "External id": 717922,"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": 6305208471309.792, "dur": 1.737, + "args": { + "External id": 717923,"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": 6305208471336.471, "dur": 268.045, + "args": { + "External id": 717924,"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": 6305208471415.314, "dur": 3.420, + "args": { + "External id": 717925,"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": 6305208471422.635, "dur": 3.078, + "args": { + "External id": 717926,"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": 6305208471426.966, "dur": 2.017, + "args": { + "External id": 717927,"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": 6305208471430.250, "dur": 2.752, + "args": { + "External id": 717928,"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": 6305208471478.233, "dur": 2.431, + "args": { + "External id": 717929,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305208471479.155, "dur": 1.384, + "args": { + "External id": 717930,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305208471482.241, "dur": 52.678, + "args": { + "External id": 717931,"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": 6305208471488.189, "dur": 4.999, + "args": { + "External id": 717932,"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": 6305208471537.714, "dur": 2.087, + "args": { + "External id": 717933,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305208471538.799, "dur": 0.938, + "args": { + "External id": 717934,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305208471542.708, "dur": 16.271, + "args": { + "External id": 717935,"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": 6305208471545.926, "dur": 0.490, + "args": { + "External id": 717936,"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": 6305208471618.051, "dur": 3.900, + "args": { + "External id": 717937,"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": 6305208471624.924, "dur": 0.680, + "args": { + "External id": 717938,"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": 6305208471627.268, "dur": 0.881, + "args": { + "External id": 717939,"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": 6305208471660.507, "dur": 224.718, + "args": { + "External id": 717940,"Record function id": 0, "Sequence number": 7674689, "Fwd thread id": 1, "Ev Idx": 7283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305208471662.138, "dur": 216.228, + "args": { + "External id": 717941,"Sequence number": 7674689, "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": 6305208471662.138, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338707, "tid": 2379456, + "ts": 6305208471682.532, "dur": 44.572, + "args": { + "External id": 717942,"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": 6305208471686.579, "dur": 3.392, + "args": { + "External id": 717943,"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": 6305208471691.658, "dur": 34.788, + "args": { + "External id": 717944,"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": 6305208471737.331, "dur": 5.496, + "args": { + "External id": 717945,"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": 6305208471739.605, "dur": 2.921, + "args": { + "External id": 717946,"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": 6305208471891.760, "dur": 160.321, + "args": { + "External id": 717947,"Record function id": 0, "Sequence number": 7674688, "Fwd thread id": 1, "Ev Idx": 7290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305208471893.717, "dur": 151.978, + "args": { + "External id": 717948,"Sequence number": 7674688, "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": 6305208471893.717, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 2338707, "tid": 2379456, + "ts": 6305208471904.204, "dur": 40.652, + "args": { + "External id": 717949,"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": 6305208471907.287, "dur": 2.599, + "args": { + "External id": 717950,"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": 6305208471911.492, "dur": 32.785, + "args": { + "External id": 717951,"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": 6305208471952.054, "dur": 5.644, + "args": { + "External id": 717952,"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": 6305208471954.565, "dur": 2.834, + "args": { + "External id": 717953,"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": 6305208472099.374, "dur": 19.523, + "args": { + "External id": 717954,"Record function id": 0, "Sequence number": 7674687, "Fwd thread id": 1, "Ev Idx": 7297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208472101.764, "dur": 13.397, + "args": { + "External id": 717955,"Sequence number": 7674687, "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": 6305208472101.764, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208472104.714, "dur": 10.120, + "args": { + "External id": 717956,"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": 6305208472106.568, "dur": 7.996, + "args": { + "External id": 717957,"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": 6305208472123.254, "dur": 6.484, + "args": { + "External id": 717958,"Record function id": 0, "Sequence number": 7674686, "Fwd thread id": 1, "Ev Idx": 7301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208472124.308, "dur": 3.746, + "args": { + "External id": 717959,"Sequence number": 7674686, "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": 6305208472124.308, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208472125.827, "dur": 2.088, + "args": { + "External id": 717960,"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": 6305208472126.683, "dur": 1.133, + "args": { + "External id": 717961,"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": 6305208472133.706, "dur": 8.140, + "args": { + "External id": 717962,"Record function id": 0, "Sequence number": 7674685, "Fwd thread id": 1, "Ev Idx": 7305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208472136.771, "dur": 3.260, + "args": { + "External id": 717963,"Sequence number": 7674685, "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": 6305208472136.771, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208472138.058, "dur": 1.819, + "args": { + "External id": 717964,"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": 6305208472138.952, "dur": 0.795, + "args": { + "External id": 717965,"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": 6305208472145.371, "dur": 5.368, + "args": { + "External id": 717966,"Record function id": 0, "Sequence number": 7674684, "Fwd thread id": 1, "Ev Idx": 7309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208472146.227, "dur": 2.770, + "args": { + "External id": 717967,"Sequence number": 7674684, "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": 6305208472146.227, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208472147.427, "dur": 1.425, + "args": { + "External id": 717968,"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": 6305208472147.891, "dur": 0.868, + "args": { + "External id": 717969,"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": 6305208472154.419, "dur": 167.204, + "args": { + "External id": 717970,"Record function id": 0, "Sequence number": 7674683, "Fwd thread id": 1, "Ev Idx": 7313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208472155.259, "dur": 158.173, + "args": { + "External id": 717971,"Sequence number": 7674683, "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": 6305208472155.259, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305208472161.463, "dur": 7.017, + "args": { + "External id": 717972,"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": 6305208472163.645, "dur": 4.142, + "args": { + "External id": 717973,"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": 6305208472166.059, "dur": 1.460, + "args": { + "External id": 717974,"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": 6305208472170.193, "dur": 77.710, + "args": { + "External id": 717975,"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": 6305208472249.138, "dur": 7.544, + "args": { + "External id": 717976,"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": 6305208472249.965, "dur": 5.895, + "args": { + "External id": 717977,"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": 6305208472254.169, "dur": 1.490, + "args": { + "External id": 717978,"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": 6305208472258.708, "dur": 3.700, + "args": { + "External id": 717979,"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": 6305208472259.821, "dur": 2.065, + "args": { + "External id": 717980,"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": 6305208472261.202, "dur": 0.598, + "args": { + "External id": 717981,"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": 6305208472263.786, "dur": 48.554, + "args": { + "External id": 717982,"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": 6305208472327.055, "dur": 7.363, + "args": { + "External id": 717983,"Record function id": 0, "Sequence number": 7674682, "Fwd thread id": 1, "Ev Idx": 7326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208472328.281, "dur": 4.558, + "args": { + "External id": 717984,"Sequence number": 7674682, "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": 6305208472328.281, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208472330.262, "dur": 2.408, + "args": { + "External id": 717985,"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": 6305208472331.199, "dur": 1.341, + "args": { + "External id": 717986,"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": 6305208472340.310, "dur": 8.150, + "args": { + "External id": 717987,"Record function id": 0, "Sequence number": 7674681, "Fwd thread id": 1, "Ev Idx": 7330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208472341.030, "dur": 5.229, + "args": { + "External id": 717988,"Sequence number": 7674681, "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": 6305208472341.030, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305208472342.150, "dur": 3.930, + "args": { + "External id": 717989,"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": 6305208472342.949, "dur": 2.558, + "args": { + "External id": 717990,"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": 6305208472344.721, "dur": 0.662, + "args": { + "External id": 717991,"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": 6305208472354.470, "dur": 10.151, + "args": { + "External id": 717992,"Record function id": 0, "Ev Idx": 7335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208472356.467, "dur": 7.329, + "args": { + "External id": 717993,"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": 6305208472359.155, "dur": 4.212, + "args": { + "External id": 717994,"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": 6305208472360.432, "dur": 2.826, + "args": { + "External id": 717995,"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": 6305208472367.980, "dur": 7.972, + "args": { + "External id": 717996,"Record function id": 0, "Sequence number": 7674680, "Fwd thread id": 1, "Ev Idx": 7339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208472368.928, "dur": 5.225, + "args": { + "External id": 717997,"Sequence number": 7674680, "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": 6305208472368.928, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208472372.528, "dur": 1.468, + "args": { + "External id": 717998,"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": 6305208472373.147, "dur": 0.714, + "args": { + "External id": 717999,"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": 6305208472379.312, "dur": 94.601, + "args": { + "External id": 718000,"Record function id": 0, "Sequence number": 7674679, "Fwd thread id": 1, "Ev Idx": 7343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208472380.121, "dur": 86.802, + "args": { + "External id": 718001,"Sequence number": 7674679, "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": 6305208472380.121, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305208472382.500, "dur": 5.362, + "args": { + "External id": 718002,"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": 6305208472383.525, "dur": 3.875, + "args": { + "External id": 718003,"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": 6305208472386.823, "dur": 0.477, + "args": { + "External id": 718004,"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": 6305208472388.653, "dur": 28.107, + "args": { + "External id": 718005,"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": 6305208472417.921, "dur": 4.019, + "args": { + "External id": 718006,"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": 6305208472418.659, "dur": 2.670, + "args": { + "External id": 718007,"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": 6305208472420.146, "dur": 1.049, + "args": { + "External id": 718008,"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": 6305208472423.109, "dur": 7.240, + "args": { + "External id": 718009,"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": 6305208472424.442, "dur": 5.458, + "args": { + "External id": 718010,"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": 6305208472427.544, "dur": 2.288, + "args": { + "External id": 718011,"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": 6305208472431.205, "dur": 34.923, + "args": { + "External id": 718012,"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": 6305208472478.531, "dur": 68.804, + "args": { + "External id": 718013,"Record function id": 0, "Sequence number": 7674678, "Fwd thread id": 1, "Ev Idx": 7356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208472488.734, "dur": 11.404, + "args": { + "External id": 718014,"Sequence number": 7674678, "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": 6305208472488.734, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208472497.830, "dur": 2.155, + "args": { + "External id": 718015,"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": 6305208472498.931, "dur": 0.917, + "args": { + "External id": 718016,"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": 6305208472503.651, "dur": 40.080, + "args": { + "External id": 718017,"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": 6305208472553.587, "dur": 12.840, + "args": { + "External id": 718018,"Record function id": 0, "Sequence number": 7674677, "Fwd thread id": 1, "Ev Idx": 7361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208472554.952, "dur": 8.772, + "args": { + "External id": 718019,"Sequence number": 7674677, "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": 6305208472554.952, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305208472558.594, "dur": 4.923, + "args": { + "External id": 718020,"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": 6305208472559.854, "dur": 2.917, + "args": { + "External id": 718021,"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": 6305208472561.801, "dur": 0.823, + "args": { + "External id": 718022,"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": 6305208472570.925, "dur": 7.107, + "args": { + "External id": 718023,"Record function id": 0, "Ev Idx": 7366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208472572.498, "dur": 5.005, + "args": { + "External id": 718024,"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": 6305208472574.087, "dur": 3.084, + "args": { + "External id": 718025,"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": 6305208472575.390, "dur": 1.655, + "args": { + "External id": 718026,"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": 6305208472581.627, "dur": 9.405, + "args": { + "External id": 718027,"Record function id": 0, "Sequence number": 7674676, "Fwd thread id": 1, "Ev Idx": 7370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208472582.761, "dur": 6.203, + "args": { + "External id": 718028,"Sequence number": 7674676, "Fwd thread 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": 6305208472582.761, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208472584.224, "dur": 4.579, + "args": { + "External id": 718029,"Record 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": 6305208472587.671, "dur": 1.040, + "args": { + "External id": 718030,"Record 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": 6305208472594.748, "dur": 105.074, + "args": { + "External id": 718031,"Record function id": 0, "Sequence number": 7674675, "Fwd thread id": 1, "Ev Idx": 7374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208472595.801, "dur": 96.832, + "args": { + "External id": 718032,"Sequence number": 7674675, "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": 6305208472595.801, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305208472598.216, "dur": 3.551, + "args": { + "External id": 718033,"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": 6305208472599.261, "dur": 2.061, + "args": { + "External id": 718034,"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": 6305208472600.535, "dur": 0.664, + "args": { + "External id": 718035,"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": 6305208472602.787, "dur": 40.977, + "args": { + "External id": 718036,"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": 6305208472646.923, "dur": 3.574, + "args": { + "External id": 718037,"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": 6305208472647.537, "dur": 2.242, + "args": { + "External id": 718038,"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": 6305208472649.131, "dur": 0.537, + "args": { + "External id": 718039,"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": 6305208472652.008, "dur": 3.898, + "args": { + "External id": 718040,"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": 6305208472652.932, "dur": 2.505, + "args": { + "External id": 718041,"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": 6305208472654.842, "dur": 0.521, + "args": { + "External id": 718042,"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": 6305208472658.489, "dur": 33.175, + "args": { + "External id": 718043,"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": 6305208472704.297, "dur": 25.858, + "args": { + "External id": 718044,"Record function id": 0, "Sequence number": 7674674, "Fwd thread id": 1, "Ev Idx": 7387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208472705.471, "dur": 4.269, + "args": { + "External id": 718045,"Sequence number": 7674674, "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": 6305208472705.471, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208472707.547, "dur": 2.015, + "args": { + "External id": 718046,"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": 6305208472708.457, "dur": 0.983, + "args": { + "External id": 718047,"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": 6305208472712.379, "dur": 15.085, + "args": { + "External id": 718048,"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": 6305208472734.184, "dur": 9.024, + "args": { + "External id": 718049,"Record function id": 0, "Sequence number": 7674673, "Fwd thread id": 1, "Ev Idx": 7392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 2338707, "tid": 2379456, + "ts": 6305208472735.153, "dur": 6.546, + "args": { + "External id": 718050,"Sequence number": 7674673, "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": 6305208472735.153, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 2338707, "tid": 2379456, + "ts": 6305208472735.947, "dur": 5.556, + "args": { + "External id": 718051,"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": 6305208472736.751, "dur": 4.172, + "args": { + "External id": 718052,"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": 6305208472740.090, "dur": 0.709, + "args": { + "External id": 718053,"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": 6305208472747.515, "dur": 4.920, + "args": { + "External id": 718054,"Record function id": 0, "Ev Idx": 7397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208472748.891, "dur": 3.035, + "args": { + "External id": 718055,"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": 6305208472749.717, "dur": 1.756, + "args": { + "External id": 718056,"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": 6305208472750.177, "dur": 1.199, + "args": { + "External id": 718057,"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": 6305208472756.737, "dur": 410.532, + "args": { + "External id": 718058,"Record function id": 0, "Sequence number": 7674672, "Fwd thread id": 1, "Ev Idx": 7401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305208472758.184, "dur": 369.665, + "args": { + "External id": 718059,"Sequence number": 7674672, "Fwd thread 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": 6305208472758.184, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2379456, + "ts": 6305208472794.382, "dur": 2.145, + "args": { + "External id": 718060,"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": 6305208472794.964, "dur": 1.450, + "args": { + "External id": 718061,"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": 6305208472814.935, "dur": 6.793, + "args": { + "External id": 718062,"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": 6305208472830.911, "dur": 2.094, + "args": { + "External id": 718063,"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": 6305208472979.069, "dur": 1.986, + "args": { + "External id": 718064,"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": 6305208472987.500, "dur": 35.351, + "args": { + "External id": 718065,"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": 6305208472999.140, "dur": 0.782, + "args": { + "External id": 718066,"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": 6305208473028.301, "dur": 71.568, + "args": { + "External id": 718067,"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": 6305208473030.053, "dur": 69.529, + "args": { + "External id": 718068,"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": 6305208473034.624, "dur": 5.240, + "args": { + "External id": 718069,"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": 6305208473044.064, "dur": 54.227, + "args": { + "External id": 718070,"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": 6305208473106.347, "dur": 3.615, + "args": { + "External id": 718071,"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": 6305208473107.909, "dur": 1.945, + "args": { + "External id": 718072,"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": 6305208473117.936, "dur": 2.828, + "args": { + "External id": 718073,"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": 6305208473119.287, "dur": 1.305, + "args": { + "External id": 718074,"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": 6305208473145.037, "dur": 17.119, + "args": { + "External id": 718075,"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": 6305208473180.183, "dur": 8.489, + "args": { + "External id": 718076,"Record function id": 0, "Ev Idx": 7419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208473182.271, "dur": 5.702, + "args": { + "External id": 718077,"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": 6305208473184.314, "dur": 2.795, + "args": { + "External id": 718078,"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": 6305208473185.068, "dur": 1.934, + "args": { + "External id": 718079,"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": 6305208473192.835, "dur": 2812.535, + "args": { + "External id": 718080,"Record function id": 0, "Ev Idx": 7423 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.25)", "pid": 2338707, "tid": 2379456, + "ts": 6305208473224.600, "dur": 930.594, + "args": { + "External id": 718081,"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": 6305208473252.416, "dur": 893.235, + "args": { + "External id": 718082,"Record function id": 0, "Ev Idx": 7425 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.24)", "pid": 2338707, "tid": 2379456, + "ts": 6305208473265.416, "dur": 863.514, + "args": { + "External id": 718083,"Record function id": 0, "Ev Idx": 7426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305208473339.530, "dur": 7.823, + "args": { + "External id": 718084,"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": 6305208473362.394, "dur": 31.913, + "args": { + "External id": 718085,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305208473366.575, "dur": 1.445, + "args": { + "External id": 718086,"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": 6305208473369.488, "dur": 2.981, + "args": { + "External id": 718087,"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": 6305208473376.193, "dur": 0.336, + "args": { + "External id": 718088,"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": 6305208473377.472, "dur": 0.464, + "args": { + "External id": 718089,"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": 6305208473379.596, "dur": 0.578, + "args": { + "External id": 718090,"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": 6305208473382.729, "dur": 0.388, + "args": { + "External id": 718091,"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": 6305208473384.829, "dur": 0.289, + "args": { + "External id": 718092,"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": 6305208473385.859, "dur": 2.151, + "args": { + "External id": 718093,"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": 6305208473390.183, "dur": 0.578, + "args": { + "External id": 718094,"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": 6305208473405.567, "dur": 41.971, + "args": { + "External id": 718095,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305208473482.624, "dur": 150.905, + "args": { + "External id": 718096,"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": 6305208473493.944, "dur": 6.235, + "args": { + "External id": 718097,"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": 6305208473521.650, "dur": 12.476, + "args": { + "External id": 718098,"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": 6305208473526.744, "dur": 7.006, + "args": { + "External id": 718099,"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": 6305208473530.862, "dur": 0.967, + "args": { + "External id": 718100,"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": 6305208473542.600, "dur": 30.952, + "args": { + "External id": 718101,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305208473544.653, "dur": 0.388, + "args": { + "External id": 718102,"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": 6305208473546.703, "dur": 2.784, + "args": { + "External id": 718103,"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": 6305208473550.772, "dur": 0.396, + "args": { + "External id": 718104,"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": 6305208473552.782, "dur": 0.354, + "args": { + "External id": 718105,"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": 6305208473556.372, "dur": 0.322, + "args": { + "External id": 718106,"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": 6305208473558.043, "dur": 0.286, + "args": { + "External id": 718107,"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": 6305208473559.217, "dur": 2.145, + "args": { + "External id": 718108,"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": 6305208473566.004, "dur": 0.269, + "args": { + "External id": 718109,"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": 6305208473567.597, "dur": 0.326, + "args": { + "External id": 718110,"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": 6305208473586.793, "dur": 38.793, + "args": { + "External id": 718111,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305208473692.194, "dur": 298.631, + "args": { + "External id": 718112,"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": 6305208473725.657, "dur": 260.198, + "args": { + "External id": 718113,"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": 6305208473736.418, "dur": 243.879, + "args": { + "External id": 718114,"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": 6305208474013.573, "dur": 2.166, + "args": { + "External id": 718115,"Record function id": 0, "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": 6305208474164.578, "dur": 1818.459, + "args": { + "External id": 718116,"Sequence number": 7674671, "Fwd thread 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": 6305208474164.578, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6305208474293.138, "dur": 116.175, + "args": { + "External id": 718117,"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": 6305208474457.865, "dur": 46.693, + "args": { + "External id": 718118,"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": 6305208474547.155, "dur": 61.913, + "args": { + "External id": 718119,"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": 6305208474619.997, "dur": 33.139, + "args": { + "External id": 718120,"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": 6305208474659.587, "dur": 32.476, + "args": { + "External id": 718121,"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": 6305208474700.706, "dur": 28.116, + "args": { + "External id": 718122,"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": 6305208474736.404, "dur": 28.173, + "args": { + "External id": 718123,"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": 6305208474796.128, "dur": 25.640, + "args": { + "External id": 718124,"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": 6305208474843.618, "dur": 32.336, + "args": { + "External id": 718125,"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": 6305208474900.704, "dur": 20.640, + "args": { + "External id": 718126,"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": 6305208474938.966, "dur": 17.016, + "args": { + "External id": 718127,"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": 6305208474967.290, "dur": 36.865, + "args": { + "External id": 718128,"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": 6305208475007.912, "dur": 33.393, + "args": { + "External id": 718129,"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": 6305208475108.305, "dur": 259.472, + "args": { + "External id": 718130,"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": 6305208475193.026, "dur": 9.361, + "args": { + "External id": 718131,"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": 6305208475204.479, "dur": 4.965, + "args": { + "External id": 718132,"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": 6305208475211.163, "dur": 2.822, + "args": { + "External id": 718133,"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": 6305208475215.199, "dur": 2.388, + "args": { + "External id": 718134,"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": 6305208475262.256, "dur": 5.686, + "args": { + "External id": 718135,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305208475264.802, "dur": 2.974, + "args": { + "External id": 718136,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305208475269.723, "dur": 32.254, + "args": { + "External id": 718137,"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": 6305208475275.863, "dur": 2.178, + "args": { + "External id": 718138,"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": 6305208475303.609, "dur": 4.111, + "args": { + "External id": 718139,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305208475307.148, "dur": 0.493, + "args": { + "External id": 718140,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305208475308.670, "dur": 16.438, + "args": { + "External id": 718141,"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": 6305208475313.256, "dur": 0.518, + "args": { + "External id": 718142,"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": 6305208475405.615, "dur": 29.213, + "args": { + "External id": 718143,"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": 6305208475456.146, "dur": 16.629, + "args": { + "External id": 718144,"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": 6305208475480.299, "dur": 65.805, + "args": { + "External id": 718145,"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": 6305208475555.748, "dur": 41.946, + "args": { + "External id": 718146,"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": 6305208475610.224, "dur": 21.982, + "args": { + "External id": 718147,"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": 6305208475638.164, "dur": 30.064, + "args": { + "External id": 718148,"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": 6305208475675.074, "dur": 27.698, + "args": { + "External id": 718149,"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": 6305208475708.818, "dur": 30.619, + "args": { + "External id": 718150,"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": 6305208475766.851, "dur": 28.022, + "args": { + "External id": 718151,"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": 6305208475815.193, "dur": 28.395, + "args": { + "External id": 718152,"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": 6305208475861.007, "dur": 17.365, + "args": { + "External id": 718153,"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": 6305208475896.185, "dur": 16.064, + "args": { + "External id": 718154,"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": 6305208475929.912, "dur": 20.452, + "args": { + "External id": 718155,"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": 6305208476028.501, "dur": 15.474, + "args": { + "External id": 718156,"Record function id": 0, "Ev Idx": 7499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208476032.025, "dur": 10.956, + "args": { + "External id": 718157,"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": 6305208476036.182, "dur": 5.822, + "args": { + "External id": 718158,"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": 6305208476037.744, "dur": 4.165, + "args": { + "External id": 718159,"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": 6305208476048.153, "dur": 5.219, + "args": { + "External id": 718160,"Record function id": 0, "Ev Idx": 7503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208476049.834, "dur": 3.050, + "args": { + "External id": 718161,"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": 6305208476050.754, "dur": 1.520, + "args": { + "External id": 718162,"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": 6305208476051.465, "dur": 0.697, + "args": { + "External id": 718163,"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": 6305208476102.793, "dur": 20.405, + "args": { + "External id": 718164,"Record function id": 0, "Ev Idx": 7507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208476109.855, "dur": 12.018, + "args": { + "External id": 718165,"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": 6305208476112.428, "dur": 6.931, + "args": { + "External id": 718166,"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": 6305208476113.859, "dur": 5.120, + "args": { + "External id": 718167,"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": 6305208476129.235, "dur": 5.036, + "args": { + "External id": 718168,"Record function id": 0, "Ev Idx": 7511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208476131.017, "dur": 2.821, + "args": { + "External id": 718169,"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": 6305208476131.923, "dur": 1.547, + "args": { + "External id": 718170,"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": 6305208476132.236, "dur": 1.123, + "args": { + "External id": 718171,"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": 6305208476137.556, "dur": 3.900, + "args": { + "External id": 718172,"Record function id": 0, "Ev Idx": 7515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208476138.794, "dur": 2.257, + "args": { + "External id": 718173,"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": 6305208476139.226, "dur": 1.203, + "args": { + "External id": 718174,"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": 6305208476139.479, "dur": 0.886, + "args": { + "External id": 718175,"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": 6305208476144.485, "dur": 7.259, + "args": { + "External id": 718176,"Record function id": 0, "Ev Idx": 7519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208476146.266, "dur": 5.070, + "args": { + "External id": 718177,"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": 6305208476146.824, "dur": 3.793, + "args": { + "External id": 718178,"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": 6305208476149.790, "dur": 0.716, + "args": { + "External id": 718179,"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": 6305208476155.073, "dur": 3.704, + "args": { + "External id": 718180,"Record function id": 0, "Ev Idx": 7523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208476156.427, "dur": 1.941, + "args": { + "External id": 718181,"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": 6305208476156.833, "dur": 0.981, + "args": { + "External id": 718182,"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": 6305208476157.092, "dur": 0.637, + "args": { + "External id": 718183,"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": 6305208476161.754, "dur": 3.818, + "args": { + "External id": 718184,"Record function id": 0, "Ev Idx": 7527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208476163.252, "dur": 1.927, + "args": { + "External id": 718185,"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": 6305208476163.853, "dur": 0.944, + "args": { + "External id": 718186,"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": 6305208476164.099, "dur": 0.633, + "args": { + "External id": 718187,"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": 6305208476168.564, "dur": 4.110, + "args": { + "External id": 718188,"Record function id": 0, "Ev Idx": 7531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208476170.132, "dur": 2.144, + "args": { + "External id": 718189,"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": 6305208476170.650, "dur": 1.254, + "args": { + "External id": 718190,"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": 6305208476171.243, "dur": 0.595, + "args": { + "External id": 718191,"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": 6305208476176.658, "dur": 279615.637, + "args": { + "External id": 718192,"Record function id": 0, "Sequence number": 7674670, "Fwd thread id": 1, "Ev Idx": 7535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305208476178.105, "dur": 279604.662, + "args": { + "External id": 718193,"Sequence number": 7674670, "Fwd thread 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": 6305208476178.105, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.25)", "pid": 2338707, "tid": 2379456, + "ts": 6305208476215.541, "dur": 45.908, + "args": { + "External id": 718194,"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": 6305208476270.037, "dur": 71.183, + "args": { + "External id": 718195,"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": 6305208476346.846, "dur": 279428.076, + "args": { + "External id": 718196,"Record function id": 0, "Ev Idx": 7539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305208476405.242, "dur": 8.491, + "args": { + "External id": 718197,"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": 6305208476425.084, "dur": 6.814, + "args": { + "External id": 718198,"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": 6305208476452.127, "dur": 278366.428, + "args": { + "External id": 718199,"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": 6305208476467.814, "dur": 278335.485, + "args": { + "External id": 718200,"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": 6305208476693.681, "dur": 5.955, + "args": { + "External id": 718201,"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": 6305208476740.140, "dur": 278005.713, + "args": { + "External id": 718202,"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": 6305208476743.193, "dur": 278000.995, + "args": { + "External id": 718203,"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": 6305208476747.324, "dur": 12.382, + "args": { + "External id": 718204,"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": 6305208476762.106, "dur": 277975.585, + "args": { + "External id": 718205,"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": 6305208754942.263, "dur": 13.775, + "args": { + "External id": 718206,"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": 6305208754946.129, "dur": 9.469, + "args": { + "External id": 718207,"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": 6305208755001.690, "dur": 353.214, + "args": { + "External id": 718208,"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": 6305208755035.793, "dur": 313.242, + "args": { + "External id": 718209,"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": 6305208755049.357, "dur": 294.491, + "args": { + "External id": 718210,"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": 6305208755381.080, "dur": 2.690, + "args": { + "External id": 718211,"Record function id": 0, "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": 6305208755447.957, "dur": 7.205, + "args": { + "External id": 718212,"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": 6305208755469.332, "dur": 55.532, + "args": { + "External id": 718213,"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": 6305208755538.833, "dur": 2.342, + "args": { + "External id": 718214,"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": 6305208755547.171, "dur": 15.146, + "args": { + "External id": 718215,"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": 6305208755568.105, "dur": 1.203, + "args": { + "External id": 718216,"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": 6305208755574.360, "dur": 10.864, + "args": { + "External id": 718217,"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": 6305208755589.964, "dur": 1.220, + "args": { + "External id": 718218,"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": 6305208755595.479, "dur": 10.983, + "args": { + "External id": 718219,"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": 6305208755611.342, "dur": 1.049, + "args": { + "External id": 718220,"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": 6305208755618.361, "dur": 10.245, + "args": { + "External id": 718221,"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": 6305208755633.364, "dur": 3.602, + "args": { + "External id": 718222,"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": 6305208755641.160, "dur": 10.361, + "args": { + "External id": 718223,"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": 6305208755656.795, "dur": 0.813, + "args": { + "External id": 718224,"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": 6305208755661.174, "dur": 9.906, + "args": { + "External id": 718225,"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": 6305208755675.729, "dur": 0.726, + "args": { + "External id": 718226,"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": 6305208755680.413, "dur": 10.161, + "args": { + "External id": 718227,"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": 6305208755697.522, "dur": 0.692, + "args": { + "External id": 718228,"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": 6305208755702.203, "dur": 10.900, + "args": { + "External id": 718229,"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": 6305208755807.960, "dur": 3016.963, + "args": { + "External id": 718230,"Record function id": 0, "Ev Idx": 7573 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.24)", "pid": 2338707, "tid": 2379456, + "ts": 6305208755829.655, "dur": 1116.485, + "args": { + "External id": 718231,"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": 6305208755846.430, "dur": 397.759, + "args": { + "External id": 718232,"Record function id": 0, "Ev Idx": 7575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6305208755929.311, "dur": 4.003, + "args": { + "External id": 718233,"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": 6305208755937.735, "dur": 0.894, + "args": { + "External id": 718234,"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": 6305208755940.394, "dur": 0.756, + "args": { + "External id": 718235,"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": 6305208755943.318, "dur": 0.990, + "args": { + "External id": 718236,"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": 6305208755945.871, "dur": 3.106, + "args": { + "External id": 718237,"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": 6305208755953.182, "dur": 0.835, + "args": { + "External id": 718238,"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": 6305208755955.477, "dur": 0.973, + "args": { + "External id": 718239,"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": 6305208755964.508, "dur": 1.020, + "args": { + "External id": 718240,"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": 6305208755967.108, "dur": 0.852, + "args": { + "External id": 718241,"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": 6305208755971.266, "dur": 0.729, + "args": { + "External id": 718242,"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": 6305208755990.683, "dur": 216.692, + "args": { + "External id": 718243,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305208756007.478, "dur": 194.401, + "args": { + "External id": 718244,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305208756051.103, "dur": 47.724, + "args": { + "External id": 718245,"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": 6305208756103.506, "dur": 68.668, + "args": { + "External id": 718246,"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": 6305208756106.036, "dur": 65.866, + "args": { + "External id": 718247,"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": 6305208756110.286, "dur": 6.616, + "args": { + "External id": 718248,"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": 6305208756118.509, "dur": 52.767, + "args": { + "External id": 718249,"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": 6305208756329.915, "dur": 608.331, + "args": { + "External id": 718250,"Record function id": 0, "Ev Idx": 7593 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.23)", "pid": 2338707, "tid": 2379456, + "ts": 6305208756348.284, "dur": 576.439, + "args": { + "External id": 718251,"Record function id": 0, "Ev Idx": 7594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305208756407.147, "dur": 7.100, + "args": { + "External id": 718252,"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": 6305208756429.824, "dur": 32.702, + "args": { + "External id": 718253,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305208756435.439, "dur": 1.510, + "args": { + "External id": 718254,"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": 6305208756438.697, "dur": 2.516, + "args": { + "External id": 718255,"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": 6305208756442.561, "dur": 0.462, + "args": { + "External id": 718256,"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": 6305208756444.347, "dur": 0.403, + "args": { + "External id": 718257,"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": 6305208756448.298, "dur": 0.312, + "args": { + "External id": 718258,"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": 6305208756449.449, "dur": 0.443, + "args": { + "External id": 718259,"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": 6305208756451.301, "dur": 0.254, + "args": { + "External id": 718260,"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": 6305208756453.880, "dur": 3.072, + "args": { + "External id": 718261,"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": 6305208756458.354, "dur": 0.583, + "args": { + "External id": 718262,"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": 6305208756473.736, "dur": 54.420, + "args": { + "External id": 718263,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305208756562.792, "dur": 119.757, + "args": { + "External id": 718264,"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": 6305208756574.095, "dur": 4.295, + "args": { + "External id": 718265,"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": 6305208756583.831, "dur": 13.442, + "args": { + "External id": 718266,"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": 6305208756590.604, "dur": 6.263, + "args": { + "External id": 718267,"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": 6305208756594.433, "dur": 0.840, + "args": { + "External id": 718268,"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": 6305208756603.944, "dur": 28.367, + "args": { + "External id": 718269,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305208756606.171, "dur": 0.517, + "args": { + "External id": 718270,"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": 6305208756610.983, "dur": 0.670, + "args": { + "External id": 718271,"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": 6305208756612.539, "dur": 0.495, + "args": { + "External id": 718272,"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": 6305208756614.203, "dur": 1.958, + "args": { + "External id": 718273,"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": 6305208756617.817, "dur": 2.606, + "args": { + "External id": 718274,"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": 6305208756621.852, "dur": 0.442, + "args": { + "External id": 718275,"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": 6305208756625.089, "dur": 0.396, + "args": { + "External id": 718276,"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": 6305208756626.571, "dur": 0.327, + "args": { + "External id": 718277,"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": 6305208756628.020, "dur": 0.304, + "args": { + "External id": 718278,"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": 6305208756644.093, "dur": 31.054, + "args": { + "External id": 718279,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305208756729.484, "dur": 122.902, + "args": { + "External id": 718280,"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": 6305208756758.464, "dur": 90.215, + "args": { + "External id": 718281,"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": 6305208756768.220, "dur": 76.224, + "args": { + "External id": 718282,"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": 6305208756869.879, "dur": 1.861, + "args": { + "External id": 718283,"Record function id": 0, "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": 6305208756953.873, "dur": 1848.368, + "args": { + "External id": 718284,"Sequence number": 7674669, "Fwd thread 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": 6305208756953.873, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6305208757104.429, "dur": 114.017, + "args": { + "External id": 718285,"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": 6305208757267.345, "dur": 42.901, + "args": { + "External id": 718286,"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": 6305208757328.466, "dur": 52.052, + "args": { + "External id": 718287,"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": 6305208757391.828, "dur": 32.433, + "args": { + "External id": 718288,"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": 6305208757432.478, "dur": 33.136, + "args": { + "External id": 718289,"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": 6305208757472.902, "dur": 30.811, + "args": { + "External id": 718290,"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": 6305208757529.443, "dur": 33.734, + "args": { + "External id": 718291,"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": 6305208757592.516, "dur": 29.856, + "args": { + "External id": 718292,"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": 6305208757643.838, "dur": 29.008, + "args": { + "External id": 718293,"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": 6305208757695.645, "dur": 20.789, + "args": { + "External id": 718294,"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": 6305208757734.040, "dur": 17.393, + "args": { + "External id": 718295,"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": 6305208757758.328, "dur": 39.287, + "args": { + "External id": 718296,"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": 6305208757800.956, "dur": 33.005, + "args": { + "External id": 718297,"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": 6305208757866.263, "dur": 295.393, + "args": { + "External id": 718298,"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": 6305208757948.825, "dur": 6.941, + "args": { + "External id": 718299,"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": 6305208757957.616, "dur": 3.001, + "args": { + "External id": 718300,"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": 6305208757961.709, "dur": 2.222, + "args": { + "External id": 718301,"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": 6305208757965.035, "dur": 2.334, + "args": { + "External id": 718302,"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": 6305208758012.549, "dur": 5.332, + "args": { + "External id": 718303,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305208758014.669, "dur": 3.023, + "args": { + "External id": 718304,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305208758019.536, "dur": 67.206, + "args": { + "External id": 718305,"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": 6305208758026.518, "dur": 1.944, + "args": { + "External id": 718306,"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": 6305208758090.383, "dur": 2.122, + "args": { + "External id": 718307,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305208758091.558, "dur": 0.851, + "args": { + "External id": 718308,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305208758093.458, "dur": 18.538, + "args": { + "External id": 718309,"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": 6305208758096.421, "dur": 0.820, + "args": { + "External id": 718310,"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": 6305208758199.309, "dur": 29.987, + "args": { + "External id": 718311,"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": 6305208758248.398, "dur": 15.631, + "args": { + "External id": 718312,"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": 6305208758271.905, "dur": 47.871, + "args": { + "External id": 718313,"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": 6305208758328.376, "dur": 39.994, + "args": { + "External id": 718314,"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": 6305208758376.075, "dur": 19.955, + "args": { + "External id": 718315,"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": 6305208758401.292, "dur": 44.931, + "args": { + "External id": 718316,"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": 6305208758461.365, "dur": 33.227, + "args": { + "External id": 718317,"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": 6305208758503.238, "dur": 55.681, + "args": { + "External id": 718318,"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": 6305208758587.778, "dur": 31.141, + "args": { + "External id": 718319,"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": 6305208758638.324, "dur": 26.497, + "args": { + "External id": 718320,"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": 6305208758680.943, "dur": 17.814, + "args": { + "External id": 718321,"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": 6305208758715.692, "dur": 17.196, + "args": { + "External id": 718322,"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": 6305208758754.152, "dur": 17.565, + "args": { + "External id": 718323,"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": 6305208758847.815, "dur": 17.994, + "args": { + "External id": 718324,"Record function id": 0, "Ev Idx": 7667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208758851.142, "dur": 13.768, + "args": { + "External id": 718325,"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": 6305208758855.224, "dur": 8.600, + "args": { + "External id": 718326,"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": 6305208758856.967, "dur": 6.772, + "args": { + "External id": 718327,"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": 6305208758869.930, "dur": 5.438, + "args": { + "External id": 718328,"Record function id": 0, "Ev Idx": 7671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208758871.763, "dur": 3.107, + "args": { + "External id": 718329,"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": 6305208758872.695, "dur": 1.626, + "args": { + "External id": 718330,"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": 6305208758873.468, "dur": 0.781, + "args": { + "External id": 718331,"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": 6305208758878.876, "dur": 4.712, + "args": { + "External id": 718332,"Record function id": 0, "Ev Idx": 7675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208758880.090, "dur": 3.018, + "args": { + "External id": 718333,"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": 6305208758880.694, "dur": 1.849, + "args": { + "External id": 718334,"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": 6305208758881.609, "dur": 0.842, + "args": { + "External id": 718335,"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": 6305208758886.928, "dur": 45.652, + "args": { + "External id": 718336,"Record function id": 0, "Ev Idx": 7679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208758929.565, "dur": 2.506, + "args": { + "External id": 718337,"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": 6305208758930.479, "dur": 0.990, + "args": { + "External id": 718338,"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": 6305208758930.769, "dur": 0.621, + "args": { + "External id": 718339,"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": 6305208758935.877, "dur": 4.354, + "args": { + "External id": 718340,"Record function id": 0, "Ev Idx": 7683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208758937.677, "dur": 2.093, + "args": { + "External id": 718341,"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": 6305208758938.233, "dur": 1.075, + "args": { + "External id": 718342,"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": 6305208758938.686, "dur": 0.556, + "args": { + "External id": 718343,"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": 6305208758943.323, "dur": 6.008, + "args": { + "External id": 718344,"Record function id": 0, "Ev Idx": 7687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208758944.438, "dur": 4.440, + "args": { + "External id": 718345,"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": 6305208758945.150, "dur": 3.291, + "args": { + "External id": 718346,"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": 6305208758947.704, "dur": 0.626, + "args": { + "External id": 718347,"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": 6305208758952.517, "dur": 3.681, + "args": { + "External id": 718348,"Record function id": 0, "Ev Idx": 7691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208758953.738, "dur": 2.054, + "args": { + "External id": 718349,"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": 6305208758954.205, "dur": 1.169, + "args": { + "External id": 718350,"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": 6305208758954.675, "dur": 0.616, + "args": { + "External id": 718351,"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": 6305208758959.388, "dur": 5.643, + "args": { + "External id": 718352,"Record function id": 0, "Ev Idx": 7695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208758960.637, "dur": 3.957, + "args": { + "External id": 718353,"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": 6305208758961.111, "dur": 3.090, + "args": { + "External id": 718354,"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": 6305208758961.394, "dur": 2.747, + "args": { + "External id": 718355,"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": 6305208758968.237, "dur": 3.951, + "args": { + "External id": 718356,"Record function id": 0, "Ev Idx": 7699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208758969.369, "dur": 2.408, + "args": { + "External id": 718357,"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": 6305208758969.845, "dur": 1.363, + "args": { + "External id": 718358,"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": 6305208758970.350, "dur": 0.788, + "args": { + "External id": 718359,"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": 6305208758976.284, "dur": 85439.929, + "args": { + "External id": 718360,"Record function id": 0, "Sequence number": 7674668, "Fwd thread id": 1, "Ev Idx": 7703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305208758977.637, "dur": 85429.946, + "args": { + "External id": 718361,"Sequence number": 7674668, "Fwd thread 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": 6305208758977.637, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.24)", "pid": 2338707, "tid": 2379456, + "ts": 6305208759007.370, "dur": 42.438, + "args": { + "External id": 718362,"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": 6305208759094.225, "dur": 69.425, + "args": { + "External id": 718363,"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": 6305208759169.948, "dur": 85228.781, + "args": { + "External id": 718364,"Record function id": 0, "Ev Idx": 7707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305208759264.993, "dur": 8.446, + "args": { + "External id": 718365,"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": 6305208759284.801, "dur": 4.936, + "args": { + "External id": 718366,"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": 6305208759307.236, "dur": 84097.694, + "args": { + "External id": 718367,"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": 6305208759321.563, "dur": 84069.232, + "args": { + "External id": 718368,"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": 6305208759534.578, "dur": 19.746, + "args": { + "External id": 718369,"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": 6305208759586.033, "dur": 83755.394, + "args": { + "External id": 718370,"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": 6305208759589.121, "dur": 83750.981, + "args": { + "External id": 718371,"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": 6305208759593.434, "dur": 11.500, + "args": { + "External id": 718372,"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": 6305208759607.366, "dur": 83727.062, + "args": { + "External id": 718373,"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": 6305208843531.825, "dur": 13.206, + "args": { + "External id": 718374,"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": 6305208843535.523, "dur": 8.936, + "args": { + "External id": 718375,"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": 6305208843578.368, "dur": 374.805, + "args": { + "External id": 718376,"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": 6305208843611.893, "dur": 336.344, + "args": { + "External id": 718377,"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": 6305208843627.818, "dur": 315.335, + "args": { + "External id": 718378,"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": 6305208843974.626, "dur": 2.224, + "args": { + "External id": 718379,"Record function id": 0, "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": 6305208844039.468, "dur": 6.944, + "args": { + "External id": 718380,"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": 6305208844094.407, "dur": 40.981, + "args": { + "External id": 718381,"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": 6305208844147.517, "dur": 2.460, + "args": { + "External id": 718382,"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": 6305208844156.123, "dur": 13.877, + "args": { + "External id": 718383,"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": 6305208844176.244, "dur": 3.523, + "args": { + "External id": 718384,"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": 6305208844186.190, "dur": 12.141, + "args": { + "External id": 718385,"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": 6305208844203.042, "dur": 1.008, + "args": { + "External id": 718386,"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": 6305208844208.562, "dur": 13.144, + "args": { + "External id": 718387,"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": 6305208844226.393, "dur": 0.807, + "args": { + "External id": 718388,"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": 6305208844230.989, "dur": 13.308, + "args": { + "External id": 718389,"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": 6305208844248.746, "dur": 1.184, + "args": { + "External id": 718390,"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": 6305208844253.999, "dur": 11.085, + "args": { + "External id": 718391,"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": 6305208844272.208, "dur": 1.021, + "args": { + "External id": 718392,"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": 6305208844283.404, "dur": 9.860, + "args": { + "External id": 718393,"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": 6305208844299.254, "dur": 0.892, + "args": { + "External id": 718394,"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": 6305208844304.443, "dur": 10.952, + "args": { + "External id": 718395,"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": 6305208844319.692, "dur": 0.843, + "args": { + "External id": 718396,"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": 6305208844326.204, "dur": 9.932, + "args": { + "External id": 718397,"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": 6305208844432.501, "dur": 2964.686, + "args": { + "External id": 718398,"Record function id": 0, "Ev Idx": 7741 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.23)", "pid": 2338707, "tid": 2379456, + "ts": 6305208844452.773, "dur": 1105.007, + "args": { + "External id": 718399,"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": 6305208844468.546, "dur": 358.026, + "args": { + "External id": 718400,"Record function id": 0, "Ev Idx": 7743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6305208844571.969, "dur": 6.832, + "args": { + "External id": 718401,"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": 6305208844583.024, "dur": 3.034, + "args": { + "External id": 718402,"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": 6305208844588.313, "dur": 0.797, + "args": { + "External id": 718403,"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": 6305208844591.020, "dur": 0.825, + "args": { + "External id": 718404,"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": 6305208844593.470, "dur": 0.862, + "args": { + "External id": 718405,"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": 6305208844595.929, "dur": 0.857, + "args": { + "External id": 718406,"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": 6305208844598.483, "dur": 1.054, + "args": { + "External id": 718407,"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": 6305208844602.866, "dur": 1.157, + "args": { + "External id": 718408,"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": 6305208844605.484, "dur": 0.815, + "args": { + "External id": 718409,"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": 6305208844607.626, "dur": 2.817, + "args": { + "External id": 718410,"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": 6305208844628.797, "dur": 165.813, + "args": { + "External id": 718411,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305208844645.090, "dur": 144.623, + "args": { + "External id": 718412,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305208844676.960, "dur": 15.563, + "args": { + "External id": 718413,"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": 6305208844696.430, "dur": 66.166, + "args": { + "External id": 718414,"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": 6305208844699.884, "dur": 62.451, + "args": { + "External id": 718415,"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": 6305208844703.537, "dur": 5.813, + "args": { + "External id": 718416,"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": 6305208844710.959, "dur": 50.616, + "args": { + "External id": 718417,"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": 6305208844906.240, "dur": 644.058, + "args": { + "External id": 718418,"Record function id": 0, "Ev Idx": 7761 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.22)", "pid": 2338707, "tid": 2379456, + "ts": 6305208844923.700, "dur": 612.239, + "args": { + "External id": 718419,"Record function id": 0, "Ev Idx": 7762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305208844980.638, "dur": 4.951, + "args": { + "External id": 718420,"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": 6305208845000.925, "dur": 32.325, + "args": { + "External id": 718421,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305208845005.590, "dur": 3.747, + "args": { + "External id": 718422,"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": 6305208845011.100, "dur": 0.532, + "args": { + "External id": 718423,"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": 6305208845013.106, "dur": 0.593, + "args": { + "External id": 718424,"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": 6305208845017.084, "dur": 0.592, + "args": { + "External id": 718425,"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": 6305208845019.338, "dur": 2.487, + "args": { + "External id": 718426,"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": 6305208845023.023, "dur": 0.270, + "args": { + "External id": 718427,"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": 6305208845025.645, "dur": 0.264, + "args": { + "External id": 718428,"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": 6305208845027.231, "dur": 0.364, + "args": { + "External id": 718429,"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": 6305208845028.513, "dur": 1.720, + "args": { + "External id": 718430,"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": 6305208845043.165, "dur": 78.766, + "args": { + "External id": 718431,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305208845156.445, "dur": 115.403, + "args": { + "External id": 718432,"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": 6305208845168.185, "dur": 4.731, + "args": { + "External id": 718433,"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": 6305208845178.645, "dur": 10.876, + "args": { + "External id": 718434,"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": 6305208845182.803, "dur": 6.306, + "args": { + "External id": 718435,"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": 6305208845186.549, "dur": 0.863, + "args": { + "External id": 718436,"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": 6305208845196.578, "dur": 25.292, + "args": { + "External id": 718437,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305208845198.734, "dur": 0.604, + "args": { + "External id": 718438,"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": 6305208845200.877, "dur": 2.468, + "args": { + "External id": 718439,"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": 6305208845204.224, "dur": 1.778, + "args": { + "External id": 718440,"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": 6305208845207.529, "dur": 0.459, + "args": { + "External id": 718441,"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": 6305208845208.922, "dur": 0.654, + "args": { + "External id": 718442,"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": 6305208845212.438, "dur": 0.422, + "args": { + "External id": 718443,"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": 6305208845213.973, "dur": 0.389, + "args": { + "External id": 718444,"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": 6305208845215.345, "dur": 0.455, + "args": { + "External id": 718445,"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": 6305208845218.213, "dur": 0.402, + "args": { + "External id": 718446,"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": 6305208845233.225, "dur": 29.367, + "args": { + "External id": 718447,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305208845319.724, "dur": 126.415, + "args": { + "External id": 718448,"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": 6305208845352.501, "dur": 89.795, + "args": { + "External id": 718449,"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": 6305208845362.595, "dur": 75.535, + "args": { + "External id": 718450,"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": 6305208845463.517, "dur": 1.852, + "args": { + "External id": 718451,"Record function id": 0, "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": 6305208845565.646, "dur": 1809.164, + "args": { + "External id": 718452,"Sequence number": 7674667, "Fwd thread 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": 6305208845565.646, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6305208845678.329, "dur": 111.733, + "args": { + "External id": 718453,"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": 6305208845834.414, "dur": 42.580, + "args": { + "External id": 718454,"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": 6305208845897.054, "dur": 52.275, + "args": { + "External id": 718455,"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": 6305208845959.932, "dur": 32.243, + "args": { + "External id": 718456,"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": 6305208845998.892, "dur": 32.923, + "args": { + "External id": 718457,"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": 6305208846038.473, "dur": 67.445, + "args": { + "External id": 718458,"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": 6305208846119.965, "dur": 33.825, + "args": { + "External id": 718459,"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": 6305208846183.608, "dur": 27.654, + "args": { + "External id": 718460,"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": 6305208846230.345, "dur": 29.089, + "args": { + "External id": 718461,"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": 6305208846282.231, "dur": 20.723, + "args": { + "External id": 718462,"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": 6305208846318.665, "dur": 15.848, + "args": { + "External id": 718463,"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": 6305208846343.805, "dur": 38.526, + "args": { + "External id": 718464,"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": 6305208846386.157, "dur": 33.298, + "args": { + "External id": 718465,"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": 6305208846449.276, "dur": 273.125, + "args": { + "External id": 718466,"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": 6305208846549.199, "dur": 7.370, + "args": { + "External id": 718467,"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": 6305208846558.809, "dur": 3.246, + "args": { + "External id": 718468,"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": 6305208846563.163, "dur": 1.958, + "args": { + "External id": 718469,"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": 6305208846566.102, "dur": 4.969, + "args": { + "External id": 718470,"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": 6305208846617.643, "dur": 7.508, + "args": { + "External id": 718471,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305208846622.054, "dur": 2.925, + "args": { + "External id": 718472,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305208846627.363, "dur": 32.946, + "args": { + "External id": 718473,"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": 6305208846632.910, "dur": 1.723, + "args": { + "External id": 718474,"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": 6305208846662.270, "dur": 1.053, + "args": { + "External id": 718475,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305208846662.775, "dur": 0.481, + "args": { + "External id": 718476,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305208846664.298, "dur": 14.789, + "args": { + "External id": 718477,"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": 6305208846666.307, "dur": 0.594, + "args": { + "External id": 718478,"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": 6305208846760.490, "dur": 28.246, + "args": { + "External id": 718479,"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": 6305208846809.214, "dur": 16.098, + "args": { + "External id": 718480,"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": 6305208846832.660, "dur": 47.908, + "args": { + "External id": 718481,"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": 6305208846887.563, "dur": 41.118, + "args": { + "External id": 718482,"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": 6305208846936.415, "dur": 20.954, + "args": { + "External id": 718483,"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": 6305208846964.814, "dur": 43.847, + "args": { + "External id": 718484,"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": 6305208847024.264, "dur": 74.419, + "args": { + "External id": 718485,"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": 6305208847109.142, "dur": 36.990, + "args": { + "External id": 718486,"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": 6305208847175.845, "dur": 30.142, + "args": { + "External id": 718487,"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": 6305208847223.832, "dur": 25.452, + "args": { + "External id": 718488,"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": 6305208847265.699, "dur": 16.720, + "args": { + "External id": 718489,"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": 6305208847297.845, "dur": 13.506, + "args": { + "External id": 718490,"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": 6305208847326.436, "dur": 14.923, + "args": { + "External id": 718491,"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": 6305208847419.299, "dur": 15.142, + "args": { + "External id": 718492,"Record function id": 0, "Ev Idx": 7835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208847422.512, "dur": 10.935, + "args": { + "External id": 718493,"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": 6305208847426.640, "dur": 5.701, + "args": { + "External id": 718494,"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": 6305208847428.302, "dur": 3.955, + "args": { + "External id": 718495,"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": 6305208847438.456, "dur": 4.452, + "args": { + "External id": 718496,"Record function id": 0, "Ev Idx": 7839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208847439.875, "dur": 2.547, + "args": { + "External id": 718497,"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": 6305208847440.522, "dur": 1.413, + "args": { + "External id": 718498,"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": 6305208847441.113, "dur": 0.713, + "args": { + "External id": 718499,"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": 6305208847446.276, "dur": 3.747, + "args": { + "External id": 718500,"Record function id": 0, "Ev Idx": 7843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208847447.234, "dur": 2.363, + "args": { + "External id": 718501,"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": 6305208847447.727, "dur": 1.365, + "args": { + "External id": 718502,"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": 6305208847448.373, "dur": 0.604, + "args": { + "External id": 718503,"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": 6305208847453.213, "dur": 3.819, + "args": { + "External id": 718504,"Record function id": 0, "Ev Idx": 7847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208847454.341, "dur": 2.298, + "args": { + "External id": 718505,"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": 6305208847454.993, "dur": 1.230, + "args": { + "External id": 718506,"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": 6305208847455.526, "dur": 0.620, + "args": { + "External id": 718507,"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": 6305208847460.151, "dur": 4.025, + "args": { + "External id": 718508,"Record function id": 0, "Ev Idx": 7851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208847461.376, "dur": 2.376, + "args": { + "External id": 718509,"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": 6305208847462.054, "dur": 1.116, + "args": { + "External id": 718510,"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": 6305208847462.316, "dur": 0.780, + "args": { + "External id": 718511,"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": 6305208847467.367, "dur": 6.937, + "args": { + "External id": 718512,"Record function id": 0, "Ev Idx": 7855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208847468.550, "dur": 5.156, + "args": { + "External id": 718513,"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": 6305208847469.272, "dur": 3.995, + "args": { + "External id": 718514,"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": 6305208847470.132, "dur": 3.065, + "args": { + "External id": 718515,"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": 6305208847477.485, "dur": 4.258, + "args": { + "External id": 718516,"Record function id": 0, "Ev Idx": 7859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208847478.810, "dur": 2.529, + "args": { + "External id": 718517,"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": 6305208847479.565, "dur": 1.333, + "args": { + "External id": 718518,"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": 6305208847480.046, "dur": 0.780, + "args": { + "External id": 718519,"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": 6305208847484.831, "dur": 5.366, + "args": { + "External id": 718520,"Record function id": 0, "Ev Idx": 7863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208847485.851, "dur": 3.955, + "args": { + "External id": 718521,"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": 6305208847486.295, "dur": 3.079, + "args": { + "External id": 718522,"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": 6305208847488.653, "dur": 0.648, + "args": { + "External id": 718523,"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": 6305208847493.336, "dur": 3.527, + "args": { + "External id": 718524,"Record function id": 0, "Ev Idx": 7867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208847494.466, "dur": 1.991, + "args": { + "External id": 718525,"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": 6305208847494.923, "dur": 1.104, + "args": { + "External id": 718526,"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": 6305208847495.272, "dur": 0.690, + "args": { + "External id": 718527,"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": 6305208847500.934, "dur": 74850.882, + "args": { + "External id": 718528,"Record function id": 0, "Sequence number": 7674666, "Fwd thread id": 1, "Ev Idx": 7871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305208847502.560, "dur": 74840.359, + "args": { + "External id": 718529,"Sequence number": 7674666, "Fwd thread 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": 6305208847502.560, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.23)", "pid": 2338707, "tid": 2379456, + "ts": 6305208847549.359, "dur": 40.431, + "args": { + "External id": 718530,"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": 6305208847598.163, "dur": 65.163, + "args": { + "External id": 718531,"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": 6305208847668.659, "dur": 74666.457, + "args": { + "External id": 718532,"Record function id": 0, "Ev Idx": 7875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305208847760.777, "dur": 7.350, + "args": { + "External id": 718533,"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": 6305208847779.113, "dur": 5.064, + "args": { + "External id": 718534,"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": 6305208847800.134, "dur": 73496.445, + "args": { + "External id": 718535,"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": 6305208847815.239, "dur": 73467.002, + "args": { + "External id": 718536,"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": 6305208847949.642, "dur": 17.609, + "args": { + "External id": 718537,"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": 6305208847990.449, "dur": 73243.358, + "args": { + "External id": 718538,"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": 6305208847993.244, "dur": 73239.195, + "args": { + "External id": 718539,"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": 6305208847999.034, "dur": 8.009, + "args": { + "External id": 718540,"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": 6305208848008.928, "dur": 73217.515, + "args": { + "External id": 718541,"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": 6305208921411.933, "dur": 13.396, + "args": { + "External id": 718542,"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": 6305208921415.737, "dur": 9.162, + "args": { + "External id": 718543,"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": 6305208921456.862, "dur": 437.310, + "args": { + "External id": 718544,"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": 6305208921489.846, "dur": 398.333, + "args": { + "External id": 718545,"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": 6305208921502.707, "dur": 379.839, + "args": { + "External id": 718546,"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": 6305208921919.217, "dur": 2.359, + "args": { + "External id": 718547,"Record function id": 0, "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": 6305208921984.716, "dur": 6.895, + "args": { + "External id": 718548,"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": 6305208922004.681, "dur": 37.372, + "args": { + "External id": 718549,"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": 6305208922089.135, "dur": 4.389, + "args": { + "External id": 718550,"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": 6305208922101.068, "dur": 17.615, + "args": { + "External id": 718551,"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": 6305208922125.445, "dur": 1.083, + "args": { + "External id": 718552,"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": 6305208922137.114, "dur": 10.815, + "args": { + "External id": 718553,"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": 6305208922155.201, "dur": 0.821, + "args": { + "External id": 718554,"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": 6305208922160.122, "dur": 11.532, + "args": { + "External id": 718555,"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": 6305208922175.807, "dur": 0.933, + "args": { + "External id": 718556,"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": 6305208922180.246, "dur": 10.077, + "args": { + "External id": 718557,"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": 6305208922194.762, "dur": 2.526, + "args": { + "External id": 718558,"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": 6305208922201.819, "dur": 10.574, + "args": { + "External id": 718559,"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": 6305208922218.679, "dur": 1.022, + "args": { + "External id": 718560,"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": 6305208922223.414, "dur": 10.199, + "args": { + "External id": 718561,"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": 6305208922237.629, "dur": 0.818, + "args": { + "External id": 718562,"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": 6305208922242.249, "dur": 10.464, + "args": { + "External id": 718563,"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": 6305208922256.668, "dur": 0.811, + "args": { + "External id": 718564,"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": 6305208922261.539, "dur": 10.865, + "args": { + "External id": 718565,"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": 6305208922368.215, "dur": 2966.258, + "args": { + "External id": 718566,"Record function id": 0, "Ev Idx": 7909 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.22)", "pid": 2338707, "tid": 2379456, + "ts": 6305208922391.886, "dur": 1077.233, + "args": { + "External id": 718567,"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": 6305208922408.242, "dur": 346.862, + "args": { + "External id": 718568,"Record function id": 0, "Ev Idx": 7911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6305208922487.788, "dur": 6.329, + "args": { + "External id": 718569,"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": 6305208922497.796, "dur": 1.038, + "args": { + "External id": 718570,"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": 6305208922500.506, "dur": 0.762, + "args": { + "External id": 718571,"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": 6305208922502.978, "dur": 0.888, + "args": { + "External id": 718572,"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": 6305208922521.244, "dur": 1.472, + "args": { + "External id": 718573,"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": 6305208922525.644, "dur": 0.899, + "args": { + "External id": 718574,"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": 6305208922528.023, "dur": 0.671, + "args": { + "External id": 718575,"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": 6305208922532.719, "dur": 0.958, + "args": { + "External id": 718576,"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": 6305208922535.262, "dur": 2.863, + "args": { + "External id": 718577,"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": 6305208922539.343, "dur": 0.901, + "args": { + "External id": 718578,"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": 6305208922558.397, "dur": 163.491, + "args": { + "External id": 718579,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305208922575.529, "dur": 141.586, + "args": { + "External id": 718580,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305208922593.120, "dur": 15.161, + "args": { + "External id": 718581,"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": 6305208922614.250, "dur": 77.498, + "args": { + "External id": 718582,"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": 6305208922617.670, "dur": 73.669, + "args": { + "External id": 718583,"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": 6305208922632.313, "dur": 7.164, + "args": { + "External id": 718584,"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": 6305208922641.238, "dur": 49.532, + "args": { + "External id": 718585,"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": 6305208922838.139, "dur": 622.856, + "args": { + "External id": 718586,"Record function id": 0, "Ev Idx": 7929 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.21)", "pid": 2338707, "tid": 2379456, + "ts": 6305208922854.709, "dur": 593.549, + "args": { + "External id": 718587,"Record function id": 0, "Ev Idx": 7930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305208922912.756, "dur": 4.602, + "args": { + "External id": 718588,"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": 6305208922932.494, "dur": 31.026, + "args": { + "External id": 718589,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305208922937.639, "dur": 3.164, + "args": { + "External id": 718590,"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": 6305208922942.647, "dur": 0.922, + "args": { + "External id": 718591,"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": 6305208922944.373, "dur": 0.631, + "args": { + "External id": 718592,"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": 6305208922947.304, "dur": 2.527, + "args": { + "External id": 718593,"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": 6305208922951.464, "dur": 0.461, + "args": { + "External id": 718594,"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": 6305208922953.124, "dur": 0.549, + "args": { + "External id": 718595,"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": 6305208922955.811, "dur": 0.304, + "args": { + "External id": 718596,"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": 6305208922957.282, "dur": 0.600, + "args": { + "External id": 718597,"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": 6305208922958.862, "dur": 1.649, + "args": { + "External id": 718598,"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": 6305208922977.704, "dur": 42.348, + "args": { + "External id": 718599,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305208923049.333, "dur": 156.199, + "args": { + "External id": 718600,"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": 6305208923098.492, "dur": 6.140, + "args": { + "External id": 718601,"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": 6305208923110.379, "dur": 11.520, + "args": { + "External id": 718602,"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": 6305208923115.147, "dur": 6.366, + "args": { + "External id": 718603,"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": 6305208923118.782, "dur": 0.815, + "args": { + "External id": 718604,"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": 6305208923129.174, "dur": 26.244, + "args": { + "External id": 718605,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305208923131.363, "dur": 2.805, + "args": { + "External id": 718606,"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": 6305208923135.357, "dur": 2.201, + "args": { + "External id": 718607,"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": 6305208923138.729, "dur": 0.549, + "args": { + "External id": 718608,"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": 6305208923140.126, "dur": 0.424, + "args": { + "External id": 718609,"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": 6305208923142.893, "dur": 0.365, + "args": { + "External id": 718610,"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": 6305208923144.308, "dur": 0.363, + "args": { + "External id": 718611,"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": 6305208923145.620, "dur": 0.352, + "args": { + "External id": 718612,"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": 6305208923148.757, "dur": 0.297, + "args": { + "External id": 718613,"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": 6305208923149.993, "dur": 2.200, + "args": { + "External id": 718614,"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": 6305208923165.974, "dur": 31.774, + "args": { + "External id": 718615,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305208923252.645, "dur": 124.931, + "args": { + "External id": 718616,"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": 6305208923285.666, "dur": 88.709, + "args": { + "External id": 718617,"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": 6305208923295.297, "dur": 74.134, + "args": { + "External id": 718618,"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": 6305208923394.362, "dur": 1.594, + "args": { + "External id": 718619,"Record function id": 0, "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": 6305208923486.515, "dur": 1825.395, + "args": { + "External id": 718620,"Sequence number": 7674665, "Fwd thread 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": 6305208923486.515, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6305208923614.949, "dur": 110.458, + "args": { + "External id": 718621,"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": 6305208923773.398, "dur": 40.880, + "args": { + "External id": 718622,"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": 6305208923834.634, "dur": 51.578, + "args": { + "External id": 718623,"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": 6305208923897.115, "dur": 31.496, + "args": { + "External id": 718624,"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": 6305208923934.984, "dur": 32.689, + "args": { + "External id": 718625,"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": 6305208923973.831, "dur": 27.117, + "args": { + "External id": 718626,"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": 6305208924009.308, "dur": 29.593, + "args": { + "External id": 718627,"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": 6305208924108.652, "dur": 27.952, + "args": { + "External id": 718628,"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": 6305208924161.507, "dur": 30.311, + "args": { + "External id": 718629,"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": 6305208924213.844, "dur": 19.033, + "args": { + "External id": 718630,"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": 6305208924250.388, "dur": 14.930, + "args": { + "External id": 718631,"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": 6305208924275.510, "dur": 43.056, + "args": { + "External id": 718632,"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": 6305208924322.369, "dur": 33.738, + "args": { + "External id": 718633,"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": 6305208924385.891, "dur": 261.601, + "args": { + "External id": 718634,"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": 6305208924461.511, "dur": 6.813, + "args": { + "External id": 718635,"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": 6305208924470.559, "dur": 3.418, + "args": { + "External id": 718636,"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": 6305208924475.096, "dur": 2.260, + "args": { + "External id": 718637,"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": 6305208924478.295, "dur": 6.081, + "args": { + "External id": 718638,"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": 6305208924544.629, "dur": 5.289, + "args": { + "External id": 718639,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305208924546.701, "dur": 2.865, + "args": { + "External id": 718640,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305208924552.020, "dur": 32.073, + "args": { + "External id": 718641,"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": 6305208924558.091, "dur": 1.791, + "args": { + "External id": 718642,"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": 6305208924585.767, "dur": 1.527, + "args": { + "External id": 718643,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305208924586.654, "dur": 0.563, + "args": { + "External id": 718644,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305208924590.798, "dur": 13.299, + "args": { + "External id": 718645,"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": 6305208924592.719, "dur": 0.641, + "args": { + "External id": 718646,"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": 6305208924686.701, "dur": 29.083, + "args": { + "External id": 718647,"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": 6305208924735.177, "dur": 16.623, + "args": { + "External id": 718648,"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": 6305208924759.072, "dur": 50.722, + "args": { + "External id": 718649,"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": 6305208924816.305, "dur": 41.506, + "args": { + "External id": 718650,"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": 6305208924865.996, "dur": 22.968, + "args": { + "External id": 718651,"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": 6305208924896.586, "dur": 31.996, + "args": { + "External id": 718652,"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": 6305208924935.708, "dur": 43.282, + "args": { + "External id": 718653,"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": 6305208924993.116, "dur": 37.156, + "args": { + "External id": 718654,"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": 6305208925092.176, "dur": 33.747, + "args": { + "External id": 718655,"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": 6305208925148.276, "dur": 30.200, + "args": { + "External id": 718656,"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": 6305208925195.960, "dur": 18.500, + "args": { + "External id": 718657,"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": 6305208925233.225, "dur": 15.811, + "args": { + "External id": 718658,"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": 6305208925262.294, "dur": 16.198, + "args": { + "External id": 718659,"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": 6305208925357.265, "dur": 15.876, + "args": { + "External id": 718660,"Record function id": 0, "Ev Idx": 8003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208925360.455, "dur": 11.637, + "args": { + "External id": 718661,"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": 6305208925364.993, "dur": 6.033, + "args": { + "External id": 718662,"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": 6305208925366.752, "dur": 4.188, + "args": { + "External id": 718663,"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": 6305208925377.226, "dur": 4.686, + "args": { + "External id": 718664,"Record function id": 0, "Ev Idx": 8007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208925378.672, "dur": 2.797, + "args": { + "External id": 718665,"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": 6305208925379.493, "dur": 1.512, + "args": { + "External id": 718666,"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": 6305208925380.223, "dur": 0.683, + "args": { + "External id": 718667,"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": 6305208925385.167, "dur": 5.138, + "args": { + "External id": 718668,"Record function id": 0, "Ev Idx": 8011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208925386.921, "dur": 2.942, + "args": { + "External id": 718669,"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": 6305208925387.700, "dur": 1.719, + "args": { + "External id": 718670,"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": 6305208925388.386, "dur": 0.949, + "args": { + "External id": 718671,"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": 6305208925393.466, "dur": 4.400, + "args": { + "External id": 718672,"Record function id": 0, "Ev Idx": 8015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208925394.920, "dur": 2.534, + "args": { + "External id": 718673,"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": 6305208925395.560, "dur": 1.483, + "args": { + "External id": 718674,"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": 6305208925396.199, "dur": 0.777, + "args": { + "External id": 718675,"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": 6305208925400.946, "dur": 3.411, + "args": { + "External id": 718676,"Record function id": 0, "Ev Idx": 8019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208925402.084, "dur": 1.852, + "args": { + "External id": 718677,"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": 6305208925402.544, "dur": 1.004, + "args": { + "External id": 718678,"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": 6305208925402.836, "dur": 0.643, + "args": { + "External id": 718679,"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": 6305208925407.565, "dur": 7.951, + "args": { + "External id": 718680,"Record function id": 0, "Ev Idx": 8023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208925408.742, "dur": 6.357, + "args": { + "External id": 718681,"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": 6305208925409.190, "dur": 5.521, + "args": { + "External id": 718682,"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": 6305208925411.686, "dur": 2.954, + "args": { + "External id": 718683,"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": 6305208925418.765, "dur": 4.354, + "args": { + "External id": 718684,"Record function id": 0, "Ev Idx": 8027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208925420.173, "dur": 2.510, + "args": { + "External id": 718685,"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": 6305208925420.866, "dur": 1.383, + "args": { + "External id": 718686,"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": 6305208925421.368, "dur": 0.812, + "args": { + "External id": 718687,"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": 6305208925426.392, "dur": 3.695, + "args": { + "External id": 718688,"Record function id": 0, "Ev Idx": 8031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208925427.625, "dur": 2.047, + "args": { + "External id": 718689,"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": 6305208925428.083, "dur": 1.175, + "args": { + "External id": 718690,"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": 6305208925428.496, "dur": 0.696, + "args": { + "External id": 718691,"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": 6305208925433.157, "dur": 3.864, + "args": { + "External id": 718692,"Record function id": 0, "Ev Idx": 8035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208925434.060, "dur": 2.539, + "args": { + "External id": 718693,"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": 6305208925434.684, "dur": 1.197, + "args": { + "External id": 718694,"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": 6305208925434.996, "dur": 0.821, + "args": { + "External id": 718695,"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": 6305208925441.387, "dur": 66203.984, + "args": { + "External id": 718696,"Record function id": 0, "Sequence number": 7674664, "Fwd thread id": 1, "Ev Idx": 8039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305208925442.683, "dur": 66193.228, + "args": { + "External id": 718697,"Sequence number": 7674664, "Fwd thread 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": 6305208925442.683, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.22)", "pid": 2338707, "tid": 2379456, + "ts": 6305208925474.044, "dur": 53.673, + "args": { + "External id": 718698,"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": 6305208925537.046, "dur": 61.421, + "args": { + "External id": 718699,"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": 6305208925604.236, "dur": 66023.626, + "args": { + "External id": 718700,"Record function id": 0, "Ev Idx": 8043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305208925695.607, "dur": 6.962, + "args": { + "External id": 718701,"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": 6305208925713.567, "dur": 4.857, + "args": { + "External id": 718702,"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": 6305208925736.083, "dur": 64890.215, + "args": { + "External id": 718703,"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": 6305208925751.364, "dur": 64861.459, + "args": { + "External id": 718704,"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": 6305208925862.742, "dur": 17.807, + "args": { + "External id": 718705,"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": 6305208925900.864, "dur": 64664.466, + "args": { + "External id": 718706,"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": 6305208925904.476, "dur": 64659.578, + "args": { + "External id": 718707,"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": 6305208925911.402, "dur": 8.743, + "args": { + "External id": 718708,"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": 6305208925925.306, "dur": 64632.872, + "args": { + "External id": 718709,"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": 6305208990739.257, "dur": 13.338, + "args": { + "External id": 718710,"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": 6305208990743.050, "dur": 9.032, + "args": { + "External id": 718711,"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": 6305208990785.513, "dur": 422.794, + "args": { + "External id": 718712,"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": 6305208990819.642, "dur": 382.970, + "args": { + "External id": 718713,"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": 6305208990833.665, "dur": 362.229, + "args": { + "External id": 718714,"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": 6305208991234.942, "dur": 2.356, + "args": { + "External id": 718715,"Record function id": 0, "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": 6305208991301.395, "dur": 6.712, + "args": { + "External id": 718716,"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": 6305208991320.220, "dur": 37.845, + "args": { + "External id": 718717,"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": 6305208991368.487, "dur": 3.686, + "args": { + "External id": 718718,"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": 6305208991377.760, "dur": 13.380, + "args": { + "External id": 718719,"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": 6305208991396.360, "dur": 0.930, + "args": { + "External id": 718720,"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": 6305208991401.391, "dur": 13.623, + "args": { + "External id": 718721,"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": 6305208991420.508, "dur": 0.828, + "args": { + "External id": 718722,"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": 6305208991425.420, "dur": 10.704, + "args": { + "External id": 718723,"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": 6305208991440.590, "dur": 0.859, + "args": { + "External id": 718724,"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": 6305208991445.696, "dur": 10.476, + "args": { + "External id": 718725,"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": 6305208991460.287, "dur": 1.253, + "args": { + "External id": 718726,"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": 6305208991471.744, "dur": 10.760, + "args": { + "External id": 718727,"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": 6305208991486.604, "dur": 0.780, + "args": { + "External id": 718728,"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": 6305208991491.607, "dur": 9.804, + "args": { + "External id": 718729,"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": 6305208991522.007, "dur": 1.726, + "args": { + "External id": 718730,"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": 6305208991529.867, "dur": 14.148, + "args": { + "External id": 718731,"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": 6305208991551.427, "dur": 0.779, + "args": { + "External id": 718732,"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": 6305208991555.781, "dur": 9.661, + "args": { + "External id": 718733,"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": 6305208991661.795, "dur": 2974.388, + "args": { + "External id": 718734,"Record function id": 0, "Ev Idx": 8077 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.21)", "pid": 2338707, "tid": 2379456, + "ts": 6305208991682.695, "dur": 1086.500, + "args": { + "External id": 718735,"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": 6305208991700.271, "dur": 328.059, + "args": { + "External id": 718736,"Record function id": 0, "Ev Idx": 8079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6305208991780.421, "dur": 6.788, + "args": { + "External id": 718737,"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": 6305208991791.017, "dur": 0.889, + "args": { + "External id": 718738,"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": 6305208991794.560, "dur": 0.775, + "args": { + "External id": 718739,"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": 6305208991797.024, "dur": 0.884, + "args": { + "External id": 718740,"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": 6305208991799.494, "dur": 1.061, + "args": { + "External id": 718741,"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": 6305208991802.355, "dur": 0.929, + "args": { + "External id": 718742,"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": 6305208991806.964, "dur": 0.992, + "args": { + "External id": 718743,"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": 6305208991809.302, "dur": 1.151, + "args": { + "External id": 718744,"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": 6305208991812.207, "dur": 2.821, + "args": { + "External id": 718745,"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": 6305208991816.481, "dur": 0.861, + "args": { + "External id": 718746,"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": 6305208991837.056, "dur": 160.948, + "args": { + "External id": 718747,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305208991854.193, "dur": 139.029, + "args": { + "External id": 718748,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305208991871.843, "dur": 13.271, + "args": { + "External id": 718749,"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": 6305208991888.676, "dur": 76.494, + "args": { + "External id": 718750,"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": 6305208991891.571, "dur": 73.200, + "args": { + "External id": 718751,"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": 6305208991905.835, "dur": 6.085, + "args": { + "External id": 718752,"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": 6305208991913.671, "dur": 50.652, + "args": { + "External id": 718753,"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": 6305208992153.148, "dur": 607.229, + "args": { + "External id": 718754,"Record function id": 0, "Ev Idx": 8097 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.20)", "pid": 2338707, "tid": 2379456, + "ts": 6305208992172.354, "dur": 574.565, + "args": { + "External id": 718755,"Record function id": 0, "Ev Idx": 8098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305208992231.427, "dur": 6.129, + "args": { + "External id": 718756,"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": 6305208992253.757, "dur": 33.819, + "args": { + "External id": 718757,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305208992259.094, "dur": 1.694, + "args": { + "External id": 718758,"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": 6305208992262.952, "dur": 2.792, + "args": { + "External id": 718759,"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": 6305208992267.056, "dur": 0.648, + "args": { + "External id": 718760,"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": 6305208992268.962, "dur": 2.553, + "args": { + "External id": 718761,"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": 6305208992274.817, "dur": 0.379, + "args": { + "External id": 718762,"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": 6305208992276.858, "dur": 0.264, + "args": { + "External id": 718763,"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": 6305208992278.654, "dur": 0.351, + "args": { + "External id": 718764,"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": 6305208992281.993, "dur": 0.310, + "args": { + "External id": 718765,"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": 6305208992283.492, "dur": 0.508, + "args": { + "External id": 718766,"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": 6305208992298.637, "dur": 45.052, + "args": { + "External id": 718767,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305208992373.357, "dur": 112.775, + "args": { + "External id": 718768,"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": 6305208992383.761, "dur": 3.457, + "args": { + "External id": 718769,"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": 6305208992392.683, "dur": 10.586, + "args": { + "External id": 718770,"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": 6305208992397.370, "dur": 5.497, + "args": { + "External id": 718771,"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": 6305208992400.823, "dur": 0.741, + "args": { + "External id": 718772,"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": 6305208992409.934, "dur": 27.643, + "args": { + "External id": 718773,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305208992411.812, "dur": 2.681, + "args": { + "External id": 718774,"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": 6305208992417.302, "dur": 0.610, + "args": { + "External id": 718775,"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": 6305208992419.542, "dur": 0.464, + "args": { + "External id": 718776,"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": 6305208992420.813, "dur": 2.050, + "args": { + "External id": 718777,"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": 6305208992424.359, "dur": 0.290, + "args": { + "External id": 718778,"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": 6305208992425.658, "dur": 0.386, + "args": { + "External id": 718779,"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": 6305208992428.928, "dur": 0.322, + "args": { + "External id": 718780,"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": 6305208992430.523, "dur": 0.601, + "args": { + "External id": 718781,"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": 6305208992432.043, "dur": 2.435, + "args": { + "External id": 718782,"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": 6305208992450.207, "dur": 28.894, + "args": { + "External id": 718783,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305208992550.024, "dur": 124.554, + "args": { + "External id": 718784,"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": 6305208992580.510, "dur": 90.403, + "args": { + "External id": 718785,"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": 6305208992590.465, "dur": 76.217, + "args": { + "External id": 718786,"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": 6305208992691.554, "dur": 1.926, + "args": { + "External id": 718787,"Record function id": 0, "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": 6305208992777.337, "dur": 1836.390, + "args": { + "External id": 718788,"Sequence number": 7674663, "Fwd thread 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": 6305208992777.337, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6305208992886.229, "dur": 108.396, + "args": { + "External id": 718789,"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": 6305208993043.836, "dur": 80.679, + "args": { + "External id": 718790,"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": 6305208993148.247, "dur": 59.048, + "args": { + "External id": 718791,"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": 6305208993218.609, "dur": 32.854, + "args": { + "External id": 718792,"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": 6305208993257.436, "dur": 33.497, + "args": { + "External id": 718793,"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": 6305208993297.714, "dur": 27.611, + "args": { + "External id": 718794,"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": 6305208993334.643, "dur": 29.875, + "args": { + "External id": 718795,"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": 6305208993393.321, "dur": 22.607, + "args": { + "External id": 718796,"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": 6305208993436.894, "dur": 27.636, + "args": { + "External id": 718797,"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": 6305208993486.767, "dur": 34.241, + "args": { + "External id": 718798,"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": 6305208993540.534, "dur": 16.713, + "args": { + "External id": 718799,"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": 6305208993567.514, "dur": 43.038, + "args": { + "External id": 718800,"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": 6305208993614.306, "dur": 33.931, + "args": { + "External id": 718801,"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": 6305208993677.303, "dur": 249.951, + "args": { + "External id": 718802,"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": 6305208993756.341, "dur": 6.633, + "args": { + "External id": 718803,"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": 6305208993765.238, "dur": 2.723, + "args": { + "External id": 718804,"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": 6305208993769.454, "dur": 2.684, + "args": { + "External id": 718805,"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": 6305208993773.244, "dur": 5.273, + "args": { + "External id": 718806,"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": 6305208993826.757, "dur": 4.824, + "args": { + "External id": 718807,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305208993828.559, "dur": 2.844, + "args": { + "External id": 718808,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305208993833.360, "dur": 33.332, + "args": { + "External id": 718809,"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": 6305208993839.027, "dur": 1.949, + "args": { + "External id": 718810,"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": 6305208993868.555, "dur": 1.349, + "args": { + "External id": 718811,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305208993869.335, "dur": 0.470, + "args": { + "External id": 718812,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305208993870.760, "dur": 15.776, + "args": { + "External id": 718813,"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": 6305208993872.585, "dur": 0.766, + "args": { + "External id": 718814,"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": 6305208993964.491, "dur": 28.490, + "args": { + "External id": 718815,"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": 6305208994014.223, "dur": 19.013, + "args": { + "External id": 718816,"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": 6305208994040.989, "dur": 85.548, + "args": { + "External id": 718817,"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": 6305208994136.476, "dur": 43.185, + "args": { + "External id": 718818,"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": 6305208994189.398, "dur": 37.943, + "args": { + "External id": 718819,"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": 6305208994243.708, "dur": 37.059, + "args": { + "External id": 718820,"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": 6305208994288.912, "dur": 29.826, + "args": { + "External id": 718821,"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": 6305208994324.901, "dur": 33.642, + "args": { + "External id": 718822,"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": 6305208994385.684, "dur": 31.413, + "args": { + "External id": 718823,"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": 6305208994433.577, "dur": 26.271, + "args": { + "External id": 718824,"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": 6305208994475.842, "dur": 18.143, + "args": { + "External id": 718825,"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": 6305208994525.803, "dur": 18.672, + "args": { + "External id": 718826,"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": 6305208994562.127, "dur": 17.377, + "args": { + "External id": 718827,"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": 6305208994658.877, "dur": 15.006, + "args": { + "External id": 718828,"Record function id": 0, "Ev Idx": 8171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208994661.953, "dur": 10.924, + "args": { + "External id": 718829,"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": 6305208994666.278, "dur": 5.758, + "args": { + "External id": 718830,"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": 6305208994667.882, "dur": 4.047, + "args": { + "External id": 718831,"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": 6305208994677.919, "dur": 4.805, + "args": { + "External id": 718832,"Record function id": 0, "Ev Idx": 8175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208994679.225, "dur": 3.049, + "args": { + "External id": 718833,"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": 6305208994680.243, "dur": 1.547, + "args": { + "External id": 718834,"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": 6305208994680.765, "dur": 0.913, + "args": { + "External id": 718835,"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": 6305208994686.171, "dur": 4.036, + "args": { + "External id": 718836,"Record function id": 0, "Ev Idx": 8179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208994687.452, "dur": 2.344, + "args": { + "External id": 718837,"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": 6305208994687.922, "dur": 1.429, + "args": { + "External id": 718838,"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": 6305208994688.484, "dur": 0.779, + "args": { + "External id": 718839,"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": 6305208994693.404, "dur": 4.017, + "args": { + "External id": 718840,"Record function id": 0, "Ev Idx": 8183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208994694.784, "dur": 2.214, + "args": { + "External id": 718841,"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": 6305208994695.438, "dur": 1.124, + "args": { + "External id": 718842,"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": 6305208994695.841, "dur": 0.627, + "args": { + "External id": 718843,"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": 6305208994700.581, "dur": 3.427, + "args": { + "External id": 718844,"Record function id": 0, "Ev Idx": 8187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208994701.557, "dur": 2.055, + "args": { + "External id": 718845,"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": 6305208994702.138, "dur": 0.916, + "args": { + "External id": 718846,"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": 6305208994702.405, "dur": 0.576, + "args": { + "External id": 718847,"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": 6305208994707.064, "dur": 47.673, + "args": { + "External id": 718848,"Record function id": 0, "Ev Idx": 8191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208994749.628, "dur": 4.671, + "args": { + "External id": 718849,"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": 6305208994750.442, "dur": 3.359, + "args": { + "External id": 718850,"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": 6305208994753.083, "dur": 0.616, + "args": { + "External id": 718851,"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": 6305208994758.221, "dur": 5.844, + "args": { + "External id": 718852,"Record function id": 0, "Ev Idx": 8195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208994759.557, "dur": 4.115, + "args": { + "External id": 718853,"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": 6305208994760.038, "dur": 3.240, + "args": { + "External id": 718854,"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": 6305208994760.332, "dur": 2.873, + "args": { + "External id": 718855,"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": 6305208994767.171, "dur": 3.653, + "args": { + "External id": 718856,"Record function id": 0, "Ev Idx": 8199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208994768.245, "dur": 2.168, + "args": { + "External id": 718857,"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": 6305208994768.748, "dur": 1.252, + "args": { + "External id": 718858,"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": 6305208994769.368, "dur": 0.552, + "args": { + "External id": 718859,"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": 6305208994773.884, "dur": 3.346, + "args": { + "External id": 718860,"Record function id": 0, "Ev Idx": 8203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305208994774.890, "dur": 1.929, + "args": { + "External id": 718861,"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": 6305208994775.458, "dur": 0.971, + "args": { + "External id": 718862,"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": 6305208994775.843, "dur": 0.510, + "args": { + "External id": 718863,"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": 6305208994781.125, "dur": 64082.385, + "args": { + "External id": 718864,"Record function id": 0, "Sequence number": 7674662, "Fwd thread id": 1, "Ev Idx": 8207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305208994782.597, "dur": 64071.053, + "args": { + "External id": 718865,"Sequence number": 7674662, "Fwd thread 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": 6305208994782.597, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.21)", "pid": 2338707, "tid": 2379456, + "ts": 6305208994814.690, "dur": 40.108, + "args": { + "External id": 718866,"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": 6305208994862.777, "dur": 62.999, + "args": { + "External id": 718867,"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": 6305208994931.451, "dur": 63913.880, + "args": { + "External id": 718868,"Record function id": 0, "Ev Idx": 8211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305208995023.705, "dur": 7.051, + "args": { + "External id": 718869,"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": 6305208995040.979, "dur": 4.467, + "args": { + "External id": 718870,"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": 6305208995098.260, "dur": 62750.503, + "args": { + "External id": 718871,"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": 6305208995115.792, "dur": 62719.708, + "args": { + "External id": 718872,"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": 6305208995220.319, "dur": 18.942, + "args": { + "External id": 718873,"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": 6305208995259.906, "dur": 62525.763, + "args": { + "External id": 718874,"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": 6305208995262.776, "dur": 62521.603, + "args": { + "External id": 718875,"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": 6305208995267.099, "dur": 11.117, + "args": { + "External id": 718876,"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": 6305208995280.341, "dur": 62498.326, + "args": { + "External id": 718877,"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": 6305209057962.552, "dur": 12.749, + "args": { + "External id": 718878,"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": 6305209057966.131, "dur": 8.806, + "args": { + "External id": 718879,"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": 6305209058007.102, "dur": 428.554, + "args": { + "External id": 718880,"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": 6305209058040.772, "dur": 389.250, + "args": { + "External id": 718881,"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": 6305209058097.554, "dur": 327.517, + "args": { + "External id": 718882,"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": 6305209058460.052, "dur": 2.847, + "args": { + "External id": 718883,"Record function id": 0, "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": 6305209058543.101, "dur": 6.954, + "args": { + "External id": 718884,"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": 6305209058563.101, "dur": 37.324, + "args": { + "External id": 718885,"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": 6305209058611.502, "dur": 3.627, + "args": { + "External id": 718886,"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": 6305209058620.522, "dur": 12.117, + "args": { + "External id": 718887,"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": 6305209058638.197, "dur": 0.998, + "args": { + "External id": 718888,"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": 6305209058647.019, "dur": 11.436, + "args": { + "External id": 718889,"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": 6305209058663.835, "dur": 0.897, + "args": { + "External id": 718890,"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": 6305209058668.604, "dur": 10.845, + "args": { + "External id": 718891,"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": 6305209058683.906, "dur": 0.969, + "args": { + "External id": 718892,"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": 6305209058689.327, "dur": 9.677, + "args": { + "External id": 718893,"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": 6305209058702.950, "dur": 1.430, + "args": { + "External id": 718894,"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": 6305209058708.825, "dur": 12.143, + "args": { + "External id": 718895,"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": 6305209058727.892, "dur": 0.854, + "args": { + "External id": 718896,"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": 6305209058733.125, "dur": 11.261, + "args": { + "External id": 718897,"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": 6305209058748.765, "dur": 0.886, + "args": { + "External id": 718898,"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": 6305209058753.922, "dur": 11.579, + "args": { + "External id": 718899,"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": 6305209058769.566, "dur": 0.775, + "args": { + "External id": 718900,"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": 6305209058776.135, "dur": 9.608, + "args": { + "External id": 718901,"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": 6305209058879.953, "dur": 3002.135, + "args": { + "External id": 718902,"Record function id": 0, "Ev Idx": 8245 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.20)", "pid": 2338707, "tid": 2379456, + "ts": 6305209058900.768, "dur": 1110.996, + "args": { + "External id": 718903,"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": 6305209058916.970, "dur": 378.012, + "args": { + "External id": 718904,"Record function id": 0, "Ev Idx": 8247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6305209059000.540, "dur": 5.923, + "args": { + "External id": 718905,"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": 6305209059010.457, "dur": 0.916, + "args": { + "External id": 718906,"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": 6305209059013.524, "dur": 0.657, + "args": { + "External id": 718907,"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": 6305209059015.993, "dur": 0.808, + "args": { + "External id": 718908,"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": 6305209059018.290, "dur": 0.700, + "args": { + "External id": 718909,"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": 6305209059020.521, "dur": 1.063, + "args": { + "External id": 718910,"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": 6305209059022.992, "dur": 0.894, + "args": { + "External id": 718911,"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": 6305209059027.248, "dur": 1.065, + "args": { + "External id": 718912,"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": 6305209059030.051, "dur": 3.028, + "args": { + "External id": 718913,"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": 6305209059034.353, "dur": 0.715, + "args": { + "External id": 718914,"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": 6305209059051.661, "dur": 208.556, + "args": { + "External id": 718915,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305209059105.670, "dur": 149.008, + "args": { + "External id": 718916,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305209059127.223, "dur": 15.679, + "args": { + "External id": 718917,"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": 6305209059146.753, "dur": 79.591, + "args": { + "External id": 718918,"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": 6305209059149.641, "dur": 76.277, + "args": { + "External id": 718919,"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": 6305209059163.891, "dur": 5.997, + "args": { + "External id": 718920,"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": 6305209059171.495, "dur": 53.695, + "args": { + "External id": 718921,"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": 6305209059379.521, "dur": 623.988, + "args": { + "External id": 718922,"Record function id": 0, "Ev Idx": 8265 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.19)", "pid": 2338707, "tid": 2379456, + "ts": 6305209059397.142, "dur": 593.445, + "args": { + "External id": 718923,"Record function id": 0, "Ev Idx": 8266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305209059453.588, "dur": 4.959, + "args": { + "External id": 718924,"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": 6305209059474.679, "dur": 46.020, + "args": { + "External id": 718925,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209059479.692, "dur": 1.887, + "args": { + "External id": 718926,"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": 6305209059484.047, "dur": 2.126, + "args": { + "External id": 718927,"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": 6305209059487.408, "dur": 0.458, + "args": { + "External id": 718928,"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": 6305209059488.882, "dur": 2.735, + "args": { + "External id": 718929,"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": 6305209059494.044, "dur": 0.571, + "args": { + "External id": 718930,"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": 6305209059496.075, "dur": 0.285, + "args": { + "External id": 718931,"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": 6305209059497.506, "dur": 0.446, + "args": { + "External id": 718932,"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": 6305209059500.351, "dur": 0.387, + "args": { + "External id": 718933,"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": 6305209059501.760, "dur": 0.473, + "args": { + "External id": 718934,"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": 6305209059533.806, "dur": 43.074, + "args": { + "External id": 718935,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305209059609.953, "dur": 117.951, + "args": { + "External id": 718936,"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": 6305209059621.018, "dur": 3.642, + "args": { + "External id": 718937,"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": 6305209059630.196, "dur": 10.733, + "args": { + "External id": 718938,"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": 6305209059634.799, "dur": 5.750, + "args": { + "External id": 718939,"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": 6305209059638.419, "dur": 0.617, + "args": { + "External id": 718940,"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": 6305209059652.437, "dur": 28.216, + "args": { + "External id": 718941,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209059654.201, "dur": 3.196, + "args": { + "External id": 718942,"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": 6305209059660.486, "dur": 0.465, + "args": { + "External id": 718943,"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": 6305209059662.058, "dur": 0.344, + "args": { + "External id": 718944,"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": 6305209059663.344, "dur": 2.507, + "args": { + "External id": 718945,"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": 6305209059666.953, "dur": 0.290, + "args": { + "External id": 718946,"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": 6305209059668.355, "dur": 0.605, + "args": { + "External id": 718947,"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": 6305209059672.152, "dur": 0.360, + "args": { + "External id": 718948,"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": 6305209059673.495, "dur": 0.380, + "args": { + "External id": 718949,"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": 6305209059674.795, "dur": 2.655, + "args": { + "External id": 718950,"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": 6305209059691.305, "dur": 29.413, + "args": { + "External id": 718951,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305209059782.732, "dur": 132.504, + "args": { + "External id": 718952,"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": 6305209059818.385, "dur": 93.290, + "args": { + "External id": 718953,"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": 6305209059828.247, "dur": 78.716, + "args": { + "External id": 718954,"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": 6305209059936.337, "dur": 2.118, + "args": { + "External id": 718955,"Record function id": 0, "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": 6305209060018.970, "dur": 1841.979, + "args": { + "External id": 718956,"Sequence number": 7674661, "Fwd thread 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": 6305209060018.970, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6305209060170.200, "dur": 114.037, + "args": { + "External id": 718957,"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": 6305209060329.365, "dur": 40.973, + "args": { + "External id": 718958,"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": 6305209060389.987, "dur": 51.157, + "args": { + "External id": 718959,"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": 6305209060450.863, "dur": 33.346, + "args": { + "External id": 718960,"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": 6305209060490.700, "dur": 51.677, + "args": { + "External id": 718961,"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": 6305209060552.703, "dur": 31.583, + "args": { + "External id": 718962,"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": 6305209060594.916, "dur": 30.496, + "args": { + "External id": 718963,"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": 6305209060653.093, "dur": 27.188, + "args": { + "External id": 718964,"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": 6305209060699.409, "dur": 28.690, + "args": { + "External id": 718965,"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": 6305209060751.519, "dur": 21.117, + "args": { + "External id": 718966,"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": 6305209060788.284, "dur": 15.576, + "args": { + "External id": 718967,"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": 6305209060813.063, "dur": 39.502, + "args": { + "External id": 718968,"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": 6305209060856.089, "dur": 32.500, + "args": { + "External id": 718969,"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": 6305209060918.932, "dur": 291.615, + "args": { + "External id": 718970,"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": 6305209061001.710, "dur": 6.953, + "args": { + "External id": 718971,"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": 6305209061011.100, "dur": 2.828, + "args": { + "External id": 718972,"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": 6305209061014.889, "dur": 2.553, + "args": { + "External id": 718973,"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": 6305209061018.253, "dur": 4.291, + "args": { + "External id": 718974,"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": 6305209061102.414, "dur": 8.472, + "args": { + "External id": 718975,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209061107.462, "dur": 3.031, + "args": { + "External id": 718976,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209061113.006, "dur": 33.348, + "args": { + "External id": 718977,"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": 6305209061120.279, "dur": 1.807, + "args": { + "External id": 718978,"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": 6305209061147.617, "dur": 2.167, + "args": { + "External id": 718979,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209061148.963, "dur": 0.724, + "args": { + "External id": 718980,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209061150.831, "dur": 13.634, + "args": { + "External id": 718981,"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": 6305209061152.738, "dur": 0.477, + "args": { + "External id": 718982,"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": 6305209061250.793, "dur": 29.044, + "args": { + "External id": 718983,"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": 6305209061303.668, "dur": 16.333, + "args": { + "External id": 718984,"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": 6305209061328.188, "dur": 51.313, + "args": { + "External id": 718985,"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": 6305209061387.317, "dur": 57.317, + "args": { + "External id": 718986,"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": 6305209061461.749, "dur": 27.116, + "args": { + "External id": 718987,"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": 6305209061496.980, "dur": 55.596, + "args": { + "External id": 718988,"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": 6305209061567.609, "dur": 34.466, + "args": { + "External id": 718989,"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": 6305209061609.595, "dur": 30.955, + "args": { + "External id": 718990,"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": 6305209061665.023, "dur": 28.726, + "args": { + "External id": 718991,"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": 6305209061713.694, "dur": 22.875, + "args": { + "External id": 718992,"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": 6305209061753.436, "dur": 16.784, + "args": { + "External id": 718993,"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": 6305209061785.960, "dur": 13.429, + "args": { + "External id": 718994,"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": 6305209061813.421, "dur": 14.529, + "args": { + "External id": 718995,"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": 6305209061904.684, "dur": 14.855, + "args": { + "External id": 718996,"Record function id": 0, "Ev Idx": 8339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209061907.817, "dur": 10.778, + "args": { + "External id": 718997,"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": 6305209061911.882, "dur": 5.639, + "args": { + "External id": 718998,"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": 6305209061913.603, "dur": 3.831, + "args": { + "External id": 718999,"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": 6305209061923.396, "dur": 4.776, + "args": { + "External id": 719000,"Record function id": 0, "Ev Idx": 8343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209061925.036, "dur": 2.629, + "args": { + "External id": 719001,"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": 6305209061925.678, "dur": 1.434, + "args": { + "External id": 719002,"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": 6305209061926.315, "dur": 0.734, + "args": { + "External id": 719003,"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": 6305209061931.367, "dur": 4.170, + "args": { + "External id": 719004,"Record function id": 0, "Ev Idx": 8347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209061932.623, "dur": 2.502, + "args": { + "External id": 719005,"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": 6305209061933.271, "dur": 1.393, + "args": { + "External id": 719006,"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": 6305209061933.861, "dur": 0.697, + "args": { + "External id": 719007,"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": 6305209061938.715, "dur": 4.595, + "args": { + "External id": 719008,"Record function id": 0, "Ev Idx": 8351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209061939.956, "dur": 2.900, + "args": { + "External id": 719009,"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": 6305209061940.796, "dur": 1.627, + "args": { + "External id": 719010,"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": 6305209061941.486, "dur": 0.872, + "args": { + "External id": 719011,"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": 6305209061946.572, "dur": 4.204, + "args": { + "External id": 719012,"Record function id": 0, "Ev Idx": 8355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209061947.910, "dur": 2.424, + "args": { + "External id": 719013,"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": 6305209061948.710, "dur": 1.050, + "args": { + "External id": 719014,"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": 6305209061948.981, "dur": 0.704, + "args": { + "External id": 719015,"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": 6305209061954.095, "dur": 6.641, + "args": { + "External id": 719016,"Record function id": 0, "Ev Idx": 8359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209061955.567, "dur": 4.774, + "args": { + "External id": 719017,"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": 6305209061956.023, "dur": 3.907, + "args": { + "External id": 719018,"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": 6305209061956.590, "dur": 3.278, + "args": { + "External id": 719019,"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": 6305209061964.061, "dur": 3.682, + "args": { + "External id": 719020,"Record function id": 0, "Ev Idx": 8363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209061965.398, "dur": 1.953, + "args": { + "External id": 719021,"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": 6305209061965.841, "dur": 1.069, + "args": { + "External id": 719022,"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": 6305209061966.102, "dur": 0.734, + "args": { + "External id": 719023,"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": 6305209061970.922, "dur": 6.163, + "args": { + "External id": 719024,"Record function id": 0, "Ev Idx": 8367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209061972.215, "dur": 4.472, + "args": { + "External id": 719025,"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": 6305209061972.661, "dur": 3.288, + "args": { + "External id": 719026,"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": 6305209061975.179, "dur": 0.704, + "args": { + "External id": 719027,"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": 6305209061980.194, "dur": 3.717, + "args": { + "External id": 719028,"Record function id": 0, "Ev Idx": 8371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209061981.477, "dur": 2.041, + "args": { + "External id": 719029,"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": 6305209061982.041, "dur": 1.033, + "args": { + "External id": 719030,"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": 6305209061982.353, "dur": 0.654, + "args": { + "External id": 719031,"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": 6305209061988.236, "dur": 63309.026, + "args": { + "External id": 719032,"Record function id": 0, "Sequence number": 7674660, "Fwd thread id": 1, "Ev Idx": 8375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305209061989.595, "dur": 63297.787, + "args": { + "External id": 719033,"Sequence number": 7674660, "Fwd thread 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": 6305209061989.595, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.20)", "pid": 2338707, "tid": 2379456, + "ts": 6305209062019.092, "dur": 79.205, + "args": { + "External id": 719034,"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": 6305209062108.221, "dur": 67.630, + "args": { + "External id": 719035,"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": 6305209062182.137, "dur": 63097.084, + "args": { + "External id": 719036,"Record function id": 0, "Ev Idx": 8379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305209062273.108, "dur": 7.280, + "args": { + "External id": 719037,"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": 6305209062291.132, "dur": 4.928, + "args": { + "External id": 719038,"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": 6305209062313.059, "dur": 61902.062, + "args": { + "External id": 719039,"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": 6305209062328.957, "dur": 61872.943, + "args": { + "External id": 719040,"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": 6305209062425.630, "dur": 17.417, + "args": { + "External id": 719041,"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": 6305209062463.178, "dur": 61695.196, + "args": { + "External id": 719042,"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": 6305209062465.870, "dur": 61691.285, + "args": { + "External id": 719043,"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": 6305209062470.834, "dur": 9.173, + "args": { + "External id": 719044,"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": 6305209062482.445, "dur": 61669.693, + "args": { + "External id": 719045,"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": 6305209124326.748, "dur": 11.910, + "args": { + "External id": 719046,"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": 6305209124330.139, "dur": 8.144, + "args": { + "External id": 719047,"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": 6305209124370.297, "dur": 448.488, + "args": { + "External id": 719048,"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": 6305209124404.316, "dur": 408.636, + "args": { + "External id": 719049,"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": 6305209124417.333, "dur": 389.378, + "args": { + "External id": 719050,"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": 6305209124849.354, "dur": 2.637, + "args": { + "External id": 719051,"Record function id": 0, "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": 6305209124917.166, "dur": 7.048, + "args": { + "External id": 719052,"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": 6305209124936.704, "dur": 36.117, + "args": { + "External id": 719053,"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": 6305209124982.669, "dur": 3.750, + "args": { + "External id": 719054,"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": 6305209124992.581, "dur": 15.130, + "args": { + "External id": 719055,"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": 6305209125013.769, "dur": 0.827, + "args": { + "External id": 719056,"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": 6305209125019.028, "dur": 12.201, + "args": { + "External id": 719057,"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": 6305209125037.866, "dur": 0.734, + "args": { + "External id": 719058,"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": 6305209125042.679, "dur": 59.415, + "args": { + "External id": 719059,"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": 6305209125110.881, "dur": 1.485, + "args": { + "External id": 719060,"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": 6305209125117.303, "dur": 12.151, + "args": { + "External id": 719061,"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": 6305209125134.059, "dur": 1.508, + "args": { + "External id": 719062,"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": 6305209125139.615, "dur": 11.190, + "args": { + "External id": 719063,"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": 6305209125155.349, "dur": 0.799, + "args": { + "External id": 719064,"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": 6305209125162.336, "dur": 11.139, + "args": { + "External id": 719065,"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": 6305209125178.206, "dur": 0.859, + "args": { + "External id": 719066,"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": 6305209125183.281, "dur": 12.735, + "args": { + "External id": 719067,"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": 6305209125199.982, "dur": 0.889, + "args": { + "External id": 719068,"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": 6305209125205.347, "dur": 10.805, + "args": { + "External id": 719069,"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": 6305209125313.909, "dur": 2967.883, + "args": { + "External id": 719070,"Record function id": 0, "Ev Idx": 8413 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.19)", "pid": 2338707, "tid": 2379456, + "ts": 6305209125334.014, "dur": 1089.233, + "args": { + "External id": 719071,"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": 6305209125350.082, "dur": 356.486, + "args": { + "External id": 719072,"Record function id": 0, "Ev Idx": 8415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6305209125432.026, "dur": 6.906, + "args": { + "External id": 719073,"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": 6305209125442.736, "dur": 0.831, + "args": { + "External id": 719074,"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": 6305209125445.541, "dur": 0.822, + "args": { + "External id": 719075,"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": 6305209125448.069, "dur": 1.068, + "args": { + "External id": 719076,"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": 6305209125452.989, "dur": 0.773, + "args": { + "External id": 719077,"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": 6305209125455.125, "dur": 0.947, + "args": { + "External id": 719078,"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": 6305209125457.865, "dur": 0.979, + "args": { + "External id": 719079,"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": 6305209125460.168, "dur": 0.893, + "args": { + "External id": 719080,"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": 6305209125464.461, "dur": 3.068, + "args": { + "External id": 719081,"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": 6305209125469.433, "dur": 0.772, + "args": { + "External id": 719082,"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": 6305209125487.859, "dur": 185.163, + "args": { + "External id": 719083,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305209125504.773, "dur": 162.539, + "args": { + "External id": 719084,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305209125538.665, "dur": 17.156, + "args": { + "External id": 719085,"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": 6305209125559.943, "dur": 80.247, + "args": { + "External id": 719086,"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": 6305209125564.749, "dur": 74.958, + "args": { + "External id": 719087,"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": 6305209125579.501, "dur": 6.431, + "args": { + "External id": 719088,"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": 6305209125587.654, "dur": 51.451, + "args": { + "External id": 719089,"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": 6305209125786.794, "dur": 628.192, + "args": { + "External id": 719090,"Record function id": 0, "Ev Idx": 8433 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.18)", "pid": 2338707, "tid": 2379456, + "ts": 6305209125804.906, "dur": 597.280, + "args": { + "External id": 719091,"Record function id": 0, "Ev Idx": 8434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305209125863.548, "dur": 5.029, + "args": { + "External id": 719092,"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": 6305209125884.597, "dur": 29.024, + "args": { + "External id": 719093,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209125889.505, "dur": 1.626, + "args": { + "External id": 719094,"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": 6305209125892.876, "dur": 1.674, + "args": { + "External id": 719095,"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": 6305209125896.313, "dur": 0.352, + "args": { + "External id": 719096,"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": 6305209125897.679, "dur": 2.866, + "args": { + "External id": 719097,"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": 6305209125902.599, "dur": 0.409, + "args": { + "External id": 719098,"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": 6305209125904.459, "dur": 0.513, + "args": { + "External id": 719099,"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": 6305209125906.072, "dur": 0.456, + "args": { + "External id": 719100,"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": 6305209125908.628, "dur": 0.258, + "args": { + "External id": 719101,"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": 6305209125909.890, "dur": 0.333, + "args": { + "External id": 719102,"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": 6305209125924.480, "dur": 43.839, + "args": { + "External id": 719103,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305209125998.190, "dur": 153.748, + "args": { + "External id": 719104,"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": 6305209126008.091, "dur": 3.664, + "args": { + "External id": 719105,"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": 6305209126017.012, "dur": 10.560, + "args": { + "External id": 719106,"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": 6305209126021.353, "dur": 5.823, + "args": { + "External id": 719107,"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": 6305209126025.038, "dur": 0.803, + "args": { + "External id": 719108,"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": 6305209126033.975, "dur": 63.150, + "args": { + "External id": 719109,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209126035.822, "dur": 2.562, + "args": { + "External id": 719110,"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": 6305209126040.419, "dur": 0.332, + "args": { + "External id": 719111,"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": 6305209126041.911, "dur": 0.474, + "args": { + "External id": 719112,"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": 6305209126043.654, "dur": 1.303, + "args": { + "External id": 719113,"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": 6305209126046.037, "dur": 0.474, + "args": { + "External id": 719114,"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": 6305209126047.880, "dur": 0.588, + "args": { + "External id": 719115,"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": 6305209126050.936, "dur": 0.425, + "args": { + "External id": 719116,"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": 6305209126088.600, "dur": 0.520, + "args": { + "External id": 719117,"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": 6305209126091.061, "dur": 2.645, + "args": { + "External id": 719118,"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": 6305209126110.239, "dur": 34.050, + "args": { + "External id": 719119,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305209126199.837, "dur": 128.890, + "args": { + "External id": 719120,"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": 6305209126231.739, "dur": 93.441, + "args": { + "External id": 719121,"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": 6305209126241.485, "dur": 78.595, + "args": { + "External id": 719122,"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": 6305209126347.886, "dur": 2.155, + "args": { + "External id": 719123,"Record function id": 0, "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": 6305209126430.186, "dur": 1830.009, + "args": { + "External id": 719124,"Sequence number": 7674659, "Fwd thread 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": 6305209126430.186, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6305209126558.971, "dur": 118.789, + "args": { + "External id": 719125,"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": 6305209126722.235, "dur": 39.945, + "args": { + "External id": 719126,"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": 6305209126781.255, "dur": 51.124, + "args": { + "External id": 719127,"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": 6305209126842.400, "dur": 32.460, + "args": { + "External id": 719128,"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": 6305209126881.365, "dur": 32.909, + "args": { + "External id": 719129,"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": 6305209126921.044, "dur": 28.657, + "args": { + "External id": 719130,"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": 6305209126959.670, "dur": 30.357, + "args": { + "External id": 719131,"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": 6305209127015.943, "dur": 22.798, + "args": { + "External id": 719132,"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": 6305209127093.015, "dur": 32.153, + "args": { + "External id": 719133,"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": 6305209127151.988, "dur": 20.747, + "args": { + "External id": 719134,"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": 6305209127187.956, "dur": 16.646, + "args": { + "External id": 719135,"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": 6305209127214.917, "dur": 44.365, + "args": { + "External id": 719136,"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": 6305209127263.190, "dur": 35.272, + "args": { + "External id": 719137,"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": 6305209127327.230, "dur": 271.437, + "args": { + "External id": 719138,"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": 6305209127407.222, "dur": 6.637, + "args": { + "External id": 719139,"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": 6305209127416.310, "dur": 3.432, + "args": { + "External id": 719140,"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": 6305209127421.229, "dur": 2.429, + "args": { + "External id": 719141,"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": 6305209127424.636, "dur": 4.587, + "args": { + "External id": 719142,"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": 6305209127475.477, "dur": 5.085, + "args": { + "External id": 719143,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209127477.570, "dur": 2.820, + "args": { + "External id": 719144,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209127482.596, "dur": 48.753, + "args": { + "External id": 719145,"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": 6305209127489.296, "dur": 1.631, + "args": { + "External id": 719146,"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": 6305209127536.235, "dur": 1.838, + "args": { + "External id": 719147,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209127537.123, "dur": 0.840, + "args": { + "External id": 719148,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209127539.463, "dur": 15.483, + "args": { + "External id": 719149,"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": 6305209127541.690, "dur": 0.559, + "args": { + "External id": 719150,"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": 6305209127640.829, "dur": 29.958, + "args": { + "External id": 719151,"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": 6305209127692.482, "dur": 16.995, + "args": { + "External id": 719152,"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": 6305209127717.715, "dur": 47.950, + "args": { + "External id": 719153,"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": 6305209127772.148, "dur": 39.263, + "args": { + "External id": 719154,"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": 6305209127819.848, "dur": 20.879, + "args": { + "External id": 719155,"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": 6305209127847.846, "dur": 32.010, + "args": { + "External id": 719156,"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": 6305209127887.317, "dur": 29.093, + "args": { + "External id": 719157,"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": 6305209127936.840, "dur": 41.251, + "args": { + "External id": 719158,"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": 6305209128003.644, "dur": 23.871, + "args": { + "External id": 719159,"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": 6305209128046.660, "dur": 63.888, + "args": { + "External id": 719160,"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": 6305209128132.260, "dur": 22.261, + "args": { + "External id": 719161,"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": 6305209128171.137, "dur": 15.871, + "args": { + "External id": 719162,"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": 6305209128207.928, "dur": 16.474, + "args": { + "External id": 719163,"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": 6305209128304.384, "dur": 15.229, + "args": { + "External id": 719164,"Record function id": 0, "Ev Idx": 8507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209128307.772, "dur": 10.783, + "args": { + "External id": 719165,"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": 6305209128312.002, "dur": 5.549, + "args": { + "External id": 719166,"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": 6305209128313.504, "dur": 3.955, + "args": { + "External id": 719167,"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": 6305209128323.595, "dur": 5.570, + "args": { + "External id": 719168,"Record function id": 0, "Ev Idx": 8511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209128325.173, "dur": 3.463, + "args": { + "External id": 719169,"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": 6305209128326.361, "dur": 1.677, + "args": { + "External id": 719170,"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": 6305209128327.046, "dur": 0.867, + "args": { + "External id": 719171,"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": 6305209128332.594, "dur": 4.344, + "args": { + "External id": 719172,"Record function id": 0, "Ev Idx": 8515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209128333.981, "dur": 2.492, + "args": { + "External id": 719173,"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": 6305209128334.646, "dur": 1.373, + "args": { + "External id": 719174,"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": 6305209128335.326, "dur": 0.605, + "args": { + "External id": 719175,"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": 6305209128340.311, "dur": 4.514, + "args": { + "External id": 719176,"Record function id": 0, "Ev Idx": 8519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209128341.833, "dur": 2.525, + "args": { + "External id": 719177,"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": 6305209128342.552, "dur": 1.346, + "args": { + "External id": 719178,"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": 6305209128342.879, "dur": 0.919, + "args": { + "External id": 719179,"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": 6305209128347.980, "dur": 3.604, + "args": { + "External id": 719180,"Record function id": 0, "Ev Idx": 8523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209128349.010, "dur": 2.149, + "args": { + "External id": 719181,"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": 6305209128349.535, "dur": 1.071, + "args": { + "External id": 719182,"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": 6305209128349.969, "dur": 0.562, + "args": { + "External id": 719183,"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": 6305209128354.780, "dur": 6.611, + "args": { + "External id": 719184,"Record function id": 0, "Ev Idx": 8527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209128356.238, "dur": 4.728, + "args": { + "External id": 719185,"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": 6305209128356.693, "dur": 3.873, + "args": { + "External id": 719186,"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": 6305209128357.628, "dur": 2.868, + "args": { + "External id": 719187,"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": 6305209128364.700, "dur": 3.644, + "args": { + "External id": 719188,"Record function id": 0, "Ev Idx": 8531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209128365.886, "dur": 2.005, + "args": { + "External id": 719189,"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": 6305209128366.567, "dur": 0.933, + "args": { + "External id": 719190,"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": 6305209128366.865, "dur": 0.570, + "args": { + "External id": 719191,"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": 6305209128371.514, "dur": 7.604, + "args": { + "External id": 719192,"Record function id": 0, "Ev Idx": 8535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209128376.624, "dur": 2.075, + "args": { + "External id": 719193,"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": 6305209128377.325, "dur": 0.932, + "args": { + "External id": 719194,"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": 6305209128377.600, "dur": 0.582, + "args": { + "External id": 719195,"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": 6305209128382.345, "dur": 5.735, + "args": { + "External id": 719196,"Record function id": 0, "Ev Idx": 8539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209128383.418, "dur": 4.227, + "args": { + "External id": 719197,"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": 6305209128384.101, "dur": 3.118, + "args": { + "External id": 719198,"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": 6305209128386.476, "dur": 0.676, + "args": { + "External id": 719199,"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": 6305209128391.933, "dur": 64589.970, + "args": { + "External id": 719200,"Record function id": 0, "Sequence number": 7674658, "Fwd thread id": 1, "Ev Idx": 8543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305209128399.748, "dur": 64572.797, + "args": { + "External id": 719201,"Sequence number": 7674658, "Fwd thread 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": 6305209128399.748, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.19)", "pid": 2338707, "tid": 2379456, + "ts": 6305209128429.899, "dur": 42.087, + "args": { + "External id": 719202,"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": 6305209128479.752, "dur": 83.310, + "args": { + "External id": 719203,"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": 6305209128570.662, "dur": 64394.059, + "args": { + "External id": 719204,"Record function id": 0, "Ev Idx": 8547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305209128664.082, "dur": 7.361, + "args": { + "External id": 719205,"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": 6305209128681.759, "dur": 5.374, + "args": { + "External id": 719206,"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": 6305209128701.591, "dur": 63284.561, + "args": { + "External id": 719207,"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": 6305209128717.975, "dur": 63254.614, + "args": { + "External id": 719208,"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": 6305209128813.175, "dur": 17.561, + "args": { + "External id": 719209,"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": 6305209128851.501, "dur": 63072.766, + "args": { + "External id": 719210,"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": 6305209128856.914, "dur": 63066.072, + "args": { + "External id": 719211,"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": 6305209128861.394, "dur": 9.147, + "args": { + "External id": 719212,"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": 6305209128872.521, "dur": 63045.077, + "args": { + "External id": 719213,"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": 6305209192128.889, "dur": 13.790, + "args": { + "External id": 719214,"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": 6305209192132.695, "dur": 9.452, + "args": { + "External id": 719215,"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": 6305209192174.086, "dur": 397.416, + "args": { + "External id": 719216,"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": 6305209192208.154, "dur": 357.273, + "args": { + "External id": 719217,"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": 6305209192221.381, "dur": 337.444, + "args": { + "External id": 719218,"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": 6305209192600.685, "dur": 2.481, + "args": { + "External id": 719219,"Record function id": 0, "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": 6305209192667.069, "dur": 7.112, + "args": { + "External id": 719220,"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": 6305209192686.430, "dur": 36.291, + "args": { + "External id": 719221,"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": 6305209192733.876, "dur": 4.252, + "args": { + "External id": 719222,"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": 6305209192743.556, "dur": 12.713, + "args": { + "External id": 719223,"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": 6305209192762.027, "dur": 0.935, + "args": { + "External id": 719224,"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": 6305209192767.764, "dur": 10.791, + "args": { + "External id": 719225,"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": 6305209192783.588, "dur": 0.829, + "args": { + "External id": 719226,"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": 6305209192788.332, "dur": 10.896, + "args": { + "External id": 719227,"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": 6305209192806.567, "dur": 0.909, + "args": { + "External id": 719228,"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": 6305209192811.263, "dur": 10.361, + "args": { + "External id": 719229,"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": 6305209192826.408, "dur": 1.464, + "args": { + "External id": 719230,"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": 6305209192831.783, "dur": 10.645, + "args": { + "External id": 719231,"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": 6305209192846.830, "dur": 0.713, + "args": { + "External id": 719232,"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": 6305209192851.809, "dur": 10.285, + "args": { + "External id": 719233,"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": 6305209192868.144, "dur": 0.877, + "args": { + "External id": 719234,"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": 6305209192872.292, "dur": 13.142, + "args": { + "External id": 719235,"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": 6305209192889.808, "dur": 0.806, + "args": { + "External id": 719236,"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": 6305209192893.778, "dur": 11.556, + "args": { + "External id": 719237,"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": 6305209192996.500, "dur": 2964.482, + "args": { + "External id": 719238,"Record function id": 0, "Ev Idx": 8581 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.18)", "pid": 2338707, "tid": 2379456, + "ts": 6305209193019.360, "dur": 1117.849, + "args": { + "External id": 719239,"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": 6305209193034.338, "dur": 374.528, + "args": { + "External id": 719240,"Record function id": 0, "Ev Idx": 8583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6305209193158.229, "dur": 7.017, + "args": { + "External id": 719241,"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": 6305209193169.112, "dur": 0.753, + "args": { + "External id": 719242,"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": 6305209193171.749, "dur": 0.739, + "args": { + "External id": 719243,"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": 6305209193173.973, "dur": 0.695, + "args": { + "External id": 719244,"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": 6305209193175.900, "dur": 0.652, + "args": { + "External id": 719245,"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": 6305209193180.667, "dur": 0.785, + "args": { + "External id": 719246,"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": 6305209193182.809, "dur": 0.947, + "args": { + "External id": 719247,"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": 6305209193185.001, "dur": 1.049, + "args": { + "External id": 719248,"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": 6305209193187.838, "dur": 6.614, + "args": { + "External id": 719249,"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": 6305209193197.909, "dur": 0.749, + "args": { + "External id": 719250,"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": 6305209193216.983, "dur": 161.865, + "args": { + "External id": 719251,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305209193234.223, "dur": 139.837, + "args": { + "External id": 719252,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305209193251.158, "dur": 13.754, + "args": { + "External id": 719253,"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": 6305209193268.364, "dur": 76.447, + "args": { + "External id": 719254,"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": 6305209193270.858, "dur": 73.567, + "args": { + "External id": 719255,"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": 6305209193285.121, "dur": 6.015, + "args": { + "External id": 719256,"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": 6305209193292.887, "dur": 50.790, + "args": { + "External id": 719257,"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": 6305209193490.823, "dur": 638.927, + "args": { + "External id": 719258,"Record function id": 0, "Ev Idx": 8601 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.17)", "pid": 2338707, "tid": 2379456, + "ts": 6305209193526.654, "dur": 588.918, + "args": { + "External id": 719259,"Record function id": 0, "Ev Idx": 8602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305209193589.450, "dur": 6.383, + "args": { + "External id": 719260,"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": 6305209193612.275, "dur": 29.756, + "args": { + "External id": 719261,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209193617.936, "dur": 2.205, + "args": { + "External id": 719262,"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": 6305209193622.149, "dur": 0.680, + "args": { + "External id": 719263,"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": 6305209193624.290, "dur": 0.509, + "args": { + "External id": 719264,"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": 6305209193626.471, "dur": 2.761, + "args": { + "External id": 719265,"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": 6305209193631.237, "dur": 0.486, + "args": { + "External id": 719266,"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": 6305209193632.812, "dur": 0.542, + "args": { + "External id": 719267,"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": 6305209193635.062, "dur": 0.576, + "args": { + "External id": 719268,"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": 6305209193637.107, "dur": 0.337, + "args": { + "External id": 719269,"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": 6305209193638.286, "dur": 0.600, + "args": { + "External id": 719270,"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": 6305209193651.713, "dur": 45.282, + "args": { + "External id": 719271,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305209193729.946, "dur": 111.352, + "args": { + "External id": 719272,"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": 6305209193740.556, "dur": 3.112, + "args": { + "External id": 719273,"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": 6305209193749.083, "dur": 10.691, + "args": { + "External id": 719274,"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": 6305209193753.945, "dur": 5.456, + "args": { + "External id": 719275,"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": 6305209193757.726, "dur": 0.551, + "args": { + "External id": 719276,"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": 6305209193766.283, "dur": 25.170, + "args": { + "External id": 719277,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209193768.063, "dur": 2.678, + "args": { + "External id": 719278,"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": 6305209193772.137, "dur": 0.567, + "args": { + "External id": 719279,"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": 6305209193774.445, "dur": 0.500, + "args": { + "External id": 719280,"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": 6305209193776.625, "dur": 0.613, + "args": { + "External id": 719281,"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": 6305209193778.077, "dur": 0.650, + "args": { + "External id": 719282,"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": 6305209193780.167, "dur": 0.444, + "args": { + "External id": 719283,"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": 6305209193782.047, "dur": 0.646, + "args": { + "External id": 719284,"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": 6305209193783.538, "dur": 0.447, + "args": { + "External id": 719285,"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": 6305209193785.453, "dur": 2.258, + "args": { + "External id": 719286,"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": 6305209193802.720, "dur": 31.305, + "args": { + "External id": 719287,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305209193885.878, "dur": 117.636, + "args": { + "External id": 719288,"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": 6305209193911.824, "dur": 88.101, + "args": { + "External id": 719289,"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": 6305209193921.394, "dur": 73.767, + "args": { + "External id": 719290,"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": 6305209194021.707, "dur": 2.036, + "args": { + "External id": 719291,"Record function id": 0, "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": 6305209194145.577, "dur": 1789.987, + "args": { + "External id": 719292,"Sequence number": 7674657, "Fwd thread 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": 6305209194145.577, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6305209194264.643, "dur": 117.691, + "args": { + "External id": 719293,"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": 6305209194429.398, "dur": 41.283, + "args": { + "External id": 719294,"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": 6305209194490.766, "dur": 70.916, + "args": { + "External id": 719295,"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": 6305209194576.380, "dur": 34.323, + "args": { + "External id": 719296,"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": 6305209194617.122, "dur": 35.289, + "args": { + "External id": 719297,"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": 6305209194659.840, "dur": 28.368, + "args": { + "External id": 719298,"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": 6305209194697.936, "dur": 29.918, + "args": { + "External id": 719299,"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": 6305209194759.219, "dur": 24.899, + "args": { + "External id": 719300,"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": 6305209194805.279, "dur": 28.529, + "args": { + "External id": 719301,"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": 6305209194855.130, "dur": 19.289, + "args": { + "External id": 719302,"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": 6305209194889.577, "dur": 15.219, + "args": { + "External id": 719303,"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": 6305209194916.537, "dur": 38.429, + "args": { + "External id": 719304,"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": 6305209194958.690, "dur": 34.432, + "args": { + "External id": 719305,"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": 6305209195021.342, "dur": 290.961, + "args": { + "External id": 719306,"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": 6305209195140.781, "dur": 7.802, + "args": { + "External id": 719307,"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": 6305209195151.143, "dur": 2.677, + "args": { + "External id": 719308,"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": 6305209195155.305, "dur": 2.189, + "args": { + "External id": 719309,"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": 6305209195158.860, "dur": 4.341, + "args": { + "External id": 719310,"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": 6305209195211.058, "dur": 4.732, + "args": { + "External id": 719311,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209195212.977, "dur": 2.648, + "args": { + "External id": 719312,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209195217.557, "dur": 32.999, + "args": { + "External id": 719313,"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": 6305209195223.700, "dur": 1.810, + "args": { + "External id": 719314,"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": 6305209195252.188, "dur": 1.975, + "args": { + "External id": 719315,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209195253.419, "dur": 0.664, + "args": { + "External id": 719316,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209195255.268, "dur": 14.176, + "args": { + "External id": 719317,"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": 6305209195257.529, "dur": 0.451, + "args": { + "External id": 719318,"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": 6305209195349.296, "dur": 28.681, + "args": { + "External id": 719319,"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": 6305209195395.790, "dur": 16.550, + "args": { + "External id": 719320,"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": 6305209195421.974, "dur": 47.743, + "args": { + "External id": 719321,"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": 6305209195477.524, "dur": 56.461, + "args": { + "External id": 719322,"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": 6305209195546.994, "dur": 25.263, + "args": { + "External id": 719323,"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": 6305209195580.543, "dur": 32.872, + "args": { + "External id": 719324,"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": 6305209195621.901, "dur": 44.961, + "args": { + "External id": 719325,"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": 6305209195682.598, "dur": 36.797, + "args": { + "External id": 719326,"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": 6305209195741.995, "dur": 25.873, + "args": { + "External id": 719327,"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": 6305209195787.461, "dur": 23.834, + "args": { + "External id": 719328,"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": 6305209195824.270, "dur": 19.875, + "args": { + "External id": 719329,"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": 6305209195858.211, "dur": 14.529, + "args": { + "External id": 719330,"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": 6305209195885.137, "dur": 15.107, + "args": { + "External id": 719331,"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": 6305209195983.195, "dur": 15.612, + "args": { + "External id": 719332,"Record function id": 0, "Ev Idx": 8675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209195986.546, "dur": 11.385, + "args": { + "External id": 719333,"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": 6305209195991.162, "dur": 5.920, + "args": { + "External id": 719334,"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": 6305209195993.091, "dur": 3.877, + "args": { + "External id": 719335,"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": 6305209196002.758, "dur": 5.396, + "args": { + "External id": 719336,"Record function id": 0, "Ev Idx": 8679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209196004.004, "dur": 3.703, + "args": { + "External id": 719337,"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": 6305209196004.559, "dur": 2.581, + "args": { + "External id": 719338,"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": 6305209196005.431, "dur": 1.617, + "args": { + "External id": 719339,"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": 6305209196011.522, "dur": 8.014, + "args": { + "External id": 719340,"Record function id": 0, "Ev Idx": 8683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209196012.919, "dur": 6.151, + "args": { + "External id": 719341,"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": 6305209196016.882, "dur": 1.677, + "args": { + "External id": 719342,"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": 6305209196017.374, "dur": 1.119, + "args": { + "External id": 719343,"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": 6305209196022.719, "dur": 4.039, + "args": { + "External id": 719344,"Record function id": 0, "Ev Idx": 8687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209196023.644, "dur": 2.683, + "args": { + "External id": 719345,"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": 6305209196024.312, "dur": 1.585, + "args": { + "External id": 719346,"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": 6305209196025.224, "dur": 0.598, + "args": { + "External id": 719347,"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": 6305209196029.974, "dur": 15.737, + "args": { + "External id": 719348,"Record function id": 0, "Ev Idx": 8691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209196042.817, "dur": 2.477, + "args": { + "External id": 719349,"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": 6305209196043.485, "dur": 1.233, + "args": { + "External id": 719350,"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": 6305209196043.956, "dur": 0.687, + "args": { + "External id": 719351,"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": 6305209196048.985, "dur": 49.004, + "args": { + "External id": 719352,"Record function id": 0, "Ev Idx": 8695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209196050.264, "dur": 46.365, + "args": { + "External id": 719353,"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": 6305209196050.833, "dur": 44.533, + "args": { + "External id": 719354,"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": 6305209196090.879, "dur": 4.122, + "args": { + "External id": 719355,"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": 6305209196103.767, "dur": 5.435, + "args": { + "External id": 719356,"Record function id": 0, "Ev Idx": 8699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209196105.669, "dur": 3.122, + "args": { + "External id": 719357,"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": 6305209196106.699, "dur": 1.665, + "args": { + "External id": 719358,"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": 6305209196107.422, "dur": 0.856, + "args": { + "External id": 719359,"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": 6305209196112.423, "dur": 49.743, + "args": { + "External id": 719360,"Record function id": 0, "Ev Idx": 8703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209196159.133, "dur": 2.562, + "args": { + "External id": 719361,"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": 6305209196159.778, "dur": 1.459, + "args": { + "External id": 719362,"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": 6305209196160.106, "dur": 1.040, + "args": { + "External id": 719363,"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": 6305209196165.948, "dur": 6.384, + "args": { + "External id": 719364,"Record function id": 0, "Ev Idx": 8707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209196167.319, "dur": 4.516, + "args": { + "External id": 719365,"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": 6305209196167.857, "dur": 3.589, + "args": { + "External id": 719366,"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": 6305209196170.650, "dur": 0.661, + "args": { + "External id": 719367,"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": 6305209196176.639, "dur": 62537.879, + "args": { + "External id": 719368,"Record function id": 0, "Sequence number": 7674656, "Fwd thread id": 1, "Ev Idx": 8711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305209196177.979, "dur": 62527.215, + "args": { + "External id": 719369,"Sequence number": 7674656, "Fwd thread 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": 6305209196177.979, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.18)", "pid": 2338707, "tid": 2379456, + "ts": 6305209196210.152, "dur": 40.514, + "args": { + "External id": 719370,"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": 6305209196258.053, "dur": 63.552, + "args": { + "External id": 719371,"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": 6305209196327.950, "dur": 62368.739, + "args": { + "External id": 719372,"Record function id": 0, "Ev Idx": 8715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305209196421.487, "dur": 7.643, + "args": { + "External id": 719373,"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": 6305209196439.051, "dur": 5.014, + "args": { + "External id": 719374,"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": 6305209196458.453, "dur": 61197.843, + "args": { + "External id": 719375,"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": 6305209196474.307, "dur": 61167.833, + "args": { + "External id": 719376,"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": 6305209196585.360, "dur": 18.226, + "args": { + "External id": 719377,"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": 6305209196624.518, "dur": 60969.989, + "args": { + "External id": 719378,"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": 6305209196627.239, "dur": 60966.072, + "args": { + "External id": 719379,"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": 6305209196632.346, "dur": 10.876, + "args": { + "External id": 719380,"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": 6305209196645.467, "dur": 60942.095, + "args": { + "External id": 719381,"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": 6305209257774.209, "dur": 16.737, + "args": { + "External id": 719382,"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": 6305209257778.037, "dur": 12.453, + "args": { + "External id": 719383,"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": 6305209257825.612, "dur": 455.243, + "args": { + "External id": 719384,"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": 6305209257859.287, "dur": 415.419, + "args": { + "External id": 719385,"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": 6305209257871.257, "dur": 396.850, + "args": { + "External id": 719386,"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": 6305209258303.961, "dur": 2.679, + "args": { + "External id": 719387,"Record function id": 0, "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": 6305209258375.527, "dur": 7.108, + "args": { + "External id": 719388,"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": 6305209258394.916, "dur": 37.132, + "args": { + "External id": 719389,"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": 6305209258442.733, "dur": 3.609, + "args": { + "External id": 719390,"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": 6305209258452.029, "dur": 12.918, + "args": { + "External id": 719391,"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": 6305209258470.591, "dur": 0.868, + "args": { + "External id": 719392,"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": 6305209258475.674, "dur": 9.930, + "args": { + "External id": 719393,"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": 6305209258490.464, "dur": 0.864, + "args": { + "External id": 719394,"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": 6305209258495.310, "dur": 28.927, + "args": { + "External id": 719395,"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": 6305209258531.982, "dur": 1.291, + "args": { + "External id": 719396,"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": 6305209258538.024, "dur": 12.661, + "args": { + "External id": 719397,"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": 6305209258555.019, "dur": 0.909, + "args": { + "External id": 719398,"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": 6305209258559.730, "dur": 12.796, + "args": { + "External id": 719399,"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": 6305209258577.230, "dur": 1.023, + "args": { + "External id": 719400,"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": 6305209258581.930, "dur": 11.575, + "args": { + "External id": 719401,"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": 6305209258597.870, "dur": 0.643, + "args": { + "External id": 719402,"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": 6305209258602.304, "dur": 11.825, + "args": { + "External id": 719403,"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": 6305209258620.702, "dur": 0.827, + "args": { + "External id": 719404,"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": 6305209258625.462, "dur": 10.040, + "args": { + "External id": 719405,"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": 6305209258730.668, "dur": 2976.764, + "args": { + "External id": 719406,"Record function id": 0, "Ev Idx": 8749 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.17)", "pid": 2338707, "tid": 2379456, + "ts": 6305209258751.806, "dur": 1065.167, + "args": { + "External id": 719407,"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": 6305209258767.849, "dur": 366.561, + "args": { + "External id": 719408,"Record function id": 0, "Ev Idx": 8751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6305209258848.599, "dur": 6.479, + "args": { + "External id": 719409,"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": 6305209258858.232, "dur": 1.030, + "args": { + "External id": 719410,"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": 6305209258861.267, "dur": 0.789, + "args": { + "External id": 719411,"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": 6305209258863.949, "dur": 0.764, + "args": { + "External id": 719412,"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": 6305209258871.644, "dur": 0.841, + "args": { + "External id": 719413,"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": 6305209258873.930, "dur": 0.897, + "args": { + "External id": 719414,"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": 6305209258876.324, "dur": 0.963, + "args": { + "External id": 719415,"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": 6305209258880.708, "dur": 1.686, + "args": { + "External id": 719416,"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": 6305209258883.676, "dur": 2.580, + "args": { + "External id": 719417,"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": 6305209258887.846, "dur": 0.677, + "args": { + "External id": 719418,"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": 6305209258905.893, "dur": 194.377, + "args": { + "External id": 719419,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305209258922.126, "dur": 171.610, + "args": { + "External id": 719420,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305209258948.649, "dur": 14.038, + "args": { + "External id": 719421,"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": 6305209258966.381, "dur": 63.790, + "args": { + "External id": 719422,"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": 6305209258968.882, "dur": 60.835, + "args": { + "External id": 719423,"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": 6305209258973.109, "dur": 5.931, + "args": { + "External id": 719424,"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": 6305209258980.826, "dur": 48.284, + "args": { + "External id": 719425,"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": 6305209259217.935, "dur": 591.333, + "args": { + "External id": 719426,"Record function id": 0, "Ev Idx": 8769 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.16)", "pid": 2338707, "tid": 2379456, + "ts": 6305209259233.616, "dur": 563.097, + "args": { + "External id": 719427,"Record function id": 0, "Ev Idx": 8770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305209259291.036, "dur": 7.180, + "args": { + "External id": 719428,"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": 6305209259312.791, "dur": 31.105, + "args": { + "External id": 719429,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209259318.298, "dur": 1.662, + "args": { + "External id": 719430,"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": 6305209259322.631, "dur": 0.540, + "args": { + "External id": 719431,"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": 6305209259324.519, "dur": 0.756, + "args": { + "External id": 719432,"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": 6305209259327.181, "dur": 2.392, + "args": { + "External id": 719433,"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": 6305209259331.372, "dur": 0.644, + "args": { + "External id": 719434,"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": 6305209259333.252, "dur": 0.601, + "args": { + "External id": 719435,"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": 6305209259336.222, "dur": 0.487, + "args": { + "External id": 719436,"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": 6305209259338.076, "dur": 0.437, + "args": { + "External id": 719437,"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": 6305209259339.958, "dur": 0.572, + "args": { + "External id": 719438,"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": 6305209259358.153, "dur": 41.265, + "args": { + "External id": 719439,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305209259433.829, "dur": 126.223, + "args": { + "External id": 719440,"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": 6305209259444.311, "dur": 3.273, + "args": { + "External id": 719441,"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": 6305209259452.535, "dur": 10.178, + "args": { + "External id": 719442,"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": 6305209259457.106, "dur": 5.212, + "args": { + "External id": 719443,"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": 6305209259460.760, "dur": 0.434, + "args": { + "External id": 719444,"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": 6305209259469.230, "dur": 26.663, + "args": { + "External id": 719445,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209259470.995, "dur": 3.023, + "args": { + "External id": 719446,"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": 6305209259475.342, "dur": 0.424, + "args": { + "External id": 719447,"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": 6305209259477.951, "dur": 0.468, + "args": { + "External id": 719448,"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": 6305209259480.142, "dur": 0.349, + "args": { + "External id": 719449,"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": 6305209259481.946, "dur": 0.556, + "args": { + "External id": 719450,"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": 6305209259484.216, "dur": 0.373, + "args": { + "External id": 719451,"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": 6305209259486.131, "dur": 0.580, + "args": { + "External id": 719452,"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": 6305209259487.834, "dur": 0.344, + "args": { + "External id": 719453,"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": 6305209259489.714, "dur": 2.740, + "args": { + "External id": 719454,"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": 6305209259521.491, "dur": 30.073, + "args": { + "External id": 719455,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305209259608.229, "dur": 116.225, + "args": { + "External id": 719456,"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": 6305209259635.329, "dur": 85.600, + "args": { + "External id": 719457,"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": 6305209259645.020, "dur": 71.386, + "args": { + "External id": 719458,"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": 6305209259741.946, "dur": 1.806, + "args": { + "External id": 719459,"Record function id": 0, "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": 6305209259825.286, "dur": 1858.787, + "args": { + "External id": 719460,"Sequence number": 7674655, "Fwd thread 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": 6305209259825.286, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6305209259939.941, "dur": 108.450, + "args": { + "External id": 719461,"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": 6305209260136.422, "dur": 41.823, + "args": { + "External id": 719462,"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": 6305209260199.434, "dur": 58.773, + "args": { + "External id": 719463,"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": 6305209260269.014, "dur": 32.571, + "args": { + "External id": 719464,"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": 6305209260308.830, "dur": 32.734, + "args": { + "External id": 719465,"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": 6305209260349.261, "dur": 28.328, + "args": { + "External id": 719466,"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": 6305209260387.208, "dur": 29.822, + "args": { + "External id": 719467,"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": 6305209260442.209, "dur": 26.392, + "args": { + "External id": 719468,"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": 6305209260486.941, "dur": 46.455, + "args": { + "External id": 719469,"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": 6305209260559.028, "dur": 23.908, + "args": { + "External id": 719470,"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": 6305209260597.872, "dur": 17.189, + "args": { + "External id": 719471,"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": 6305209260626.931, "dur": 48.101, + "args": { + "External id": 719472,"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": 6305209260678.799, "dur": 34.845, + "args": { + "External id": 719473,"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": 6305209260743.130, "dur": 259.313, + "args": { + "External id": 719474,"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": 6305209260825.421, "dur": 6.619, + "args": { + "External id": 719475,"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": 6305209260834.485, "dur": 3.003, + "args": { + "External id": 719476,"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": 6305209260838.850, "dur": 3.233, + "args": { + "External id": 719477,"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": 6305209260843.365, "dur": 4.505, + "args": { + "External id": 719478,"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": 6305209260897.158, "dur": 4.660, + "args": { + "External id": 719479,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209260898.993, "dur": 2.690, + "args": { + "External id": 719480,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209260904.003, "dur": 33.783, + "args": { + "External id": 719481,"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": 6305209260909.901, "dur": 1.862, + "args": { + "External id": 719482,"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": 6305209260939.287, "dur": 2.314, + "args": { + "External id": 719483,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209260940.782, "dur": 0.742, + "args": { + "External id": 719484,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209260942.871, "dur": 16.999, + "args": { + "External id": 719485,"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": 6305209260945.105, "dur": 0.578, + "args": { + "External id": 719486,"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": 6305209261036.590, "dur": 65.595, + "args": { + "External id": 719487,"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": 6305209261122.494, "dur": 21.303, + "args": { + "External id": 719488,"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": 6305209261153.965, "dur": 50.500, + "args": { + "External id": 719489,"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": 6305209261211.988, "dur": 41.358, + "args": { + "External id": 719490,"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": 6305209261262.829, "dur": 24.361, + "args": { + "External id": 719491,"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": 6305209261296.547, "dur": 47.544, + "args": { + "External id": 719492,"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": 6305209261359.605, "dur": 35.362, + "args": { + "External id": 719493,"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": 6305209261403.475, "dur": 31.856, + "args": { + "External id": 719494,"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": 6305209261459.285, "dur": 27.307, + "args": { + "External id": 719495,"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": 6305209261502.210, "dur": 45.326, + "args": { + "External id": 719496,"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": 6305209261564.176, "dur": 20.423, + "args": { + "External id": 719497,"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": 6305209261599.081, "dur": 19.411, + "args": { + "External id": 719498,"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": 6305209261631.529, "dur": 16.950, + "args": { + "External id": 719499,"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": 6305209261730.101, "dur": 26.958, + "args": { + "External id": 719500,"Record function id": 0, "Ev Idx": 8843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209261733.470, "dur": 22.622, + "args": { + "External id": 719501,"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": 6305209261748.584, "dur": 6.493, + "args": { + "External id": 719502,"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": 6305209261750.604, "dur": 4.343, + "args": { + "External id": 719503,"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": 6305209261761.246, "dur": 5.700, + "args": { + "External id": 719504,"Record function id": 0, "Ev Idx": 8847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209261762.376, "dur": 4.136, + "args": { + "External id": 719505,"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": 6305209261763.287, "dur": 2.562, + "args": { + "External id": 719506,"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": 6305209261764.395, "dur": 1.337, + "args": { + "External id": 719507,"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": 6305209261770.266, "dur": 4.979, + "args": { + "External id": 719508,"Record function id": 0, "Ev Idx": 8851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209261771.835, "dur": 2.911, + "args": { + "External id": 719509,"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": 6305209261772.346, "dur": 1.891, + "args": { + "External id": 719510,"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": 6305209261772.827, "dur": 1.345, + "args": { + "External id": 719511,"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": 6305209261778.457, "dur": 3.831, + "args": { + "External id": 719512,"Record function id": 0, "Ev Idx": 8855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209261779.581, "dur": 2.253, + "args": { + "External id": 719513,"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": 6305209261780.160, "dur": 1.245, + "args": { + "External id": 719514,"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": 6305209261780.578, "dur": 0.763, + "args": { + "External id": 719515,"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": 6305209261785.335, "dur": 3.893, + "args": { + "External id": 719516,"Record function id": 0, "Ev Idx": 8859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209261786.554, "dur": 2.256, + "args": { + "External id": 719517,"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": 6305209261787.265, "dur": 1.016, + "args": { + "External id": 719518,"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": 6305209261787.551, "dur": 0.665, + "args": { + "External id": 719519,"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": 6305209261792.375, "dur": 6.205, + "args": { + "External id": 719520,"Record function id": 0, "Ev Idx": 8863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209261793.505, "dur": 4.636, + "args": { + "External id": 719521,"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": 6305209261794.007, "dur": 3.634, + "args": { + "External id": 719522,"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": 6305209261794.510, "dur": 3.059, + "args": { + "External id": 719523,"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": 6305209261801.719, "dur": 3.422, + "args": { + "External id": 719524,"Record function id": 0, "Ev Idx": 8867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209261802.792, "dur": 1.942, + "args": { + "External id": 719525,"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": 6305209261803.260, "dur": 1.079, + "args": { + "External id": 719526,"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": 6305209261803.524, "dur": 0.729, + "args": { + "External id": 719527,"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": 6305209261808.292, "dur": 5.560, + "args": { + "External id": 719528,"Record function id": 0, "Ev Idx": 8871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209261809.212, "dur": 4.220, + "args": { + "External id": 719529,"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": 6305209261809.688, "dur": 3.352, + "args": { + "External id": 719530,"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": 6305209261812.274, "dur": 0.658, + "args": { + "External id": 719531,"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": 6305209261817.542, "dur": 3.866, + "args": { + "External id": 719532,"Record function id": 0, "Ev Idx": 8875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209261818.709, "dur": 2.296, + "args": { + "External id": 719533,"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": 6305209261819.361, "dur": 1.113, + "args": { + "External id": 719534,"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": 6305209261819.827, "dur": 0.572, + "args": { + "External id": 719535,"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": 6305209261825.790, "dur": 61750.513, + "args": { + "External id": 719536,"Record function id": 0, "Sequence number": 7674654, "Fwd thread id": 1, "Ev Idx": 8879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305209261827.292, "dur": 61738.500, + "args": { + "External id": 719537,"Sequence number": 7674654, "Fwd thread 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": 6305209261827.292, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.17)", "pid": 2338707, "tid": 2379456, + "ts": 6305209261857.043, "dur": 38.769, + "args": { + "External id": 719538,"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": 6305209261903.630, "dur": 61.691, + "args": { + "External id": 719539,"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": 6305209261971.470, "dur": 61585.615, + "args": { + "External id": 719540,"Record function id": 0, "Ev Idx": 8883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305209262096.322, "dur": 8.898, + "args": { + "External id": 719541,"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": 6305209262118.299, "dur": 5.344, + "args": { + "External id": 719542,"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": 6305209262139.489, "dur": 60411.918, + "args": { + "External id": 719543,"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": 6305209262154.523, "dur": 60382.678, + "args": { + "External id": 719544,"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": 6305209262252.635, "dur": 18.552, + "args": { + "External id": 719545,"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": 6305209262297.570, "dur": 60181.314, + "args": { + "External id": 719546,"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": 6305209262300.434, "dur": 60177.375, + "args": { + "External id": 719547,"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": 6305209262310.589, "dur": 9.025, + "args": { + "External id": 719548,"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": 6305209262322.136, "dur": 60150.201, + "args": { + "External id": 719549,"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": 6305209322660.824, "dur": 12.331, + "args": { + "External id": 719550,"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": 6305209322664.553, "dur": 8.237, + "args": { + "External id": 719551,"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": 6305209322706.614, "dur": 434.450, + "args": { + "External id": 719552,"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": 6305209322740.565, "dur": 394.507, + "args": { + "External id": 719553,"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": 6305209322753.018, "dur": 375.987, + "args": { + "External id": 719554,"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": 6305209323164.213, "dur": 2.195, + "args": { + "External id": 719555,"Record function id": 0, "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": 6305209323230.345, "dur": 6.788, + "args": { + "External id": 719556,"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": 6305209323249.105, "dur": 38.018, + "args": { + "External id": 719557,"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": 6305209323297.827, "dur": 3.780, + "args": { + "External id": 719558,"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": 6305209323306.723, "dur": 14.027, + "args": { + "External id": 719559,"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": 6305209323326.323, "dur": 0.836, + "args": { + "External id": 719560,"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": 6305209323332.105, "dur": 11.840, + "args": { + "External id": 719561,"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": 6305209323348.643, "dur": 0.741, + "args": { + "External id": 719562,"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": 6305209323352.968, "dur": 12.721, + "args": { + "External id": 719563,"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": 6305209323370.110, "dur": 4.323, + "args": { + "External id": 719564,"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": 6305209323378.357, "dur": 11.712, + "args": { + "External id": 719565,"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": 6305209323394.956, "dur": 0.919, + "args": { + "External id": 719566,"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": 6305209323399.920, "dur": 12.157, + "args": { + "External id": 719567,"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": 6305209323416.706, "dur": 1.095, + "args": { + "External id": 719568,"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": 6305209323422.256, "dur": 14.952, + "args": { + "External id": 719569,"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": 6305209323441.469, "dur": 0.628, + "args": { + "External id": 719570,"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": 6305209323446.387, "dur": 12.185, + "args": { + "External id": 719571,"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": 6305209323465.114, "dur": 0.841, + "args": { + "External id": 719572,"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": 6305209323469.717, "dur": 11.323, + "args": { + "External id": 719573,"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": 6305209323592.960, "dur": 3032.304, + "args": { + "External id": 719574,"Record function id": 0, "Ev Idx": 8917 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.16)", "pid": 2338707, "tid": 2379456, + "ts": 6305209323614.050, "dur": 1101.127, + "args": { + "External id": 719575,"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": 6305209323630.536, "dur": 330.713, + "args": { + "External id": 719576,"Record function id": 0, "Ev Idx": 8919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6305209323711.919, "dur": 6.898, + "args": { + "External id": 719577,"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": 6305209323722.592, "dur": 1.031, + "args": { + "External id": 719578,"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": 6305209323726.100, "dur": 1.027, + "args": { + "External id": 719579,"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": 6305209323729.375, "dur": 0.663, + "args": { + "External id": 719580,"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": 6305209323732.247, "dur": 0.696, + "args": { + "External id": 719581,"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": 6305209323734.291, "dur": 0.699, + "args": { + "External id": 719582,"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": 6305209323736.784, "dur": 0.717, + "args": { + "External id": 719583,"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": 6305209323740.860, "dur": 2.018, + "args": { + "External id": 719584,"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": 6305209323744.562, "dur": 3.157, + "args": { + "External id": 719585,"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": 6305209323749.399, "dur": 0.677, + "args": { + "External id": 719586,"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": 6305209323767.536, "dur": 162.869, + "args": { + "External id": 719587,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305209323783.967, "dur": 141.284, + "args": { + "External id": 719588,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305209323811.056, "dur": 15.411, + "args": { + "External id": 719589,"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": 6305209323830.259, "dur": 65.694, + "args": { + "External id": 719590,"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": 6305209323833.079, "dur": 62.566, + "args": { + "External id": 719591,"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": 6305209323837.603, "dur": 5.800, + "args": { + "External id": 719592,"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": 6305209323845.325, "dur": 49.521, + "args": { + "External id": 719593,"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": 6305209324039.626, "dur": 666.988, + "args": { + "External id": 719594,"Record function id": 0, "Ev Idx": 8937 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.15)", "pid": 2338707, "tid": 2379456, + "ts": 6305209324107.572, "dur": 586.356, + "args": { + "External id": 719595,"Record function id": 0, "Ev Idx": 8938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305209324172.975, "dur": 6.729, + "args": { + "External id": 719596,"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": 6305209324195.797, "dur": 29.878, + "args": { + "External id": 719597,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209324201.504, "dur": 1.606, + "args": { + "External id": 719598,"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": 6305209324204.932, "dur": 0.344, + "args": { + "External id": 719599,"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": 6305209324207.545, "dur": 0.497, + "args": { + "External id": 719600,"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": 6305209324209.642, "dur": 2.326, + "args": { + "External id": 719601,"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": 6305209324213.096, "dur": 0.356, + "args": { + "External id": 719602,"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": 6305209324215.494, "dur": 0.371, + "args": { + "External id": 719603,"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": 6305209324217.662, "dur": 0.390, + "args": { + "External id": 719604,"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": 6305209324219.229, "dur": 0.421, + "args": { + "External id": 719605,"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": 6305209324221.314, "dur": 0.594, + "args": { + "External id": 719606,"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": 6305209324236.586, "dur": 46.994, + "args": { + "External id": 719607,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305209324317.392, "dur": 110.891, + "args": { + "External id": 719608,"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": 6305209324328.542, "dur": 2.934, + "args": { + "External id": 719609,"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": 6305209324336.838, "dur": 10.570, + "args": { + "External id": 719610,"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": 6305209324341.184, "dur": 5.819, + "args": { + "External id": 719611,"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": 6305209324345.021, "dur": 0.662, + "args": { + "External id": 719612,"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": 6305209324353.501, "dur": 26.345, + "args": { + "External id": 719613,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209324355.845, "dur": 2.412, + "args": { + "External id": 719614,"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": 6305209324360.241, "dur": 0.529, + "args": { + "External id": 719615,"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": 6305209324362.377, "dur": 0.379, + "args": { + "External id": 719616,"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": 6305209324363.895, "dur": 0.431, + "args": { + "External id": 719617,"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": 6305209324366.398, "dur": 0.458, + "args": { + "External id": 719618,"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": 6305209324368.827, "dur": 0.343, + "args": { + "External id": 719619,"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": 6305209324370.443, "dur": 0.433, + "args": { + "External id": 719620,"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": 6305209324372.216, "dur": 0.409, + "args": { + "External id": 719621,"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": 6305209324374.199, "dur": 2.755, + "args": { + "External id": 719622,"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": 6305209324390.441, "dur": 30.743, + "args": { + "External id": 719623,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305209324472.952, "dur": 144.741, + "args": { + "External id": 719624,"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": 6305209324501.822, "dur": 111.878, + "args": { + "External id": 719625,"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": 6305209324530.407, "dur": 79.108, + "args": { + "External id": 719626,"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": 6305209324636.278, "dur": 2.045, + "args": { + "External id": 719627,"Record function id": 0, "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": 6305209324722.972, "dur": 1881.104, + "args": { + "External id": 719628,"Sequence number": 7674653, "Fwd thread 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": 6305209324722.972, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6305209324835.542, "dur": 110.517, + "args": { + "External id": 719629,"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": 6305209324990.994, "dur": 43.154, + "args": { + "External id": 719630,"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": 6305209325109.974, "dur": 63.710, + "args": { + "External id": 719631,"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": 6305209325187.218, "dur": 35.879, + "args": { + "External id": 719632,"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": 6305209325230.075, "dur": 35.760, + "args": { + "External id": 719633,"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": 6305209325272.918, "dur": 30.100, + "args": { + "External id": 719634,"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": 6305209325312.821, "dur": 30.762, + "args": { + "External id": 719635,"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": 6305209325372.182, "dur": 26.692, + "args": { + "External id": 719636,"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": 6305209325418.540, "dur": 32.865, + "args": { + "External id": 719637,"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": 6305209325474.188, "dur": 24.493, + "args": { + "External id": 719638,"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": 6305209325528.947, "dur": 20.050, + "args": { + "External id": 719639,"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": 6305209325561.868, "dur": 46.658, + "args": { + "External id": 719640,"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": 6305209325612.652, "dur": 34.874, + "args": { + "External id": 719641,"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": 6305209325676.100, "dur": 252.749, + "args": { + "External id": 719642,"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": 6305209325757.093, "dur": 6.284, + "args": { + "External id": 719643,"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": 6305209325765.761, "dur": 2.912, + "args": { + "External id": 719644,"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": 6305209325770.086, "dur": 2.270, + "args": { + "External id": 719645,"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": 6305209325773.681, "dur": 4.484, + "args": { + "External id": 719646,"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": 6305209325825.047, "dur": 5.295, + "args": { + "External id": 719647,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209325827.363, "dur": 2.836, + "args": { + "External id": 719648,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209325832.012, "dur": 33.892, + "args": { + "External id": 719649,"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": 6305209325838.096, "dur": 1.806, + "args": { + "External id": 719650,"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": 6305209325867.634, "dur": 2.165, + "args": { + "External id": 719651,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209325868.985, "dur": 0.710, + "args": { + "External id": 719652,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209325871.081, "dur": 16.600, + "args": { + "External id": 719653,"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": 6305209325873.519, "dur": 0.620, + "args": { + "External id": 719654,"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": 6305209325961.449, "dur": 29.026, + "args": { + "External id": 719655,"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": 6305209326007.342, "dur": 18.497, + "args": { + "External id": 719656,"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": 6305209326034.828, "dur": 84.686, + "args": { + "External id": 719657,"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": 6305209326130.889, "dur": 45.128, + "args": { + "External id": 719658,"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": 6305209326187.104, "dur": 23.965, + "args": { + "External id": 719659,"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": 6305209326219.533, "dur": 33.071, + "args": { + "External id": 719660,"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": 6305209326261.084, "dur": 28.833, + "args": { + "External id": 719661,"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": 6305209326297.957, "dur": 47.179, + "args": { + "External id": 719662,"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": 6305209326373.321, "dur": 26.235, + "args": { + "External id": 719663,"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": 6305209326415.296, "dur": 25.728, + "args": { + "External id": 719664,"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": 6305209326465.419, "dur": 18.198, + "args": { + "External id": 719665,"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": 6305209326503.623, "dur": 31.503, + "args": { + "External id": 719666,"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": 6305209326552.551, "dur": 16.116, + "args": { + "External id": 719667,"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": 6305209326647.724, "dur": 15.499, + "args": { + "External id": 719668,"Record function id": 0, "Ev Idx": 9011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209326651.027, "dur": 11.198, + "args": { + "External id": 719669,"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": 6305209326655.484, "dur": 5.849, + "args": { + "External id": 719670,"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": 6305209326657.238, "dur": 3.952, + "args": { + "External id": 719671,"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": 6305209326667.477, "dur": 5.471, + "args": { + "External id": 719672,"Record function id": 0, "Ev Idx": 9015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209326669.132, "dur": 3.397, + "args": { + "External id": 719673,"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": 6305209326670.009, "dur": 2.017, + "args": { + "External id": 719674,"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": 6305209326670.855, "dur": 1.079, + "args": { + "External id": 719675,"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": 6305209326680.079, "dur": 4.791, + "args": { + "External id": 719676,"Record function id": 0, "Ev Idx": 9019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209326681.561, "dur": 2.883, + "args": { + "External id": 719677,"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": 6305209326682.343, "dur": 1.653, + "args": { + "External id": 719678,"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": 6305209326682.813, "dur": 1.117, + "args": { + "External id": 719679,"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": 6305209326688.164, "dur": 3.606, + "args": { + "External id": 719680,"Record function id": 0, "Ev Idx": 9023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209326689.415, "dur": 1.939, + "args": { + "External id": 719681,"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": 6305209326689.891, "dur": 1.045, + "args": { + "External id": 719682,"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": 6305209326690.177, "dur": 0.691, + "args": { + "External id": 719683,"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": 6305209326695.038, "dur": 3.728, + "args": { + "External id": 719684,"Record function id": 0, "Ev Idx": 9027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209326696.141, "dur": 2.221, + "args": { + "External id": 719685,"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": 6305209326696.617, "dur": 1.171, + "args": { + "External id": 719686,"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": 6305209326697.133, "dur": 0.590, + "args": { + "External id": 719687,"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": 6305209326701.916, "dur": 5.667, + "args": { + "External id": 719688,"Record function id": 0, "Ev Idx": 9031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209326702.923, "dur": 4.224, + "args": { + "External id": 719689,"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": 6305209326703.404, "dur": 3.313, + "args": { + "External id": 719690,"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": 6305209326703.842, "dur": 2.773, + "args": { + "External id": 719691,"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": 6305209326710.825, "dur": 3.518, + "args": { + "External id": 719692,"Record function id": 0, "Ev Idx": 9035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209326711.866, "dur": 2.061, + "args": { + "External id": 719693,"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": 6305209326712.347, "dur": 1.179, + "args": { + "External id": 719694,"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": 6305209326712.646, "dur": 0.811, + "args": { + "External id": 719695,"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": 6305209326717.949, "dur": 3.990, + "args": { + "External id": 719696,"Record function id": 0, "Ev Idx": 9039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209326719.157, "dur": 2.346, + "args": { + "External id": 719697,"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": 6305209326719.600, "dur": 1.485, + "args": { + "External id": 719698,"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": 6305209326719.970, "dur": 1.031, + "args": { + "External id": 719699,"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": 6305209326725.470, "dur": 3.720, + "args": { + "External id": 719700,"Record function id": 0, "Ev Idx": 9043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209326726.539, "dur": 2.203, + "args": { + "External id": 719701,"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": 6305209326726.995, "dur": 1.235, + "args": { + "External id": 719702,"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": 6305209326727.437, "dur": 0.683, + "args": { + "External id": 719703,"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": 6305209326733.577, "dur": 62406.031, + "args": { + "External id": 719704,"Record function id": 0, "Sequence number": 7674652, "Fwd thread id": 1, "Ev Idx": 9047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305209326734.866, "dur": 62393.572, + "args": { + "External id": 719705,"Sequence number": 7674652, "Fwd thread 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": 6305209326734.866, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.16)", "pid": 2338707, "tid": 2379456, + "ts": 6305209326768.015, "dur": 39.315, + "args": { + "External id": 719706,"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": 6305209326815.129, "dur": 61.468, + "args": { + "External id": 719707,"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": 6305209326881.986, "dur": 62237.214, + "args": { + "External id": 719708,"Record function id": 0, "Ev Idx": 9051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305209326972.818, "dur": 6.681, + "args": { + "External id": 719709,"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": 6305209326989.658, "dur": 4.813, + "args": { + "External id": 719710,"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": 6305209327009.720, "dur": 61137.098, + "args": { + "External id": 719711,"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": 6305209327023.346, "dur": 61110.433, + "args": { + "External id": 719712,"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": 6305209327162.800, "dur": 19.873, + "args": { + "External id": 719713,"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": 6305209327203.877, "dur": 60882.825, + "args": { + "External id": 719714,"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": 6305209327206.974, "dur": 60878.137, + "args": { + "External id": 719715,"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": 6305209327212.498, "dur": 10.481, + "args": { + "External id": 719716,"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": 6305209327224.962, "dur": 60822.910, + "args": { + "External id": 719717,"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": 6305209388261.545, "dur": 12.608, + "args": { + "External id": 719718,"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": 6305209388265.014, "dur": 8.750, + "args": { + "External id": 719719,"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": 6305209388304.256, "dur": 394.881, + "args": { + "External id": 719720,"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": 6305209388334.586, "dur": 359.038, + "args": { + "External id": 719721,"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": 6305209388345.826, "dur": 341.548, + "args": { + "External id": 719722,"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": 6305209388722.133, "dur": 2.732, + "args": { + "External id": 719723,"Record function id": 0, "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": 6305209388786.405, "dur": 7.040, + "args": { + "External id": 719724,"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": 6305209388805.912, "dur": 36.483, + "args": { + "External id": 719725,"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": 6305209388853.049, "dur": 3.396, + "args": { + "External id": 719726,"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": 6305209388861.744, "dur": 11.976, + "args": { + "External id": 719727,"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": 6305209388878.772, "dur": 0.880, + "args": { + "External id": 719728,"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": 6305209388883.319, "dur": 11.396, + "args": { + "External id": 719729,"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": 6305209388899.482, "dur": 0.760, + "args": { + "External id": 719730,"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": 6305209388904.451, "dur": 15.363, + "args": { + "External id": 719731,"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": 6305209388923.999, "dur": 0.834, + "args": { + "External id": 719732,"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": 6305209388928.939, "dur": 11.140, + "args": { + "External id": 719733,"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": 6305209388944.721, "dur": 1.203, + "args": { + "External id": 719734,"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": 6305209388950.399, "dur": 11.153, + "args": { + "External id": 719735,"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": 6305209388969.689, "dur": 0.986, + "args": { + "External id": 719736,"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": 6305209388975.306, "dur": 9.499, + "args": { + "External id": 719737,"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": 6305209388989.771, "dur": 0.958, + "args": { + "External id": 719738,"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": 6305209388994.766, "dur": 10.494, + "args": { + "External id": 719739,"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": 6305209389009.704, "dur": 0.891, + "args": { + "External id": 719740,"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": 6305209389014.277, "dur": 9.357, + "args": { + "External id": 719741,"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": 6305209389156.864, "dur": 3042.010, + "args": { + "External id": 719742,"Record function id": 0, "Ev Idx": 9085 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.15)", "pid": 2338707, "tid": 2379456, + "ts": 6305209389179.803, "dur": 1107.994, + "args": { + "External id": 719743,"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": 6305209389196.212, "dur": 357.518, + "args": { + "External id": 719744,"Record function id": 0, "Ev Idx": 9087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6305209389281.469, "dur": 6.888, + "args": { + "External id": 719745,"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": 6305209389294.963, "dur": 0.920, + "args": { + "External id": 719746,"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": 6305209389298.154, "dur": 1.059, + "args": { + "External id": 719747,"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": 6305209389300.824, "dur": 0.769, + "args": { + "External id": 719748,"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": 6305209389303.995, "dur": 0.745, + "args": { + "External id": 719749,"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": 6305209389306.384, "dur": 0.962, + "args": { + "External id": 719750,"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": 6305209389309.126, "dur": 0.835, + "args": { + "External id": 719751,"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": 6305209389311.553, "dur": 1.981, + "args": { + "External id": 719752,"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": 6305209389317.055, "dur": 2.798, + "args": { + "External id": 719753,"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": 6305209389321.048, "dur": 0.687, + "args": { + "External id": 719754,"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": 6305209389339.655, "dur": 163.894, + "args": { + "External id": 719755,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305209389356.307, "dur": 142.423, + "args": { + "External id": 719756,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305209389383.322, "dur": 16.077, + "args": { + "External id": 719757,"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": 6305209389403.506, "dur": 66.629, + "args": { + "External id": 719758,"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": 6305209389406.348, "dur": 63.449, + "args": { + "External id": 719759,"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": 6305209389410.425, "dur": 5.554, + "args": { + "External id": 719760,"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": 6305209389417.928, "dur": 51.302, + "args": { + "External id": 719761,"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": 6305209389638.295, "dur": 641.485, + "args": { + "External id": 719762,"Record function id": 0, "Ev Idx": 9105 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.14)", "pid": 2338707, "tid": 2379456, + "ts": 6305209389656.980, "dur": 609.542, + "args": { + "External id": 719763,"Record function id": 0, "Ev Idx": 9106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305209389720.215, "dur": 8.953, + "args": { + "External id": 719764,"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": 6305209389744.088, "dur": 30.958, + "args": { + "External id": 719765,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209389749.739, "dur": 1.656, + "args": { + "External id": 719766,"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": 6305209389753.685, "dur": 0.660, + "args": { + "External id": 719767,"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": 6305209389756.020, "dur": 0.959, + "args": { + "External id": 719768,"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": 6305209389758.260, "dur": 2.643, + "args": { + "External id": 719769,"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": 6305209389762.801, "dur": 0.449, + "args": { + "External id": 719770,"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": 6305209389764.733, "dur": 0.486, + "args": { + "External id": 719771,"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": 6305209389766.638, "dur": 0.611, + "args": { + "External id": 719772,"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": 6305209389768.802, "dur": 0.487, + "args": { + "External id": 719773,"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": 6305209389770.793, "dur": 0.462, + "args": { + "External id": 719774,"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": 6305209389786.029, "dur": 43.120, + "args": { + "External id": 719775,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305209389859.729, "dur": 124.947, + "args": { + "External id": 719776,"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": 6305209389869.909, "dur": 3.208, + "args": { + "External id": 719777,"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": 6305209389878.368, "dur": 11.210, + "args": { + "External id": 719778,"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": 6305209389883.169, "dur": 6.000, + "args": { + "External id": 719779,"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": 6305209389887.367, "dur": 0.708, + "args": { + "External id": 719780,"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": 6305209389896.431, "dur": 42.438, + "args": { + "External id": 719781,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209389906.209, "dur": 12.366, + "args": { + "External id": 719782,"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": 6305209389920.332, "dur": 0.443, + "args": { + "External id": 719783,"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": 6305209389922.500, "dur": 0.304, + "args": { + "External id": 719784,"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": 6305209389923.913, "dur": 0.426, + "args": { + "External id": 719785,"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": 6305209389926.145, "dur": 0.432, + "args": { + "External id": 719786,"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": 6305209389928.201, "dur": 0.256, + "args": { + "External id": 719787,"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": 6305209389929.573, "dur": 0.359, + "args": { + "External id": 719788,"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": 6305209389931.605, "dur": 0.371, + "args": { + "External id": 719789,"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": 6305209389933.796, "dur": 2.340, + "args": { + "External id": 719790,"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": 6305209389948.599, "dur": 29.042, + "args": { + "External id": 719791,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305209390026.943, "dur": 161.678, + "args": { + "External id": 719792,"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": 6305209390089.869, "dur": 94.815, + "args": { + "External id": 719793,"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": 6305209390102.077, "dur": 77.622, + "args": { + "External id": 719794,"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": 6305209390207.089, "dur": 1.908, + "args": { + "External id": 719795,"Record function id": 0, "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": 6305209390295.300, "dur": 1881.003, + "args": { + "External id": 719796,"Sequence number": 7674651, "Fwd thread 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": 6305209390295.300, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6305209390408.650, "dur": 130.453, + "args": { + "External id": 719797,"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": 6305209390589.617, "dur": 42.328, + "args": { + "External id": 719798,"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": 6305209390653.461, "dur": 56.181, + "args": { + "External id": 719799,"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": 6305209390719.978, "dur": 32.919, + "args": { + "External id": 719800,"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": 6305209390759.312, "dur": 34.949, + "args": { + "External id": 719801,"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": 6305209390800.942, "dur": 27.400, + "args": { + "External id": 719802,"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": 6305209390837.663, "dur": 31.050, + "args": { + "External id": 719803,"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": 6305209390895.229, "dur": 28.038, + "args": { + "External id": 719804,"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": 6305209390945.593, "dur": 28.007, + "args": { + "External id": 719805,"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": 6305209390995.137, "dur": 21.630, + "args": { + "External id": 719806,"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": 6305209391030.746, "dur": 16.507, + "args": { + "External id": 719807,"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": 6305209391093.171, "dur": 47.645, + "args": { + "External id": 719808,"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": 6305209391145.861, "dur": 35.039, + "args": { + "External id": 719809,"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": 6305209391212.512, "dur": 266.185, + "args": { + "External id": 719810,"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": 6305209391295.527, "dur": 6.111, + "args": { + "External id": 719811,"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": 6305209391304.445, "dur": 3.051, + "args": { + "External id": 719812,"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": 6305209391309.012, "dur": 2.541, + "args": { + "External id": 719813,"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": 6305209391313.133, "dur": 5.038, + "args": { + "External id": 719814,"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": 6305209391368.365, "dur": 5.255, + "args": { + "External id": 719815,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209391370.745, "dur": 2.735, + "args": { + "External id": 719816,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209391375.667, "dur": 37.727, + "args": { + "External id": 719817,"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": 6305209391381.606, "dur": 1.721, + "args": { + "External id": 719818,"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": 6305209391414.924, "dur": 2.088, + "args": { + "External id": 719819,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209391416.120, "dur": 0.812, + "args": { + "External id": 719820,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209391418.183, "dur": 17.498, + "args": { + "External id": 719821,"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": 6305209391420.641, "dur": 0.706, + "args": { + "External id": 719822,"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": 6305209391530.909, "dur": 33.558, + "args": { + "External id": 719823,"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": 6305209391583.757, "dur": 18.426, + "args": { + "External id": 719824,"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": 6305209391612.342, "dur": 53.362, + "args": { + "External id": 719825,"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": 6305209391673.179, "dur": 41.557, + "args": { + "External id": 719826,"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": 6305209391725.031, "dur": 24.295, + "args": { + "External id": 719827,"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": 6305209391757.284, "dur": 32.505, + "args": { + "External id": 719828,"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": 6305209391797.736, "dur": 48.999, + "args": { + "External id": 719829,"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": 6305209391870.967, "dur": 40.200, + "args": { + "External id": 719830,"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": 6305209391938.411, "dur": 25.216, + "args": { + "External id": 719831,"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": 6305209391981.337, "dur": 27.099, + "args": { + "External id": 719832,"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": 6305209392023.100, "dur": 17.089, + "args": { + "External id": 719833,"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": 6305209392089.923, "dur": 18.092, + "args": { + "External id": 719834,"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": 6305209392125.664, "dur": 15.685, + "args": { + "External id": 719835,"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": 6305209392221.272, "dur": 16.316, + "args": { + "External id": 719836,"Record function id": 0, "Ev Idx": 9179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209392224.345, "dur": 12.129, + "args": { + "External id": 719837,"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": 6305209392228.803, "dur": 6.662, + "args": { + "External id": 719838,"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": 6305209392230.997, "dur": 4.344, + "args": { + "External id": 719839,"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": 6305209392241.576, "dur": 5.434, + "args": { + "External id": 719840,"Record function id": 0, "Ev Idx": 9183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209392242.802, "dur": 3.654, + "args": { + "External id": 719841,"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": 6305209392243.735, "dur": 2.148, + "args": { + "External id": 719842,"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": 6305209392244.464, "dur": 1.330, + "args": { + "External id": 719843,"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": 6305209392250.361, "dur": 4.921, + "args": { + "External id": 719844,"Record function id": 0, "Ev Idx": 9187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209392251.470, "dur": 3.429, + "args": { + "External id": 719845,"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": 6305209392252.126, "dur": 2.312, + "args": { + "External id": 719846,"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": 6305209392252.783, "dur": 1.583, + "args": { + "External id": 719847,"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": 6305209392261.700, "dur": 3.456, + "args": { + "External id": 719848,"Record function id": 0, "Ev Idx": 9191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209392262.650, "dur": 2.108, + "args": { + "External id": 719849,"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": 6305209392263.094, "dur": 1.194, + "args": { + "External id": 719850,"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": 6305209392263.437, "dur": 0.786, + "args": { + "External id": 719851,"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": 6305209392268.232, "dur": 4.385, + "args": { + "External id": 719852,"Record function id": 0, "Ev Idx": 9195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209392269.503, "dur": 2.733, + "args": { + "External id": 719853,"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": 6305209392270.141, "dur": 1.582, + "args": { + "External id": 719854,"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": 6305209392270.553, "dur": 1.094, + "args": { + "External id": 719855,"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": 6305209392275.823, "dur": 6.917, + "args": { + "External id": 719856,"Record function id": 0, "Ev Idx": 9199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209392277.065, "dur": 5.264, + "args": { + "External id": 719857,"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": 6305209392277.565, "dur": 4.320, + "args": { + "External id": 719858,"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": 6305209392278.109, "dur": 3.676, + "args": { + "External id": 719859,"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": 6305209392286.053, "dur": 3.908, + "args": { + "External id": 719860,"Record function id": 0, "Ev Idx": 9203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209392287.321, "dur": 2.230, + "args": { + "External id": 719861,"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": 6305209392287.788, "dur": 1.327, + "args": { + "External id": 719862,"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": 6305209392288.083, "dur": 0.965, + "args": { + "External id": 719863,"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": 6305209392293.423, "dur": 3.555, + "args": { + "External id": 719864,"Record function id": 0, "Ev Idx": 9207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209392294.561, "dur": 1.970, + "args": { + "External id": 719865,"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": 6305209392295.074, "dur": 1.024, + "args": { + "External id": 719866,"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": 6305209392295.356, "dur": 0.622, + "args": { + "External id": 719867,"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": 6305209392300.557, "dur": 3.884, + "args": { + "External id": 719868,"Record function id": 0, "Ev Idx": 9211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209392301.704, "dur": 2.328, + "args": { + "External id": 719869,"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": 6305209392302.127, "dur": 1.344, + "args": { + "External id": 719870,"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": 6305209392302.621, "dur": 0.735, + "args": { + "External id": 719871,"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": 6305209392308.651, "dur": 64474.413, + "args": { + "External id": 719872,"Record function id": 0, "Sequence number": 7674650, "Fwd thread id": 1, "Ev Idx": 9215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305209392349.950, "dur": 64423.120, + "args": { + "External id": 719873,"Sequence number": 7674650, "Fwd thread 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": 6305209392349.950, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.15)", "pid": 2338707, "tid": 2379456, + "ts": 6305209392387.244, "dur": 40.655, + "args": { + "External id": 719874,"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": 6305209392435.573, "dur": 62.683, + "args": { + "External id": 719875,"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": 6305209392504.227, "dur": 64260.470, + "args": { + "External id": 719876,"Record function id": 0, "Ev Idx": 9219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305209392616.381, "dur": 8.116, + "args": { + "External id": 719877,"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": 6305209392635.085, "dur": 5.405, + "args": { + "External id": 719878,"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": 6305209392657.264, "dur": 63050.866, + "args": { + "External id": 719879,"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": 6305209392671.891, "dur": 63023.033, + "args": { + "External id": 719880,"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": 6305209392769.716, "dur": 17.823, + "args": { + "External id": 719881,"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": 6305209392807.689, "dur": 62836.675, + "args": { + "External id": 719882,"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": 6305209392810.598, "dur": 62832.562, + "args": { + "External id": 719883,"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": 6305209392815.218, "dur": 8.661, + "args": { + "External id": 719884,"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": 6305209392826.267, "dur": 62811.509, + "args": { + "External id": 719885,"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": 6305209455826.213, "dur": 12.617, + "args": { + "External id": 719886,"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": 6305209455830.035, "dur": 8.379, + "args": { + "External id": 719887,"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": 6305209455870.492, "dur": 469.043, + "args": { + "External id": 719888,"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": 6305209455903.385, "dur": 430.221, + "args": { + "External id": 719889,"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": 6305209455915.299, "dur": 411.253, + "args": { + "External id": 719890,"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": 6305209456364.220, "dur": 2.769, + "args": { + "External id": 719891,"Record function id": 0, "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": 6305209456435.141, "dur": 6.980, + "args": { + "External id": 719892,"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": 6305209456454.919, "dur": 36.018, + "args": { + "External id": 719893,"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": 6305209456500.961, "dur": 3.734, + "args": { + "External id": 719894,"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": 6305209456526.885, "dur": 17.627, + "args": { + "External id": 719895,"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": 6305209456556.269, "dur": 1.436, + "args": { + "External id": 719896,"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": 6305209456562.146, "dur": 11.453, + "args": { + "External id": 719897,"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": 6305209456577.939, "dur": 0.966, + "args": { + "External id": 719898,"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": 6305209456583.674, "dur": 13.029, + "args": { + "External id": 719899,"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": 6305209456600.968, "dur": 0.656, + "args": { + "External id": 719900,"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": 6305209456609.056, "dur": 11.550, + "args": { + "External id": 719901,"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": 6305209456624.680, "dur": 0.945, + "args": { + "External id": 719902,"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": 6305209456629.953, "dur": 11.768, + "args": { + "External id": 719903,"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": 6305209456646.499, "dur": 0.856, + "args": { + "External id": 719904,"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": 6305209456651.839, "dur": 10.024, + "args": { + "External id": 719905,"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": 6305209456666.072, "dur": 0.828, + "args": { + "External id": 719906,"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": 6305209456670.726, "dur": 10.114, + "args": { + "External id": 719907,"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": 6305209456686.819, "dur": 0.633, + "args": { + "External id": 719908,"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": 6305209456691.407, "dur": 10.427, + "args": { + "External id": 719909,"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": 6305209456798.794, "dur": 3041.676, + "args": { + "External id": 719910,"Record function id": 0, "Ev Idx": 9253 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.14)", "pid": 2338707, "tid": 2379456, + "ts": 6305209456819.716, "dur": 1103.587, + "args": { + "External id": 719911,"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": 6305209456834.841, "dur": 386.167, + "args": { + "External id": 719912,"Record function id": 0, "Ev Idx": 9255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6305209456914.091, "dur": 6.426, + "args": { + "External id": 719913,"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": 6305209456924.110, "dur": 1.006, + "args": { + "External id": 719914,"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": 6305209456927.441, "dur": 0.985, + "args": { + "External id": 719915,"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": 6305209456930.527, "dur": 0.883, + "args": { + "External id": 719916,"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": 6305209456934.201, "dur": 0.819, + "args": { + "External id": 719917,"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": 6305209456936.540, "dur": 1.028, + "args": { + "External id": 719918,"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": 6305209456939.193, "dur": 0.839, + "args": { + "External id": 719919,"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": 6305209456944.095, "dur": 2.038, + "args": { + "External id": 719920,"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": 6305209456947.669, "dur": 3.378, + "args": { + "External id": 719921,"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": 6305209456952.412, "dur": 0.805, + "args": { + "External id": 719922,"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": 6305209456970.647, "dur": 215.027, + "args": { + "External id": 719923,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305209456987.206, "dur": 192.692, + "args": { + "External id": 719924,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305209457014.520, "dur": 14.301, + "args": { + "External id": 719925,"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": 6305209457032.901, "dur": 118.799, + "args": { + "External id": 719926,"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": 6305209457036.166, "dur": 115.151, + "args": { + "External id": 719927,"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": 6305209457039.984, "dur": 6.340, + "args": { + "External id": 719928,"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": 6305209457048.113, "dur": 101.792, + "args": { + "External id": 719929,"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": 6305209457309.517, "dur": 605.949, + "args": { + "External id": 719930,"Record function id": 0, "Ev Idx": 9273 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.13)", "pid": 2338707, "tid": 2379456, + "ts": 6305209457327.009, "dur": 575.722, + "args": { + "External id": 719931,"Record function id": 0, "Ev Idx": 9274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305209457393.064, "dur": 5.761, + "args": { + "External id": 719932,"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": 6305209457414.380, "dur": 31.343, + "args": { + "External id": 719933,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209457420.277, "dur": 1.849, + "args": { + "External id": 719934,"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": 6305209457423.970, "dur": 0.987, + "args": { + "External id": 719935,"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": 6305209457426.423, "dur": 0.720, + "args": { + "External id": 719936,"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": 6305209457428.868, "dur": 2.532, + "args": { + "External id": 719937,"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": 6305209457432.439, "dur": 0.657, + "args": { + "External id": 719938,"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": 6305209457434.895, "dur": 0.427, + "args": { + "External id": 719939,"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": 6305209457436.904, "dur": 0.716, + "args": { + "External id": 719940,"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": 6305209457438.923, "dur": 0.477, + "args": { + "External id": 719941,"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": 6305209457441.322, "dur": 0.385, + "args": { + "External id": 719942,"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": 6305209457456.702, "dur": 43.475, + "args": { + "External id": 719943,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305209457549.377, "dur": 117.502, + "args": { + "External id": 719944,"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": 6305209457561.213, "dur": 4.811, + "args": { + "External id": 719945,"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": 6305209457571.309, "dur": 11.862, + "args": { + "External id": 719946,"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": 6305209457576.617, "dur": 6.178, + "args": { + "External id": 719947,"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": 6305209457580.546, "dur": 0.665, + "args": { + "External id": 719948,"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": 6305209457589.784, "dur": 27.509, + "args": { + "External id": 719949,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209457591.693, "dur": 2.894, + "args": { + "External id": 719950,"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": 6305209457596.229, "dur": 0.681, + "args": { + "External id": 719951,"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": 6305209457598.842, "dur": 0.555, + "args": { + "External id": 719952,"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": 6305209457601.186, "dur": 0.592, + "args": { + "External id": 719953,"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": 6305209457602.672, "dur": 0.814, + "args": { + "External id": 719954,"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": 6305209457605.417, "dur": 0.638, + "args": { + "External id": 719955,"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": 6305209457607.835, "dur": 0.783, + "args": { + "External id": 719956,"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": 6305209457609.986, "dur": 0.443, + "args": { + "External id": 719957,"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": 6305209457611.857, "dur": 2.622, + "args": { + "External id": 719958,"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": 6305209457628.417, "dur": 30.833, + "args": { + "External id": 719959,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305209457711.475, "dur": 121.640, + "args": { + "External id": 719960,"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": 6305209457739.598, "dur": 90.005, + "args": { + "External id": 719961,"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": 6305209457749.842, "dur": 75.066, + "args": { + "External id": 719962,"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": 6305209457851.312, "dur": 2.242, + "args": { + "External id": 719963,"Record function id": 0, "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": 6305209457930.704, "dur": 1887.107, + "args": { + "External id": 719964,"Sequence number": 7674649, "Fwd thread 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": 6305209457930.704, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6305209458040.785, "dur": 169.119, + "args": { + "External id": 719965,"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": 6305209458262.398, "dur": 41.541, + "args": { + "External id": 719966,"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": 6305209458327.089, "dur": 53.609, + "args": { + "External id": 719967,"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": 6305209458391.192, "dur": 34.054, + "args": { + "External id": 719968,"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": 6305209458431.425, "dur": 32.273, + "args": { + "External id": 719969,"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": 6305209458470.378, "dur": 28.422, + "args": { + "External id": 719970,"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": 6305209458523.372, "dur": 34.387, + "args": { + "External id": 719971,"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": 6305209458590.151, "dur": 27.085, + "args": { + "External id": 719972,"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": 6305209458640.955, "dur": 28.648, + "args": { + "External id": 719973,"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": 6305209458693.475, "dur": 21.203, + "args": { + "External id": 719974,"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": 6305209458727.495, "dur": 17.114, + "args": { + "External id": 719975,"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": 6305209458756.242, "dur": 38.051, + "args": { + "External id": 719976,"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": 6305209458798.366, "dur": 34.640, + "args": { + "External id": 719977,"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": 6305209458862.445, "dur": 298.343, + "args": { + "External id": 719978,"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": 6305209458944.030, "dur": 6.327, + "args": { + "External id": 719979,"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": 6305209458952.482, "dur": 2.592, + "args": { + "External id": 719980,"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": 6305209458956.285, "dur": 2.383, + "args": { + "External id": 719981,"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": 6305209458959.812, "dur": 3.920, + "args": { + "External id": 719982,"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": 6305209459011.733, "dur": 5.469, + "args": { + "External id": 719983,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209459014.110, "dur": 2.957, + "args": { + "External id": 719984,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209459019.270, "dur": 68.619, + "args": { + "External id": 719985,"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": 6305209459024.989, "dur": 1.904, + "args": { + "External id": 719986,"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": 6305209459090.898, "dur": 2.762, + "args": { + "External id": 719987,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209459092.198, "dur": 1.336, + "args": { + "External id": 719988,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209459095.120, "dur": 19.858, + "args": { + "External id": 719989,"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": 6305209459097.852, "dur": 0.911, + "args": { + "External id": 719990,"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": 6305209459196.684, "dur": 31.171, + "args": { + "External id": 719991,"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": 6305209459246.207, "dur": 17.691, + "args": { + "External id": 719992,"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": 6305209459272.778, "dur": 51.121, + "args": { + "External id": 719993,"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": 6305209459331.248, "dur": 59.833, + "args": { + "External id": 719994,"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": 6305209459422.095, "dur": 24.231, + "args": { + "External id": 719995,"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": 6305209459453.121, "dur": 35.360, + "args": { + "External id": 719996,"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": 6305209459496.892, "dur": 48.653, + "args": { + "External id": 719997,"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": 6305209459556.192, "dur": 36.175, + "args": { + "External id": 719998,"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": 6305209459617.671, "dur": 27.409, + "args": { + "External id": 719999,"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": 6305209459663.585, "dur": 24.408, + "args": { + "External id": 720000,"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": 6305209459703.797, "dur": 17.435, + "args": { + "External id": 720001,"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": 6305209459737.681, "dur": 15.455, + "args": { + "External id": 720002,"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": 6305209459770.601, "dur": 15.834, + "args": { + "External id": 720003,"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": 6305209459862.980, "dur": 16.178, + "args": { + "External id": 720004,"Record function id": 0, "Ev Idx": 9347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209459866.422, "dur": 11.589, + "args": { + "External id": 720005,"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": 6305209459870.748, "dur": 6.466, + "args": { + "External id": 720006,"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": 6305209459872.690, "dur": 4.404, + "args": { + "External id": 720007,"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": 6305209459883.156, "dur": 4.978, + "args": { + "External id": 720008,"Record function id": 0, "Ev Idx": 9351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209459884.231, "dur": 3.459, + "args": { + "External id": 720009,"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": 6305209459885.185, "dur": 2.033, + "args": { + "External id": 720010,"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": 6305209459886.103, "dur": 1.020, + "args": { + "External id": 720011,"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": 6305209459891.393, "dur": 4.492, + "args": { + "External id": 720012,"Record function id": 0, "Ev Idx": 9355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209459892.590, "dur": 2.879, + "args": { + "External id": 720013,"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": 6305209459893.307, "dur": 1.698, + "args": { + "External id": 720014,"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": 6305209459893.716, "dur": 1.218, + "args": { + "External id": 720015,"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": 6305209459899.037, "dur": 6.090, + "args": { + "External id": 720016,"Record function id": 0, "Ev Idx": 9359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209459900.251, "dur": 4.436, + "args": { + "External id": 720017,"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": 6305209459900.880, "dur": 3.382, + "args": { + "External id": 720018,"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": 6305209459901.549, "dur": 2.641, + "args": { + "External id": 720019,"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": 6305209459908.207, "dur": 4.063, + "args": { + "External id": 720020,"Record function id": 0, "Ev Idx": 9363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209459909.407, "dur": 2.451, + "args": { + "External id": 720021,"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": 6305209459909.868, "dur": 1.473, + "args": { + "External id": 720022,"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": 6305209459910.293, "dur": 0.985, + "args": { + "External id": 720023,"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": 6305209459915.443, "dur": 4.587, + "args": { + "External id": 720024,"Record function id": 0, "Ev Idx": 9367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209459916.811, "dur": 2.789, + "args": { + "External id": 720025,"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": 6305209459917.396, "dur": 1.796, + "args": { + "External id": 720026,"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": 6305209459918.306, "dur": 0.775, + "args": { + "External id": 720027,"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": 6305209459923.285, "dur": 3.698, + "args": { + "External id": 720028,"Record function id": 0, "Ev Idx": 9371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209459924.450, "dur": 2.067, + "args": { + "External id": 720029,"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": 6305209459924.915, "dur": 1.200, + "args": { + "External id": 720030,"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": 6305209459925.371, "dur": 0.676, + "args": { + "External id": 720031,"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": 6305209459930.054, "dur": 4.120, + "args": { + "External id": 720032,"Record function id": 0, "Ev Idx": 9375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209459931.103, "dur": 2.646, + "args": { + "External id": 720033,"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": 6305209459931.707, "dur": 1.589, + "args": { + "External id": 720034,"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": 6305209459932.272, "dur": 0.922, + "args": { + "External id": 720035,"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": 6305209459937.220, "dur": 4.659, + "args": { + "External id": 720036,"Record function id": 0, "Ev Idx": 9379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209459938.906, "dur": 2.555, + "args": { + "External id": 720037,"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": 6305209459939.358, "dur": 1.446, + "args": { + "External id": 720038,"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": 6305209459940.025, "dur": 0.659, + "args": { + "External id": 720039,"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": 6305209459945.870, "dur": 68321.953, + "args": { + "External id": 720040,"Record function id": 0, "Sequence number": 7674648, "Fwd thread id": 1, "Ev Idx": 9383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305209459947.092, "dur": 68311.364, + "args": { + "External id": 720041,"Sequence number": 7674648, "Fwd thread 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": 6305209459947.092, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.14)", "pid": 2338707, "tid": 2379456, + "ts": 6305209459975.745, "dur": 39.102, + "args": { + "External id": 720042,"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": 6305209460022.797, "dur": 102.670, + "args": { + "External id": 720043,"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": 6305209460134.004, "dur": 68116.190, + "args": { + "External id": 720044,"Record function id": 0, "Ev Idx": 9387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305209460228.710, "dur": 8.087, + "args": { + "External id": 720045,"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": 6305209460250.780, "dur": 5.219, + "args": { + "External id": 720046,"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": 6305209460270.914, "dur": 66993.476, + "args": { + "External id": 720047,"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": 6305209460285.201, "dur": 66965.935, + "args": { + "External id": 720048,"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": 6305209460381.324, "dur": 17.501, + "args": { + "External id": 720049,"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": 6305209460418.739, "dur": 66783.541, + "args": { + "External id": 720050,"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": 6305209460421.510, "dur": 66779.604, + "args": { + "External id": 720051,"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": 6305209460426.318, "dur": 10.934, + "args": { + "External id": 720052,"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": 6305209460439.006, "dur": 66756.528, + "args": { + "External id": 720053,"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": 6305209527378.140, "dur": 12.227, + "args": { + "External id": 720054,"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": 6305209527381.806, "dur": 8.175, + "args": { + "External id": 720055,"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": 6305209527424.194, "dur": 400.437, + "args": { + "External id": 720056,"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": 6305209527456.010, "dur": 363.168, + "args": { + "External id": 720057,"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": 6305209527470.618, "dur": 342.711, + "args": { + "External id": 720058,"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": 6305209527846.222, "dur": 2.302, + "args": { + "External id": 720059,"Record function id": 0, "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": 6305209527907.770, "dur": 7.080, + "args": { + "External id": 720060,"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": 6305209527927.403, "dur": 36.034, + "args": { + "External id": 720061,"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": 6305209527973.257, "dur": 1.467, + "args": { + "External id": 720062,"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": 6305209527980.360, "dur": 12.031, + "args": { + "External id": 720063,"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": 6305209527997.441, "dur": 0.907, + "args": { + "External id": 720064,"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": 6305209528002.438, "dur": 10.894, + "args": { + "External id": 720065,"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": 6305209528018.067, "dur": 1.217, + "args": { + "External id": 720066,"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": 6305209528023.227, "dur": 10.797, + "args": { + "External id": 720067,"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": 6305209528038.076, "dur": 0.867, + "args": { + "External id": 720068,"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": 6305209528043.272, "dur": 45.626, + "args": { + "External id": 720069,"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": 6305209528097.313, "dur": 1.788, + "args": { + "External id": 720070,"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": 6305209528104.383, "dur": 14.995, + "args": { + "External id": 720071,"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": 6305209528124.216, "dur": 3.129, + "args": { + "External id": 720072,"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": 6305209528131.678, "dur": 11.339, + "args": { + "External id": 720073,"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": 6305209528147.274, "dur": 0.804, + "args": { + "External id": 720074,"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": 6305209528152.541, "dur": 13.450, + "args": { + "External id": 720075,"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": 6305209528171.943, "dur": 0.768, + "args": { + "External id": 720076,"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": 6305209528176.732, "dur": 11.366, + "args": { + "External id": 720077,"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": 6305209528283.891, "dur": 2979.710, + "args": { + "External id": 720078,"Record function id": 0, "Ev Idx": 9421 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.13)", "pid": 2338707, "tid": 2379456, + "ts": 6305209528304.379, "dur": 1090.780, + "args": { + "External id": 720079,"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": 6305209528320.434, "dur": 352.031, + "args": { + "External id": 720080,"Record function id": 0, "Ev Idx": 9423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6305209528401.639, "dur": 4.227, + "args": { + "External id": 720081,"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": 6305209528409.339, "dur": 0.955, + "args": { + "External id": 720082,"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": 6305209528412.607, "dur": 1.084, + "args": { + "External id": 720083,"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": 6305209528415.347, "dur": 1.062, + "args": { + "External id": 720084,"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": 6305209528418.392, "dur": 0.718, + "args": { + "External id": 720085,"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": 6305209528420.740, "dur": 3.068, + "args": { + "External id": 720086,"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": 6305209528425.452, "dur": 0.862, + "args": { + "External id": 720087,"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": 6305209528429.755, "dur": 2.182, + "args": { + "External id": 720088,"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": 6305209528433.514, "dur": 0.732, + "args": { + "External id": 720089,"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": 6305209528435.603, "dur": 1.061, + "args": { + "External id": 720090,"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": 6305209528453.710, "dur": 185.467, + "args": { + "External id": 720091,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305209528473.319, "dur": 160.627, + "args": { + "External id": 720092,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305209528500.486, "dur": 31.141, + "args": { + "External id": 720093,"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": 6305209528536.695, "dur": 68.165, + "args": { + "External id": 720094,"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": 6305209528539.936, "dur": 64.496, + "args": { + "External id": 720095,"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": 6305209528544.436, "dur": 6.109, + "args": { + "External id": 720096,"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": 6305209528552.580, "dur": 51.362, + "args": { + "External id": 720097,"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": 6305209528754.118, "dur": 633.084, + "args": { + "External id": 720098,"Record function id": 0, "Ev Idx": 9441 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.12)", "pid": 2338707, "tid": 2379456, + "ts": 6305209528771.461, "dur": 602.989, + "args": { + "External id": 720099,"Record function id": 0, "Ev Idx": 9442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305209528830.685, "dur": 5.148, + "args": { + "External id": 720100,"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": 6305209528850.260, "dur": 36.394, + "args": { + "External id": 720101,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209528855.514, "dur": 3.688, + "args": { + "External id": 720102,"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": 6305209528861.586, "dur": 0.696, + "args": { + "External id": 720103,"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": 6305209528863.790, "dur": 0.346, + "args": { + "External id": 720104,"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": 6305209528865.630, "dur": 0.766, + "args": { + "External id": 720105,"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": 6305209528868.164, "dur": 0.354, + "args": { + "External id": 720106,"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": 6305209528870.538, "dur": 0.672, + "args": { + "External id": 720107,"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": 6305209528872.435, "dur": 0.583, + "args": { + "External id": 720108,"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": 6305209528875.163, "dur": 0.419, + "args": { + "External id": 720109,"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": 6305209528879.877, "dur": 3.130, + "args": { + "External id": 720110,"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": 6305209528897.557, "dur": 42.163, + "args": { + "External id": 720111,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305209528969.462, "dur": 165.678, + "args": { + "External id": 720112,"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": 6305209528980.334, "dur": 3.038, + "args": { + "External id": 720113,"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": 6305209528988.503, "dur": 10.216, + "args": { + "External id": 720114,"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": 6305209528992.826, "dur": 5.480, + "args": { + "External id": 720115,"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": 6305209528996.820, "dur": 0.439, + "args": { + "External id": 720116,"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": 6305209529005.162, "dur": 29.183, + "args": { + "External id": 720117,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209529006.994, "dur": 0.669, + "args": { + "External id": 720118,"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": 6305209529009.417, "dur": 0.642, + "args": { + "External id": 720119,"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": 6305209529012.021, "dur": 0.487, + "args": { + "External id": 720120,"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": 6305209529014.732, "dur": 0.365, + "args": { + "External id": 720121,"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": 6305209529016.568, "dur": 0.334, + "args": { + "External id": 720122,"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": 6305209529022.887, "dur": 2.794, + "args": { + "External id": 720123,"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": 6305209529027.094, "dur": 0.377, + "args": { + "External id": 720124,"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": 6305209529029.159, "dur": 0.462, + "args": { + "External id": 720125,"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": 6305209529031.212, "dur": 0.326, + "args": { + "External id": 720126,"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": 6305209529044.585, "dur": 80.596, + "args": { + "External id": 720127,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305209529184.298, "dur": 118.895, + "args": { + "External id": 720128,"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": 6305209529211.888, "dur": 87.881, + "args": { + "External id": 720129,"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": 6305209529222.873, "dur": 72.494, + "args": { + "External id": 720130,"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": 6305209529319.542, "dur": 1.774, + "args": { + "External id": 720131,"Record function id": 0, "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": 6305209529402.085, "dur": 1840.429, + "args": { + "External id": 720132,"Sequence number": 7674647, "Fwd thread 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": 6305209529402.085, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6305209529530.208, "dur": 115.348, + "args": { + "External id": 720133,"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": 6305209529697.445, "dur": 43.653, + "args": { + "External id": 720134,"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": 6305209529758.957, "dur": 49.935, + "args": { + "External id": 720135,"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": 6305209529818.624, "dur": 31.866, + "args": { + "External id": 720136,"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": 6305209529856.650, "dur": 33.740, + "args": { + "External id": 720137,"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": 6305209529898.457, "dur": 28.014, + "args": { + "External id": 720138,"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": 6305209529932.321, "dur": 29.910, + "args": { + "External id": 720139,"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": 6305209529988.511, "dur": 23.753, + "args": { + "External id": 720140,"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": 6305209530031.531, "dur": 70.760, + "args": { + "External id": 720141,"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": 6305209530128.455, "dur": 25.474, + "args": { + "External id": 720142,"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": 6305209530168.427, "dur": 16.248, + "args": { + "External id": 720143,"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": 6305209530195.308, "dur": 44.742, + "args": { + "External id": 720144,"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": 6305209530244.177, "dur": 34.802, + "args": { + "External id": 720145,"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": 6305209530308.849, "dur": 283.848, + "args": { + "External id": 720146,"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": 6305209530392.503, "dur": 8.014, + "args": { + "External id": 720147,"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": 6305209530402.842, "dur": 2.597, + "args": { + "External id": 720148,"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": 6305209530406.812, "dur": 2.398, + "args": { + "External id": 720149,"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": 6305209530410.539, "dur": 2.592, + "args": { + "External id": 720150,"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": 6305209530460.013, "dur": 5.098, + "args": { + "External id": 720151,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209530461.908, "dur": 3.053, + "args": { + "External id": 720152,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209530466.748, "dur": 37.343, + "args": { + "External id": 720153,"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": 6305209530472.781, "dur": 1.805, + "args": { + "External id": 720154,"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": 6305209530522.242, "dur": 2.760, + "args": { + "External id": 720155,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209530523.434, "dur": 1.281, + "args": { + "External id": 720156,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209530526.359, "dur": 21.618, + "args": { + "External id": 720157,"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": 6305209530528.804, "dur": 1.046, + "args": { + "External id": 720158,"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": 6305209530627.654, "dur": 29.399, + "args": { + "External id": 720159,"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": 6305209530679.075, "dur": 17.136, + "args": { + "External id": 720160,"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": 6305209530705.207, "dur": 47.169, + "args": { + "External id": 720161,"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": 6305209530759.424, "dur": 40.152, + "args": { + "External id": 720162,"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": 6305209530811.809, "dur": 23.886, + "args": { + "External id": 720163,"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": 6305209530842.966, "dur": 32.454, + "args": { + "External id": 720164,"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": 6305209530883.566, "dur": 29.474, + "args": { + "External id": 720165,"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": 6305209530920.370, "dur": 30.494, + "args": { + "External id": 720166,"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": 6305209530969.708, "dur": 44.118, + "args": { + "External id": 720167,"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": 6305209531036.000, "dur": 61.740, + "args": { + "External id": 720168,"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": 6305209531115.836, "dur": 23.948, + "args": { + "External id": 720169,"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": 6305209531157.693, "dur": 16.635, + "args": { + "External id": 720170,"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": 6305209531188.264, "dur": 20.370, + "args": { + "External id": 720171,"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": 6305209531290.092, "dur": 16.332, + "args": { + "External id": 720172,"Record function id": 0, "Ev Idx": 9515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209531293.491, "dur": 11.935, + "args": { + "External id": 720173,"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": 6305209531297.960, "dur": 6.616, + "args": { + "External id": 720174,"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": 6305209531300.202, "dur": 4.265, + "args": { + "External id": 720175,"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": 6305209531310.448, "dur": 5.180, + "args": { + "External id": 720176,"Record function id": 0, "Ev Idx": 9519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209531311.560, "dur": 3.611, + "args": { + "External id": 720177,"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": 6305209531312.363, "dur": 2.279, + "args": { + "External id": 720178,"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": 6305209531313.565, "dur": 0.990, + "args": { + "External id": 720179,"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": 6305209531319.129, "dur": 4.290, + "args": { + "External id": 720180,"Record function id": 0, "Ev Idx": 9523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209531320.430, "dur": 2.581, + "args": { + "External id": 720181,"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": 6305209531320.912, "dur": 1.655, + "args": { + "External id": 720182,"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": 6305209531321.335, "dur": 1.146, + "args": { + "External id": 720183,"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": 6305209531326.730, "dur": 3.474, + "args": { + "External id": 720184,"Record function id": 0, "Ev Idx": 9527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209531327.704, "dur": 2.096, + "args": { + "External id": 720185,"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": 6305209531328.326, "dur": 1.062, + "args": { + "External id": 720186,"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": 6305209531328.724, "dur": 0.578, + "args": { + "External id": 720187,"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": 6305209531333.340, "dur": 9.333, + "args": { + "External id": 720188,"Record function id": 0, "Ev Idx": 9531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209531334.399, "dur": 7.863, + "args": { + "External id": 720189,"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": 6305209531334.835, "dur": 3.845, + "args": { + "External id": 720190,"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": 6305209531335.201, "dur": 3.414, + "args": { + "External id": 720191,"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": 6305209531345.806, "dur": 4.209, + "args": { + "External id": 720192,"Record function id": 0, "Ev Idx": 9535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209531346.861, "dur": 2.696, + "args": { + "External id": 720193,"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": 6305209531347.334, "dur": 1.737, + "args": { + "External id": 720194,"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": 6305209531347.916, "dur": 1.042, + "args": { + "External id": 720195,"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": 6305209531353.337, "dur": 3.752, + "args": { + "External id": 720196,"Record function id": 0, "Ev Idx": 9539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209531354.353, "dur": 2.302, + "args": { + "External id": 720197,"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": 6305209531355.074, "dur": 1.101, + "args": { + "External id": 720198,"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": 6305209531355.369, "dur": 0.744, + "args": { + "External id": 720199,"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": 6305209531360.224, "dur": 3.682, + "args": { + "External id": 720200,"Record function id": 0, "Ev Idx": 9543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209531361.298, "dur": 2.197, + "args": { + "External id": 720201,"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": 6305209531362.048, "dur": 0.992, + "args": { + "External id": 720202,"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": 6305209531362.327, "dur": 0.616, + "args": { + "External id": 720203,"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": 6305209531366.943, "dur": 3.890, + "args": { + "External id": 720204,"Record function id": 0, "Ev Idx": 9547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209531367.835, "dur": 2.566, + "args": { + "External id": 720205,"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": 6305209531368.308, "dur": 1.672, + "args": { + "External id": 720206,"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": 6305209531369.066, "dur": 0.792, + "args": { + "External id": 720207,"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": 6305209531375.332, "dur": 69080.763, + "args": { + "External id": 720208,"Record function id": 0, "Sequence number": 7674646, "Fwd thread id": 1, "Ev Idx": 9551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305209531376.783, "dur": 69069.937, + "args": { + "External id": 720209,"Sequence number": 7674646, "Fwd thread 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": 6305209531376.783, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.13)", "pid": 2338707, "tid": 2379456, + "ts": 6305209531411.169, "dur": 40.950, + "args": { + "External id": 720210,"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": 6305209531462.725, "dur": 80.926, + "args": { + "External id": 720211,"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": 6305209531550.974, "dur": 68887.648, + "args": { + "External id": 720212,"Record function id": 0, "Ev Idx": 9555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305209531645.396, "dur": 7.460, + "args": { + "External id": 720213,"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": 6305209531663.868, "dur": 5.074, + "args": { + "External id": 720214,"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": 6305209531683.651, "dur": 67772.747, + "args": { + "External id": 720215,"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": 6305209531697.776, "dur": 67745.977, + "args": { + "External id": 720216,"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": 6305209531792.547, "dur": 18.690, + "args": { + "External id": 720217,"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": 6305209531834.138, "dur": 67557.951, + "args": { + "External id": 720218,"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": 6305209531836.791, "dur": 67553.891, + "args": { + "External id": 720219,"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": 6305209531841.689, "dur": 8.431, + "args": { + "External id": 720220,"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": 6305209531854.365, "dur": 67530.435, + "args": { + "External id": 720221,"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": 6305209599583.922, "dur": 13.237, + "args": { + "External id": 720222,"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": 6305209599587.419, "dur": 9.134, + "args": { + "External id": 720223,"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": 6305209599630.500, "dur": 383.936, + "args": { + "External id": 720224,"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": 6305209599662.826, "dur": 346.496, + "args": { + "External id": 720225,"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": 6305209599677.477, "dur": 325.743, + "args": { + "External id": 720226,"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": 6305209600033.912, "dur": 2.332, + "args": { + "External id": 720227,"Record function id": 0, "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": 6305209600136.238, "dur": 8.797, + "args": { + "External id": 720228,"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": 6305209600157.713, "dur": 39.944, + "args": { + "External id": 720229,"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": 6305209600208.652, "dur": 1.654, + "args": { + "External id": 720230,"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": 6305209600216.386, "dur": 13.229, + "args": { + "External id": 720231,"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": 6305209600235.748, "dur": 0.960, + "args": { + "External id": 720232,"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": 6305209600241.203, "dur": 10.330, + "args": { + "External id": 720233,"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": 6305209600256.959, "dur": 0.785, + "args": { + "External id": 720234,"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": 6305209600261.829, "dur": 11.537, + "args": { + "External id": 720235,"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": 6305209600277.479, "dur": 0.714, + "args": { + "External id": 720236,"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": 6305209600281.960, "dur": 9.654, + "args": { + "External id": 720237,"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": 6305209600296.111, "dur": 1.208, + "args": { + "External id": 720238,"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": 6305209600301.273, "dur": 10.143, + "args": { + "External id": 720239,"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": 6305209600315.644, "dur": 1.022, + "args": { + "External id": 720240,"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": 6305209600320.491, "dur": 9.385, + "args": { + "External id": 720241,"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": 6305209600336.119, "dur": 0.981, + "args": { + "External id": 720242,"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": 6305209600340.831, "dur": 10.748, + "args": { + "External id": 720243,"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": 6305209600355.386, "dur": 2.716, + "args": { + "External id": 720244,"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": 6305209600362.594, "dur": 11.426, + "args": { + "External id": 720245,"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": 6305209600475.788, "dur": 3022.503, + "args": { + "External id": 720246,"Record function id": 0, "Ev Idx": 9589 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.12)", "pid": 2338707, "tid": 2379456, + "ts": 6305209600496.534, "dur": 1108.924, + "args": { + "External id": 720247,"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": 6305209600536.752, "dur": 331.908, + "args": { + "External id": 720248,"Record function id": 0, "Ev Idx": 9591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6305209600624.805, "dur": 4.942, + "args": { + "External id": 720249,"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": 6305209600633.562, "dur": 1.097, + "args": { + "External id": 720250,"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": 6305209600636.834, "dur": 1.280, + "args": { + "External id": 720251,"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": 6305209600639.838, "dur": 0.884, + "args": { + "External id": 720252,"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": 6305209600642.995, "dur": 0.584, + "args": { + "External id": 720253,"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": 6305209600644.922, "dur": 0.861, + "args": { + "External id": 720254,"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": 6305209600647.211, "dur": 0.871, + "args": { + "External id": 720255,"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": 6305209600651.337, "dur": 3.846, + "args": { + "External id": 720256,"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": 6305209600656.753, "dur": 0.569, + "args": { + "External id": 720257,"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": 6305209600658.627, "dur": 0.827, + "args": { + "External id": 720258,"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": 6305209600678.136, "dur": 160.014, + "args": { + "External id": 720259,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305209600694.144, "dur": 139.710, + "args": { + "External id": 720260,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305209600721.287, "dur": 14.883, + "args": { + "External id": 720261,"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": 6305209600740.119, "dur": 66.332, + "args": { + "External id": 720262,"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": 6305209600743.080, "dur": 63.109, + "args": { + "External id": 720263,"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": 6305209600747.207, "dur": 5.361, + "args": { + "External id": 720264,"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": 6305209600754.805, "dur": 50.844, + "args": { + "External id": 720265,"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": 6305209600947.721, "dur": 650.166, + "args": { + "External id": 720266,"Record function id": 0, "Ev Idx": 9609 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.11)", "pid": 2338707, "tid": 2379456, + "ts": 6305209600964.468, "dur": 619.761, + "args": { + "External id": 720267,"Record function id": 0, "Ev Idx": 9610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305209601021.950, "dur": 5.628, + "args": { + "External id": 720268,"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": 6305209601042.815, "dur": 80.156, + "args": { + "External id": 720269,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209601048.188, "dur": 1.610, + "args": { + "External id": 720270,"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": 6305209601051.641, "dur": 49.805, + "args": { + "External id": 720271,"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": 6305209601104.552, "dur": 2.574, + "args": { + "External id": 720272,"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": 6305209601108.739, "dur": 0.290, + "args": { + "External id": 720273,"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": 6305209601110.291, "dur": 0.638, + "args": { + "External id": 720274,"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": 6305209601112.778, "dur": 0.629, + "args": { + "External id": 720275,"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": 6305209601114.796, "dur": 0.273, + "args": { + "External id": 720276,"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": 6305209601115.902, "dur": 0.453, + "args": { + "External id": 720277,"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": 6305209601117.995, "dur": 0.394, + "args": { + "External id": 720278,"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": 6305209601135.429, "dur": 43.932, + "args": { + "External id": 720279,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305209601213.985, "dur": 111.287, + "args": { + "External id": 720280,"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": 6305209601225.640, "dur": 4.091, + "args": { + "External id": 720281,"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": 6305209601234.942, "dur": 12.734, + "args": { + "External id": 720282,"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": 6305209601239.607, "dur": 7.679, + "args": { + "External id": 720283,"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": 6305209601243.182, "dur": 2.846, + "args": { + "External id": 720284,"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": 6305209601254.343, "dur": 23.788, + "args": { + "External id": 720285,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209601256.457, "dur": 0.518, + "args": { + "External id": 720286,"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": 6305209601258.229, "dur": 0.720, + "args": { + "External id": 720287,"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": 6305209601260.734, "dur": 0.502, + "args": { + "External id": 720288,"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": 6305209601262.906, "dur": 0.418, + "args": { + "External id": 720289,"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": 6305209601264.432, "dur": 0.375, + "args": { + "External id": 720290,"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": 6305209601266.770, "dur": 0.368, + "args": { + "External id": 720291,"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": 6305209601268.471, "dur": 0.396, + "args": { + "External id": 720292,"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": 6305209601270.149, "dur": 2.564, + "args": { + "External id": 720293,"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": 6305209601274.727, "dur": 0.444, + "args": { + "External id": 720294,"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": 6305209601289.022, "dur": 28.648, + "args": { + "External id": 720295,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305209601371.911, "dur": 116.967, + "args": { + "External id": 720296,"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": 6305209601395.759, "dur": 89.653, + "args": { + "External id": 720297,"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": 6305209601407.710, "dur": 72.566, + "args": { + "External id": 720298,"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": 6305209601523.496, "dur": 2.836, + "args": { + "External id": 720299,"Record function id": 0, "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": 6305209601614.743, "dur": 1862.480, + "args": { + "External id": 720300,"Sequence number": 7674645, "Fwd thread 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": 6305209601614.743, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6305209601727.756, "dur": 111.395, + "args": { + "External id": 720301,"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": 6305209601881.439, "dur": 39.986, + "args": { + "External id": 720302,"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": 6305209601940.568, "dur": 51.873, + "args": { + "External id": 720303,"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": 6305209602003.105, "dur": 31.969, + "args": { + "External id": 720304,"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": 6305209602041.549, "dur": 76.469, + "args": { + "External id": 720305,"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": 6305209602128.667, "dur": 33.992, + "args": { + "External id": 720306,"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": 6305209602171.941, "dur": 31.511, + "args": { + "External id": 720307,"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": 6305209602232.598, "dur": 28.410, + "args": { + "External id": 720308,"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": 6305209602280.316, "dur": 28.301, + "args": { + "External id": 720309,"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": 6305209602330.661, "dur": 19.529, + "args": { + "External id": 720310,"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": 6305209602364.290, "dur": 15.487, + "args": { + "External id": 720311,"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": 6305209602391.090, "dur": 40.597, + "args": { + "External id": 720312,"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": 6305209602435.907, "dur": 35.036, + "args": { + "External id": 720313,"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": 6305209602501.071, "dur": 277.465, + "args": { + "External id": 720314,"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": 6305209602600.751, "dur": 7.292, + "args": { + "External id": 720315,"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": 6305209602610.900, "dur": 2.606, + "args": { + "External id": 720316,"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": 6305209602615.056, "dur": 4.962, + "args": { + "External id": 720317,"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": 6305209602621.521, "dur": 2.206, + "args": { + "External id": 720318,"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": 6305209602669.839, "dur": 5.410, + "args": { + "External id": 720319,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209602672.260, "dur": 2.845, + "args": { + "External id": 720320,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209602677.283, "dur": 35.082, + "args": { + "External id": 720321,"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": 6305209602683.423, "dur": 1.726, + "args": { + "External id": 720322,"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": 6305209602714.139, "dur": 1.973, + "args": { + "External id": 720323,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209602715.335, "dur": 0.709, + "args": { + "External id": 720324,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209602717.451, "dur": 14.466, + "args": { + "External id": 720325,"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": 6305209602720.330, "dur": 0.552, + "args": { + "External id": 720326,"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": 6305209602818.719, "dur": 29.856, + "args": { + "External id": 720327,"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": 6305209602866.922, "dur": 16.941, + "args": { + "External id": 720328,"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": 6305209602893.041, "dur": 48.886, + "args": { + "External id": 720329,"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": 6305209602949.656, "dur": 41.203, + "args": { + "External id": 720330,"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": 6305209603000.779, "dur": 22.502, + "args": { + "External id": 720331,"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": 6305209603032.614, "dur": 89.968, + "args": { + "External id": 720332,"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": 6305209603146.627, "dur": 41.236, + "args": { + "External id": 720333,"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": 6305209603195.423, "dur": 32.199, + "args": { + "External id": 720334,"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": 6305209603250.933, "dur": 27.971, + "args": { + "External id": 720335,"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": 6305209603298.155, "dur": 25.475, + "args": { + "External id": 720336,"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": 6305209603337.454, "dur": 22.155, + "args": { + "External id": 720337,"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": 6305209603389.582, "dur": 15.821, + "args": { + "External id": 720338,"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": 6305209603423.952, "dur": 15.311, + "args": { + "External id": 720339,"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": 6305209603536.846, "dur": 17.262, + "args": { + "External id": 720340,"Record function id": 0, "Ev Idx": 9683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209603540.394, "dur": 12.479, + "args": { + "External id": 720341,"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": 6305209603544.587, "dur": 6.980, + "args": { + "External id": 720342,"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": 6305209603546.926, "dur": 4.384, + "args": { + "External id": 720343,"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": 6305209603558.515, "dur": 5.020, + "args": { + "External id": 720344,"Record function id": 0, "Ev Idx": 9687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209603559.764, "dur": 3.374, + "args": { + "External id": 720345,"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": 6305209603560.479, "dur": 2.111, + "args": { + "External id": 720346,"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": 6305209603561.478, "dur": 1.033, + "args": { + "External id": 720347,"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": 6305209603566.937, "dur": 4.613, + "args": { + "External id": 720348,"Record function id": 0, "Ev Idx": 9691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209603568.475, "dur": 2.615, + "args": { + "External id": 720349,"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": 6305209603568.948, "dur": 1.569, + "args": { + "External id": 720350,"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": 6305209603569.277, "dur": 1.174, + "args": { + "External id": 720351,"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": 6305209603574.798, "dur": 3.828, + "args": { + "External id": 720352,"Record function id": 0, "Ev Idx": 9695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209603575.822, "dur": 2.410, + "args": { + "External id": 720353,"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": 6305209603576.410, "dur": 1.362, + "args": { + "External id": 720354,"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": 6305209603576.839, "dur": 0.860, + "args": { + "External id": 720355,"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": 6305209603581.728, "dur": 3.654, + "args": { + "External id": 720356,"Record function id": 0, "Ev Idx": 9699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209603582.957, "dur": 2.028, + "args": { + "External id": 720357,"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": 6305209603583.430, "dur": 1.127, + "args": { + "External id": 720358,"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": 6305209603583.810, "dur": 0.672, + "args": { + "External id": 720359,"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": 6305209603588.500, "dur": 6.452, + "args": { + "External id": 720360,"Record function id": 0, "Ev Idx": 9703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209603589.763, "dur": 4.749, + "args": { + "External id": 720361,"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": 6305209603590.362, "dur": 3.748, + "args": { + "External id": 720362,"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": 6305209603590.836, "dur": 3.160, + "args": { + "External id": 720363,"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": 6305209603598.162, "dur": 3.796, + "args": { + "External id": 720364,"Record function id": 0, "Ev Idx": 9707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209603599.397, "dur": 2.122, + "args": { + "External id": 720365,"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": 6305209603599.851, "dur": 1.199, + "args": { + "External id": 720366,"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": 6305209603600.143, "dur": 0.842, + "args": { + "External id": 720367,"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": 6305209603604.999, "dur": 3.871, + "args": { + "External id": 720368,"Record function id": 0, "Ev Idx": 9711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209603606.137, "dur": 2.312, + "args": { + "External id": 720369,"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": 6305209603606.611, "dur": 1.230, + "args": { + "External id": 720370,"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": 6305209603607.024, "dur": 0.741, + "args": { + "External id": 720371,"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": 6305209603612.290, "dur": 3.753, + "args": { + "External id": 720372,"Record function id": 0, "Ev Idx": 9715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209603613.533, "dur": 2.043, + "args": { + "External id": 720373,"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": 6305209603613.982, "dur": 1.221, + "args": { + "External id": 720374,"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": 6305209603614.423, "dur": 0.660, + "args": { + "External id": 720375,"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": 6305209603620.037, "dur": 66877.504, + "args": { + "External id": 720376,"Record function id": 0, "Sequence number": 7674644, "Fwd thread id": 1, "Ev Idx": 9719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305209603621.770, "dur": 66865.260, + "args": { + "External id": 720377,"Sequence number": 7674644, "Fwd thread 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": 6305209603621.770, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.12)", "pid": 2338707, "tid": 2379456, + "ts": 6305209603653.212, "dur": 41.926, + "args": { + "External id": 720378,"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": 6305209603703.570, "dur": 63.962, + "args": { + "External id": 720379,"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": 6305209603773.632, "dur": 66705.427, + "args": { + "External id": 720380,"Record function id": 0, "Ev Idx": 9723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305209603865.050, "dur": 7.109, + "args": { + "External id": 720381,"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": 6305209603882.957, "dur": 4.622, + "args": { + "External id": 720382,"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": 6305209603902.684, "dur": 65644.952, + "args": { + "External id": 720383,"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": 6305209603916.971, "dur": 65616.820, + "args": { + "External id": 720384,"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": 6305209604050.002, "dur": 75.992, + "args": { + "External id": 720385,"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": 6305209604153.250, "dur": 65318.448, + "args": { + "External id": 720386,"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": 6305209604156.432, "dur": 65314.092, + "args": { + "External id": 720387,"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": 6305209604162.850, "dur": 12.124, + "args": { + "External id": 720388,"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": 6305209604176.835, "dur": 65288.602, + "args": { + "External id": 720389,"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": 6305209669662.955, "dur": 13.216, + "args": { + "External id": 720390,"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": 6305209669666.637, "dur": 9.044, + "args": { + "External id": 720391,"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": 6305209669708.432, "dur": 341.104, + "args": { + "External id": 720392,"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": 6305209669739.694, "dur": 304.746, + "args": { + "External id": 720393,"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": 6305209669753.780, "dur": 285.455, + "args": { + "External id": 720394,"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": 6305209670108.602, "dur": 3.949, + "args": { + "External id": 720395,"Record function id": 0, "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": 6305209670176.963, "dur": 7.098, + "args": { + "External id": 720396,"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": 6305209670196.714, "dur": 39.005, + "args": { + "External id": 720397,"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": 6305209670246.300, "dur": 3.798, + "args": { + "External id": 720398,"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": 6305209670255.372, "dur": 13.758, + "args": { + "External id": 720399,"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": 6305209670274.761, "dur": 1.004, + "args": { + "External id": 720400,"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": 6305209670280.006, "dur": 10.344, + "args": { + "External id": 720401,"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": 6305209670295.053, "dur": 1.090, + "args": { + "External id": 720402,"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": 6305209670300.151, "dur": 10.574, + "args": { + "External id": 720403,"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": 6305209670315.295, "dur": 0.788, + "args": { + "External id": 720404,"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": 6305209670320.067, "dur": 9.953, + "args": { + "External id": 720405,"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": 6305209670333.753, "dur": 1.156, + "args": { + "External id": 720406,"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": 6305209670338.885, "dur": 10.259, + "args": { + "External id": 720407,"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": 6305209670353.316, "dur": 0.809, + "args": { + "External id": 720408,"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": 6305209670357.990, "dur": 13.584, + "args": { + "External id": 720409,"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": 6305209670377.916, "dur": 0.920, + "args": { + "External id": 720410,"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": 6305209670382.641, "dur": 12.779, + "args": { + "External id": 720411,"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": 6305209670399.366, "dur": 0.681, + "args": { + "External id": 720412,"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": 6305209670404.156, "dur": 11.356, + "args": { + "External id": 720413,"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": 6305209670528.714, "dur": 2955.950, + "args": { + "External id": 720414,"Record function id": 0, "Ev Idx": 9757 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.11)", "pid": 2338707, "tid": 2379456, + "ts": 6305209670551.571, "dur": 1081.713, + "args": { + "External id": 720415,"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": 6305209670567.968, "dur": 333.227, + "args": { + "External id": 720416,"Record function id": 0, "Ev Idx": 9759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6305209670649.712, "dur": 6.920, + "args": { + "External id": 720417,"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": 6305209670660.020, "dur": 1.082, + "args": { + "External id": 720418,"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": 6305209670663.127, "dur": 0.895, + "args": { + "External id": 720419,"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": 6305209670665.535, "dur": 0.775, + "args": { + "External id": 720420,"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": 6305209670668.167, "dur": 0.876, + "args": { + "External id": 720421,"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": 6305209670670.311, "dur": 0.908, + "args": { + "External id": 720422,"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": 6305209670675.664, "dur": 0.838, + "args": { + "External id": 720423,"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": 6305209670678.291, "dur": 2.127, + "args": { + "External id": 720424,"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": 6305209670681.891, "dur": 2.857, + "args": { + "External id": 720425,"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": 6305209670686.201, "dur": 0.716, + "args": { + "External id": 720426,"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": 6305209670710.812, "dur": 158.470, + "args": { + "External id": 720427,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305209670727.136, "dur": 137.538, + "args": { + "External id": 720428,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305209670752.182, "dur": 13.801, + "args": { + "External id": 720429,"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": 6305209670769.851, "dur": 66.652, + "args": { + "External id": 720430,"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": 6305209670772.674, "dur": 63.514, + "args": { + "External id": 720431,"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": 6305209670776.888, "dur": 5.597, + "args": { + "External id": 720432,"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": 6305209670784.385, "dur": 51.070, + "args": { + "External id": 720433,"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": 6305209670980.105, "dur": 645.499, + "args": { + "External id": 720434,"Record function id": 0, "Ev Idx": 9777 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.10)", "pid": 2338707, "tid": 2379456, + "ts": 6305209670997.603, "dur": 615.060, + "args": { + "External id": 720435,"Record function id": 0, "Ev Idx": 9778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305209671094.824, "dur": 7.355, + "args": { + "External id": 720436,"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": 6305209671119.050, "dur": 31.624, + "args": { + "External id": 720437,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209671124.938, "dur": 1.961, + "args": { + "External id": 720438,"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": 6305209671129.459, "dur": 0.682, + "args": { + "External id": 720439,"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": 6305209671131.061, "dur": 0.654, + "args": { + "External id": 720440,"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": 6305209671133.365, "dur": 2.918, + "args": { + "External id": 720441,"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": 6305209671137.992, "dur": 0.384, + "args": { + "External id": 720442,"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": 6305209671139.351, "dur": 1.373, + "args": { + "External id": 720443,"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": 6305209671142.585, "dur": 0.616, + "args": { + "External id": 720444,"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": 6305209671144.971, "dur": 0.272, + "args": { + "External id": 720445,"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": 6305209671146.148, "dur": 0.389, + "args": { + "External id": 720446,"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": 6305209671161.476, "dur": 46.731, + "args": { + "External id": 720447,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305209671240.000, "dur": 110.327, + "args": { + "External id": 720448,"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": 6305209671251.523, "dur": 2.988, + "args": { + "External id": 720449,"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": 6305209671259.843, "dur": 10.573, + "args": { + "External id": 720450,"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": 6305209671264.303, "dur": 5.694, + "args": { + "External id": 720451,"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": 6305209671267.985, "dur": 0.821, + "args": { + "External id": 720452,"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": 6305209671276.442, "dur": 25.057, + "args": { + "External id": 720453,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209671278.618, "dur": 2.701, + "args": { + "External id": 720454,"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": 6305209671282.877, "dur": 0.644, + "args": { + "External id": 720455,"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": 6305209671285.215, "dur": 0.488, + "args": { + "External id": 720456,"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": 6305209671287.171, "dur": 0.746, + "args": { + "External id": 720457,"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": 6305209671288.815, "dur": 0.433, + "args": { + "External id": 720458,"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": 6305209671290.742, "dur": 0.592, + "args": { + "External id": 720459,"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": 6305209671293.017, "dur": 0.272, + "args": { + "External id": 720460,"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": 6305209671294.310, "dur": 0.593, + "args": { + "External id": 720461,"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": 6305209671296.329, "dur": 2.143, + "args": { + "External id": 720462,"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": 6305209671312.295, "dur": 30.734, + "args": { + "External id": 720463,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305209671400.204, "dur": 136.077, + "args": { + "External id": 720464,"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": 6305209671428.105, "dur": 104.240, + "args": { + "External id": 720465,"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": 6305209671437.857, "dur": 89.152, + "args": { + "External id": 720466,"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": 6305209671554.421, "dur": 2.468, + "args": { + "External id": 720467,"Record function id": 0, "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": 6305209671640.494, "dur": 1822.551, + "args": { + "External id": 720468,"Sequence number": 7674643, "Fwd thread 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": 6305209671640.494, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6305209671750.166, "dur": 110.722, + "args": { + "External id": 720469,"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": 6305209671901.525, "dur": 41.720, + "args": { + "External id": 720470,"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": 6305209671962.280, "dur": 54.217, + "args": { + "External id": 720471,"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": 6305209672026.822, "dur": 76.014, + "args": { + "External id": 720472,"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": 6305209672113.955, "dur": 43.284, + "args": { + "External id": 720473,"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": 6305209672165.562, "dur": 29.613, + "args": { + "External id": 720474,"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": 6305209672208.356, "dur": 30.332, + "args": { + "External id": 720475,"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": 6305209672264.245, "dur": 25.714, + "args": { + "External id": 720476,"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": 6305209672307.241, "dur": 28.719, + "args": { + "External id": 720477,"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": 6305209672359.327, "dur": 22.066, + "args": { + "External id": 720478,"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": 6305209672395.880, "dur": 16.587, + "args": { + "External id": 720479,"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": 6305209672424.164, "dur": 40.501, + "args": { + "External id": 720480,"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": 6305209672468.643, "dur": 33.797, + "args": { + "External id": 720481,"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": 6305209672547.228, "dur": 257.067, + "args": { + "External id": 720482,"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": 6305209672626.901, "dur": 6.496, + "args": { + "External id": 720483,"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": 6305209672635.689, "dur": 2.441, + "args": { + "External id": 720484,"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": 6305209672640.148, "dur": 2.363, + "args": { + "External id": 720485,"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": 6305209672644.061, "dur": 4.454, + "args": { + "External id": 720486,"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": 6305209672697.068, "dur": 5.400, + "args": { + "External id": 720487,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209672699.195, "dur": 3.073, + "args": { + "External id": 720488,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209672704.126, "dur": 32.248, + "args": { + "External id": 720489,"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": 6305209672710.143, "dur": 1.811, + "args": { + "External id": 720490,"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": 6305209672738.037, "dur": 7.064, + "args": { + "External id": 720491,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209672744.268, "dur": 0.733, + "args": { + "External id": 720492,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209672746.277, "dur": 15.924, + "args": { + "External id": 720493,"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": 6305209672748.550, "dur": 0.735, + "args": { + "External id": 720494,"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": 6305209672836.904, "dur": 29.463, + "args": { + "External id": 720495,"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": 6305209672882.589, "dur": 18.503, + "args": { + "External id": 720496,"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": 6305209672909.352, "dur": 48.265, + "args": { + "External id": 720497,"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": 6305209672965.337, "dur": 42.514, + "args": { + "External id": 720498,"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": 6305209673016.971, "dur": 23.366, + "args": { + "External id": 720499,"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": 6305209673048.440, "dur": 77.592, + "args": { + "External id": 720500,"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": 6305209673137.704, "dur": 45.916, + "args": { + "External id": 720501,"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": 6305209673199.214, "dur": 40.799, + "args": { + "External id": 720502,"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": 6305209673262.733, "dur": 28.711, + "args": { + "External id": 720503,"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": 6305209673310.527, "dur": 26.891, + "args": { + "External id": 720504,"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": 6305209673350.687, "dur": 21.004, + "args": { + "External id": 720505,"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": 6305209673385.353, "dur": 14.511, + "args": { + "External id": 720506,"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": 6305209673412.340, "dur": 15.779, + "args": { + "External id": 720507,"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": 6305209673523.452, "dur": 18.347, + "args": { + "External id": 720508,"Record function id": 0, "Ev Idx": 9851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209673528.261, "dur": 12.306, + "args": { + "External id": 720509,"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": 6305209673532.558, "dur": 6.610, + "args": { + "External id": 720510,"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": 6305209673534.613, "dur": 4.276, + "args": { + "External id": 720511,"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": 6305209673547.344, "dur": 5.552, + "args": { + "External id": 720512,"Record function id": 0, "Ev Idx": 9855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209673548.860, "dur": 3.540, + "args": { + "External id": 720513,"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": 6305209673549.653, "dur": 2.255, + "args": { + "External id": 720514,"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": 6305209673550.731, "dur": 1.081, + "args": { + "External id": 720515,"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": 6305209673556.273, "dur": 4.651, + "args": { + "External id": 720516,"Record function id": 0, "Ev Idx": 9859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209673557.389, "dur": 3.094, + "args": { + "External id": 720517,"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": 6305209673557.853, "dur": 2.180, + "args": { + "External id": 720518,"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": 6305209673558.587, "dur": 1.377, + "args": { + "External id": 720519,"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": 6305209673564.126, "dur": 3.816, + "args": { + "External id": 720520,"Record function id": 0, "Ev Idx": 9863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209673565.069, "dur": 2.442, + "args": { + "External id": 720521,"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": 6305209673565.652, "dur": 1.426, + "args": { + "External id": 720522,"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": 6305209673566.169, "dur": 0.842, + "args": { + "External id": 720523,"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": 6305209673571.018, "dur": 3.510, + "args": { + "External id": 720524,"Record function id": 0, "Ev Idx": 9867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209673572.046, "dur": 2.031, + "args": { + "External id": 720525,"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": 6305209673572.465, "dur": 1.025, + "args": { + "External id": 720526,"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": 6305209673572.753, "dur": 0.639, + "args": { + "External id": 720527,"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": 6305209673577.652, "dur": 6.432, + "args": { + "External id": 720528,"Record function id": 0, "Ev Idx": 9871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209673578.790, "dur": 4.873, + "args": { + "External id": 720529,"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": 6305209673579.504, "dur": 3.640, + "args": { + "External id": 720530,"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": 6305209673580.020, "dur": 3.031, + "args": { + "External id": 720531,"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": 6305209673587.442, "dur": 3.838, + "args": { + "External id": 720532,"Record function id": 0, "Ev Idx": 9875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209673588.713, "dur": 2.127, + "args": { + "External id": 720533,"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": 6305209673589.340, "dur": 1.099, + "args": { + "External id": 720534,"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": 6305209673589.623, "dur": 0.706, + "args": { + "External id": 720535,"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": 6305209673594.400, "dur": 3.650, + "args": { + "External id": 720536,"Record function id": 0, "Ev Idx": 9879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209673595.362, "dur": 2.253, + "args": { + "External id": 720537,"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": 6305209673595.824, "dur": 1.388, + "args": { + "External id": 720538,"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": 6305209673596.117, "dur": 1.020, + "args": { + "External id": 720539,"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": 6305209673601.644, "dur": 4.387, + "args": { + "External id": 720540,"Record function id": 0, "Ev Idx": 9883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209673602.686, "dur": 2.848, + "args": { + "External id": 720541,"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": 6305209673603.325, "dur": 1.818, + "args": { + "External id": 720542,"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": 6305209673604.129, "dur": 0.897, + "args": { + "External id": 720543,"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": 6305209673610.851, "dur": 62598.710, + "args": { + "External id": 720544,"Record function id": 0, "Sequence number": 7674642, "Fwd thread id": 1, "Ev Idx": 9887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305209673612.460, "dur": 62587.641, + "args": { + "External id": 720545,"Sequence number": 7674642, "Fwd thread 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": 6305209673612.460, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.11)", "pid": 2338707, "tid": 2379456, + "ts": 6305209673642.409, "dur": 40.021, + "args": { + "External id": 720546,"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": 6305209673689.798, "dur": 61.604, + "args": { + "External id": 720547,"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": 6305209673756.827, "dur": 62435.825, + "args": { + "External id": 720548,"Record function id": 0, "Ev Idx": 9891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305209673851.833, "dur": 7.452, + "args": { + "External id": 720549,"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": 6305209673869.802, "dur": 4.608, + "args": { + "External id": 720550,"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": 6305209673888.749, "dur": 61317.788, + "args": { + "External id": 720551,"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": 6305209673903.440, "dur": 61289.794, + "args": { + "External id": 720552,"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": 6305209674000.775, "dur": 17.798, + "args": { + "External id": 720553,"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": 6305209674045.066, "dur": 61099.602, + "args": { + "External id": 720554,"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": 6305209674047.945, "dur": 61095.531, + "args": { + "External id": 720555,"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": 6305209674053.174, "dur": 52.599, + "args": { + "External id": 720556,"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": 6305209674109.265, "dur": 61028.997, + "args": { + "External id": 720557,"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": 6305209735320.359, "dur": 12.549, + "args": { + "External id": 720558,"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": 6305209735324.135, "dur": 8.289, + "args": { + "External id": 720559,"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": 6305209735366.392, "dur": 405.081, + "args": { + "External id": 720560,"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": 6305209735399.515, "dur": 366.591, + "args": { + "External id": 720561,"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": 6305209735411.782, "dur": 348.321, + "args": { + "External id": 720562,"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": 6305209735795.089, "dur": 2.258, + "args": { + "External id": 720563,"Record function id": 0, "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": 6305209735857.628, "dur": 7.276, + "args": { + "External id": 720564,"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": 6305209735876.910, "dur": 36.091, + "args": { + "External id": 720565,"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": 6305209735924.235, "dur": 3.851, + "args": { + "External id": 720566,"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": 6305209735933.555, "dur": 12.785, + "args": { + "External id": 720567,"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": 6305209735951.755, "dur": 0.973, + "args": { + "External id": 720568,"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": 6305209735957.427, "dur": 9.853, + "args": { + "External id": 720569,"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": 6305209735972.122, "dur": 0.654, + "args": { + "External id": 720570,"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": 6305209735977.164, "dur": 11.222, + "args": { + "External id": 720571,"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": 6305209735992.733, "dur": 1.037, + "args": { + "External id": 720572,"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": 6305209735998.120, "dur": 10.187, + "args": { + "External id": 720573,"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": 6305209736012.765, "dur": 0.949, + "args": { + "External id": 720574,"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": 6305209736017.747, "dur": 10.733, + "args": { + "External id": 720575,"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": 6305209736032.980, "dur": 1.314, + "args": { + "External id": 720576,"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": 6305209736038.451, "dur": 9.891, + "args": { + "External id": 720577,"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": 6305209736086.400, "dur": 2.182, + "args": { + "External id": 720578,"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": 6305209736094.972, "dur": 15.089, + "args": { + "External id": 720579,"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": 6305209736115.712, "dur": 0.977, + "args": { + "External id": 720580,"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": 6305209736120.741, "dur": 11.686, + "args": { + "External id": 720581,"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": 6305209736226.098, "dur": 2977.401, + "args": { + "External id": 720582,"Record function id": 0, "Ev Idx": 9925 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.10)", "pid": 2338707, "tid": 2379456, + "ts": 6305209736247.571, "dur": 1085.220, + "args": { + "External id": 720583,"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": 6305209736263.625, "dur": 352.465, + "args": { + "External id": 720584,"Record function id": 0, "Ev Idx": 9927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6305209736344.916, "dur": 6.490, + "args": { + "External id": 720585,"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": 6305209736354.963, "dur": 0.877, + "args": { + "External id": 720586,"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": 6305209736357.907, "dur": 1.012, + "args": { + "External id": 720587,"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": 6305209736360.542, "dur": 0.721, + "args": { + "External id": 720588,"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": 6305209736363.368, "dur": 0.876, + "args": { + "External id": 720589,"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": 6305209736365.521, "dur": 0.929, + "args": { + "External id": 720590,"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": 6305209736368.099, "dur": 0.707, + "args": { + "External id": 720591,"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": 6305209736370.760, "dur": 2.273, + "args": { + "External id": 720592,"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": 6305209736376.468, "dur": 2.834, + "args": { + "External id": 720593,"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": 6305209736380.718, "dur": 0.878, + "args": { + "External id": 720594,"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": 6305209736400.198, "dur": 181.875, + "args": { + "External id": 720595,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305209736416.812, "dur": 159.789, + "args": { + "External id": 720596,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305209736444.342, "dur": 16.380, + "args": { + "External id": 720597,"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": 6305209736464.938, "dur": 83.207, + "args": { + "External id": 720598,"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": 6305209736468.417, "dur": 79.305, + "args": { + "External id": 720599,"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": 6305209736472.443, "dur": 6.264, + "args": { + "External id": 720600,"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": 6305209736481.147, "dur": 65.437, + "args": { + "External id": 720601,"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": 6305209736696.201, "dur": 628.497, + "args": { + "External id": 720602,"Record function id": 0, "Ev Idx": 9945 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.9)", "pid": 2338707, "tid": 2379456, + "ts": 6305209736714.423, "dur": 598.386, + "args": { + "External id": 720603,"Record function id": 0, "Ev Idx": 9946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305209736774.777, "dur": 9.338, + "args": { + "External id": 720604,"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": 6305209736798.693, "dur": 31.235, + "args": { + "External id": 720605,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209736804.611, "dur": 2.007, + "args": { + "External id": 720606,"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": 6305209736809.058, "dur": 0.558, + "args": { + "External id": 720607,"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": 6305209736811.309, "dur": 0.947, + "args": { + "External id": 720608,"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": 6305209736813.867, "dur": 2.466, + "args": { + "External id": 720609,"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": 6305209736817.617, "dur": 0.478, + "args": { + "External id": 720610,"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": 6305209736819.991, "dur": 0.368, + "args": { + "External id": 720611,"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": 6305209736821.890, "dur": 0.405, + "args": { + "External id": 720612,"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": 6305209736823.409, "dur": 0.320, + "args": { + "External id": 720613,"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": 6305209736825.550, "dur": 0.480, + "args": { + "External id": 720614,"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": 6305209736843.916, "dur": 38.727, + "args": { + "External id": 720615,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305209736913.762, "dur": 113.213, + "args": { + "External id": 720616,"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": 6305209736925.030, "dur": 3.287, + "args": { + "External id": 720617,"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": 6305209736933.858, "dur": 10.718, + "args": { + "External id": 720618,"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": 6305209736938.764, "dur": 5.420, + "args": { + "External id": 720619,"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": 6305209736942.319, "dur": 0.604, + "args": { + "External id": 720620,"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": 6305209736954.063, "dur": 24.720, + "args": { + "External id": 720621,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209736956.370, "dur": 2.344, + "args": { + "External id": 720622,"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": 6305209736960.645, "dur": 0.806, + "args": { + "External id": 720623,"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": 6305209736962.838, "dur": 0.380, + "args": { + "External id": 720624,"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": 6305209736964.283, "dur": 0.371, + "args": { + "External id": 720625,"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": 6305209736966.415, "dur": 0.448, + "args": { + "External id": 720626,"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": 6305209736968.787, "dur": 0.290, + "args": { + "External id": 720627,"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": 6305209736970.093, "dur": 0.400, + "args": { + "External id": 720628,"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": 6305209736972.183, "dur": 0.497, + "args": { + "External id": 720629,"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": 6305209736973.987, "dur": 2.037, + "args": { + "External id": 720630,"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": 6305209736989.415, "dur": 30.508, + "args": { + "External id": 720631,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305209737109.150, "dur": 129.504, + "args": { + "External id": 720632,"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": 6305209737137.576, "dur": 97.342, + "args": { + "External id": 720633,"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": 6305209737147.932, "dur": 82.690, + "args": { + "External id": 720634,"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": 6305209737256.892, "dur": 1.777, + "args": { + "External id": 720635,"Record function id": 0, "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": 6305209737340.198, "dur": 1841.421, + "args": { + "External id": 720636,"Sequence number": 7674641, "Fwd thread 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": 6305209737340.198, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6305209737451.293, "dur": 130.766, + "args": { + "External id": 720637,"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": 6305209737626.487, "dur": 40.659, + "args": { + "External id": 720638,"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": 6305209737688.609, "dur": 54.277, + "args": { + "External id": 720639,"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": 6305209737753.859, "dur": 32.849, + "args": { + "External id": 720640,"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": 6305209737793.162, "dur": 33.896, + "args": { + "External id": 720641,"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": 6305209737834.001, "dur": 27.976, + "args": { + "External id": 720642,"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": 6305209737870.892, "dur": 29.463, + "args": { + "External id": 720643,"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": 6305209737926.734, "dur": 23.375, + "args": { + "External id": 720644,"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": 6305209737969.581, "dur": 28.470, + "args": { + "External id": 720645,"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": 6305209738019.473, "dur": 18.553, + "args": { + "External id": 720646,"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": 6305209738088.238, "dur": 19.555, + "args": { + "External id": 720647,"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": 6305209738121.899, "dur": 43.849, + "args": { + "External id": 720648,"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": 6305209738170.341, "dur": 34.486, + "args": { + "External id": 720649,"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": 6305209738235.250, "dur": 266.644, + "args": { + "External id": 720650,"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": 6305209738316.674, "dur": 6.361, + "args": { + "External id": 720651,"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": 6305209738325.530, "dur": 3.142, + "args": { + "External id": 720652,"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": 6305209738330.102, "dur": 2.437, + "args": { + "External id": 720653,"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": 6305209738333.745, "dur": 4.250, + "args": { + "External id": 720654,"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": 6305209738385.024, "dur": 5.218, + "args": { + "External id": 720655,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209738387.246, "dur": 2.830, + "args": { + "External id": 720656,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209738397.735, "dur": 37.459, + "args": { + "External id": 720657,"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": 6305209738403.754, "dur": 1.817, + "args": { + "External id": 720658,"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": 6305209738436.468, "dur": 1.980, + "args": { + "External id": 720659,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209738437.592, "dur": 0.773, + "args": { + "External id": 720660,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209738439.401, "dur": 17.070, + "args": { + "External id": 720661,"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": 6305209738441.845, "dur": 0.591, + "args": { + "External id": 720662,"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": 6305209738554.200, "dur": 31.666, + "args": { + "External id": 720663,"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": 6305209738602.574, "dur": 18.878, + "args": { + "External id": 720664,"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": 6305209738630.231, "dur": 48.382, + "args": { + "External id": 720665,"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": 6305209738687.377, "dur": 39.783, + "args": { + "External id": 720666,"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": 6305209738736.775, "dur": 21.909, + "args": { + "External id": 720667,"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": 6305209738767.156, "dur": 33.133, + "args": { + "External id": 720668,"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": 6305209738807.934, "dur": 49.276, + "args": { + "External id": 720669,"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": 6305209738872.336, "dur": 38.840, + "args": { + "External id": 720670,"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": 6305209738931.889, "dur": 29.041, + "args": { + "External id": 720671,"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": 6305209738976.096, "dur": 25.021, + "args": { + "External id": 720672,"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": 6305209739018.403, "dur": 19.205, + "args": { + "External id": 720673,"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": 6305209739088.875, "dur": 21.391, + "args": { + "External id": 720674,"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": 6305209739129.097, "dur": 17.300, + "args": { + "External id": 720675,"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": 6305209739226.464, "dur": 15.352, + "args": { + "External id": 720676,"Record function id": 0, "Ev Idx": 10019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209739229.689, "dur": 11.201, + "args": { + "External id": 720677,"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": 6305209739233.980, "dur": 6.104, + "args": { + "External id": 720678,"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": 6305209739235.768, "dur": 4.184, + "args": { + "External id": 720679,"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": 6305209739245.780, "dur": 5.327, + "args": { + "External id": 720680,"Record function id": 0, "Ev Idx": 10023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209739247.125, "dur": 3.544, + "args": { + "External id": 720681,"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": 6305209739247.990, "dur": 2.101, + "args": { + "External id": 720682,"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": 6305209739249.013, "dur": 0.974, + "args": { + "External id": 720683,"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": 6305209739254.311, "dur": 4.604, + "args": { + "External id": 720684,"Record function id": 0, "Ev Idx": 10027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209739255.662, "dur": 2.854, + "args": { + "External id": 720685,"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": 6305209739256.736, "dur": 1.347, + "args": { + "External id": 720686,"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": 6305209739257.038, "dur": 0.960, + "args": { + "External id": 720687,"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": 6305209739262.230, "dur": 3.488, + "args": { + "External id": 720688,"Record function id": 0, "Ev Idx": 10031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209739263.374, "dur": 1.950, + "args": { + "External id": 720689,"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": 6305209739263.837, "dur": 1.065, + "args": { + "External id": 720690,"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": 6305209739264.130, "dur": 0.708, + "args": { + "External id": 720691,"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": 6305209739268.883, "dur": 4.546, + "args": { + "External id": 720692,"Record function id": 0, "Ev Idx": 10035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209739270.513, "dur": 2.515, + "args": { + "External id": 720693,"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": 6305209739271.020, "dur": 1.431, + "args": { + "External id": 720694,"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": 6305209739271.382, "dur": 1.002, + "args": { + "External id": 720695,"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": 6305209739276.612, "dur": 5.922, + "args": { + "External id": 720696,"Record function id": 0, "Ev Idx": 10039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209739277.830, "dur": 4.303, + "args": { + "External id": 720697,"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": 6305209739278.345, "dur": 3.336, + "args": { + "External id": 720698,"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": 6305209739278.811, "dur": 2.768, + "args": { + "External id": 720699,"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": 6305209739285.829, "dur": 4.055, + "args": { + "External id": 720700,"Record function id": 0, "Ev Idx": 10043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209739287.052, "dur": 2.422, + "args": { + "External id": 720701,"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": 6305209739287.638, "dur": 1.430, + "args": { + "External id": 720702,"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": 6305209739288.244, "dur": 0.727, + "args": { + "External id": 720703,"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": 6305209739292.934, "dur": 3.705, + "args": { + "External id": 720704,"Record function id": 0, "Ev Idx": 10047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209739294.174, "dur": 2.070, + "args": { + "External id": 720705,"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": 6305209739294.792, "dur": 1.012, + "args": { + "External id": 720706,"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": 6305209739295.052, "dur": 0.677, + "args": { + "External id": 720707,"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": 6305209739299.651, "dur": 3.634, + "args": { + "External id": 720708,"Record function id": 0, "Ev Idx": 10051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209739300.598, "dur": 2.279, + "args": { + "External id": 720709,"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": 6305209739301.044, "dur": 1.420, + "args": { + "External id": 720710,"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": 6305209739301.593, "dur": 0.764, + "args": { + "External id": 720711,"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": 6305209739308.008, "dur": 62547.580, + "args": { + "External id": 720712,"Record function id": 0, "Sequence number": 7674640, "Fwd thread id": 1, "Ev Idx": 10055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305209739309.526, "dur": 62536.704, + "args": { + "External id": 720713,"Sequence number": 7674640, "Fwd thread 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": 6305209739309.526, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.10)", "pid": 2338707, "tid": 2379456, + "ts": 6305209739339.154, "dur": 38.703, + "args": { + "External id": 720714,"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": 6305209739384.818, "dur": 60.656, + "args": { + "External id": 720715,"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": 6305209739450.934, "dur": 62387.093, + "args": { + "External id": 720716,"Record function id": 0, "Ev Idx": 10059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305209739559.904, "dur": 7.991, + "args": { + "External id": 720717,"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": 6305209739579.514, "dur": 5.136, + "args": { + "External id": 720718,"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": 6305209739599.048, "dur": 61188.022, + "args": { + "External id": 720719,"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": 6305209739614.524, "dur": 61158.320, + "args": { + "External id": 720720,"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": 6305209739707.245, "dur": 17.494, + "args": { + "External id": 720721,"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": 6305209739744.825, "dur": 60980.613, + "args": { + "External id": 720722,"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": 6305209739747.866, "dur": 60976.510, + "args": { + "External id": 720723,"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": 6305209739752.426, "dur": 8.264, + "args": { + "External id": 720724,"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": 6305209739763.035, "dur": 60956.650, + "args": { + "External id": 720725,"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": 6305209800899.267, "dur": 12.273, + "args": { + "External id": 720726,"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": 6305209800902.914, "dur": 8.257, + "args": { + "External id": 720727,"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": 6305209800942.156, "dur": 468.736, + "args": { + "External id": 720728,"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": 6305209800975.996, "dur": 429.037, + "args": { + "External id": 720729,"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": 6305209800988.290, "dur": 409.810, + "args": { + "External id": 720730,"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": 6305209801445.567, "dur": 2.729, + "args": { + "External id": 720731,"Record function id": 0, "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": 6305209801533.948, "dur": 8.659, + "args": { + "External id": 720732,"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": 6305209801556.064, "dur": 44.630, + "args": { + "External id": 720733,"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": 6305209801611.499, "dur": 1.751, + "args": { + "External id": 720734,"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": 6305209801618.479, "dur": 12.888, + "args": { + "External id": 720735,"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": 6305209801640.128, "dur": 1.002, + "args": { + "External id": 720736,"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": 6305209801645.400, "dur": 10.252, + "args": { + "External id": 720737,"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": 6305209801661.283, "dur": 0.790, + "args": { + "External id": 720738,"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": 6305209801665.995, "dur": 10.625, + "args": { + "External id": 720739,"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": 6305209801680.902, "dur": 0.864, + "args": { + "External id": 720740,"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": 6305209801685.176, "dur": 9.550, + "args": { + "External id": 720741,"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": 6305209801698.706, "dur": 0.913, + "args": { + "External id": 720742,"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": 6305209801703.921, "dur": 10.464, + "args": { + "External id": 720743,"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": 6305209801718.973, "dur": 0.735, + "args": { + "External id": 720744,"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": 6305209801723.830, "dur": 10.018, + "args": { + "External id": 720745,"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": 6305209801738.213, "dur": 0.804, + "args": { + "External id": 720746,"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": 6305209801743.397, "dur": 10.170, + "args": { + "External id": 720747,"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": 6305209801759.653, "dur": 2.921, + "args": { + "External id": 720748,"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": 6305209801765.993, "dur": 10.558, + "args": { + "External id": 720749,"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": 6305209801872.637, "dur": 3007.287, + "args": { + "External id": 720750,"Record function id": 0, "Ev Idx": 10093 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.9)", "pid": 2338707, "tid": 2379456, + "ts": 6305209801893.506, "dur": 1057.085, + "args": { + "External id": 720751,"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": 6305209801912.699, "dur": 364.364, + "args": { + "External id": 720752,"Record function id": 0, "Ev Idx": 10095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6305209801992.675, "dur": 4.393, + "args": { + "External id": 720753,"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": 6305209802000.403, "dur": 0.912, + "args": { + "External id": 720754,"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": 6305209802003.426, "dur": 0.858, + "args": { + "External id": 720755,"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": 6305209802005.791, "dur": 0.857, + "args": { + "External id": 720756,"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": 6305209802008.525, "dur": 0.850, + "args": { + "External id": 720757,"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": 6305209802010.629, "dur": 0.862, + "args": { + "External id": 720758,"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": 6305209802013.008, "dur": 0.719, + "args": { + "External id": 720759,"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": 6305209802017.126, "dur": 4.257, + "args": { + "External id": 720760,"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": 6305209802022.782, "dur": 0.664, + "args": { + "External id": 720761,"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": 6305209802025.283, "dur": 0.742, + "args": { + "External id": 720762,"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": 6305209802043.951, "dur": 198.857, + "args": { + "External id": 720763,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305209802095.914, "dur": 141.814, + "args": { + "External id": 720764,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305209802122.869, "dur": 14.566, + "args": { + "External id": 720765,"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": 6305209802143.187, "dur": 67.495, + "args": { + "External id": 720766,"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": 6305209802146.299, "dur": 63.999, + "args": { + "External id": 720767,"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": 6305209802150.979, "dur": 6.930, + "args": { + "External id": 720768,"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": 6305209802159.416, "dur": 50.165, + "args": { + "External id": 720769,"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": 6305209802358.703, "dur": 584.263, + "args": { + "External id": 720770,"Record function id": 0, "Ev Idx": 10113 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.8)", "pid": 2338707, "tid": 2379456, + "ts": 6305209802374.606, "dur": 554.533, + "args": { + "External id": 720771,"Record function id": 0, "Ev Idx": 10114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305209802432.932, "dur": 4.788, + "args": { + "External id": 720772,"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": 6305209802453.949, "dur": 28.361, + "args": { + "External id": 720773,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209802459.297, "dur": 1.867, + "args": { + "External id": 720774,"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": 6305209802463.036, "dur": 0.523, + "args": { + "External id": 720775,"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": 6305209802465.272, "dur": 2.356, + "args": { + "External id": 720776,"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": 6305209802469.295, "dur": 0.284, + "args": { + "External id": 720777,"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": 6305209802470.546, "dur": 0.724, + "args": { + "External id": 720778,"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": 6305209802472.950, "dur": 0.312, + "args": { + "External id": 720779,"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": 6305209802474.722, "dur": 0.268, + "args": { + "External id": 720780,"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": 6305209802476.051, "dur": 0.501, + "args": { + "External id": 720781,"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": 6305209802478.061, "dur": 0.378, + "args": { + "External id": 720782,"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": 6305209802492.763, "dur": 59.584, + "args": { + "External id": 720783,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305209802586.621, "dur": 112.296, + "args": { + "External id": 720784,"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": 6305209802597.910, "dur": 3.980, + "args": { + "External id": 720785,"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": 6305209802607.260, "dur": 12.770, + "args": { + "External id": 720786,"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": 6305209802611.582, "dur": 8.039, + "args": { + "External id": 720787,"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": 6305209802615.246, "dur": 2.974, + "args": { + "External id": 720788,"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": 6305209802626.765, "dur": 24.385, + "args": { + "External id": 720789,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209802629.152, "dur": 0.704, + "args": { + "External id": 720790,"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": 6305209802631.533, "dur": 0.544, + "args": { + "External id": 720791,"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": 6305209802633.842, "dur": 0.653, + "args": { + "External id": 720792,"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": 6305209802636.162, "dur": 0.404, + "args": { + "External id": 720793,"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": 6305209802637.632, "dur": 0.641, + "args": { + "External id": 720794,"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": 6305209802640.177, "dur": 0.380, + "args": { + "External id": 720795,"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": 6305209802642.484, "dur": 0.270, + "args": { + "External id": 720796,"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": 6305209802643.799, "dur": 2.620, + "args": { + "External id": 720797,"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": 6305209802647.880, "dur": 0.501, + "args": { + "External id": 720798,"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": 6305209802661.438, "dur": 30.146, + "args": { + "External id": 720799,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305209802743.452, "dur": 114.811, + "args": { + "External id": 720800,"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": 6305209802766.788, "dur": 87.919, + "args": { + "External id": 720801,"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": 6305209802778.128, "dur": 71.249, + "args": { + "External id": 720802,"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": 6305209802875.849, "dur": 1.775, + "args": { + "External id": 720803,"Record function id": 0, "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": 6305209802957.886, "dur": 1901.411, + "args": { + "External id": 720804,"Sequence number": 7674639, "Fwd thread 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": 6305209802957.886, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6305209803119.925, "dur": 120.063, + "args": { + "External id": 720805,"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": 6305209803289.363, "dur": 46.351, + "args": { + "External id": 720806,"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": 6305209803354.701, "dur": 52.031, + "args": { + "External id": 720807,"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": 6305209803416.599, "dur": 31.595, + "args": { + "External id": 720808,"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": 6305209803454.548, "dur": 33.572, + "args": { + "External id": 720809,"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": 6305209803494.411, "dur": 41.821, + "args": { + "External id": 720810,"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": 6305209803549.194, "dur": 33.504, + "args": { + "External id": 720811,"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": 6305209803610.028, "dur": 24.304, + "args": { + "External id": 720812,"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": 6305209803652.157, "dur": 28.247, + "args": { + "External id": 720813,"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": 6305209803702.867, "dur": 19.424, + "args": { + "External id": 720814,"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": 6305209803736.446, "dur": 15.661, + "args": { + "External id": 720815,"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": 6305209803763.551, "dur": 41.071, + "args": { + "External id": 720816,"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": 6305209803808.813, "dur": 35.258, + "args": { + "External id": 720817,"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": 6305209803879.669, "dur": 327.360, + "args": { + "External id": 720818,"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": 6305209803966.371, "dur": 6.229, + "args": { + "External id": 720819,"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": 6305209803974.381, "dur": 3.756, + "args": { + "External id": 720820,"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": 6305209803979.719, "dur": 8.484, + "args": { + "External id": 720821,"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": 6305209803989.101, "dur": 2.796, + "args": { + "External id": 720822,"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": 6305209804037.630, "dur": 5.453, + "args": { + "External id": 720823,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209804039.922, "dur": 2.947, + "args": { + "External id": 720824,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209804045.076, "dur": 88.079, + "args": { + "External id": 720825,"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": 6305209804050.378, "dur": 53.460, + "args": { + "External id": 720826,"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": 6305209804136.635, "dur": 2.847, + "args": { + "External id": 720827,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209804138.214, "dur": 1.154, + "args": { + "External id": 720828,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209804140.608, "dur": 15.840, + "args": { + "External id": 720829,"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": 6305209804143.284, "dur": 0.864, + "args": { + "External id": 720830,"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": 6305209804242.861, "dur": 30.389, + "args": { + "External id": 720831,"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": 6305209804290.987, "dur": 17.822, + "args": { + "External id": 720832,"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": 6305209804317.747, "dur": 51.720, + "args": { + "External id": 720833,"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": 6305209804377.696, "dur": 41.273, + "args": { + "External id": 720834,"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": 6305209804427.955, "dur": 23.998, + "args": { + "External id": 720835,"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": 6305209804460.325, "dur": 31.984, + "args": { + "External id": 720836,"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": 6305209804500.527, "dur": 68.037, + "args": { + "External id": 720837,"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": 6305209804590.367, "dur": 40.755, + "args": { + "External id": 720838,"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": 6305209804657.803, "dur": 27.798, + "args": { + "External id": 720839,"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": 6305209804702.444, "dur": 29.418, + "args": { + "External id": 720840,"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": 6305209804745.800, "dur": 19.367, + "args": { + "External id": 720841,"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": 6305209804779.377, "dur": 15.905, + "args": { + "External id": 720842,"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": 6305209804807.311, "dur": 17.520, + "args": { + "External id": 720843,"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": 6305209804903.413, "dur": 15.828, + "args": { + "External id": 720844,"Record function id": 0, "Ev Idx": 10187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209804906.755, "dur": 11.499, + "args": { + "External id": 720845,"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": 6305209804910.824, "dur": 6.542, + "args": { + "External id": 720846,"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": 6305209804913.039, "dur": 4.201, + "args": { + "External id": 720847,"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": 6305209804923.121, "dur": 4.919, + "args": { + "External id": 720848,"Record function id": 0, "Ev Idx": 10191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209804924.340, "dur": 3.271, + "args": { + "External id": 720849,"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": 6305209804925.044, "dur": 2.057, + "args": { + "External id": 720850,"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": 6305209804925.924, "dur": 1.114, + "args": { + "External id": 720851,"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": 6305209804931.461, "dur": 4.255, + "args": { + "External id": 720852,"Record function id": 0, "Ev Idx": 10195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209804932.631, "dur": 2.656, + "args": { + "External id": 720853,"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": 6305209804933.269, "dur": 1.509, + "args": { + "External id": 720854,"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": 6305209804933.638, "dur": 1.070, + "args": { + "External id": 720855,"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": 6305209804938.987, "dur": 4.342, + "args": { + "External id": 720856,"Record function id": 0, "Ev Idx": 10199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209804940.249, "dur": 2.686, + "args": { + "External id": 720857,"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": 6305209804940.722, "dur": 1.796, + "args": { + "External id": 720858,"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": 6305209804941.678, "dur": 0.770, + "args": { + "External id": 720859,"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": 6305209804946.476, "dur": 3.646, + "args": { + "External id": 720860,"Record function id": 0, "Ev Idx": 10203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209804947.742, "dur": 1.987, + "args": { + "External id": 720861,"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": 6305209804948.229, "dur": 0.949, + "args": { + "External id": 720862,"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": 6305209804948.542, "dur": 0.563, + "args": { + "External id": 720863,"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": 6305209804953.363, "dur": 7.544, + "args": { + "External id": 720864,"Record function id": 0, "Ev Idx": 10207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209804954.587, "dur": 2.431, + "args": { + "External id": 720865,"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": 6305209804955.124, "dur": 1.463, + "args": { + "External id": 720866,"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": 6305209804955.661, "dur": 0.823, + "args": { + "External id": 720867,"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": 6305209804964.460, "dur": 5.751, + "args": { + "External id": 720868,"Record function id": 0, "Ev Idx": 10211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209804965.409, "dur": 4.352, + "args": { + "External id": 720869,"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": 6305209804965.873, "dur": 3.483, + "args": { + "External id": 720870,"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": 6305209804966.376, "dur": 2.910, + "args": { + "External id": 720871,"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": 6305209804973.372, "dur": 3.706, + "args": { + "External id": 720872,"Record function id": 0, "Ev Idx": 10215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209804974.468, "dur": 2.196, + "args": { + "External id": 720873,"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": 6305209804974.952, "dur": 1.246, + "args": { + "External id": 720874,"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": 6305209804975.207, "dur": 0.893, + "args": { + "External id": 720875,"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": 6305209804980.146, "dur": 3.519, + "args": { + "External id": 720876,"Record function id": 0, "Ev Idx": 10219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209804981.103, "dur": 2.162, + "args": { + "External id": 720877,"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": 6305209804981.576, "dur": 1.289, + "args": { + "External id": 720878,"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": 6305209804982.051, "dur": 0.703, + "args": { + "External id": 720879,"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": 6305209804987.455, "dur": 63129.124, + "args": { + "External id": 720880,"Record function id": 0, "Sequence number": 7674638, "Fwd thread id": 1, "Ev Idx": 10223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305209804988.705, "dur": 63117.398, + "args": { + "External id": 720881,"Sequence number": 7674638, "Fwd thread 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": 6305209804988.705, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.9)", "pid": 2338707, "tid": 2379456, + "ts": 6305209805021.762, "dur": 72.361, + "args": { + "External id": 720882,"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": 6305209805104.085, "dur": 64.160, + "args": { + "External id": 720883,"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": 6305209805174.977, "dur": 62920.892, + "args": { + "External id": 720884,"Record function id": 0, "Ev Idx": 10227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305209805267.784, "dur": 7.262, + "args": { + "External id": 720885,"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": 6305209805285.796, "dur": 5.107, + "args": { + "External id": 720886,"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": 6305209805305.324, "dur": 61743.224, + "args": { + "External id": 720887,"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": 6305209805319.356, "dur": 61715.458, + "args": { + "External id": 720888,"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": 6305209805412.498, "dur": 18.145, + "args": { + "External id": 720889,"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": 6305209805453.399, "dur": 61532.614, + "args": { + "External id": 720890,"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": 6305209805456.117, "dur": 61528.761, + "args": { + "External id": 720891,"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": 6305209805460.826, "dur": 8.627, + "args": { + "External id": 720892,"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": 6305209805471.706, "dur": 61507.733, + "args": { + "External id": 720893,"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": 6305209867187.338, "dur": 12.877, + "args": { + "External id": 720894,"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": 6305209867190.952, "dur": 8.632, + "args": { + "External id": 720895,"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": 6305209867231.630, "dur": 436.650, + "args": { + "External id": 720896,"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": 6305209867311.062, "dur": 351.559, + "args": { + "External id": 720897,"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": 6305209867324.473, "dur": 331.704, + "args": { + "External id": 720898,"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": 6305209867692.100, "dur": 2.527, + "args": { + "External id": 720899,"Record function id": 0, "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": 6305209867759.655, "dur": 7.267, + "args": { + "External id": 720900,"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": 6305209867779.948, "dur": 38.887, + "args": { + "External id": 720901,"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": 6305209867829.869, "dur": 3.557, + "args": { + "External id": 720902,"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": 6305209867838.704, "dur": 17.514, + "args": { + "External id": 720903,"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": 6305209867861.729, "dur": 0.916, + "args": { + "External id": 720904,"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": 6305209867867.442, "dur": 11.358, + "args": { + "External id": 720905,"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": 6305209867883.888, "dur": 0.848, + "args": { + "External id": 720906,"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": 6305209867888.302, "dur": 12.967, + "args": { + "External id": 720907,"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": 6305209867905.634, "dur": 0.798, + "args": { + "External id": 720908,"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": 6305209867909.556, "dur": 10.311, + "args": { + "External id": 720909,"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": 6305209867924.421, "dur": 1.513, + "args": { + "External id": 720910,"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": 6305209867929.991, "dur": 10.871, + "args": { + "External id": 720911,"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": 6305209867944.912, "dur": 1.197, + "args": { + "External id": 720912,"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": 6305209867949.905, "dur": 10.786, + "args": { + "External id": 720913,"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": 6305209867966.923, "dur": 1.163, + "args": { + "External id": 720914,"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": 6305209867971.587, "dur": 11.476, + "args": { + "External id": 720915,"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": 6305209867987.489, "dur": 1.053, + "args": { + "External id": 720916,"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": 6305209867992.143, "dur": 10.386, + "args": { + "External id": 720917,"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": 6305209868134.629, "dur": 2993.071, + "args": { + "External id": 720918,"Record function id": 0, "Ev Idx": 10261 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.8)", "pid": 2338707, "tid": 2379456, + "ts": 6305209868156.577, "dur": 1104.666, + "args": { + "External id": 720919,"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": 6305209868173.602, "dur": 359.945, + "args": { + "External id": 720920,"Record function id": 0, "Ev Idx": 10263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6305209868258.438, "dur": 6.773, + "args": { + "External id": 720921,"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": 6305209868269.488, "dur": 1.145, + "args": { + "External id": 720922,"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": 6305209868272.416, "dur": 0.684, + "args": { + "External id": 720923,"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": 6305209868275.627, "dur": 0.901, + "args": { + "External id": 720924,"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": 6305209868278.144, "dur": 0.884, + "args": { + "External id": 720925,"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": 6305209868280.308, "dur": 0.823, + "args": { + "External id": 720926,"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": 6305209868282.938, "dur": 0.649, + "args": { + "External id": 720927,"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": 6305209868285.193, "dur": 1.999, + "args": { + "External id": 720928,"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": 6305209868290.157, "dur": 2.739, + "args": { + "External id": 720929,"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": 6305209868294.567, "dur": 0.671, + "args": { + "External id": 720930,"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": 6305209868316.756, "dur": 166.940, + "args": { + "External id": 720931,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305209868332.937, "dur": 146.223, + "args": { + "External id": 720932,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305209868358.601, "dur": 17.760, + "args": { + "External id": 720933,"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": 6305209868379.900, "dur": 70.177, + "args": { + "External id": 720934,"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": 6305209868382.788, "dur": 66.992, + "args": { + "External id": 720935,"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": 6305209868387.434, "dur": 6.325, + "args": { + "External id": 720936,"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": 6305209868397.396, "dur": 51.685, + "args": { + "External id": 720937,"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": 6305209868619.645, "dur": 633.684, + "args": { + "External id": 720938,"Record function id": 0, "Ev Idx": 10281 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.7)", "pid": 2338707, "tid": 2379456, + "ts": 6305209868638.745, "dur": 601.718, + "args": { + "External id": 720939,"Record function id": 0, "Ev Idx": 10282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305209868701.737, "dur": 6.221, + "args": { + "External id": 720940,"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": 6305209868724.026, "dur": 29.934, + "args": { + "External id": 720941,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209868729.189, "dur": 1.710, + "args": { + "External id": 720942,"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": 6305209868733.063, "dur": 0.530, + "args": { + "External id": 720943,"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": 6305209868735.383, "dur": 0.291, + "args": { + "External id": 720944,"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": 6305209868736.929, "dur": 2.883, + "args": { + "External id": 720945,"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": 6305209868741.606, "dur": 0.467, + "args": { + "External id": 720946,"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": 6305209868743.797, "dur": 0.358, + "args": { + "External id": 720947,"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": 6305209868745.619, "dur": 0.607, + "args": { + "External id": 720948,"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": 6305209868748.000, "dur": 0.345, + "args": { + "External id": 720949,"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": 6305209868749.807, "dur": 0.339, + "args": { + "External id": 720950,"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": 6305209868771.002, "dur": 47.030, + "args": { + "External id": 720951,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305209868849.092, "dur": 108.213, + "args": { + "External id": 720952,"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": 6305209868859.109, "dur": 3.391, + "args": { + "External id": 720953,"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": 6305209868867.663, "dur": 10.409, + "args": { + "External id": 720954,"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": 6305209868872.147, "dur": 5.537, + "args": { + "External id": 720955,"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": 6305209868875.776, "dur": 0.614, + "args": { + "External id": 720956,"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": 6305209868884.656, "dur": 24.324, + "args": { + "External id": 720957,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209868886.209, "dur": 2.440, + "args": { + "External id": 720958,"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": 6305209868890.467, "dur": 0.513, + "args": { + "External id": 720959,"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": 6305209868892.472, "dur": 0.584, + "args": { + "External id": 720960,"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": 6305209868894.745, "dur": 0.515, + "args": { + "External id": 720961,"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": 6305209868896.836, "dur": 0.447, + "args": { + "External id": 720962,"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": 6305209868898.318, "dur": 0.354, + "args": { + "External id": 720963,"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": 6305209868900.192, "dur": 0.364, + "args": { + "External id": 720964,"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": 6305209868902.102, "dur": 0.265, + "args": { + "External id": 720965,"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": 6305209868903.419, "dur": 2.867, + "args": { + "External id": 720966,"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": 6305209868919.572, "dur": 30.853, + "args": { + "External id": 720967,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305209869002.229, "dur": 157.920, + "args": { + "External id": 720968,"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": 6305209869029.577, "dur": 126.383, + "args": { + "External id": 720969,"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": 6305209869039.300, "dur": 111.796, + "args": { + "External id": 720970,"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": 6305209869181.550, "dur": 2.047, + "args": { + "External id": 720971,"Record function id": 0, "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": 6305209869268.407, "dur": 1836.399, + "args": { + "External id": 720972,"Sequence number": 7674637, "Fwd thread 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": 6305209869268.407, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6305209869382.599, "dur": 114.760, + "args": { + "External id": 720973,"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": 6305209869560.356, "dur": 40.443, + "args": { + "External id": 720974,"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": 6305209869621.659, "dur": 56.602, + "args": { + "External id": 720975,"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": 6305209869688.023, "dur": 32.441, + "args": { + "External id": 720976,"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": 6305209869726.995, "dur": 35.695, + "args": { + "External id": 720977,"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": 6305209869769.007, "dur": 27.989, + "args": { + "External id": 720978,"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": 6305209869805.459, "dur": 30.734, + "args": { + "External id": 720979,"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": 6305209869862.782, "dur": 24.224, + "args": { + "External id": 720980,"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": 6305209869906.735, "dur": 33.596, + "args": { + "External id": 720981,"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": 6305209869962.201, "dur": 20.810, + "args": { + "External id": 720982,"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": 6305209870000.512, "dur": 17.423, + "args": { + "External id": 720983,"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": 6305209870029.160, "dur": 76.427, + "args": { + "External id": 720984,"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": 6305209870112.399, "dur": 38.876, + "args": { + "External id": 720985,"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": 6305209870186.313, "dur": 254.118, + "args": { + "External id": 720986,"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": 6305209870269.013, "dur": 6.479, + "args": { + "External id": 720987,"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": 6305209870277.769, "dur": 3.174, + "args": { + "External id": 720988,"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": 6305209870282.520, "dur": 2.425, + "args": { + "External id": 720989,"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": 6305209870286.254, "dur": 4.389, + "args": { + "External id": 720990,"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": 6305209870338.827, "dur": 5.905, + "args": { + "External id": 720991,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209870341.477, "dur": 3.111, + "args": { + "External id": 720992,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209870346.299, "dur": 31.653, + "args": { + "External id": 720993,"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": 6305209870352.090, "dur": 1.860, + "args": { + "External id": 720994,"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": 6305209870379.381, "dur": 2.174, + "args": { + "External id": 720995,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209870380.726, "dur": 0.761, + "args": { + "External id": 720996,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209870382.675, "dur": 14.938, + "args": { + "External id": 720997,"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": 6305209870385.040, "dur": 0.555, + "args": { + "External id": 720998,"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": 6305209870476.936, "dur": 44.812, + "args": { + "External id": 720999,"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": 6305209870542.685, "dur": 19.273, + "args": { + "External id": 721000,"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": 6305209870571.610, "dur": 50.202, + "args": { + "External id": 721001,"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": 6305209870629.119, "dur": 41.348, + "args": { + "External id": 721002,"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": 6305209870680.478, "dur": 24.245, + "args": { + "External id": 721003,"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": 6305209870713.364, "dur": 33.326, + "args": { + "External id": 721004,"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": 6305209870754.841, "dur": 29.811, + "args": { + "External id": 721005,"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": 6305209870791.646, "dur": 30.892, + "args": { + "External id": 721006,"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": 6305209870855.165, "dur": 32.612, + "args": { + "External id": 721007,"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": 6305209870905.857, "dur": 24.524, + "args": { + "External id": 721008,"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": 6305209870944.572, "dur": 17.534, + "args": { + "External id": 721009,"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": 6305209870980.763, "dur": 13.936, + "args": { + "External id": 721010,"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": 6305209871013.710, "dur": 15.907, + "args": { + "External id": 721011,"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": 6305209871155.508, "dur": 16.036, + "args": { + "External id": 721012,"Record function id": 0, "Ev Idx": 10355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209871158.726, "dur": 11.820, + "args": { + "External id": 721013,"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": 6305209871163.214, "dur": 6.302, + "args": { + "External id": 721014,"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": 6305209871164.982, "dur": 4.378, + "args": { + "External id": 721015,"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": 6305209871175.549, "dur": 5.624, + "args": { + "External id": 721016,"Record function id": 0, "Ev Idx": 10359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209871177.086, "dur": 3.624, + "args": { + "External id": 721017,"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": 6305209871178.089, "dur": 2.092, + "args": { + "External id": 721018,"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": 6305209871179.133, "dur": 0.942, + "args": { + "External id": 721019,"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": 6305209871184.592, "dur": 4.454, + "args": { + "External id": 721020,"Record function id": 0, "Ev Idx": 10363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209871185.805, "dur": 2.835, + "args": { + "External id": 721021,"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": 6305209871186.387, "dur": 1.788, + "args": { + "External id": 721022,"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": 6305209871187.091, "dur": 1.019, + "args": { + "External id": 721023,"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": 6305209871192.559, "dur": 3.731, + "args": { + "External id": 721024,"Record function id": 0, "Ev Idx": 10367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209871193.750, "dur": 2.132, + "args": { + "External id": 721025,"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": 6305209871194.415, "dur": 1.079, + "args": { + "External id": 721026,"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": 6305209871194.745, "dur": 0.683, + "args": { + "External id": 721027,"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": 6305209871199.400, "dur": 3.416, + "args": { + "External id": 721028,"Record function id": 0, "Ev Idx": 10371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209871200.414, "dur": 1.994, + "args": { + "External id": 721029,"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": 6305209871200.858, "dur": 1.180, + "args": { + "External id": 721030,"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": 6305209871201.329, "dur": 0.641, + "args": { + "External id": 721031,"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": 6305209871205.940, "dur": 6.315, + "args": { + "External id": 721032,"Record function id": 0, "Ev Idx": 10375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209871206.940, "dur": 4.905, + "args": { + "External id": 721033,"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": 6305209871207.673, "dur": 3.720, + "args": { + "External id": 721034,"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": 6305209871208.310, "dur": 2.996, + "args": { + "External id": 721035,"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": 6305209871215.622, "dur": 4.193, + "args": { + "External id": 721036,"Record function id": 0, "Ev Idx": 10379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209871216.695, "dur": 2.718, + "args": { + "External id": 721037,"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": 6305209871217.466, "dur": 1.580, + "args": { + "External id": 721038,"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": 6305209871217.995, "dur": 0.985, + "args": { + "External id": 721039,"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": 6305209871222.900, "dur": 3.860, + "args": { + "External id": 721040,"Record function id": 0, "Ev Idx": 10383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209871224.070, "dur": 2.284, + "args": { + "External id": 721041,"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": 6305209871224.846, "dur": 1.117, + "args": { + "External id": 721042,"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": 6305209871225.126, "dur": 0.749, + "args": { + "External id": 721043,"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": 6305209871230.297, "dur": 3.349, + "args": { + "External id": 721044,"Record function id": 0, "Ev Idx": 10387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209871231.217, "dur": 2.006, + "args": { + "External id": 721045,"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": 6305209871231.633, "dur": 1.213, + "args": { + "External id": 721046,"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": 6305209871232.100, "dur": 0.635, + "args": { + "External id": 721047,"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": 6305209871237.988, "dur": 62991.271, + "args": { + "External id": 721048,"Record function id": 0, "Sequence number": 7674636, "Fwd thread id": 1, "Ev Idx": 10391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305209871239.467, "dur": 62979.148, + "args": { + "External id": 721049,"Sequence number": 7674636, "Fwd thread 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": 6305209871239.467, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.8)", "pid": 2338707, "tid": 2379456, + "ts": 6305209871270.173, "dur": 39.857, + "args": { + "External id": 721050,"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": 6305209871317.948, "dur": 61.348, + "args": { + "External id": 721051,"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": 6305209871386.032, "dur": 62824.653, + "args": { + "External id": 721052,"Record function id": 0, "Ev Idx": 10395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305209871475.829, "dur": 10.489, + "args": { + "External id": 721053,"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": 6305209871496.640, "dur": 4.760, + "args": { + "External id": 721054,"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": 6305209871532.799, "dur": 61657.549, + "args": { + "External id": 721055,"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": 6305209871551.348, "dur": 61623.875, + "args": { + "External id": 721056,"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": 6305209871647.357, "dur": 23.319, + "args": { + "External id": 721057,"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": 6305209871691.386, "dur": 61431.906, + "args": { + "External id": 721058,"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": 6305209871693.946, "dur": 61428.070, + "args": { + "External id": 721059,"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": 6305209871698.368, "dur": 10.262, + "args": { + "External id": 721060,"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": 6305209871710.829, "dur": 61405.094, + "args": { + "External id": 721061,"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": 6305209933308.031, "dur": 13.453, + "args": { + "External id": 721062,"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": 6305209933311.902, "dur": 9.194, + "args": { + "External id": 721063,"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": 6305209933355.468, "dur": 403.688, + "args": { + "External id": 721064,"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": 6305209933388.119, "dur": 365.281, + "args": { + "External id": 721065,"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": 6305209933400.809, "dur": 346.553, + "args": { + "External id": 721066,"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": 6305209933782.766, "dur": 2.361, + "args": { + "External id": 721067,"Record function id": 0, "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": 6305209933849.339, "dur": 6.974, + "args": { + "External id": 721068,"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": 6305209933870.350, "dur": 37.309, + "args": { + "External id": 721069,"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": 6305209933918.408, "dur": 1.658, + "args": { + "External id": 721070,"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": 6305209933925.874, "dur": 14.556, + "args": { + "External id": 721071,"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": 6305209933946.558, "dur": 3.773, + "args": { + "External id": 721072,"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": 6305209933954.492, "dur": 11.574, + "args": { + "External id": 721073,"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": 6305209933971.532, "dur": 0.938, + "args": { + "External id": 721074,"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": 6305209933976.419, "dur": 13.262, + "args": { + "External id": 721075,"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": 6305209933994.510, "dur": 0.805, + "args": { + "External id": 721076,"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": 6305209933999.637, "dur": 11.291, + "args": { + "External id": 721077,"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": 6305209934014.760, "dur": 1.198, + "args": { + "External id": 721078,"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": 6305209934019.607, "dur": 11.810, + "args": { + "External id": 721079,"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": 6305209934035.515, "dur": 1.247, + "args": { + "External id": 721080,"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": 6305209934040.529, "dur": 10.686, + "args": { + "External id": 721081,"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": 6305209934105.271, "dur": 1.894, + "args": { + "External id": 721082,"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": 6305209934112.313, "dur": 13.505, + "args": { + "External id": 721083,"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": 6305209934130.358, "dur": 1.164, + "args": { + "External id": 721084,"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": 6305209934135.958, "dur": 10.170, + "args": { + "External id": 721085,"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": 6305209934246.057, "dur": 3095.143, + "args": { + "External id": 721086,"Record function id": 0, "Ev Idx": 10429 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.7)", "pid": 2338707, "tid": 2379456, + "ts": 6305209934268.846, "dur": 1084.796, + "args": { + "External id": 721087,"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": 6305209934286.962, "dur": 360.476, + "args": { + "External id": 721088,"Record function id": 0, "Ev Idx": 10431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6305209934370.375, "dur": 4.420, + "args": { + "External id": 721089,"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": 6305209934378.692, "dur": 3.316, + "args": { + "External id": 721090,"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": 6305209934384.152, "dur": 0.950, + "args": { + "External id": 721091,"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": 6305209934386.620, "dur": 0.888, + "args": { + "External id": 721092,"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": 6305209934389.386, "dur": 0.826, + "args": { + "External id": 721093,"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": 6305209934391.672, "dur": 0.682, + "args": { + "External id": 721094,"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": 6305209934394.106, "dur": 0.654, + "args": { + "External id": 721095,"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": 6305209934396.512, "dur": 2.474, + "args": { + "External id": 721096,"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": 6305209934400.485, "dur": 0.739, + "args": { + "External id": 721097,"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": 6305209934404.859, "dur": 3.129, + "args": { + "External id": 721098,"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": 6305209934425.472, "dur": 188.327, + "args": { + "External id": 721099,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305209934445.498, "dur": 163.324, + "args": { + "External id": 721100,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305209934472.512, "dur": 14.030, + "args": { + "External id": 721101,"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": 6305209934490.523, "dur": 88.328, + "args": { + "External id": 721102,"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": 6305209934493.464, "dur": 85.031, + "args": { + "External id": 721103,"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": 6305209934497.965, "dur": 24.934, + "args": { + "External id": 721104,"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": 6305209934525.908, "dur": 51.964, + "args": { + "External id": 721105,"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": 6305209934730.729, "dur": 615.187, + "args": { + "External id": 721106,"Record function id": 0, "Ev Idx": 10449 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.6)", "pid": 2338707, "tid": 2379456, + "ts": 6305209934749.020, "dur": 581.064, + "args": { + "External id": 721107,"Record function id": 0, "Ev Idx": 10450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305209934809.295, "dur": 5.565, + "args": { + "External id": 721108,"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": 6305209934830.088, "dur": 29.572, + "args": { + "External id": 721109,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209934835.398, "dur": 1.526, + "args": { + "External id": 721110,"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": 6305209934839.310, "dur": 0.930, + "args": { + "External id": 721111,"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": 6305209934841.697, "dur": 0.656, + "args": { + "External id": 721112,"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": 6305209934844.392, "dur": 0.741, + "args": { + "External id": 721113,"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": 6305209934846.636, "dur": 2.270, + "args": { + "External id": 721114,"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": 6305209934850.031, "dur": 0.446, + "args": { + "External id": 721115,"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": 6305209934851.885, "dur": 0.375, + "args": { + "External id": 721116,"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": 6305209934853.562, "dur": 0.473, + "args": { + "External id": 721117,"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": 6305209934855.302, "dur": 0.458, + "args": { + "External id": 721118,"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": 6305209934870.472, "dur": 43.315, + "args": { + "External id": 721119,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305209934943.980, "dur": 105.231, + "args": { + "External id": 721120,"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": 6305209934954.333, "dur": 2.875, + "args": { + "External id": 721121,"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": 6305209934962.507, "dur": 10.291, + "args": { + "External id": 721122,"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": 6305209934966.962, "dur": 5.445, + "args": { + "External id": 721123,"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": 6305209934970.747, "dur": 0.457, + "args": { + "External id": 721124,"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": 6305209934979.287, "dur": 21.911, + "args": { + "External id": 721125,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209934980.894, "dur": 0.462, + "args": { + "External id": 721126,"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": 6305209934982.547, "dur": 2.321, + "args": { + "External id": 721127,"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": 6305209934986.845, "dur": 0.384, + "args": { + "External id": 721128,"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": 6305209934988.887, "dur": 0.384, + "args": { + "External id": 721129,"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": 6305209934990.434, "dur": 0.493, + "args": { + "External id": 721130,"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": 6305209934992.844, "dur": 0.379, + "args": { + "External id": 721131,"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": 6305209934994.900, "dur": 0.367, + "args": { + "External id": 721132,"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": 6305209934996.192, "dur": 0.450, + "args": { + "External id": 721133,"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": 6305209934998.096, "dur": 0.454, + "args": { + "External id": 721134,"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": 6305209935010.854, "dur": 29.233, + "args": { + "External id": 721135,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305209935134.608, "dur": 119.765, + "args": { + "External id": 721136,"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": 6305209935160.753, "dur": 89.832, + "args": { + "External id": 721137,"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": 6305209935170.901, "dur": 74.967, + "args": { + "External id": 721138,"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": 6305209935271.302, "dur": 1.879, + "args": { + "External id": 721139,"Record function id": 0, "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": 6305209935362.023, "dur": 1956.552, + "args": { + "External id": 721140,"Sequence number": 7674635, "Fwd thread 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": 6305209935362.023, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6305209935473.415, "dur": 129.293, + "args": { + "External id": 721141,"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": 6305209935649.316, "dur": 46.850, + "args": { + "External id": 721142,"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": 6305209935718.936, "dur": 53.600, + "args": { + "External id": 721143,"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": 6305209935782.254, "dur": 33.417, + "args": { + "External id": 721144,"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": 6305209935821.710, "dur": 33.180, + "args": { + "External id": 721145,"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": 6305209935860.881, "dur": 28.252, + "args": { + "External id": 721146,"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": 6305209935897.821, "dur": 30.179, + "args": { + "External id": 721147,"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": 6305209935955.824, "dur": 24.772, + "args": { + "External id": 721148,"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": 6305209936000.099, "dur": 28.937, + "args": { + "External id": 721149,"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": 6305209936090.869, "dur": 28.012, + "args": { + "External id": 721150,"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": 6305209936137.613, "dur": 16.818, + "args": { + "External id": 721151,"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": 6305209936170.553, "dur": 45.318, + "args": { + "External id": 721152,"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": 6305209936220.430, "dur": 42.561, + "args": { + "External id": 721153,"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": 6305209936301.758, "dur": 304.504, + "args": { + "External id": 721154,"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": 6305209936401.392, "dur": 7.539, + "args": { + "External id": 721155,"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": 6305209936411.185, "dur": 3.066, + "args": { + "External id": 721156,"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": 6305209936415.914, "dur": 2.163, + "args": { + "External id": 721157,"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": 6305209936419.427, "dur": 4.378, + "args": { + "External id": 721158,"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": 6305209936473.338, "dur": 5.530, + "args": { + "External id": 721159,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209936475.832, "dur": 2.882, + "args": { + "External id": 721160,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209936480.732, "dur": 54.898, + "args": { + "External id": 721161,"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": 6305209936487.012, "dur": 1.760, + "args": { + "External id": 721162,"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": 6305209936538.664, "dur": 2.512, + "args": { + "External id": 721163,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209936539.945, "dur": 1.121, + "args": { + "External id": 721164,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209936542.469, "dur": 17.560, + "args": { + "External id": 721165,"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": 6305209936544.910, "dur": 0.764, + "args": { + "External id": 721166,"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": 6305209936646.953, "dur": 34.437, + "args": { + "External id": 721167,"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": 6305209936699.675, "dur": 19.070, + "args": { + "External id": 721168,"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": 6305209936728.073, "dur": 66.009, + "args": { + "External id": 721169,"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": 6305209936801.428, "dur": 64.879, + "args": { + "External id": 721170,"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": 6305209936882.779, "dur": 29.775, + "args": { + "External id": 721171,"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": 6305209936921.376, "dur": 33.748, + "args": { + "External id": 721172,"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": 6305209936965.886, "dur": 29.495, + "args": { + "External id": 721173,"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": 6305209937002.676, "dur": 34.060, + "args": { + "External id": 721174,"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": 6305209937097.358, "dur": 32.536, + "args": { + "External id": 721175,"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": 6305209937151.687, "dur": 27.565, + "args": { + "External id": 721176,"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": 6305209937193.626, "dur": 23.857, + "args": { + "External id": 721177,"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": 6305209937235.173, "dur": 16.863, + "args": { + "External id": 721178,"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": 6305209937264.860, "dur": 16.153, + "args": { + "External id": 721179,"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": 6305209937369.004, "dur": 16.064, + "args": { + "External id": 721180,"Record function id": 0, "Ev Idx": 10523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209937372.621, "dur": 11.434, + "args": { + "External id": 721181,"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": 6305209937376.889, "dur": 6.227, + "args": { + "External id": 721182,"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": 6305209937378.831, "dur": 4.174, + "args": { + "External id": 721183,"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": 6305209937388.888, "dur": 6.253, + "args": { + "External id": 721184,"Record function id": 0, "Ev Idx": 10527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209937390.463, "dur": 4.206, + "args": { + "External id": 721185,"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": 6305209937391.579, "dur": 2.465, + "args": { + "External id": 721186,"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": 6305209937392.876, "dur": 1.098, + "args": { + "External id": 721187,"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": 6305209937398.473, "dur": 4.996, + "args": { + "External id": 721188,"Record function id": 0, "Ev Idx": 10531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209937399.905, "dur": 3.150, + "args": { + "External id": 721189,"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": 6305209937400.799, "dur": 1.793, + "args": { + "External id": 721190,"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": 6305209937401.491, "dur": 1.014, + "args": { + "External id": 721191,"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": 6305209937406.802, "dur": 3.695, + "args": { + "External id": 721192,"Record function id": 0, "Ev Idx": 10535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209937407.954, "dur": 2.141, + "args": { + "External id": 721193,"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": 6305209937408.583, "dur": 1.106, + "args": { + "External id": 721194,"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": 6305209937408.871, "dur": 0.731, + "args": { + "External id": 721195,"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": 6305209937413.532, "dur": 3.736, + "args": { + "External id": 721196,"Record function id": 0, "Ev Idx": 10539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209937414.821, "dur": 2.049, + "args": { + "External id": 721197,"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": 6305209937415.290, "dur": 1.170, + "args": { + "External id": 721198,"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": 6305209937415.781, "dur": 0.612, + "args": { + "External id": 721199,"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": 6305209937420.447, "dur": 6.694, + "args": { + "External id": 721200,"Record function id": 0, "Ev Idx": 10543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209937421.755, "dur": 4.961, + "args": { + "External id": 721201,"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": 6305209937422.358, "dur": 3.890, + "args": { + "External id": 721202,"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": 6305209937422.904, "dur": 3.230, + "args": { + "External id": 721203,"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": 6305209937430.456, "dur": 3.892, + "args": { + "External id": 721204,"Record function id": 0, "Ev Idx": 10547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209937431.815, "dur": 2.120, + "args": { + "External id": 721205,"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": 6305209937432.312, "dur": 1.230, + "args": { + "External id": 721206,"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": 6305209937432.723, "dur": 0.753, + "args": { + "External id": 721207,"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": 6305209937437.494, "dur": 3.868, + "args": { + "External id": 721208,"Record function id": 0, "Ev Idx": 10551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209937438.486, "dur": 2.465, + "args": { + "External id": 721209,"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": 6305209937439.156, "dur": 1.381, + "args": { + "External id": 721210,"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": 6305209937439.452, "dur": 1.006, + "args": { + "External id": 721211,"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": 6305209937444.854, "dur": 3.769, + "args": { + "External id": 721212,"Record function id": 0, "Ev Idx": 10555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305209937446.085, "dur": 2.102, + "args": { + "External id": 721213,"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": 6305209937446.543, "dur": 1.265, + "args": { + "External id": 721214,"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": 6305209937447.008, "dur": 0.687, + "args": { + "External id": 721215,"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": 6305209937452.802, "dur": 60760.181, + "args": { + "External id": 721216,"Record function id": 0, "Sequence number": 7674634, "Fwd thread id": 1, "Ev Idx": 10559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305209937454.078, "dur": 60749.095, + "args": { + "External id": 721217,"Sequence number": 7674634, "Fwd thread 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": 6305209937454.078, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.7)", "pid": 2338707, "tid": 2379456, + "ts": 6305209937484.949, "dur": 54.278, + "args": { + "External id": 721218,"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": 6305209937548.974, "dur": 66.213, + "args": { + "External id": 721219,"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": 6305209937621.316, "dur": 60574.209, + "args": { + "External id": 721220,"Record function id": 0, "Ev Idx": 10563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305209937718.236, "dur": 7.328, + "args": { + "External id": 721221,"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": 6305209937735.678, "dur": 4.989, + "args": { + "External id": 721222,"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": 6305209937756.696, "dur": 59406.337, + "args": { + "External id": 721223,"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": 6305209937770.956, "dur": 59378.762, + "args": { + "External id": 721224,"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": 6305209937871.330, "dur": 17.882, + "args": { + "External id": 721225,"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": 6305209937909.375, "dur": 59195.013, + "args": { + "External id": 721226,"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": 6305209937912.399, "dur": 59190.837, + "args": { + "External id": 721227,"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": 6305209937916.879, "dur": 11.564, + "args": { + "External id": 721228,"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": 6305209937930.580, "dur": 59167.332, + "args": { + "External id": 721229,"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": 6305209997271.543, "dur": 11.885, + "args": { + "External id": 721230,"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": 6305209997275.077, "dur": 7.969, + "args": { + "External id": 721231,"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": 6305209997314.471, "dur": 439.782, + "args": { + "External id": 721232,"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": 6305209997350.386, "dur": 397.793, + "args": { + "External id": 721233,"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": 6305209997362.426, "dur": 379.669, + "args": { + "External id": 721234,"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": 6305209997777.333, "dur": 2.605, + "args": { + "External id": 721235,"Record function id": 0, "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": 6305209997844.329, "dur": 10.383, + "args": { + "External id": 721236,"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": 6305209997867.253, "dur": 36.813, + "args": { + "External id": 721237,"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": 6305209997917.672, "dur": 3.380, + "args": { + "External id": 721238,"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": 6305209997926.563, "dur": 13.115, + "args": { + "External id": 721239,"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": 6305209997945.293, "dur": 0.750, + "args": { + "External id": 721240,"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": 6305209997950.471, "dur": 12.541, + "args": { + "External id": 721241,"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": 6305209997968.083, "dur": 0.748, + "args": { + "External id": 721242,"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": 6305209997972.612, "dur": 12.783, + "args": { + "External id": 721243,"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": 6305209997989.718, "dur": 0.916, + "args": { + "External id": 721244,"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": 6305209997994.222, "dur": 12.167, + "args": { + "External id": 721245,"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": 6305209998010.779, "dur": 1.093, + "args": { + "External id": 721246,"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": 6305209998015.719, "dur": 12.465, + "args": { + "External id": 721247,"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": 6305209998032.215, "dur": 0.838, + "args": { + "External id": 721248,"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": 6305209998037.425, "dur": 12.040, + "args": { + "External id": 721249,"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": 6305209998088.864, "dur": 1.651, + "args": { + "External id": 721250,"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": 6305209998095.798, "dur": 16.251, + "args": { + "External id": 721251,"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": 6305209998117.532, "dur": 1.128, + "args": { + "External id": 721252,"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": 6305209998122.163, "dur": 11.705, + "args": { + "External id": 721253,"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": 6305209998229.848, "dur": 2975.689, + "args": { + "External id": 721254,"Record function id": 0, "Ev Idx": 10597 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.6)", "pid": 2338707, "tid": 2379456, + "ts": 6305209998250.094, "dur": 1082.611, + "args": { + "External id": 721255,"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": 6305209998267.136, "dur": 351.006, + "args": { + "External id": 721256,"Record function id": 0, "Ev Idx": 10599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6305209998348.080, "dur": 6.454, + "args": { + "External id": 721257,"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": 6305209998358.150, "dur": 0.909, + "args": { + "External id": 721258,"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": 6305209998361.255, "dur": 1.066, + "args": { + "External id": 721259,"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": 6305209998363.935, "dur": 0.926, + "args": { + "External id": 721260,"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": 6305209998366.966, "dur": 0.834, + "args": { + "External id": 721261,"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": 6305209998371.191, "dur": 1.034, + "args": { + "External id": 721262,"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": 6305209998373.693, "dur": 1.093, + "args": { + "External id": 721263,"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": 6305209998376.805, "dur": 1.825, + "args": { + "External id": 721264,"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": 6305209998380.063, "dur": 3.430, + "args": { + "External id": 721265,"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": 6305209998386.678, "dur": 0.814, + "args": { + "External id": 721266,"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": 6305209998405.231, "dur": 179.126, + "args": { + "External id": 721267,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305209998420.981, "dur": 158.562, + "args": { + "External id": 721268,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305209998446.779, "dur": 13.928, + "args": { + "External id": 721269,"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": 6305209998464.462, "dur": 85.686, + "args": { + "External id": 721270,"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": 6305209998467.394, "dur": 82.302, + "args": { + "External id": 721271,"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": 6305209998471.733, "dur": 5.920, + "args": { + "External id": 721272,"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": 6305209998479.567, "dur": 68.938, + "args": { + "External id": 721273,"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": 6305209998700.964, "dur": 623.623, + "args": { + "External id": 721274,"Record function id": 0, "Ev Idx": 10617 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.5)", "pid": 2338707, "tid": 2379456, + "ts": 6305209998717.420, "dur": 594.704, + "args": { + "External id": 721275,"Record function id": 0, "Ev Idx": 10618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305209998777.977, "dur": 5.477, + "args": { + "External id": 721276,"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": 6305209998799.034, "dur": 30.049, + "args": { + "External id": 721277,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209998804.766, "dur": 2.001, + "args": { + "External id": 721278,"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": 6305209998809.209, "dur": 0.529, + "args": { + "External id": 721279,"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": 6305209998811.351, "dur": 0.610, + "args": { + "External id": 721280,"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": 6305209998812.982, "dur": 2.404, + "args": { + "External id": 721281,"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": 6305209998817.293, "dur": 0.448, + "args": { + "External id": 721282,"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": 6305209998819.441, "dur": 0.329, + "args": { + "External id": 721283,"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": 6305209998821.082, "dur": 0.436, + "args": { + "External id": 721284,"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": 6305209998823.141, "dur": 0.440, + "args": { + "External id": 721285,"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": 6305209998825.445, "dur": 0.359, + "args": { + "External id": 721286,"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": 6305209998840.178, "dur": 41.890, + "args": { + "External id": 721287,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305209998912.650, "dur": 111.972, + "args": { + "External id": 721288,"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": 6305209998923.303, "dur": 3.332, + "args": { + "External id": 721289,"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": 6305209998932.071, "dur": 10.397, + "args": { + "External id": 721290,"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": 6305209998936.221, "dur": 5.863, + "args": { + "External id": 721291,"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": 6305209998940.142, "dur": 0.796, + "args": { + "External id": 721292,"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": 6305209998948.692, "dur": 28.149, + "args": { + "External id": 721293,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305209998950.822, "dur": 2.778, + "args": { + "External id": 721294,"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": 6305209998955.102, "dur": 0.435, + "args": { + "External id": 721295,"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": 6305209998957.569, "dur": 0.954, + "args": { + "External id": 721296,"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": 6305209998959.978, "dur": 0.433, + "args": { + "External id": 721297,"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": 6305209998961.749, "dur": 0.482, + "args": { + "External id": 721298,"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": 6305209998963.989, "dur": 0.590, + "args": { + "External id": 721299,"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": 6305209998966.178, "dur": 0.550, + "args": { + "External id": 721300,"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": 6305209998967.655, "dur": 0.372, + "args": { + "External id": 721301,"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": 6305209998970.025, "dur": 2.664, + "args": { + "External id": 721302,"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": 6305209998987.021, "dur": 30.434, + "args": { + "External id": 721303,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305209999105.494, "dur": 131.099, + "args": { + "External id": 721304,"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": 6305209999142.047, "dur": 90.562, + "args": { + "External id": 721305,"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": 6305209999152.884, "dur": 74.749, + "args": { + "External id": 721306,"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": 6305209999254.737, "dur": 1.781, + "args": { + "External id": 721307,"Record function id": 0, "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": 6305209999339.790, "dur": 1844.749, + "args": { + "External id": 721308,"Sequence number": 7674633, "Fwd thread 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": 6305209999339.790, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6305209999454.913, "dur": 135.604, + "args": { + "External id": 721309,"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": 6305209999641.898, "dur": 42.053, + "args": { + "External id": 721310,"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": 6305209999703.724, "dur": 58.526, + "args": { + "External id": 721311,"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": 6305209999772.485, "dur": 33.056, + "args": { + "External id": 721312,"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": 6305209999811.510, "dur": 32.360, + "args": { + "External id": 721313,"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": 6305209999850.227, "dur": 26.756, + "args": { + "External id": 721314,"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": 6305209999885.416, "dur": 29.378, + "args": { + "External id": 721315,"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": 6305209999940.974, "dur": 23.107, + "args": { + "External id": 721316,"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": 6305209999987.692, "dur": 28.740, + "args": { + "External id": 721317,"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": 6305210000036.677, "dur": 56.922, + "args": { + "External id": 721318,"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": 6305210000112.764, "dur": 18.085, + "args": { + "External id": 721319,"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": 6305210000142.265, "dur": 43.693, + "args": { + "External id": 721320,"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": 6305210000190.465, "dur": 36.321, + "args": { + "External id": 721321,"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": 6305210000256.381, "dur": 276.280, + "args": { + "External id": 721322,"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": 6305210000344.692, "dur": 6.388, + "args": { + "External id": 721323,"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": 6305210000353.196, "dur": 2.603, + "args": { + "External id": 721324,"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": 6305210000357.229, "dur": 3.018, + "args": { + "External id": 721325,"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": 6305210000361.787, "dur": 4.408, + "args": { + "External id": 721326,"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": 6305210000411.633, "dur": 5.107, + "args": { + "External id": 721327,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305210000413.635, "dur": 2.941, + "args": { + "External id": 721328,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305210000418.817, "dur": 33.622, + "args": { + "External id": 721329,"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": 6305210000424.484, "dur": 1.749, + "args": { + "External id": 721330,"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": 6305210000453.842, "dur": 1.863, + "args": { + "External id": 721331,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305210000454.922, "dur": 0.705, + "args": { + "External id": 721332,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305210000456.949, "dur": 16.858, + "args": { + "External id": 721333,"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": 6305210000459.378, "dur": 0.544, + "args": { + "External id": 721334,"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": 6305210000570.025, "dur": 31.137, + "args": { + "External id": 721335,"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": 6305210000618.270, "dur": 18.803, + "args": { + "External id": 721336,"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": 6305210000646.087, "dur": 47.016, + "args": { + "External id": 721337,"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": 6305210000701.078, "dur": 39.201, + "args": { + "External id": 721338,"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": 6305210000749.147, "dur": 21.336, + "args": { + "External id": 721339,"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": 6305210000779.070, "dur": 31.871, + "args": { + "External id": 721340,"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": 6305210000818.841, "dur": 45.238, + "args": { + "External id": 721341,"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": 6305210000878.861, "dur": 36.628, + "args": { + "External id": 721342,"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": 6305210000936.235, "dur": 27.226, + "args": { + "External id": 721343,"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": 6305210000982.175, "dur": 27.446, + "args": { + "External id": 721344,"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": 6305210001023.701, "dur": 22.391, + "args": { + "External id": 721345,"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": 6305210001096.645, "dur": 19.462, + "args": { + "External id": 721346,"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": 6305210001130.264, "dur": 17.703, + "args": { + "External id": 721347,"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": 6305210001227.816, "dur": 19.239, + "args": { + "External id": 721348,"Record function id": 0, "Ev Idx": 10691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305210001234.269, "dur": 11.748, + "args": { + "External id": 721349,"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": 6305210001238.590, "dur": 6.493, + "args": { + "External id": 721350,"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": 6305210001240.860, "dur": 4.103, + "args": { + "External id": 721351,"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": 6305210001251.019, "dur": 5.239, + "args": { + "External id": 721352,"Record function id": 0, "Ev Idx": 10695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305210001252.238, "dur": 3.569, + "args": { + "External id": 721353,"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": 6305210001252.969, "dur": 2.347, + "args": { + "External id": 721354,"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": 6305210001253.945, "dur": 1.297, + "args": { + "External id": 721355,"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": 6305210001259.500, "dur": 4.516, + "args": { + "External id": 721356,"Record function id": 0, "Ev Idx": 10699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305210001261.120, "dur": 2.474, + "args": { + "External id": 721357,"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": 6305210001261.674, "dur": 1.479, + "args": { + "External id": 721358,"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": 6305210001262.234, "dur": 0.855, + "args": { + "External id": 721359,"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": 6305210001267.348, "dur": 4.540, + "args": { + "External id": 721360,"Record function id": 0, "Ev Idx": 10703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305210001268.842, "dur": 2.608, + "args": { + "External id": 721361,"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": 6305210001269.674, "dur": 1.383, + "args": { + "External id": 721362,"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": 6305210001270.006, "dur": 0.986, + "args": { + "External id": 721363,"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": 6305210001274.932, "dur": 3.951, + "args": { + "External id": 721364,"Record function id": 0, "Ev Idx": 10707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305210001276.526, "dur": 1.945, + "args": { + "External id": 721365,"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": 6305210001277.081, "dur": 1.000, + "args": { + "External id": 721366,"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": 6305210001277.374, "dur": 0.633, + "args": { + "External id": 721367,"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": 6305210001282.017, "dur": 4.353, + "args": { + "External id": 721368,"Record function id": 0, "Ev Idx": 10711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305210001283.267, "dur": 2.672, + "args": { + "External id": 721369,"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": 6305210001283.925, "dur": 1.254, + "args": { + "External id": 721370,"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": 6305210001284.387, "dur": 0.690, + "args": { + "External id": 721371,"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": 6305210001289.663, "dur": 6.154, + "args": { + "External id": 721372,"Record function id": 0, "Ev Idx": 10715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305210001290.948, "dur": 4.444, + "args": { + "External id": 721373,"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": 6305210001291.528, "dur": 3.477, + "args": { + "External id": 721374,"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": 6305210001291.906, "dur": 3.033, + "args": { + "External id": 721375,"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": 6305210001299.001, "dur": 4.350, + "args": { + "External id": 721376,"Record function id": 0, "Ev Idx": 10719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305210001300.315, "dur": 2.595, + "args": { + "External id": 721377,"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": 6305210001301.111, "dur": 1.360, + "args": { + "External id": 721378,"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": 6305210001301.451, "dur": 0.925, + "args": { + "External id": 721379,"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": 6305210001307.043, "dur": 3.899, + "args": { + "External id": 721380,"Record function id": 0, "Ev Idx": 10723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305210001308.182, "dur": 2.332, + "args": { + "External id": 721381,"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": 6305210001308.623, "dur": 1.510, + "args": { + "External id": 721382,"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": 6305210001309.354, "dur": 0.669, + "args": { + "External id": 721383,"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": 6305210001315.273, "dur": 62134.065, + "args": { + "External id": 721384,"Record function id": 0, "Sequence number": 7674632, "Fwd thread id": 1, "Ev Idx": 10727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305210001316.785, "dur": 62123.092, + "args": { + "External id": 721385,"Sequence number": 7674632, "Fwd thread 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": 6305210001316.785, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.6)", "pid": 2338707, "tid": 2379456, + "ts": 6305210001346.772, "dur": 37.468, + "args": { + "External id": 721386,"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": 6305210001392.068, "dur": 63.379, + "args": { + "External id": 721387,"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": 6305210001461.507, "dur": 61970.247, + "args": { + "External id": 721388,"Record function id": 0, "Ev Idx": 10731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305210001568.295, "dur": 8.341, + "args": { + "External id": 721389,"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": 6305210001587.591, "dur": 5.044, + "args": { + "External id": 721390,"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": 6305210001608.633, "dur": 60783.536, + "args": { + "External id": 721391,"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": 6305210001623.399, "dur": 60755.114, + "args": { + "External id": 721392,"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": 6305210001724.305, "dur": 18.070, + "args": { + "External id": 721393,"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": 6305210001762.721, "dur": 60567.280, + "args": { + "External id": 721394,"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": 6305210001769.164, "dur": 60559.543, + "args": { + "External id": 721395,"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": 6305210001774.174, "dur": 9.137, + "args": { + "External id": 721396,"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": 6305210001785.502, "dur": 60537.526, + "args": { + "External id": 721397,"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": 6305210062520.847, "dur": 19.147, + "args": { + "External id": 721398,"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": 6305210062525.050, "dur": 14.434, + "args": { + "External id": 721399,"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": 6305210062576.192, "dur": 384.665, + "args": { + "External id": 721400,"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": 6305210062614.158, "dur": 341.963, + "args": { + "External id": 721401,"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": 6305210062626.701, "dur": 324.304, + "args": { + "External id": 721402,"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": 6305210062981.183, "dur": 2.339, + "args": { + "External id": 721403,"Record function id": 0, "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": 6305210063043.859, "dur": 7.283, + "args": { + "External id": 721404,"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": 6305210063110.857, "dur": 41.061, + "args": { + "External id": 721405,"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": 6305210063163.640, "dur": 3.901, + "args": { + "External id": 721406,"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": 6305210063173.023, "dur": 15.729, + "args": { + "External id": 721407,"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": 6305210063193.571, "dur": 1.070, + "args": { + "External id": 721408,"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": 6305210063227.656, "dur": 12.944, + "args": { + "External id": 721409,"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": 6305210063248.341, "dur": 0.842, + "args": { + "External id": 721410,"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": 6305210063252.938, "dur": 13.499, + "args": { + "External id": 721411,"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": 6305210063270.198, "dur": 0.793, + "args": { + "External id": 721412,"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": 6305210063274.964, "dur": 11.577, + "args": { + "External id": 721413,"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": 6305210063290.325, "dur": 0.766, + "args": { + "External id": 721414,"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": 6305210063294.384, "dur": 12.732, + "args": { + "External id": 721415,"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": 6305210063313.308, "dur": 0.812, + "args": { + "External id": 721416,"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": 6305210063317.524, "dur": 11.027, + "args": { + "External id": 721417,"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": 6305210063332.718, "dur": 0.709, + "args": { + "External id": 721418,"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": 6305210063336.597, "dur": 12.333, + "args": { + "External id": 721419,"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": 6305210063353.346, "dur": 0.796, + "args": { + "External id": 721420,"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": 6305210063357.989, "dur": 10.804, + "args": { + "External id": 721421,"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": 6305210063469.611, "dur": 2978.118, + "args": { + "External id": 721422,"Record function id": 0, "Ev Idx": 10765 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.5)", "pid": 2338707, "tid": 2379456, + "ts": 6305210063492.162, "dur": 1094.695, + "args": { + "External id": 721423,"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": 6305210063524.737, "dur": 336.571, + "args": { + "External id": 721424,"Record function id": 0, "Ev Idx": 10767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6305210063613.150, "dur": 7.040, + "args": { + "External id": 721425,"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": 6305210063623.465, "dur": 0.854, + "args": { + "External id": 721426,"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": 6305210063626.487, "dur": 0.792, + "args": { + "External id": 721427,"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": 6305210063628.827, "dur": 0.719, + "args": { + "External id": 721428,"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": 6305210063631.390, "dur": 0.635, + "args": { + "External id": 721429,"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": 6305210063633.755, "dur": 1.423, + "args": { + "External id": 721430,"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": 6305210063636.797, "dur": 1.141, + "args": { + "External id": 721431,"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": 6305210063639.714, "dur": 1.938, + "args": { + "External id": 721432,"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": 6305210063645.137, "dur": 2.561, + "args": { + "External id": 721433,"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": 6305210063648.885, "dur": 0.541, + "args": { + "External id": 721434,"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": 6305210063666.877, "dur": 163.027, + "args": { + "External id": 721435,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305210063682.622, "dur": 142.556, + "args": { + "External id": 721436,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305210063708.066, "dur": 14.421, + "args": { + "External id": 721437,"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": 6305210063725.961, "dur": 71.853, + "args": { + "External id": 721438,"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": 6305210063730.721, "dur": 66.689, + "args": { + "External id": 721439,"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": 6305210063735.303, "dur": 6.599, + "args": { + "External id": 721440,"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": 6305210063745.943, "dur": 50.941, + "args": { + "External id": 721441,"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": 6305210063941.390, "dur": 634.832, + "args": { + "External id": 721442,"Record function id": 0, "Ev Idx": 10785 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.4)", "pid": 2338707, "tid": 2379456, + "ts": 6305210063956.005, "dur": 606.666, + "args": { + "External id": 721443,"Record function id": 0, "Ev Idx": 10786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305210064013.802, "dur": 4.391, + "args": { + "External id": 721444,"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": 6305210064032.970, "dur": 64.268, + "args": { + "External id": 721445,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305210064038.077, "dur": 1.614, + "args": { + "External id": 721446,"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": 6305210064041.242, "dur": 0.390, + "args": { + "External id": 721447,"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": 6305210064043.215, "dur": 0.432, + "args": { + "External id": 721448,"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": 6305210064044.966, "dur": 2.514, + "args": { + "External id": 721449,"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": 6305210064048.632, "dur": 0.701, + "args": { + "External id": 721450,"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": 6305210064050.982, "dur": 0.458, + "args": { + "External id": 721451,"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": 6305210064087.923, "dur": 0.800, + "args": { + "External id": 721452,"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": 6305210064090.961, "dur": 0.414, + "args": { + "External id": 721453,"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": 6305210064092.634, "dur": 0.473, + "args": { + "External id": 721454,"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": 6305210064108.771, "dur": 44.045, + "args": { + "External id": 721455,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305210064189.207, "dur": 114.002, + "args": { + "External id": 721456,"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": 6305210064200.608, "dur": 4.269, + "args": { + "External id": 721457,"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": 6305210064210.184, "dur": 10.234, + "args": { + "External id": 721458,"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": 6305210064214.379, "dur": 5.658, + "args": { + "External id": 721459,"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": 6305210064218.186, "dur": 0.715, + "args": { + "External id": 721460,"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": 6305210064227.319, "dur": 26.746, + "args": { + "External id": 721461,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305210064229.298, "dur": 2.463, + "args": { + "External id": 721462,"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": 6305210064233.048, "dur": 0.346, + "args": { + "External id": 721463,"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": 6305210064235.147, "dur": 0.503, + "args": { + "External id": 721464,"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": 6305210064237.450, "dur": 0.384, + "args": { + "External id": 721465,"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": 6305210064239.123, "dur": 0.447, + "args": { + "External id": 721466,"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": 6305210064241.283, "dur": 0.566, + "args": { + "External id": 721467,"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": 6305210064243.577, "dur": 0.577, + "args": { + "External id": 721468,"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": 6305210064244.970, "dur": 0.424, + "args": { + "External id": 721469,"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": 6305210064246.958, "dur": 2.736, + "args": { + "External id": 721470,"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": 6305210064264.686, "dur": 30.843, + "args": { + "External id": 721471,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305210064350.176, "dur": 122.941, + "args": { + "External id": 721472,"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": 6305210064378.315, "dur": 90.933, + "args": { + "External id": 721473,"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": 6305210064388.336, "dur": 76.683, + "args": { + "External id": 721474,"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": 6305210064488.406, "dur": 1.786, + "args": { + "External id": 721475,"Record function id": 0, "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": 6305210064595.548, "dur": 1828.982, + "args": { + "External id": 721476,"Sequence number": 7674631, "Fwd thread 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": 6305210064595.548, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6305210064710.639, "dur": 112.847, + "args": { + "External id": 721477,"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": 6305210064867.782, "dur": 40.489, + "args": { + "External id": 721478,"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": 6305210064927.109, "dur": 51.954, + "args": { + "External id": 721479,"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": 6305210064989.201, "dur": 32.822, + "args": { + "External id": 721480,"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": 6305210065028.103, "dur": 72.326, + "args": { + "External id": 721481,"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": 6305210065111.063, "dur": 33.275, + "args": { + "External id": 721482,"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": 6305210065156.499, "dur": 31.383, + "args": { + "External id": 721483,"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": 6305210065220.791, "dur": 25.521, + "args": { + "External id": 721484,"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": 6305210065265.586, "dur": 28.626, + "args": { + "External id": 721485,"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": 6305210065315.551, "dur": 19.695, + "args": { + "External id": 721486,"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": 6305210065349.551, "dur": 15.461, + "args": { + "External id": 721487,"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": 6305210065379.826, "dur": 39.116, + "args": { + "External id": 721488,"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": 6305210065422.502, "dur": 35.096, + "args": { + "External id": 721489,"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": 6305210065487.262, "dur": 272.919, + "args": { + "External id": 721490,"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": 6305210065587.397, "dur": 7.251, + "args": { + "External id": 721491,"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": 6305210065597.029, "dur": 3.346, + "args": { + "External id": 721492,"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": 6305210065601.999, "dur": 2.552, + "args": { + "External id": 721493,"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": 6305210065605.568, "dur": 4.708, + "args": { + "External id": 721494,"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": 6305210065656.525, "dur": 5.462, + "args": { + "External id": 721495,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305210065658.828, "dur": 2.996, + "args": { + "External id": 721496,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305210065663.575, "dur": 32.073, + "args": { + "External id": 721497,"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": 6305210065669.351, "dur": 1.933, + "args": { + "External id": 721498,"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": 6305210065697.372, "dur": 1.887, + "args": { + "External id": 721499,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305210065698.403, "dur": 0.783, + "args": { + "External id": 721500,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305210065700.457, "dur": 17.375, + "args": { + "External id": 721501,"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": 6305210065702.481, "dur": 0.624, + "args": { + "External id": 721502,"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": 6305210065792.945, "dur": 29.161, + "args": { + "External id": 721503,"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": 6305210065851.552, "dur": 19.862, + "args": { + "External id": 721504,"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": 6305210065879.891, "dur": 48.617, + "args": { + "External id": 721505,"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": 6305210065935.851, "dur": 40.915, + "args": { + "External id": 721506,"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": 6305210065985.874, "dur": 22.951, + "args": { + "External id": 721507,"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": 6305210066017.030, "dur": 32.130, + "args": { + "External id": 721508,"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": 6305210066096.944, "dur": 35.975, + "args": { + "External id": 721509,"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": 6305210066140.744, "dur": 46.927, + "args": { + "External id": 721510,"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": 6305210066218.969, "dur": 30.732, + "args": { + "External id": 721511,"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": 6305210066269.285, "dur": 25.307, + "args": { + "External id": 721512,"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": 6305210066308.389, "dur": 21.717, + "args": { + "External id": 721513,"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": 6305210066344.831, "dur": 14.750, + "args": { + "External id": 721514,"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": 6305210066372.030, "dur": 19.023, + "args": { + "External id": 721515,"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": 6305210066470.708, "dur": 15.530, + "args": { + "External id": 721516,"Record function id": 0, "Ev Idx": 10859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305210066473.956, "dur": 11.352, + "args": { + "External id": 721517,"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": 6305210066478.224, "dur": 6.138, + "args": { + "External id": 721518,"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": 6305210066479.976, "dur": 4.253, + "args": { + "External id": 721519,"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": 6305210066490.084, "dur": 5.127, + "args": { + "External id": 721520,"Record function id": 0, "Ev Idx": 10863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305210066491.360, "dur": 3.423, + "args": { + "External id": 721521,"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": 6305210066492.200, "dur": 2.080, + "args": { + "External id": 721522,"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": 6305210066493.073, "dur": 1.067, + "args": { + "External id": 721523,"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": 6305210066498.482, "dur": 5.042, + "args": { + "External id": 721524,"Record function id": 0, "Ev Idx": 10867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305210066499.722, "dur": 3.381, + "args": { + "External id": 721525,"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": 6305210066500.250, "dur": 2.414, + "args": { + "External id": 721526,"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": 6305210066501.039, "dur": 1.559, + "args": { + "External id": 721527,"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": 6305210066522.608, "dur": 6.793, + "args": { + "External id": 721528,"Record function id": 0, "Ev Idx": 10871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305210066524.518, "dur": 4.237, + "args": { + "External id": 721529,"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": 6305210066525.652, "dur": 2.235, + "args": { + "External id": 721530,"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": 6305210066526.432, "dur": 1.246, + "args": { + "External id": 721531,"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": 6305210066532.951, "dur": 4.400, + "args": { + "External id": 721532,"Record function id": 0, "Ev Idx": 10875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305210066534.330, "dur": 2.629, + "args": { + "External id": 721533,"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": 6305210066534.870, "dur": 1.691, + "args": { + "External id": 721534,"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": 6305210066535.476, "dur": 1.025, + "args": { + "External id": 721535,"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": 6305210066540.541, "dur": 6.638, + "args": { + "External id": 721536,"Record function id": 0, "Ev Idx": 10879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305210066541.936, "dur": 4.814, + "args": { + "External id": 721537,"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": 6305210066542.825, "dur": 3.501, + "args": { + "External id": 721538,"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": 6305210066543.495, "dur": 2.728, + "args": { + "External id": 721539,"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": 6305210066550.411, "dur": 4.180, + "args": { + "External id": 721540,"Record function id": 0, "Ev Idx": 10883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305210066551.795, "dur": 2.363, + "args": { + "External id": 721541,"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": 6305210066552.310, "dur": 1.420, + "args": { + "External id": 721542,"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": 6305210066552.741, "dur": 0.927, + "args": { + "External id": 721543,"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": 6305210066557.734, "dur": 3.807, + "args": { + "External id": 721544,"Record function id": 0, "Ev Idx": 10887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305210066558.975, "dur": 2.152, + "args": { + "External id": 721545,"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": 6305210066559.595, "dur": 1.077, + "args": { + "External id": 721546,"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": 6305210066559.928, "dur": 0.667, + "args": { + "External id": 721547,"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": 6305210066564.519, "dur": 4.329, + "args": { + "External id": 721548,"Record function id": 0, "Ev Idx": 10891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305210066565.832, "dur": 2.627, + "args": { + "External id": 721549,"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": 6305210066566.557, "dur": 1.457, + "args": { + "External id": 721550,"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": 6305210066567.238, "dur": 0.650, + "args": { + "External id": 721551,"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": 6305210066573.298, "dur": 64461.412, + "args": { + "External id": 721552,"Record function id": 0, "Sequence number": 7674630, "Fwd thread id": 1, "Ev Idx": 10895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305210066574.592, "dur": 64450.753, + "args": { + "External id": 721553,"Sequence number": 7674630, "Fwd thread 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": 6305210066574.592, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.5)", "pid": 2338707, "tid": 2379456, + "ts": 6305210066604.694, "dur": 39.516, + "args": { + "External id": 721554,"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": 6305210066651.999, "dur": 64.916, + "args": { + "External id": 721555,"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": 6305210066722.611, "dur": 64294.948, + "args": { + "External id": 721556,"Record function id": 0, "Ev Idx": 10899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305210066814.211, "dur": 6.671, + "args": { + "External id": 721557,"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": 6305210066830.454, "dur": 4.626, + "args": { + "External id": 721558,"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": 6305210066848.875, "dur": 63292.571, + "args": { + "External id": 721559,"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": 6305210066863.974, "dur": 63262.848, + "args": { + "External id": 721560,"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": 6305210066960.341, "dur": 18.143, + "args": { + "External id": 721561,"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": 6305210066999.009, "dur": 63048.605, + "args": { + "External id": 721562,"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": 6305210067001.930, "dur": 63044.386, + "args": { + "External id": 721563,"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": 6305210067006.515, "dur": 7.991, + "args": { + "External id": 721564,"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": 6305210067016.618, "dur": 63023.736, + "args": { + "External id": 721565,"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": 6305210130261.668, "dur": 13.390, + "args": { + "External id": 721566,"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": 6305210130265.455, "dur": 9.133, + "args": { + "External id": 721567,"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": 6305210130310.141, "dur": 330.057, + "args": { + "External id": 721568,"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": 6305210130343.209, "dur": 291.548, + "args": { + "External id": 721569,"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": 6305210130355.842, "dur": 272.673, + "args": { + "External id": 721570,"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": 6305210130661.411, "dur": 2.328, + "args": { + "External id": 721571,"Record function id": 0, "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": 6305210130721.752, "dur": 9.218, + "args": { + "External id": 721572,"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": 6305210130743.578, "dur": 34.942, + "args": { + "External id": 721573,"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": 6305210130789.331, "dur": 1.576, + "args": { + "External id": 721574,"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": 6305210130796.768, "dur": 15.334, + "args": { + "External id": 721575,"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": 6305210130817.264, "dur": 0.993, + "args": { + "External id": 721576,"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": 6305210130822.550, "dur": 11.790, + "args": { + "External id": 721577,"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": 6305210130839.375, "dur": 0.871, + "args": { + "External id": 721578,"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": 6305210130844.144, "dur": 12.666, + "args": { + "External id": 721579,"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": 6305210130861.358, "dur": 0.659, + "args": { + "External id": 721580,"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": 6305210130865.895, "dur": 10.534, + "args": { + "External id": 721581,"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": 6305210130881.047, "dur": 1.003, + "args": { + "External id": 721582,"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": 6305210130885.928, "dur": 10.875, + "args": { + "External id": 721583,"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": 6305210130901.173, "dur": 0.745, + "args": { + "External id": 721584,"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": 6305210130907.955, "dur": 9.995, + "args": { + "External id": 721585,"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": 6305210130921.887, "dur": 0.898, + "args": { + "External id": 721586,"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": 6305210130926.826, "dur": 10.633, + "args": { + "External id": 721587,"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": 6305210130941.262, "dur": 3.109, + "args": { + "External id": 721588,"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": 6305210130948.650, "dur": 10.003, + "args": { + "External id": 721589,"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": 6305210131049.165, "dur": 2990.393, + "args": { + "External id": 721590,"Record function id": 0, "Ev Idx": 10933 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.4)", "pid": 2338707, "tid": 2379456, + "ts": 6305210131107.694, "dur": 1108.694, + "args": { + "External id": 721591,"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": 6305210131125.790, "dur": 344.786, + "args": { + "External id": 721592,"Record function id": 0, "Ev Idx": 10935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6305210131220.331, "dur": 5.215, + "args": { + "External id": 721593,"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": 6305210131229.341, "dur": 1.040, + "args": { + "External id": 721594,"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": 6305210131232.288, "dur": 1.302, + "args": { + "External id": 721595,"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": 6305210131235.004, "dur": 0.868, + "args": { + "External id": 721596,"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": 6305210131239.976, "dur": 0.894, + "args": { + "External id": 721597,"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": 6305210131242.195, "dur": 0.751, + "args": { + "External id": 721598,"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": 6305210131244.473, "dur": 1.645, + "args": { + "External id": 721599,"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": 6305210131247.552, "dur": 3.978, + "args": { + "External id": 721600,"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": 6305210131255.336, "dur": 0.717, + "args": { + "External id": 721601,"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": 6305210131257.252, "dur": 0.578, + "args": { + "External id": 721602,"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": 6305210131279.476, "dur": 159.652, + "args": { + "External id": 721603,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305210131296.894, "dur": 137.879, + "args": { + "External id": 721604,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305210131322.212, "dur": 17.304, + "args": { + "External id": 721605,"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": 6305210131343.750, "dur": 63.677, + "args": { + "External id": 721606,"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": 6305210131346.570, "dur": 60.466, + "args": { + "External id": 721607,"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": 6305210131350.915, "dur": 5.281, + "args": { + "External id": 721608,"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": 6305210131358.188, "dur": 48.328, + "args": { + "External id": 721609,"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": 6305210131575.477, "dur": 630.347, + "args": { + "External id": 721610,"Record function id": 0, "Ev Idx": 10953 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.3)", "pid": 2338707, "tid": 2379456, + "ts": 6305210131593.120, "dur": 599.415, + "args": { + "External id": 721611,"Record function id": 0, "Ev Idx": 10954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305210131653.610, "dur": 5.608, + "args": { + "External id": 721612,"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": 6305210131674.888, "dur": 29.289, + "args": { + "External id": 721613,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305210131680.647, "dur": 1.780, + "args": { + "External id": 721614,"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": 6305210131684.219, "dur": 0.524, + "args": { + "External id": 721615,"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": 6305210131686.418, "dur": 2.795, + "args": { + "External id": 721616,"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": 6305210131690.758, "dur": 0.462, + "args": { + "External id": 721617,"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": 6305210131692.824, "dur": 0.726, + "args": { + "External id": 721618,"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": 6305210131695.046, "dur": 0.537, + "args": { + "External id": 721619,"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": 6305210131697.055, "dur": 0.338, + "args": { + "External id": 721620,"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": 6305210131698.280, "dur": 0.424, + "args": { + "External id": 721621,"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": 6305210131700.409, "dur": 0.382, + "args": { + "External id": 721622,"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": 6305210131714.480, "dur": 40.448, + "args": { + "External id": 721623,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305210131789.001, "dur": 116.067, + "args": { + "External id": 721624,"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": 6305210131799.660, "dur": 3.039, + "args": { + "External id": 721625,"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": 6305210131807.605, "dur": 15.962, + "args": { + "External id": 721626,"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": 6305210131812.530, "dur": 10.624, + "args": { + "External id": 721627,"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": 6305210131819.247, "dur": 2.625, + "args": { + "External id": 721628,"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": 6305210131829.974, "dur": 28.840, + "args": { + "External id": 721629,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305210131831.932, "dur": 0.717, + "args": { + "External id": 721630,"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": 6305210131834.755, "dur": 0.459, + "args": { + "External id": 721631,"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": 6305210131836.658, "dur": 0.444, + "args": { + "External id": 721632,"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": 6305210131838.249, "dur": 0.477, + "args": { + "External id": 721633,"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": 6305210131840.199, "dur": 0.468, + "args": { + "External id": 721634,"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": 6305210131842.053, "dur": 0.665, + "args": { + "External id": 721635,"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": 6305210131847.368, "dur": 0.542, + "args": { + "External id": 721636,"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": 6305210131849.465, "dur": 2.585, + "args": { + "External id": 721637,"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": 6305210131853.486, "dur": 0.344, + "args": { + "External id": 721638,"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": 6305210131868.784, "dur": 28.968, + "args": { + "External id": 721639,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305210131950.354, "dur": 159.693, + "args": { + "External id": 721640,"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": 6305210131976.996, "dur": 128.668, + "args": { + "External id": 721641,"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": 6305210131986.890, "dur": 113.889, + "args": { + "External id": 721642,"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": 6305210132129.546, "dur": 2.540, + "args": { + "External id": 721643,"Record function id": 0, "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": 6305210132224.976, "dur": 1793.400, + "args": { + "External id": 721644,"Sequence number": 7674629, "Fwd thread 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": 6305210132224.976, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6305210132337.582, "dur": 111.470, + "args": { + "External id": 721645,"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": 6305210132491.396, "dur": 58.935, + "args": { + "External id": 721646,"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": 6305210132573.331, "dur": 56.187, + "args": { + "External id": 721647,"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": 6305210132644.369, "dur": 34.017, + "args": { + "External id": 721648,"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": 6305210132684.998, "dur": 33.877, + "args": { + "External id": 721649,"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": 6305210132725.503, "dur": 28.388, + "args": { + "External id": 721650,"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": 6305210132762.265, "dur": 29.791, + "args": { + "External id": 721651,"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": 6305210132821.617, "dur": 25.733, + "args": { + "External id": 721652,"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": 6305210132865.900, "dur": 28.133, + "args": { + "External id": 721653,"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": 6305210132916.446, "dur": 25.255, + "args": { + "External id": 721654,"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": 6305210132954.681, "dur": 16.107, + "args": { + "External id": 721655,"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": 6305210132981.695, "dur": 41.866, + "args": { + "External id": 721656,"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": 6305210133027.797, "dur": 70.987, + "args": { + "External id": 721657,"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": 6305210133132.416, "dur": 256.725, + "args": { + "External id": 721658,"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": 6305210133214.649, "dur": 6.933, + "args": { + "External id": 721659,"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": 6305210133223.943, "dur": 2.627, + "args": { + "External id": 721660,"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": 6305210133228.040, "dur": 2.255, + "args": { + "External id": 721661,"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": 6305210133231.580, "dur": 4.193, + "args": { + "External id": 721662,"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": 6305210133283.021, "dur": 5.391, + "args": { + "External id": 721663,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305210133285.284, "dur": 2.964, + "args": { + "External id": 721664,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305210133290.335, "dur": 34.998, + "args": { + "External id": 721665,"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": 6305210133296.277, "dur": 1.821, + "args": { + "External id": 721666,"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": 6305210133326.812, "dur": 1.905, + "args": { + "External id": 721667,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305210133327.931, "dur": 0.709, + "args": { + "External id": 721668,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305210133329.712, "dur": 17.496, + "args": { + "External id": 721669,"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": 6305210133331.802, "dur": 0.724, + "args": { + "External id": 721670,"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": 6305210133424.152, "dur": 29.559, + "args": { + "External id": 721671,"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": 6305210133469.388, "dur": 22.236, + "args": { + "External id": 721672,"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": 6305210133500.219, "dur": 71.240, + "args": { + "External id": 721673,"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": 6305210133581.572, "dur": 42.075, + "args": { + "External id": 721674,"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": 6305210133634.253, "dur": 23.168, + "args": { + "External id": 721675,"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": 6305210133666.066, "dur": 32.398, + "args": { + "External id": 721676,"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": 6305210133706.790, "dur": 29.705, + "args": { + "External id": 721677,"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": 6305210133743.899, "dur": 30.967, + "args": { + "External id": 721678,"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": 6305210133794.013, "dur": 47.184, + "args": { + "External id": 721679,"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": 6305210133864.420, "dur": 26.631, + "args": { + "External id": 721680,"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": 6305210133905.255, "dur": 18.489, + "args": { + "External id": 721681,"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": 6305210133937.959, "dur": 15.158, + "args": { + "External id": 721682,"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": 6305210133965.047, "dur": 16.240, + "args": { + "External id": 721683,"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": 6305210134102.961, "dur": 17.667, + "args": { + "External id": 721684,"Record function id": 0, "Ev Idx": 11027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305210134106.815, "dur": 12.606, + "args": { + "External id": 721685,"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": 6305210134111.275, "dur": 6.683, + "args": { + "External id": 721686,"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": 6305210134113.112, "dur": 4.588, + "args": { + "External id": 721687,"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": 6305210134125.160, "dur": 5.406, + "args": { + "External id": 721688,"Record function id": 0, "Ev Idx": 11031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305210134126.351, "dur": 3.780, + "args": { + "External id": 721689,"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": 6305210134127.608, "dur": 1.975, + "args": { + "External id": 721690,"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": 6305210134128.467, "dur": 1.027, + "args": { + "External id": 721691,"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": 6305210134133.749, "dur": 4.596, + "args": { + "External id": 721692,"Record function id": 0, "Ev Idx": 11035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305210134134.915, "dur": 2.978, + "args": { + "External id": 721693,"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": 6305210134135.609, "dur": 1.752, + "args": { + "External id": 721694,"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": 6305210134136.101, "dur": 1.193, + "args": { + "External id": 721695,"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": 6305210134141.559, "dur": 3.780, + "args": { + "External id": 721696,"Record function id": 0, "Ev Idx": 11039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305210134142.761, "dur": 2.120, + "args": { + "External id": 721697,"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": 6305210134143.311, "dur": 1.142, + "args": { + "External id": 721698,"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": 6305210134143.807, "dur": 0.582, + "args": { + "External id": 721699,"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": 6305210134148.426, "dur": 3.882, + "args": { + "External id": 721700,"Record function id": 0, "Ev Idx": 11043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305210134149.676, "dur": 2.191, + "args": { + "External id": 721701,"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": 6305210134150.166, "dur": 1.149, + "args": { + "External id": 721702,"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": 6305210134150.616, "dur": 0.635, + "args": { + "External id": 721703,"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": 6305210134155.476, "dur": 4.232, + "args": { + "External id": 721704,"Record function id": 0, "Ev Idx": 11047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305210134156.458, "dur": 2.810, + "args": { + "External id": 721705,"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": 6305210134157.270, "dur": 1.574, + "args": { + "External id": 721706,"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": 6305210134157.741, "dur": 0.997, + "args": { + "External id": 721707,"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": 6305210134162.873, "dur": 5.720, + "args": { + "External id": 721708,"Record function id": 0, "Ev Idx": 11051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305210134163.895, "dur": 4.218, + "args": { + "External id": 721709,"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": 6305210134164.424, "dur": 3.224, + "args": { + "External id": 721710,"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": 6305210134164.718, "dur": 2.850, + "args": { + "External id": 721711,"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": 6305210134171.697, "dur": 4.053, + "args": { + "External id": 721712,"Record function id": 0, "Ev Idx": 11055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305210134172.974, "dur": 2.354, + "args": { + "External id": 721713,"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": 6305210134173.654, "dur": 1.210, + "args": { + "External id": 721714,"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": 6305210134173.935, "dur": 0.835, + "args": { + "External id": 721715,"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": 6305210134179.414, "dur": 4.185, + "args": { + "External id": 721716,"Record function id": 0, "Ev Idx": 11059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305210134180.614, "dur": 2.440, + "args": { + "External id": 721717,"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": 6305210134181.114, "dur": 1.527, + "args": { + "External id": 721718,"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": 6305210134181.774, "dur": 0.760, + "args": { + "External id": 721719,"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": 6305210134188.048, "dur": 62685.269, + "args": { + "External id": 721720,"Record function id": 0, "Sequence number": 7674628, "Fwd thread id": 1, "Ev Idx": 11063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305210134189.425, "dur": 62674.515, + "args": { + "External id": 721721,"Sequence number": 7674628, "Fwd thread 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": 6305210134189.425, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.4)", "pid": 2338707, "tid": 2379456, + "ts": 6305210134220.028, "dur": 40.892, + "args": { + "External id": 721722,"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": 6305210134269.117, "dur": 63.947, + "args": { + "External id": 721723,"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": 6305210134338.999, "dur": 62517.315, + "args": { + "External id": 721724,"Record function id": 0, "Ev Idx": 11067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305210134430.371, "dur": 6.973, + "args": { + "External id": 721725,"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": 6305210134447.133, "dur": 4.995, + "args": { + "External id": 721726,"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": 6305210134466.891, "dur": 61330.862, + "args": { + "External id": 721727,"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": 6305210134481.642, "dur": 61302.124, + "args": { + "External id": 721728,"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": 6305210134601.407, "dur": 19.264, + "args": { + "External id": 721729,"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": 6305210134645.171, "dur": 61080.818, + "args": { + "External id": 721730,"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": 6305210134648.534, "dur": 61075.922, + "args": { + "External id": 721731,"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": 6305210134653.164, "dur": 11.305, + "args": { + "External id": 721732,"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": 6305210134666.887, "dur": 61050.645, + "args": { + "External id": 721733,"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": 6305210195918.766, "dur": 14.233, + "args": { + "External id": 721734,"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": 6305210195922.688, "dur": 9.967, + "args": { + "External id": 721735,"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": 6305210195965.099, "dur": 470.044, + "args": { + "External id": 721736,"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": 6305210195999.042, "dur": 429.807, + "args": { + "External id": 721737,"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": 6305210196011.393, "dur": 411.117, + "args": { + "External id": 721738,"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": 6305210196459.284, "dur": 2.615, + "args": { + "External id": 721739,"Record function id": 0, "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": 6305210196546.517, "dur": 10.862, + "args": { + "External id": 721740,"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": 6305210196570.155, "dur": 37.771, + "args": { + "External id": 721741,"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": 6305210196622.242, "dur": 1.799, + "args": { + "External id": 721742,"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": 6305210196629.722, "dur": 12.327, + "args": { + "External id": 721743,"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": 6305210196647.548, "dur": 3.280, + "args": { + "External id": 721744,"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": 6305210196655.279, "dur": 10.620, + "args": { + "External id": 721745,"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": 6305210196671.598, "dur": 0.879, + "args": { + "External id": 721746,"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": 6305210196676.360, "dur": 10.653, + "args": { + "External id": 721747,"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": 6305210196691.388, "dur": 0.750, + "args": { + "External id": 721748,"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": 6305210196696.082, "dur": 11.069, + "args": { + "External id": 721749,"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": 6305210196711.461, "dur": 1.111, + "args": { + "External id": 721750,"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": 6305210196716.151, "dur": 14.154, + "args": { + "External id": 721751,"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": 6305210196734.070, "dur": 1.039, + "args": { + "External id": 721752,"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": 6305210196739.264, "dur": 11.399, + "args": { + "External id": 721753,"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": 6305210196754.959, "dur": 1.260, + "args": { + "External id": 721754,"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": 6305210196760.617, "dur": 12.858, + "args": { + "External id": 721755,"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": 6305210196777.228, "dur": 1.024, + "args": { + "External id": 721756,"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": 6305210196782.336, "dur": 11.439, + "args": { + "External id": 721757,"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": 6305210196890.125, "dur": 3203.798, + "args": { + "External id": 721758,"Record function id": 0, "Ev Idx": 11101 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.3)", "pid": 2338707, "tid": 2379456, + "ts": 6305210196911.607, "dur": 1114.589, + "args": { + "External id": 721759,"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": 6305210196930.430, "dur": 404.905, + "args": { + "External id": 721760,"Record function id": 0, "Ev Idx": 11103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6305210197015.874, "dur": 4.400, + "args": { + "External id": 721761,"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": 6305210197023.509, "dur": 3.344, + "args": { + "External id": 721762,"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": 6305210197028.665, "dur": 1.027, + "args": { + "External id": 721763,"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": 6305210197032.159, "dur": 1.042, + "args": { + "External id": 721764,"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": 6305210197035.392, "dur": 0.928, + "args": { + "External id": 721765,"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": 6305210197038.078, "dur": 1.103, + "args": { + "External id": 721766,"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": 6305210197042.699, "dur": 1.145, + "args": { + "External id": 721767,"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": 6305210197045.175, "dur": 1.563, + "args": { + "External id": 721768,"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": 6305210197048.319, "dur": 0.640, + "args": { + "External id": 721769,"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": 6305210197050.520, "dur": 51.399, + "args": { + "External id": 721770,"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": 6305210197125.634, "dur": 170.291, + "args": { + "External id": 721771,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305210197143.431, "dur": 147.443, + "args": { + "External id": 721772,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305210197170.519, "dur": 15.456, + "args": { + "External id": 721773,"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": 6305210197190.324, "dur": 67.772, + "args": { + "External id": 721774,"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": 6305210197193.326, "dur": 64.388, + "args": { + "External id": 721775,"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": 6305210197197.762, "dur": 5.777, + "args": { + "External id": 721776,"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": 6305210197205.885, "dur": 51.193, + "args": { + "External id": 721777,"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": 6305210197424.502, "dur": 593.914, + "args": { + "External id": 721778,"Record function id": 0, "Ev Idx": 11121 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.2)", "pid": 2338707, "tid": 2379456, + "ts": 6305210197442.388, "dur": 563.319, + "args": { + "External id": 721779,"Record function id": 0, "Ev Idx": 11122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305210197504.241, "dur": 20.103, + "args": { + "External id": 721780,"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": 6305210197542.627, "dur": 30.498, + "args": { + "External id": 721781,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305210197548.421, "dur": 1.640, + "args": { + "External id": 721782,"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": 6305210197552.149, "dur": 0.657, + "args": { + "External id": 721783,"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": 6305210197554.554, "dur": 0.548, + "args": { + "External id": 721784,"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": 6305210197556.764, "dur": 0.681, + "args": { + "External id": 721785,"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": 6305210197558.588, "dur": 2.599, + "args": { + "External id": 721786,"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": 6305210197563.123, "dur": 0.500, + "args": { + "External id": 721787,"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": 6305210197565.375, "dur": 0.555, + "args": { + "External id": 721788,"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": 6305210197567.103, "dur": 0.564, + "args": { + "External id": 721789,"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": 6305210197569.274, "dur": 0.346, + "args": { + "External id": 721790,"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": 6305210197584.260, "dur": 42.800, + "args": { + "External id": 721791,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305210197659.293, "dur": 113.754, + "args": { + "External id": 721792,"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": 6305210197670.487, "dur": 3.151, + "args": { + "External id": 721793,"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": 6305210197678.803, "dur": 10.779, + "args": { + "External id": 721794,"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": 6305210197683.726, "dur": 5.481, + "args": { + "External id": 721795,"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": 6305210197687.308, "dur": 0.721, + "args": { + "External id": 721796,"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": 6305210197696.287, "dur": 27.782, + "args": { + "External id": 721797,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305210197698.294, "dur": 0.458, + "args": { + "External id": 721798,"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": 6305210197700.920, "dur": 2.490, + "args": { + "External id": 721799,"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": 6305210197705.595, "dur": 0.519, + "args": { + "External id": 721800,"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": 6305210197707.046, "dur": 0.558, + "args": { + "External id": 721801,"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": 6305210197709.335, "dur": 0.533, + "args": { + "External id": 721802,"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": 6305210197711.471, "dur": 0.391, + "args": { + "External id": 721803,"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": 6305210197712.742, "dur": 0.769, + "args": { + "External id": 721804,"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": 6305210197715.188, "dur": 0.437, + "args": { + "External id": 721805,"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": 6305210197717.498, "dur": 0.322, + "args": { + "External id": 721806,"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": 6305210197734.721, "dur": 29.180, + "args": { + "External id": 721807,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305210197819.982, "dur": 113.956, + "args": { + "External id": 721808,"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": 6305210197842.137, "dur": 88.172, + "args": { + "External id": 721809,"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": 6305210197853.010, "dur": 72.590, + "args": { + "External id": 721810,"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": 6305210197951.554, "dur": 1.849, + "args": { + "External id": 721811,"Record function id": 0, "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": 6305210198033.357, "dur": 2004.928, + "args": { + "External id": 721812,"Sequence number": 7674627, "Fwd thread 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": 6305210198033.357, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6305210198187.256, "dur": 116.773, + "args": { + "External id": 721813,"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": 6305210198352.797, "dur": 41.520, + "args": { + "External id": 721814,"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": 6305210198413.335, "dur": 53.137, + "args": { + "External id": 721815,"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": 6305210198476.890, "dur": 50.829, + "args": { + "External id": 721816,"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": 6305210198537.476, "dur": 37.094, + "args": { + "External id": 721817,"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": 6305210198581.630, "dur": 30.041, + "args": { + "External id": 721818,"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": 6305210198620.356, "dur": 30.555, + "args": { + "External id": 721819,"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": 6305210198680.633, "dur": 25.203, + "args": { + "External id": 721820,"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": 6305210198725.551, "dur": 28.546, + "args": { + "External id": 721821,"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": 6305210198776.731, "dur": 19.307, + "args": { + "External id": 721822,"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": 6305210198810.353, "dur": 15.432, + "args": { + "External id": 721823,"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": 6305210198836.878, "dur": 42.069, + "args": { + "External id": 721824,"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": 6305210198882.746, "dur": 33.100, + "args": { + "External id": 721825,"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": 6305210198948.835, "dur": 309.799, + "args": { + "External id": 721826,"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": 6305210199034.581, "dur": 6.028, + "args": { + "External id": 721827,"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": 6305210199046.383, "dur": 3.333, + "args": { + "External id": 721828,"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": 6305210199051.255, "dur": 2.724, + "args": { + "External id": 721829,"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": 6305210199055.291, "dur": 41.185, + "args": { + "External id": 721830,"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": 6305210199149.380, "dur": 5.492, + "args": { + "External id": 721831,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305210199151.526, "dur": 3.031, + "args": { + "External id": 721832,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305210199156.591, "dur": 36.151, + "args": { + "External id": 721833,"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": 6305210199162.502, "dur": 1.870, + "args": { + "External id": 721834,"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": 6305210199194.491, "dur": 1.865, + "args": { + "External id": 721835,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305210199195.478, "dur": 0.800, + "args": { + "External id": 721836,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305210199197.409, "dur": 15.202, + "args": { + "External id": 721837,"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": 6305210199199.369, "dur": 0.594, + "args": { + "External id": 721838,"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": 6305210199297.287, "dur": 35.771, + "args": { + "External id": 721839,"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": 6305210199358.065, "dur": 21.372, + "args": { + "External id": 721840,"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": 6305210199392.430, "dur": 90.099, + "args": { + "External id": 721841,"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": 6305210199498.919, "dur": 71.432, + "args": { + "External id": 721842,"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": 6305210199587.174, "dur": 30.776, + "args": { + "External id": 721843,"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": 6305210199627.180, "dur": 33.643, + "args": { + "External id": 721844,"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": 6305210199669.371, "dur": 29.662, + "args": { + "External id": 721845,"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": 6305210199709.484, "dur": 42.844, + "args": { + "External id": 721846,"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": 6305210199783.401, "dur": 31.006, + "args": { + "External id": 721847,"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": 6305210199832.104, "dur": 33.777, + "args": { + "External id": 721848,"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": 6305210199886.496, "dur": 27.196, + "args": { + "External id": 721849,"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": 6305210199936.233, "dur": 21.447, + "args": { + "External id": 721850,"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": 6305210199976.736, "dur": 20.930, + "args": { + "External id": 721851,"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": 6305210200120.536, "dur": 17.579, + "args": { + "External id": 721852,"Record function id": 0, "Ev Idx": 11195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305210200124.109, "dur": 12.897, + "args": { + "External id": 721853,"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": 6305210200128.843, "dur": 6.692, + "args": { + "External id": 721854,"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": 6305210200130.742, "dur": 4.658, + "args": { + "External id": 721855,"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": 6305210200142.034, "dur": 5.165, + "args": { + "External id": 721856,"Record function id": 0, "Ev Idx": 11199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305210200143.509, "dur": 3.283, + "args": { + "External id": 721857,"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": 6305210200144.182, "dur": 2.112, + "args": { + "External id": 721858,"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": 6305210200145.063, "dur": 1.166, + "args": { + "External id": 721859,"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": 6305210200150.530, "dur": 4.806, + "args": { + "External id": 721860,"Record function id": 0, "Ev Idx": 11203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305210200152.059, "dur": 2.862, + "args": { + "External id": 721861,"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": 6305210200152.970, "dur": 1.531, + "args": { + "External id": 721862,"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": 6305210200153.269, "dur": 1.165, + "args": { + "External id": 721863,"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": 6305210200158.680, "dur": 3.950, + "args": { + "External id": 721864,"Record function id": 0, "Ev Idx": 11207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305210200159.892, "dur": 2.350, + "args": { + "External id": 721865,"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": 6305210200160.575, "dur": 1.269, + "args": { + "External id": 721866,"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": 6305210200161.063, "dur": 0.709, + "args": { + "External id": 721867,"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": 6305210200165.830, "dur": 3.751, + "args": { + "External id": 721868,"Record function id": 0, "Ev Idx": 11211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305210200167.062, "dur": 2.144, + "args": { + "External id": 721869,"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": 6305210200167.563, "dur": 1.021, + "args": { + "External id": 721870,"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": 6305210200167.816, "dur": 0.706, + "args": { + "External id": 721871,"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": 6305210200172.745, "dur": 6.916, + "args": { + "External id": 721872,"Record function id": 0, "Ev Idx": 11215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305210200174.036, "dur": 5.202, + "args": { + "External id": 721873,"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": 6305210200174.520, "dur": 4.259, + "args": { + "External id": 721874,"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": 6305210200175.326, "dur": 3.350, + "args": { + "External id": 721875,"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": 6305210200182.959, "dur": 4.103, + "args": { + "External id": 721876,"Record function id": 0, "Ev Idx": 11219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305210200184.299, "dur": 2.350, + "args": { + "External id": 721877,"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": 6305210200184.775, "dur": 1.477, + "args": { + "External id": 721878,"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": 6305210200185.055, "dur": 1.130, + "args": { + "External id": 721879,"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": 6305210200190.272, "dur": 4.486, + "args": { + "External id": 721880,"Record function id": 0, "Ev Idx": 11223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305210200191.855, "dur": 2.494, + "args": { + "External id": 721881,"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": 6305210200192.694, "dur": 1.214, + "args": { + "External id": 721882,"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": 6305210200192.950, "dur": 0.873, + "args": { + "External id": 721883,"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": 6305210200198.376, "dur": 4.511, + "args": { + "External id": 721884,"Record function id": 0, "Ev Idx": 11227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305210200199.350, "dur": 3.146, + "args": { + "External id": 721885,"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": 6305210200199.792, "dur": 1.969, + "args": { + "External id": 721886,"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": 6305210200200.765, "dur": 0.874, + "args": { + "External id": 721887,"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": 6305210200207.139, "dur": 62749.305, + "args": { + "External id": 721888,"Record function id": 0, "Sequence number": 7674626, "Fwd thread id": 1, "Ev Idx": 11231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305210200208.566, "dur": 62737.890, + "args": { + "External id": 721889,"Sequence number": 7674626, "Fwd thread 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": 6305210200208.566, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.3)", "pid": 2338707, "tid": 2379456, + "ts": 6305210200243.463, "dur": 42.791, + "args": { + "External id": 721890,"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": 6305210200294.672, "dur": 68.620, + "args": { + "External id": 721891,"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": 6305210200369.719, "dur": 62568.307, + "args": { + "External id": 721892,"Record function id": 0, "Ev Idx": 11235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305210200464.657, "dur": 8.262, + "args": { + "External id": 721893,"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": 6305210200482.877, "dur": 5.186, + "args": { + "External id": 721894,"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": 6305210200502.733, "dur": 61384.095, + "args": { + "External id": 721895,"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": 6305210200533.643, "dur": 61338.746, + "args": { + "External id": 721896,"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": 6305210200634.318, "dur": 19.574, + "args": { + "External id": 721897,"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": 6305210200674.706, "dur": 61144.625, + "args": { + "External id": 721898,"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": 6305210200677.594, "dur": 61140.100, + "args": { + "External id": 721899,"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": 6305210200682.499, "dur": 10.611, + "args": { + "External id": 721900,"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": 6305210200695.241, "dur": 61115.449, + "args": { + "External id": 721901,"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": 6305210262007.350, "dur": 17.231, + "args": { + "External id": 721902,"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": 6305210262011.296, "dur": 12.968, + "args": { + "External id": 721903,"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": 6305210262103.203, "dur": 383.172, + "args": { + "External id": 721904,"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": 6305210262138.003, "dur": 343.369, + "args": { + "External id": 721905,"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": 6305210262152.143, "dur": 323.641, + "args": { + "External id": 721906,"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": 6305210262520.270, "dur": 3.271, + "args": { + "External id": 721907,"Record function id": 0, "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": 6305210262594.889, "dur": 6.712, + "args": { + "External id": 721908,"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": 6305210262617.518, "dur": 39.305, + "args": { + "External id": 721909,"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": 6305210262667.752, "dur": 1.767, + "args": { + "External id": 721910,"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": 6305210262675.212, "dur": 15.000, + "args": { + "External id": 721911,"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": 6305210262695.632, "dur": 2.940, + "args": { + "External id": 721912,"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": 6305210262702.726, "dur": 11.455, + "args": { + "External id": 721913,"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": 6305210262726.530, "dur": 0.721, + "args": { + "External id": 721914,"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": 6305210262731.843, "dur": 13.611, + "args": { + "External id": 721915,"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": 6305210262750.377, "dur": 0.650, + "args": { + "External id": 721916,"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": 6305210262754.834, "dur": 12.016, + "args": { + "External id": 721917,"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": 6305210262771.099, "dur": 0.945, + "args": { + "External id": 721918,"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": 6305210262776.002, "dur": 12.370, + "args": { + "External id": 721919,"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": 6305210262794.846, "dur": 1.002, + "args": { + "External id": 721920,"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": 6305210262818.634, "dur": 10.787, + "args": { + "External id": 721921,"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": 6305210262842.366, "dur": 0.755, + "args": { + "External id": 721922,"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": 6305210262846.605, "dur": 10.641, + "args": { + "External id": 721923,"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": 6305210262861.759, "dur": 0.691, + "args": { + "External id": 721924,"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": 6305210262866.041, "dur": 9.769, + "args": { + "External id": 721925,"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": 6305210262973.040, "dur": 2995.502, + "args": { + "External id": 721926,"Record function id": 0, "Ev Idx": 11269 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.2)", "pid": 2338707, "tid": 2379456, + "ts": 6305210262996.111, "dur": 1154.149, + "args": { + "External id": 721927,"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": 6305210263014.086, "dur": 378.535, + "args": { + "External id": 721928,"Record function id": 0, "Ev Idx": 11271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6305210263139.512, "dur": 5.520, + "args": { + "External id": 721929,"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": 6305210263148.889, "dur": 3.427, + "args": { + "External id": 721930,"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": 6305210263154.032, "dur": 1.000, + "args": { + "External id": 721931,"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": 6305210263156.926, "dur": 0.910, + "args": { + "External id": 721932,"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": 6305210263159.612, "dur": 0.966, + "args": { + "External id": 721933,"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": 6305210263162.182, "dur": 0.885, + "args": { + "External id": 721934,"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": 6305210263164.419, "dur": 0.862, + "args": { + "External id": 721935,"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": 6305210263166.506, "dur": 1.615, + "args": { + "External id": 721936,"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": 6305210263171.846, "dur": 0.597, + "args": { + "External id": 721937,"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": 6305210263173.960, "dur": 3.406, + "args": { + "External id": 721938,"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": 6305210263195.956, "dur": 163.139, + "args": { + "External id": 721939,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305210263212.376, "dur": 142.063, + "args": { + "External id": 721940,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305210263238.366, "dur": 14.472, + "args": { + "External id": 721941,"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": 6305210263256.459, "dur": 69.979, + "args": { + "External id": 721942,"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": 6305210263259.278, "dur": 66.829, + "args": { + "External id": 721943,"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": 6305210263263.661, "dur": 5.765, + "args": { + "External id": 721944,"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": 6305210263273.183, "dur": 52.129, + "args": { + "External id": 721945,"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": 6305210263479.946, "dur": 662.266, + "args": { + "External id": 721946,"Record function id": 0, "Ev Idx": 11289 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.1)", "pid": 2338707, "tid": 2379456, + "ts": 6305210263497.364, "dur": 630.527, + "args": { + "External id": 721947,"Record function id": 0, "Ev Idx": 11290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305210263580.677, "dur": 6.542, + "args": { + "External id": 721948,"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": 6305210263602.339, "dur": 30.237, + "args": { + "External id": 721949,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305210263607.641, "dur": 1.995, + "args": { + "External id": 721950,"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": 6305210263611.848, "dur": 0.747, + "args": { + "External id": 721951,"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": 6305210263614.231, "dur": 0.645, + "args": { + "External id": 721952,"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": 6305210263615.994, "dur": 0.520, + "args": { + "External id": 721953,"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": 6305210263618.273, "dur": 2.751, + "args": { + "External id": 721954,"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": 6305210263622.386, "dur": 0.396, + "args": { + "External id": 721955,"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": 6305210263623.715, "dur": 0.560, + "args": { + "External id": 721956,"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": 6305210263625.890, "dur": 0.511, + "args": { + "External id": 721957,"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": 6305210263628.200, "dur": 0.446, + "args": { + "External id": 721958,"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": 6305210263646.662, "dur": 51.825, + "args": { + "External id": 721959,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305210263730.203, "dur": 112.601, + "args": { + "External id": 721960,"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": 6305210263740.469, "dur": 2.920, + "args": { + "External id": 721961,"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": 6305210263748.576, "dur": 10.720, + "args": { + "External id": 721962,"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": 6305210263752.870, "dur": 6.024, + "args": { + "External id": 721963,"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": 6305210263756.886, "dur": 0.754, + "args": { + "External id": 721964,"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": 6305210263765.490, "dur": 24.696, + "args": { + "External id": 721965,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305210263767.415, "dur": 0.807, + "args": { + "External id": 721966,"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": 6305210263769.632, "dur": 2.665, + "args": { + "External id": 721967,"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": 6305210263773.865, "dur": 0.497, + "args": { + "External id": 721968,"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": 6305210263775.798, "dur": 0.265, + "args": { + "External id": 721969,"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": 6305210263777.112, "dur": 0.501, + "args": { + "External id": 721970,"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": 6305210263779.032, "dur": 0.444, + "args": { + "External id": 721971,"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": 6305210263780.983, "dur": 0.397, + "args": { + "External id": 721972,"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": 6305210263782.267, "dur": 0.372, + "args": { + "External id": 721973,"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": 6305210263784.225, "dur": 0.504, + "args": { + "External id": 721974,"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": 6305210263800.409, "dur": 32.780, + "args": { + "External id": 721975,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305210263890.983, "dur": 120.987, + "args": { + "External id": 721976,"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": 6305210263918.628, "dur": 89.859, + "args": { + "External id": 721977,"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": 6305210263929.234, "dur": 74.941, + "args": { + "External id": 721978,"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": 6305210264030.316, "dur": 1.961, + "args": { + "External id": 721979,"Record function id": 0, "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": 6305210264158.682, "dur": 1790.071, + "args": { + "External id": 721980,"Sequence number": 7674625, "Fwd thread 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": 6305210264158.682, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6305210264280.687, "dur": 114.501, + "args": { + "External id": 721981,"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": 6305210264439.184, "dur": 41.840, + "args": { + "External id": 721982,"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": 6305210264501.452, "dur": 73.923, + "args": { + "External id": 721983,"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": 6305210264589.672, "dur": 33.656, + "args": { + "External id": 721984,"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": 6305210264630.171, "dur": 33.900, + "args": { + "External id": 721985,"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": 6305210264670.490, "dur": 28.849, + "args": { + "External id": 721986,"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": 6305210264707.447, "dur": 29.578, + "args": { + "External id": 721987,"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": 6305210264765.235, "dur": 24.640, + "args": { + "External id": 721988,"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": 6305210264809.420, "dur": 28.422, + "args": { + "External id": 721989,"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": 6305210264857.870, "dur": 19.428, + "args": { + "External id": 721990,"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": 6305210264891.626, "dur": 17.557, + "args": { + "External id": 721991,"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": 6305210264919.044, "dur": 41.802, + "args": { + "External id": 721992,"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": 6305210264964.462, "dur": 33.831, + "args": { + "External id": 721993,"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": 6305210265026.566, "dur": 305.458, + "args": { + "External id": 721994,"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": 6305210265157.871, "dur": 7.396, + "args": { + "External id": 721995,"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": 6305210265167.533, "dur": 2.662, + "args": { + "External id": 721996,"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": 6305210265171.178, "dur": 2.473, + "args": { + "External id": 721997,"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": 6305210265174.973, "dur": 4.740, + "args": { + "External id": 721998,"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": 6305210265229.786, "dur": 5.104, + "args": { + "External id": 721999,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305210265231.720, "dur": 2.994, + "args": { + "External id": 722000,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305210265236.729, "dur": 33.024, + "args": { + "External id": 722001,"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": 6305210265242.622, "dur": 1.886, + "args": { + "External id": 722002,"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": 6305210265271.146, "dur": 2.186, + "args": { + "External id": 722003,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305210265272.541, "dur": 0.716, + "args": { + "External id": 722004,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305210265274.340, "dur": 14.348, + "args": { + "External id": 722005,"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": 6305210265276.395, "dur": 0.466, + "args": { + "External id": 722006,"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": 6305210265365.624, "dur": 25.856, + "args": { + "External id": 722007,"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": 6305210265407.279, "dur": 15.958, + "args": { + "External id": 722008,"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": 6305210265431.471, "dur": 52.770, + "args": { + "External id": 722009,"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": 6305210265491.475, "dur": 63.545, + "args": { + "External id": 722010,"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": 6305210265567.382, "dur": 23.450, + "args": { + "External id": 722011,"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": 6305210265599.633, "dur": 43.503, + "args": { + "External id": 722012,"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": 6305210265658.620, "dur": 38.775, + "args": { + "External id": 722013,"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": 6305210265704.515, "dur": 33.840, + "args": { + "External id": 722014,"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": 6305210265762.490, "dur": 25.356, + "args": { + "External id": 722015,"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": 6305210265802.814, "dur": 26.353, + "args": { + "External id": 722016,"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": 6305210265843.095, "dur": 16.442, + "args": { + "External id": 722017,"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": 6305210265872.851, "dur": 15.793, + "args": { + "External id": 722018,"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": 6305210265900.405, "dur": 16.339, + "args": { + "External id": 722019,"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": 6305210265991.069, "dur": 15.147, + "args": { + "External id": 722020,"Record function id": 0, "Ev Idx": 11363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305210265994.367, "dur": 10.842, + "args": { + "External id": 722021,"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": 6305210265998.249, "dur": 5.987, + "args": { + "External id": 722022,"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": 6305210266000.064, "dur": 4.046, + "args": { + "External id": 722023,"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": 6305210266010.060, "dur": 5.109, + "args": { + "External id": 722024,"Record function id": 0, "Ev Idx": 11367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305210266011.450, "dur": 3.295, + "args": { + "External id": 722025,"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": 6305210266012.244, "dur": 1.996, + "args": { + "External id": 722026,"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": 6305210266012.970, "dur": 1.154, + "args": { + "External id": 722027,"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": 6305210266018.556, "dur": 4.215, + "args": { + "External id": 722028,"Record function id": 0, "Ev Idx": 11371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305210266019.847, "dur": 2.485, + "args": { + "External id": 722029,"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": 6305210266020.367, "dur": 1.460, + "args": { + "External id": 722030,"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": 6305210266020.760, "dur": 1.004, + "args": { + "External id": 722031,"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": 6305210266025.982, "dur": 3.546, + "args": { + "External id": 722032,"Record function id": 0, "Ev Idx": 11375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305210266026.911, "dur": 2.225, + "args": { + "External id": 722033,"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": 6305210266027.383, "dur": 1.340, + "args": { + "External id": 722034,"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": 6305210266027.913, "dur": 0.743, + "args": { + "External id": 722035,"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": 6305210266042.331, "dur": 3.839, + "args": { + "External id": 722036,"Record function id": 0, "Ev Idx": 11379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305210266043.479, "dur": 2.283, + "args": { + "External id": 722037,"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": 6305210266044.152, "dur": 1.015, + "args": { + "External id": 722038,"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": 6305210266044.484, "dur": 0.619, + "args": { + "External id": 722039,"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": 6305210266049.369, "dur": 57.529, + "args": { + "External id": 722040,"Record function id": 0, "Ev Idx": 11383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305210266050.484, "dur": 55.085, + "args": { + "External id": 722041,"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": 6305210266050.979, "dur": 53.117, + "args": { + "External id": 722042,"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": 6305210266099.646, "dur": 4.080, + "args": { + "External id": 722043,"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": 6305210266112.438, "dur": 5.044, + "args": { + "External id": 722044,"Record function id": 0, "Ev Idx": 11387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305210266114.217, "dur": 2.860, + "args": { + "External id": 722045,"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": 6305210266115.357, "dur": 1.286, + "args": { + "External id": 722046,"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": 6305210266115.783, "dur": 0.774, + "args": { + "External id": 722047,"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": 6305210266120.788, "dur": 4.304, + "args": { + "External id": 722048,"Record function id": 0, "Ev Idx": 11391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305210266122.247, "dur": 2.437, + "args": { + "External id": 722049,"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": 6305210266122.727, "dur": 1.524, + "args": { + "External id": 722050,"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": 6305210266123.413, "dur": 0.756, + "args": { + "External id": 722051,"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": 6305210266128.437, "dur": 4.070, + "args": { + "External id": 722052,"Record function id": 0, "Ev Idx": 11395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305210266129.707, "dur": 2.393, + "args": { + "External id": 722053,"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": 6305210266130.309, "dur": 1.203, + "args": { + "External id": 722054,"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": 6305210266130.763, "dur": 0.682, + "args": { + "External id": 722055,"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": 6305210266136.479, "dur": 63512.066, + "args": { + "External id": 722056,"Record function id": 0, "Sequence number": 7674624, "Fwd thread id": 1, "Ev Idx": 11399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305210266138.092, "dur": 63499.848, + "args": { + "External id": 722057,"Sequence number": 7674624, "Fwd thread 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": 6305210266138.092, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.2)", "pid": 2338707, "tid": 2379456, + "ts": 6305210266170.304, "dur": 39.040, + "args": { + "External id": 722058,"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": 6305210266217.575, "dur": 65.279, + "args": { + "External id": 722059,"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": 6305210266290.270, "dur": 63340.077, + "args": { + "External id": 722060,"Record function id": 0, "Ev Idx": 11403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305210266382.708, "dur": 7.310, + "args": { + "External id": 722061,"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": 6305210266400.218, "dur": 4.666, + "args": { + "External id": 722062,"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": 6305210266420.371, "dur": 62190.492, + "args": { + "External id": 722063,"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": 6305210266435.714, "dur": 62161.221, + "args": { + "External id": 722064,"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": 6305210266558.602, "dur": 19.769, + "args": { + "External id": 722065,"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": 6305210266604.337, "dur": 61940.346, + "args": { + "External id": 722066,"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": 6305210266607.384, "dur": 61936.006, + "args": { + "External id": 722067,"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": 6305210266612.840, "dur": 9.890, + "args": { + "External id": 722068,"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": 6305210266624.692, "dur": 61912.467, + "args": { + "External id": 722069,"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": 6305210328725.746, "dur": 13.716, + "args": { + "External id": 722070,"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": 6305210328729.610, "dur": 9.480, + "args": { + "External id": 722071,"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": 6305210328771.737, "dur": 452.643, + "args": { + "External id": 722072,"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": 6305210328803.277, "dur": 414.790, + "args": { + "External id": 722073,"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": 6305210328815.049, "dur": 396.821, + "args": { + "External id": 722074,"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": 6305210329246.027, "dur": 2.534, + "args": { + "External id": 722075,"Record function id": 0, "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": 6305210329311.459, "dur": 6.909, + "args": { + "External id": 722076,"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": 6305210329330.873, "dur": 35.180, + "args": { + "External id": 722077,"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": 6305210329377.101, "dur": 4.402, + "args": { + "External id": 722078,"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": 6305210329386.880, "dur": 12.726, + "args": { + "External id": 722079,"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": 6305210329405.329, "dur": 0.827, + "args": { + "External id": 722080,"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": 6305210329410.862, "dur": 12.309, + "args": { + "External id": 722081,"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": 6305210329428.572, "dur": 1.045, + "args": { + "External id": 722082,"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": 6305210329433.489, "dur": 12.535, + "args": { + "External id": 722083,"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": 6305210329450.127, "dur": 0.672, + "args": { + "External id": 722084,"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": 6305210329454.903, "dur": 10.023, + "args": { + "External id": 722085,"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": 6305210329469.207, "dur": 0.816, + "args": { + "External id": 722086,"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": 6305210329473.874, "dur": 10.250, + "args": { + "External id": 722087,"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": 6305210329489.218, "dur": 0.686, + "args": { + "External id": 722088,"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": 6305210329494.009, "dur": 10.963, + "args": { + "External id": 722089,"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": 6305210329527.139, "dur": 1.328, + "args": { + "External id": 722090,"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": 6305210329532.977, "dur": 15.802, + "args": { + "External id": 722091,"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": 6305210329553.029, "dur": 0.697, + "args": { + "External id": 722092,"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": 6305210329557.912, "dur": 11.239, + "args": { + "External id": 722093,"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": 6305210329664.806, "dur": 2983.408, + "args": { + "External id": 722094,"Record function id": 0, "Ev Idx": 11437 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.1)", "pid": 2338707, "tid": 2379456, + "ts": 6305210329685.803, "dur": 1104.899, + "args": { + "External id": 722095,"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": 6305210329701.666, "dur": 339.997, + "args": { + "External id": 722096,"Record function id": 0, "Ev Idx": 11439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6305210329787.770, "dur": 6.397, + "args": { + "External id": 722097,"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": 6305210329797.897, "dur": 1.021, + "args": { + "External id": 722098,"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": 6305210329800.751, "dur": 1.042, + "args": { + "External id": 722099,"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": 6305210329803.504, "dur": 0.857, + "args": { + "External id": 722100,"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": 6305210329807.063, "dur": 0.753, + "args": { + "External id": 722101,"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": 6305210329809.696, "dur": 0.812, + "args": { + "External id": 722102,"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": 6305210329811.824, "dur": 0.948, + "args": { + "External id": 722103,"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": 6305210329814.125, "dur": 1.685, + "args": { + "External id": 722104,"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": 6305210329818.595, "dur": 2.946, + "args": { + "External id": 722105,"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": 6305210329822.960, "dur": 0.603, + "args": { + "External id": 722106,"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": 6305210329849.382, "dur": 159.651, + "args": { + "External id": 722107,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305210329865.461, "dur": 138.895, + "args": { + "External id": 722108,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305210329891.047, "dur": 15.139, + "args": { + "External id": 722109,"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": 6305210329910.131, "dur": 66.898, + "args": { + "External id": 722110,"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": 6305210329912.920, "dur": 63.659, + "args": { + "External id": 722111,"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": 6305210329916.957, "dur": 8.851, + "args": { + "External id": 722112,"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": 6305210329927.391, "dur": 48.510, + "args": { + "External id": 722113,"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": 6305210330184.105, "dur": 598.445, + "args": { + "External id": 722114,"Record function id": 0, "Ev Idx": 11457 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.0)", "pid": 2338707, "tid": 2379456, + "ts": 6305210330203.538, "dur": 566.043, + "args": { + "External id": 722115,"Record function id": 0, "Ev Idx": 11458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305210330268.889, "dur": 6.418, + "args": { + "External id": 722116,"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": 6305210330290.287, "dur": 28.042, + "args": { + "External id": 722117,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305210330296.114, "dur": 1.958, + "args": { + "External id": 722118,"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": 6305210330300.095, "dur": 0.426, + "args": { + "External id": 722119,"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": 6305210330301.801, "dur": 0.904, + "args": { + "External id": 722120,"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": 6305210330304.245, "dur": 2.163, + "args": { + "External id": 722121,"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": 6305210330307.891, "dur": 0.376, + "args": { + "External id": 722122,"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": 6305210330309.294, "dur": 0.305, + "args": { + "External id": 722123,"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": 6305210330310.900, "dur": 0.405, + "args": { + "External id": 722124,"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": 6305210330312.613, "dur": 0.302, + "args": { + "External id": 722125,"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": 6305210330314.239, "dur": 0.297, + "args": { + "External id": 722126,"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": 6305210330329.365, "dur": 45.769, + "args": { + "External id": 722127,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305210330406.099, "dur": 130.595, + "args": { + "External id": 722128,"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": 6305210330416.475, "dur": 3.178, + "args": { + "External id": 722129,"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": 6305210330424.787, "dur": 10.319, + "args": { + "External id": 722130,"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": 6305210330429.201, "dur": 5.521, + "args": { + "External id": 722131,"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": 6305210330433.034, "dur": 0.535, + "args": { + "External id": 722132,"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": 6305210330441.878, "dur": 25.354, + "args": { + "External id": 722133,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305210330444.120, "dur": 2.401, + "args": { + "External id": 722134,"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": 6305210330447.563, "dur": 0.422, + "args": { + "External id": 722135,"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": 6305210330449.390, "dur": 0.605, + "args": { + "External id": 722136,"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": 6305210330451.532, "dur": 0.360, + "args": { + "External id": 722137,"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": 6305210330453.011, "dur": 0.776, + "args": { + "External id": 722138,"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": 6305210330455.246, "dur": 0.414, + "args": { + "External id": 722139,"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": 6305210330457.051, "dur": 0.376, + "args": { + "External id": 722140,"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": 6305210330458.276, "dur": 0.300, + "args": { + "External id": 722141,"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": 6305210330459.917, "dur": 2.695, + "args": { + "External id": 722142,"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": 6305210330481.158, "dur": 46.091, + "args": { + "External id": 722143,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305210330583.106, "dur": 118.038, + "args": { + "External id": 722144,"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": 6305210330608.900, "dur": 88.866, + "args": { + "External id": 722145,"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": 6305210330618.285, "dur": 74.723, + "args": { + "External id": 722146,"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": 6305210330715.590, "dur": 1.813, + "args": { + "External id": 722147,"Record function id": 0, "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": 6305210330798.561, "dur": 1828.793, + "args": { + "External id": 722148,"Sequence number": 7674623, "Fwd thread 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": 6305210330798.561, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6305210330908.639, "dur": 114.718, + "args": { + "External id": 722149,"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": 6305210331104.822, "dur": 45.026, + "args": { + "External id": 722150,"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": 6305210331171.875, "dur": 59.968, + "args": { + "External id": 722151,"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": 6305210331241.695, "dur": 32.921, + "args": { + "External id": 722152,"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": 6305210331281.295, "dur": 33.413, + "args": { + "External id": 722153,"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": 6305210331321.515, "dur": 28.151, + "args": { + "External id": 722154,"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": 6305210331357.888, "dur": 29.550, + "args": { + "External id": 722155,"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": 6305210331415.556, "dur": 26.363, + "args": { + "External id": 722156,"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": 6305210331459.075, "dur": 27.897, + "args": { + "External id": 722157,"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": 6305210331524.016, "dur": 23.773, + "args": { + "External id": 722158,"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": 6305210331565.844, "dur": 16.665, + "args": { + "External id": 722159,"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": 6305210331594.844, "dur": 56.637, + "args": { + "External id": 722160,"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": 6305210331655.757, "dur": 37.599, + "args": { + "External id": 722161,"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": 6305210331722.560, "dur": 245.905, + "args": { + "External id": 722162,"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": 6305210331803.596, "dur": 6.649, + "args": { + "External id": 722163,"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": 6305210331812.292, "dur": 3.409, + "args": { + "External id": 722164,"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": 6305210331817.115, "dur": 2.331, + "args": { + "External id": 722165,"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": 6305210331820.390, "dur": 4.260, + "args": { + "External id": 722166,"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": 6305210331870.665, "dur": 4.765, + "args": { + "External id": 722167,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305210331872.534, "dur": 2.750, + "args": { + "External id": 722168,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305210331877.068, "dur": 31.089, + "args": { + "External id": 722169,"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": 6305210331882.593, "dur": 1.970, + "args": { + "External id": 722170,"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": 6305210331909.771, "dur": 1.853, + "args": { + "External id": 722171,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305210331910.868, "dur": 0.679, + "args": { + "External id": 722172,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305210331912.725, "dur": 13.964, + "args": { + "External id": 722173,"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": 6305210331914.530, "dur": 0.694, + "args": { + "External id": 722174,"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": 6305210332001.217, "dur": 26.955, + "args": { + "External id": 722175,"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": 6305210332043.564, "dur": 56.465, + "args": { + "External id": 722176,"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": 6305210332112.938, "dur": 52.983, + "args": { + "External id": 722177,"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": 6305210332173.306, "dur": 44.171, + "args": { + "External id": 722178,"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": 6305210332229.621, "dur": 35.880, + "args": { + "External id": 722179,"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": 6305210332280.272, "dur": 39.616, + "args": { + "External id": 722180,"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": 6305210332328.490, "dur": 29.377, + "args": { + "External id": 722181,"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": 6305210332365.207, "dur": 34.564, + "args": { + "External id": 722182,"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": 6305210332421.268, "dur": 29.205, + "args": { + "External id": 722183,"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": 6305210332465.092, "dur": 23.687, + "args": { + "External id": 722184,"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": 6305210332501.195, "dur": 31.872, + "args": { + "External id": 722185,"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": 6305210332549.588, "dur": 14.572, + "args": { + "External id": 722186,"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": 6305210332576.262, "dur": 14.783, + "args": { + "External id": 722187,"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": 6305210332674.868, "dur": 15.645, + "args": { + "External id": 722188,"Record function id": 0, "Ev Idx": 11531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305210332678.191, "dur": 11.352, + "args": { + "External id": 722189,"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": 6305210332682.629, "dur": 5.865, + "args": { + "External id": 722190,"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": 6305210332684.164, "dur": 4.236, + "args": { + "External id": 722191,"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": 6305210332694.357, "dur": 4.791, + "args": { + "External id": 722192,"Record function id": 0, "Ev Idx": 11535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305210332695.761, "dur": 2.909, + "args": { + "External id": 722193,"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": 6305210332696.442, "dur": 1.558, + "args": { + "External id": 722194,"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": 6305210332697.088, "dur": 0.825, + "args": { + "External id": 722195,"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": 6305210332702.466, "dur": 4.247, + "args": { + "External id": 722196,"Record function id": 0, "Ev Idx": 11539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305210332703.766, "dur": 2.531, + "args": { + "External id": 722197,"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": 6305210332704.400, "dur": 1.387, + "args": { + "External id": 722198,"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": 6305210332705.005, "dur": 0.696, + "args": { + "External id": 722199,"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": 6305210332709.914, "dur": 7.286, + "args": { + "External id": 722200,"Record function id": 0, "Ev Idx": 11543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305210332710.950, "dur": 5.783, + "args": { + "External id": 722201,"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": 6305210332714.796, "dur": 1.491, + "args": { + "External id": 722202,"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": 6305210332715.569, "dur": 0.617, + "args": { + "External id": 722203,"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": 6305210332720.341, "dur": 3.670, + "args": { + "External id": 722204,"Record function id": 0, "Ev Idx": 11547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305210332721.413, "dur": 2.194, + "args": { + "External id": 722205,"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": 6305210332721.965, "dur": 1.098, + "args": { + "External id": 722206,"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": 6305210332722.374, "dur": 0.626, + "args": { + "External id": 722207,"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": 6305210332727.093, "dur": 6.023, + "args": { + "External id": 722208,"Record function id": 0, "Ev Idx": 11551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305210332728.223, "dur": 4.460, + "args": { + "External id": 722209,"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": 6305210332728.705, "dur": 3.397, + "args": { + "External id": 722210,"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": 6305210332729.033, "dur": 2.994, + "args": { + "External id": 722211,"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": 6305210332736.314, "dur": 4.274, + "args": { + "External id": 722212,"Record function id": 0, "Ev Idx": 11555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305210332737.517, "dur": 2.636, + "args": { + "External id": 722213,"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": 6305210332737.994, "dur": 1.698, + "args": { + "External id": 722214,"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": 6305210332738.873, "dur": 0.712, + "args": { + "External id": 722215,"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": 6305210332744.268, "dur": 3.448, + "args": { + "External id": 722216,"Record function id": 0, "Ev Idx": 11559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305210332745.132, "dur": 2.174, + "args": { + "External id": 722217,"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": 6305210332745.589, "dur": 1.177, + "args": { + "External id": 722218,"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": 6305210332745.844, "dur": 0.849, + "args": { + "External id": 722219,"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": 6305210332751.164, "dur": 3.977, + "args": { + "External id": 722220,"Record function id": 0, "Ev Idx": 11563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305210332752.697, "dur": 2.008, + "args": { + "External id": 722221,"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": 6305210332753.207, "dur": 1.102, + "args": { + "External id": 722222,"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": 6305210332753.533, "dur": 0.685, + "args": { + "External id": 722223,"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": 6305210332759.613, "dur": 62621.684, + "args": { + "External id": 722224,"Record function id": 0, "Sequence number": 7674622, "Fwd thread id": 1, "Ev Idx": 11567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305210332761.208, "dur": 62610.973, + "args": { + "External id": 722225,"Sequence number": 7674622, "Fwd thread 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": 6305210332761.208, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.1)", "pid": 2338707, "tid": 2379456, + "ts": 6305210332795.489, "dur": 39.531, + "args": { + "External id": 722226,"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": 6305210332842.793, "dur": 68.895, + "args": { + "External id": 722227,"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": 6305210332917.410, "dur": 62446.692, + "args": { + "External id": 722228,"Record function id": 0, "Ev Idx": 11571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305210333008.630, "dur": 7.031, + "args": { + "External id": 722229,"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": 6305210333025.651, "dur": 4.590, + "args": { + "External id": 722230,"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": 6305210333043.965, "dur": 61330.494, + "args": { + "External id": 722231,"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": 6305210333093.941, "dur": 61266.390, + "args": { + "External id": 722232,"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": 6305210333200.624, "dur": 19.512, + "args": { + "External id": 722233,"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": 6305210333240.553, "dur": 61071.650, + "args": { + "External id": 722234,"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": 6305210333243.446, "dur": 61067.260, + "args": { + "External id": 722235,"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": 6305210333248.001, "dur": 10.310, + "args": { + "External id": 722236,"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": 6305210333260.471, "dur": 61044.555, + "args": { + "External id": 722237,"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": 6305210394489.324, "dur": 13.197, + "args": { + "External id": 722238,"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": 6305210394493.212, "dur": 8.921, + "args": { + "External id": 722239,"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": 6305210394551.226, "dur": 374.503, + "args": { + "External id": 722240,"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": 6305210394580.925, "dur": 339.879, + "args": { + "External id": 722241,"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": 6305210394593.758, "dur": 321.405, + "args": { + "External id": 722242,"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": 6305210394944.105, "dur": 2.296, + "args": { + "External id": 722243,"Record function id": 0, "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": 6305210395006.026, "dur": 6.946, + "args": { + "External id": 722244,"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": 6305210395025.702, "dur": 74.734, + "args": { + "External id": 722245,"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": 6305210395114.999, "dur": 2.529, + "args": { + "External id": 722246,"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": 6305210395129.422, "dur": 17.952, + "args": { + "External id": 722247,"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": 6305210395153.975, "dur": 0.861, + "args": { + "External id": 722248,"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": 6305210395159.343, "dur": 11.443, + "args": { + "External id": 722249,"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": 6305210395176.634, "dur": 0.873, + "args": { + "External id": 722250,"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": 6305210395181.309, "dur": 10.952, + "args": { + "External id": 722251,"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": 6305210395196.962, "dur": 3.081, + "args": { + "External id": 722252,"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": 6305210395203.631, "dur": 10.501, + "args": { + "External id": 722253,"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": 6305210395218.834, "dur": 0.902, + "args": { + "External id": 722254,"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": 6305210395223.562, "dur": 16.247, + "args": { + "External id": 722255,"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": 6305210395245.584, "dur": 0.681, + "args": { + "External id": 722256,"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": 6305210395250.299, "dur": 11.096, + "args": { + "External id": 722257,"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": 6305210395265.185, "dur": 0.675, + "args": { + "External id": 722258,"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": 6305210395269.871, "dur": 12.096, + "args": { + "External id": 722259,"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": 6305210395286.155, "dur": 3.711, + "args": { + "External id": 722260,"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": 6305210395294.365, "dur": 9.221, + "args": { + "External id": 722261,"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": 6305210395397.801, "dur": 2300.334, + "args": { + "External id": 722262,"Record function id": 0, "Ev Idx": 11605 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.0)", "pid": 2338707, "tid": 2379456, + "ts": 6305210395418.437, "dur": 473.149, + "args": { + "External id": 722263,"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": 6305210395435.186, "dur": 357.439, + "args": { + "External id": 722264,"Record function id": 0, "Ev Idx": 11607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2379456, + "ts": 6305210395543.295, "dur": 4.933, + "args": { + "External id": 722265,"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": 6305210395552.211, "dur": 0.922, + "args": { + "External id": 722266,"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": 6305210395554.735, "dur": 1.060, + "args": { + "External id": 722267,"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": 6305210395557.637, "dur": 2.989, + "args": { + "External id": 722268,"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": 6305210395562.770, "dur": 0.747, + "args": { + "External id": 722269,"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": 6305210395564.990, "dur": 0.821, + "args": { + "External id": 722270,"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": 6305210395568.793, "dur": 0.960, + "args": { + "External id": 722271,"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": 6305210395571.366, "dur": 1.505, + "args": { + "External id": 722272,"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": 6305210395574.210, "dur": 0.709, + "args": { + "External id": 722273,"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": 6305210395576.294, "dur": 0.925, + "args": { + "External id": 722274,"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": 6305210395597.784, "dur": 161.776, + "args": { + "External id": 722275,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305210395614.148, "dur": 140.529, + "args": { + "External id": 722276,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305210395639.912, "dur": 15.563, + "args": { + "External id": 722277,"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": 6305210395659.415, "dur": 69.717, + "args": { + "External id": 722278,"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": 6305210395662.171, "dur": 66.521, + "args": { + "External id": 722279,"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": 6305210395666.378, "dur": 8.483, + "args": { + "External id": 722280,"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": 6305210395676.712, "dur": 51.412, + "args": { + "External id": 722281,"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": 6305210395898.878, "dur": 1778.534, + "args": { + "External id": 722282,"Sequence number": 7674621, "Fwd thread 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": 6305210395898.878, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2379456, + "ts": 6305210396008.497, "dur": 154.877, + "args": { + "External id": 722283,"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": 6305210396209.413, "dur": 43.782, + "args": { + "External id": 722284,"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": 6305210396273.752, "dur": 57.310, + "args": { + "External id": 722285,"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": 6305210396344.940, "dur": 34.813, + "args": { + "External id": 722286,"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": 6305210396387.255, "dur": 34.158, + "args": { + "External id": 722287,"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": 6305210396429.586, "dur": 29.262, + "args": { + "External id": 722288,"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": 6305210396468.978, "dur": 30.483, + "args": { + "External id": 722289,"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": 6305210396540.554, "dur": 27.513, + "args": { + "External id": 722290,"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": 6305210396585.053, "dur": 27.278, + "args": { + "External id": 722291,"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": 6305210396632.427, "dur": 19.457, + "args": { + "External id": 722292,"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": 6305210396665.021, "dur": 14.639, + "args": { + "External id": 722293,"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": 6305210396690.202, "dur": 42.545, + "args": { + "External id": 722294,"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": 6305210396736.751, "dur": 33.041, + "args": { + "External id": 722295,"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": 6305210396799.758, "dur": 292.542, + "args": { + "External id": 722296,"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": 6305210396882.945, "dur": 9.215, + "args": { + "External id": 722297,"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": 6305210396894.025, "dur": 3.220, + "args": { + "External id": 722298,"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": 6305210396898.495, "dur": 2.739, + "args": { + "External id": 722299,"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": 6305210396902.122, "dur": 4.647, + "args": { + "External id": 722300,"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": 6305210396951.138, "dur": 4.759, + "args": { + "External id": 722301,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305210396952.938, "dur": 2.823, + "args": { + "External id": 722302,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305210396957.559, "dur": 33.579, + "args": { + "External id": 722303,"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": 6305210396963.119, "dur": 1.823, + "args": { + "External id": 722304,"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": 6305210396992.428, "dur": 2.123, + "args": { + "External id": 722305,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305210396993.682, "dur": 0.801, + "args": { + "External id": 722306,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305210396995.555, "dur": 16.387, + "args": { + "External id": 722307,"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": 6305210396998.003, "dur": 0.522, + "args": { + "External id": 722308,"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": 6305210397130.667, "dur": 32.982, + "args": { + "External id": 722309,"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": 6305210397180.449, "dur": 16.343, + "args": { + "External id": 722310,"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": 6305210397205.320, "dur": 50.589, + "args": { + "External id": 722311,"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": 6305210397262.497, "dur": 39.862, + "args": { + "External id": 722312,"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": 6305210397312.896, "dur": 21.242, + "args": { + "External id": 722313,"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": 6305210397340.551, "dur": 34.308, + "args": { + "External id": 722314,"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": 6305210397382.651, "dur": 29.181, + "args": { + "External id": 722315,"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": 6305210397419.720, "dur": 34.720, + "args": { + "External id": 722316,"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": 6305210397471.669, "dur": 23.762, + "args": { + "External id": 722317,"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": 6305210397523.611, "dur": 25.346, + "args": { + "External id": 722318,"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": 6305210397563.817, "dur": 16.976, + "args": { + "External id": 722319,"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": 6305210397595.610, "dur": 19.314, + "args": { + "External id": 722320,"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": 6305210397627.101, "dur": 14.838, + "args": { + "External id": 722321,"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": 6305210397720.391, "dur": 15.171, + "args": { + "External id": 722322,"Record function id": 0, "Ev Idx": 11665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305210397723.949, "dur": 10.682, + "args": { + "External id": 722323,"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": 6305210397727.950, "dur": 5.771, + "args": { + "External id": 722324,"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": 6305210397729.258, "dur": 4.369, + "args": { + "External id": 722325,"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": 6305210397739.363, "dur": 4.795, + "args": { + "External id": 722326,"Record function id": 0, "Ev Idx": 11669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305210397740.952, "dur": 2.807, + "args": { + "External id": 722327,"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": 6305210397741.538, "dur": 1.606, + "args": { + "External id": 722328,"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": 6305210397742.204, "dur": 0.820, + "args": { + "External id": 722329,"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": 6305210397747.384, "dur": 4.403, + "args": { + "External id": 722330,"Record function id": 0, "Ev Idx": 11673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305210397749.107, "dur": 2.293, + "args": { + "External id": 722331,"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": 6305210397749.891, "dur": 0.965, + "args": { + "External id": 722332,"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": 6305210397750.193, "dur": 0.598, + "args": { + "External id": 722333,"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": 6305210397755.006, "dur": 4.343, + "args": { + "External id": 722334,"Record function id": 0, "Ev Idx": 11677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305210397756.295, "dur": 2.615, + "args": { + "External id": 722335,"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": 6305210397757.038, "dur": 1.426, + "args": { + "External id": 722336,"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": 6305210397757.738, "dur": 0.635, + "args": { + "External id": 722337,"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": 6305210397762.515, "dur": 4.103, + "args": { + "External id": 722338,"Record function id": 0, "Ev Idx": 11681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305210397763.900, "dur": 2.320, + "args": { + "External id": 722339,"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": 6305210397764.491, "dur": 0.964, + "args": { + "External id": 722340,"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": 6305210397764.781, "dur": 0.556, + "args": { + "External id": 722341,"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": 6305210397769.724, "dur": 4.541, + "args": { + "External id": 722342,"Record function id": 0, "Ev Idx": 11685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305210397771.462, "dur": 2.384, + "args": { + "External id": 722343,"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": 6305210397772.011, "dur": 1.243, + "args": { + "External id": 722344,"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": 6305210397772.508, "dur": 0.656, + "args": { + "External id": 722345,"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": 6305210397777.445, "dur": 7.076, + "args": { + "External id": 722346,"Record function id": 0, "Ev Idx": 11689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305210397778.722, "dur": 5.397, + "args": { + "External id": 722347,"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": 6305210397779.201, "dur": 4.450, + "args": { + "External id": 722348,"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": 6305210397780.540, "dur": 3.003, + "args": { + "External id": 722349,"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": 6305210397787.629, "dur": 4.510, + "args": { + "External id": 722350,"Record function id": 0, "Ev Idx": 11693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305210397789.318, "dur": 2.421, + "args": { + "External id": 722351,"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": 6305210397789.816, "dur": 1.362, + "args": { + "External id": 722352,"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": 6305210397790.418, "dur": 0.695, + "args": { + "External id": 722353,"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": 6305210397795.911, "dur": 3.589, + "args": { + "External id": 722354,"Record function id": 0, "Ev Idx": 11697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305210397797.134, "dur": 1.983, + "args": { + "External id": 722355,"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": 6305210397797.596, "dur": 1.118, + "args": { + "External id": 722356,"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": 6305210397798.009, "dur": 0.640, + "args": { + "External id": 722357,"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": 6305210397803.758, "dur": 63839.881, + "args": { + "External id": 722358,"Record function id": 0, "Sequence number": 7674620, "Fwd thread id": 1, "Ev Idx": 11701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305210397805.017, "dur": 63829.196, + "args": { + "External id": 722359,"Sequence number": 7674620, "Fwd thread 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": 6305210397805.017, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.0)", "pid": 2338707, "tid": 2379456, + "ts": 6305210397833.687, "dur": 39.140, + "args": { + "External id": 722360,"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": 6305210397880.545, "dur": 69.593, + "args": { + "External id": 722361,"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": 6305210397956.298, "dur": 63670.027, + "args": { + "External id": 722362,"Record function id": 0, "Ev Idx": 11705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305210398109.086, "dur": 9.612, + "args": { + "External id": 722363,"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": 6305210398130.888, "dur": 5.522, + "args": { + "External id": 722364,"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": 6305210398156.439, "dur": 62457.989, + "args": { + "External id": 722365,"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": 6305210398171.431, "dur": 62429.091, + "args": { + "External id": 722366,"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": 6305210398272.792, "dur": 17.758, + "args": { + "External id": 722367,"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": 6305210398310.760, "dur": 62234.531, + "args": { + "External id": 722368,"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": 6305210398314.033, "dur": 62229.868, + "args": { + "External id": 722369,"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": 6305210398318.941, "dur": 8.976, + "args": { + "External id": 722370,"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": 6305210398330.381, "dur": 62206.037, + "args": { + "External id": 722371,"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": 6305210460737.005, "dur": 13.648, + "args": { + "External id": 722372,"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": 6305210460740.942, "dur": 9.261, + "args": { + "External id": 722373,"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": 6305210460784.629, "dur": 414.912, + "args": { + "External id": 722374,"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": 6305210460814.838, "dur": 378.854, + "args": { + "External id": 722375,"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": 6305210460827.329, "dur": 359.709, + "args": { + "External id": 722376,"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": 6305210461223.948, "dur": 2.642, + "args": { + "External id": 722377,"Record function id": 0, "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": 6305210461293.711, "dur": 7.197, + "args": { + "External id": 722378,"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": 6305210461313.562, "dur": 36.138, + "args": { + "External id": 722379,"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": 6305210461360.874, "dur": 1.657, + "args": { + "External id": 722380,"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": 6305210461368.221, "dur": 13.124, + "args": { + "External id": 722381,"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": 6305210461387.427, "dur": 0.915, + "args": { + "External id": 722382,"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": 6305210461395.246, "dur": 10.689, + "args": { + "External id": 722383,"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": 6305210461411.437, "dur": 1.117, + "args": { + "External id": 722384,"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": 6305210461416.843, "dur": 11.540, + "args": { + "External id": 722385,"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": 6305210461432.651, "dur": 2.705, + "args": { + "External id": 722386,"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": 6305210461439.595, "dur": 14.789, + "args": { + "External id": 722387,"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": 6305210461458.771, "dur": 0.963, + "args": { + "External id": 722388,"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": 6305210461463.087, "dur": 12.585, + "args": { + "External id": 722389,"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": 6305210461480.345, "dur": 0.653, + "args": { + "External id": 722390,"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": 6305210461485.163, "dur": 12.415, + "args": { + "External id": 722391,"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": 6305210461502.152, "dur": 0.779, + "args": { + "External id": 722392,"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": 6305210461524.846, "dur": 15.344, + "args": { + "External id": 722393,"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": 6305210461546.781, "dur": 1.137, + "args": { + "External id": 722394,"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": 6305210461551.675, "dur": 12.074, + "args": { + "External id": 722395,"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": 6305210461660.837, "dur": 278.501, + "args": { + "External id": 722396,"Record function id": 0, "Sequence number": 7674619, "Fwd thread id": 1, "Ev Idx": 11739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 2338707, "tid": 2379456, + "ts": 6305210461663.873, "dur": 268.318, + "args": { + "External id": 722397,"Sequence number": 7674619, "Fwd thread 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": 6305210461663.873, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_embedding_dense_backward_0", "pid": 2338707, "tid": 2379456, + "ts": 6305210461785.723, "dur": 41.788, + "args": { + "External id": 722398,"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": 6305210461844.638, "dur": 27.440, + "args": { + "External id": 722399,"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": 6305210461891.276, "dur": 25.352, + "args": { + "External id": 722400,"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": 6305210461949.197, "dur": 19.377, + "args": { + "External id": 722401,"Record function id": 0, "Ev Idx": 11744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 2338707, "tid": 2379456, + "ts": 6305210461951.856, "dur": 15.825, + "args": { + "External id": 722402,"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": 6305210461955.939, "dur": 10.903, + "args": { + "External id": 722403,"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": 6305210461960.894, "dur": 5.786, + "args": { + "External id": 722404,"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": 6305210461991.069, "dur": 14250.358, + "args": { + "External id": 722405,"Record function id": 0, "Ev Idx": 11748 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate", "pid": 2338707, "tid": 2379456, + "ts": 6305210462011.220, "dur": 36.076, + "args": { + "External id": 722406,"Record function id": 0, "Ev Idx": 11749 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard", "pid": 2338707, "tid": 2379456, + "ts": 6305210462093.025, "dur": 240.081, + "args": { + "External id": 722407,"Record function id": 0, "Ev Idx": 11750 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce", "pid": 2338707, "tid": 2379456, + "ts": 6305210462340.431, "dur": 13617.655, + "args": { + "External id": 722408,"Record function id": 0, "Ev Idx": 11751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2379456, + "ts": 6305210462466.145, "dur": 8.315, + "args": { + "External id": 722409,"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": 6305210462486.267, "dur": 5.285, + "args": { + "External id": 722410,"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": 6305210462529.047, "dur": 11728.459, + "args": { + "External id": 722411,"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": 6305210462555.727, "dur": 11686.961, + "args": { + "External id": 722412,"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": 6305210463434.585, "dur": 26.243, + "args": { + "External id": 722413,"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": 6305210463717.629, "dur": 10473.704, + "args": { + "External id": 722414,"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": 6305210463721.859, "dur": 10468.184, + "args": { + "External id": 722415,"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": 6305210463728.727, "dur": 18.265, + "args": { + "External id": 722416,"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": 6305210463750.439, "dur": 10432.948, + "args": { + "External id": 722417,"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": 6305210474404.029, "dur": 13.011, + "args": { + "External id": 722418,"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": 6305210474408.591, "dur": 8.037, + "args": { + "External id": 722419,"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": 6305210474448.341, "dur": 393.500, + "args": { + "External id": 722420,"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": 6305210474474.868, "dur": 360.968, + "args": { + "External id": 722421,"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": 6305210474485.915, "dur": 344.399, + "args": { + "External id": 722422,"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": 6305210474863.073, "dur": 2.242, + "args": { + "External id": 722423,"Record function id": 0, "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": 6305210474927.023, "dur": 7.153, + "args": { + "External id": 722424,"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": 6305210474945.395, "dur": 33.063, + "args": { + "External id": 722425,"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": 6305210474989.305, "dur": 1.543, + "args": { + "External id": 722426,"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": 6305210474996.835, "dur": 14.011, + "args": { + "External id": 722427,"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": 6305210475016.536, "dur": 1.101, + "args": { + "External id": 722428,"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": 6305210475022.052, "dur": 13.121, + "args": { + "External id": 722429,"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": 6305210475041.082, "dur": 0.921, + "args": { + "External id": 722430,"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": 6305210475046.249, "dur": 49.535, + "args": { + "External id": 722431,"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": 6305210475104.955, "dur": 1.624, + "args": { + "External id": 722432,"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": 6305210475145.336, "dur": 14.934, + "args": { + "External id": 722433,"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": 6305210475167.789, "dur": 0.913, + "args": { + "External id": 722434,"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": 6305210475173.009, "dur": 13.438, + "args": { + "External id": 722435,"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": 6305210475191.023, "dur": 3.125, + "args": { + "External id": 722436,"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": 6305210475197.953, "dur": 11.921, + "args": { + "External id": 722437,"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": 6305210475214.995, "dur": 0.686, + "args": { + "External id": 722438,"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": 6305210475219.221, "dur": 12.279, + "args": { + "External id": 722439,"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": 6305210475237.352, "dur": 0.754, + "args": { + "External id": 722440,"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": 6305210475242.490, "dur": 10.930, + "args": { + "External id": 722441,"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": 6305210475258.128, "dur": 0.788, + "args": { + "External id": 722442,"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": 6305210475262.590, "dur": 11.960, + "args": { + "External id": 722443,"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": 6305210475278.996, "dur": 1.037, + "args": { + "External id": 722444,"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": 6305210475283.574, "dur": 11.041, + "args": { + "External id": 722445,"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": 6305210475298.503, "dur": 0.924, + "args": { + "External id": 722446,"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": 6305210475303.489, "dur": 10.415, + "args": { + "External id": 722447,"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": 6305210475320.218, "dur": 0.978, + "args": { + "External id": 722448,"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": 6305210475325.424, "dur": 9.626, + "args": { + "External id": 722449,"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": 6305210475339.591, "dur": 0.836, + "args": { + "External id": 722450,"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": 6305210475344.523, "dur": 10.577, + "args": { + "External id": 722451,"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": 6305210475359.248, "dur": 2.707, + "args": { + "External id": 722452,"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": 6305210475368.218, "dur": 11.064, + "args": { + "External id": 722453,"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": 6305210475384.188, "dur": 0.788, + "args": { + "External id": 722454,"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": 6305210475388.583, "dur": 12.759, + "args": { + "External id": 722455,"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": 6305210475406.117, "dur": 0.880, + "args": { + "External id": 722456,"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": 6305210475410.524, "dur": 10.997, + "args": { + "External id": 722457,"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": 6305210475425.981, "dur": 0.965, + "args": { + "External id": 722458,"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": 6305210475430.846, "dur": 12.725, + "args": { + "External id": 722459,"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": 6305210475450.013, "dur": 0.779, + "args": { + "External id": 722460,"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": 6305210475454.426, "dur": 12.005, + "args": { + "External id": 722461,"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": 6305210475471.208, "dur": 0.755, + "args": { + "External id": 722462,"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": 6305210475475.559, "dur": 12.123, + "args": { + "External id": 722463,"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": 6305210475492.246, "dur": 0.934, + "args": { + "External id": 722464,"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": 6305210475497.037, "dur": 25.101, + "args": { + "External id": 722465,"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": 6305210475529.951, "dur": 1.579, + "args": { + "External id": 722466,"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": 6305210475536.376, "dur": 14.321, + "args": { + "External id": 722467,"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": 6305210475554.893, "dur": 3.250, + "args": { + "External id": 722468,"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": 6305210475561.931, "dur": 10.755, + "args": { + "External id": 722469,"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": 6305210475576.902, "dur": 0.773, + "args": { + "External id": 722470,"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": 6305210475582.139, "dur": 10.500, + "args": { + "External id": 722471,"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": 6305210475596.729, "dur": 0.789, + "args": { + "External id": 722472,"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": 6305210475601.276, "dur": 9.285, + "args": { + "External id": 722473,"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": 6305210475616.223, "dur": 0.838, + "args": { + "External id": 722474,"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": 6305210475621.038, "dur": 12.678, + "args": { + "External id": 722475,"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": 6305210475638.331, "dur": 0.689, + "args": { + "External id": 722476,"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": 6305210475642.436, "dur": 11.508, + "args": { + "External id": 722477,"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": 6305210475658.471, "dur": 0.725, + "args": { + "External id": 722478,"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": 6305210475663.335, "dur": 12.494, + "args": { + "External id": 722479,"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": 6305210475680.128, "dur": 0.705, + "args": { + "External id": 722480,"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": 6305210475685.723, "dur": 11.639, + "args": { + "External id": 722481,"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": 6305210475700.949, "dur": 0.807, + "args": { + "External id": 722482,"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": 6305210475705.452, "dur": 12.258, + "args": { + "External id": 722483,"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": 6305210475721.669, "dur": 2.817, + "args": { + "External id": 722484,"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": 6305210475727.960, "dur": 10.091, + "args": { + "External id": 722485,"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": 6305210475743.975, "dur": 0.708, + "args": { + "External id": 722486,"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": 6305210475748.277, "dur": 10.594, + "args": { + "External id": 722487,"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": 6305210475762.618, "dur": 0.633, + "args": { + "External id": 722488,"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": 6305210475767.213, "dur": 9.240, + "args": { + "External id": 722489,"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": 6305210475780.313, "dur": 0.667, + "args": { + "External id": 722490,"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": 6305210475784.915, "dur": 10.037, + "args": { + "External id": 722491,"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": 6305210475798.908, "dur": 0.633, + "args": { + "External id": 722492,"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": 6305210475804.873, "dur": 10.445, + "args": { + "External id": 722493,"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": 6305210475819.741, "dur": 0.947, + "args": { + "External id": 722494,"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": 6305210475825.058, "dur": 11.041, + "args": { + "External id": 722495,"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": 6305210475839.903, "dur": 0.687, + "args": { + "External id": 722496,"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": 6305210475844.220, "dur": 9.751, + "args": { + "External id": 722497,"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": 6305210475857.808, "dur": 0.748, + "args": { + "External id": 722498,"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": 6305210475862.346, "dur": 10.183, + "args": { + "External id": 722499,"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": 6305210475877.445, "dur": 2.790, + "args": { + "External id": 722500,"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": 6305210475883.959, "dur": 9.928, + "args": { + "External id": 722501,"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#16383", "pid": 2338707, "tid": 2338707, + "ts": 6305203983649.570, "dur": 6521921.658, + "args": { + "External id": 701441,"Record function id": 0, "Ev Idx": 11845 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "Optimizer.zero_grad#AdamW.zero_grad", "pid": 2338707, "tid": 2338707, + "ts": 6305203983681.374, "dur": 685.388, + "args": { + "External id": 701442,"Record function id": 0, "Ev Idx": 11846 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "enumerate(DataLoader)#_StatefulMultiProcessingDataLoaderIter.__next__", "pid": 2338707, "tid": 2338707, + "ts": 6305203984422.990, "dur": 2047.004, + "args": { + "External id": 701443,"Record function id": 0, "Ev Idx": 11847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6305203985534.681, "dur": 7.556, + "args": { + "External id": 701444,"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": 6305203985565.236, "dur": 8.253, + "args": { + "External id": 701445,"Sequence number": 7674390, "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": 6305203985971.769, "dur": 2.281, + "args": { + "External id": 701446,"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": 6305203985984.306, "dur": 2.432, + "args": { + "External id": 701447,"Sequence number": 7674390, "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": 6305203986360.147, "dur": 1.785, + "args": { + "External id": 701448,"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": 6305203986366.001, "dur": 2.232, + "args": { + "External id": 701449,"Sequence number": 7674390, "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": 6305203986864.256, "dur": 15.905, + "args": { + "External id": 701450,"Sequence number": 7674390, "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": 6305203986873.981, "dur": 2.425, + "args": { + "External id": 701451,"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": 6305203986881.937, "dur": 4.235, + "args": { + "External id": 701452,"Sequence number": 7674390, "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": 6305203986883.868, "dur": 1.189, + "args": { + "External id": 701453,"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": 6305203986913.676, "dur": 3214.229, + "args": { + "External id": 701454,"Sequence number": 7674390, "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": 6305203986921.348, "dur": 3205.808, + "args": { + "External id": 701455,"Sequence number": 7674390, "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": 6305203986931.525, "dur": 10.050, + "args": { + "External id": 701456,"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": 6305203986944.057, "dur": 3181.803, + "args": { + "External id": 701457,"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": 6305203986953.782, "dur": 0.540, + "args": { + "External id": 701458,"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": 6305203986957.091, "dur": 7.210, + "args": { + "External id": 701459,"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": 6305203986959.763, "dur": 4.376, + "args": { + "External id": 701460,"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": 6305203986963.209, "dur": 0.687, + "args": { + "External id": 701461,"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": 6305203986966.173, "dur": 192.423, + "args": { + "External id": 701462,"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": 6305203986968.862, "dur": 189.407, + "args": { + "External id": 701463,"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": 6305203986971.283, "dur": 17.796, + "args": { + "External id": 701464,"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": 6305203986975.956, "dur": 12.530, + "args": { + "External id": 701465,"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": 6305203986989.858, "dur": 167.504, + "args": { + "External id": 701466,"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": 6305203987161.129, "dur": 2961.705, + "args": { + "External id": 701467,"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": 6305203990142.354, "dur": 353.525, + "args": { + "External id": 701468,"Sequence number": 7674390, "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": 6305203990144.337, "dur": 351.110, + "args": { + "External id": 701469,"Sequence number": 7674390, "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": 6305203990151.091, "dur": 8.946, + "args": { + "External id": 701470,"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": 6305203990164.008, "dur": 330.091, + "args": { + "External id": 701471,"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": 6305203990533.890, "dur": 57.065, + "args": { + "External id": 701472,"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": 6305203990539.483, "dur": 5.213, + "args": { + "External id": 701473,"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": 6305203990547.912, "dur": 42.731, + "args": { + "External id": 701474,"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": 6305203990555.120, "dur": 8.174, + "args": { + "External id": 701475,"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": 6305203990603.302, "dur": 73.975, + "args": { + "External id": 701476,"Sequence number": 7674390, "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": 6305203990611.067, "dur": 7.030, + "args": { + "External id": 701477,"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": 6305203990616.233, "dur": 1.594, + "args": { + "External id": 701478,"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": 6305203990619.191, "dur": 3.078, + "args": { + "External id": 701479,"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": 6305203990624.967, "dur": 3.640, + "args": { + "External id": 701480,"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": 6305203990631.616, "dur": 5.167, + "args": { + "External id": 701481,"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": 6305203990636.114, "dur": 0.532, + "args": { + "External id": 701482,"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": 6305203990637.593, "dur": 5.271, + "args": { + "External id": 701483,"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": 6305203990642.007, "dur": 0.761, + "args": { + "External id": 701484,"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": 6305203990644.557, "dur": 6.453, + "args": { + "External id": 701485,"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": 6305203990648.321, "dur": 2.579, + "args": { + "External id": 701486,"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": 6305203990650.100, "dur": 0.708, + "args": { + "External id": 701487,"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": 6305203990652.259, "dur": 24.354, + "args": { + "External id": 701488,"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": 6305203990685.025, "dur": 28.688, + "args": { + "External id": 701489,"Sequence number": 7674390, "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": 6305203990686.595, "dur": 26.917, + "args": { + "External id": 701490,"Sequence number": 7674390, "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": 6305203990691.902, "dur": 3.840, + "args": { + "External id": 701491,"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": 6305203990696.471, "dur": 16.606, + "args": { + "External id": 701492,"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": 6305203990828.373, "dur": 148.414, + "args": { + "External id": 701493,"Record function id": 0, "Ev Idx": 11897 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::inputs_to_device", "pid": 2338707, "tid": 2338707, + "ts": 6305203990909.253, "dur": 56.232, + "args": { + "External id": 701494,"Record function id": 0, "Ev Idx": 11898 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6305203990983.842, "dur": 48.549, + "args": { + "External id": 701495,"Record function id": 0, "Ev Idx": 11899 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward", "pid": 2338707, "tid": 2338707, + "ts": 6305203991040.982, "dur": 14217.466, + "args": { + "External id": 701496,"Record function id": 0, "Ev Idx": 11900 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather", "pid": 2338707, "tid": 2338707, + "ts": 6305203991050.393, "dur": 1437.806, + "args": { + "External id": 701497,"Record function id": 0, "Ev Idx": 11901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6305203991200.069, "dur": 8.463, + "args": { + "External id": 701498,"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": 6305203991225.269, "dur": 139.162, + "args": { + "External id": 701499,"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": 6305203991230.669, "dur": 1.344, + "args": { + "External id": 701500,"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": 6305203991238.936, "dur": 0.398, + "args": { + "External id": 701501,"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": 6305203991240.293, "dur": 0.543, + "args": { + "External id": 701502,"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": 6305203991241.539, "dur": 2.577, + "args": { + "External id": 701503,"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": 6305203991249.342, "dur": 0.449, + "args": { + "External id": 701504,"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": 6305203991250.424, "dur": 0.405, + "args": { + "External id": 701505,"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": 6305203991251.671, "dur": 2.213, + "args": { + "External id": 701506,"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": 6305203991257.083, "dur": 0.399, + "args": { + "External id": 701507,"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": 6305203991258.244, "dur": 0.341, + "args": { + "External id": 701508,"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": 6305203991263.718, "dur": 0.351, + "args": { + "External id": 701509,"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": 6305203991264.619, "dur": 0.249, + "args": { + "External id": 701510,"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": 6305203991265.322, "dur": 2.294, + "args": { + "External id": 701511,"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": 6305203991271.390, "dur": 0.319, + "args": { + "External id": 701512,"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": 6305203991272.240, "dur": 0.299, + "args": { + "External id": 701513,"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": 6305203991273.422, "dur": 2.551, + "args": { + "External id": 701514,"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": 6305203991278.825, "dur": 0.251, + "args": { + "External id": 701515,"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": 6305203991279.807, "dur": 0.257, + "args": { + "External id": 701516,"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": 6305203991285.453, "dur": 0.315, + "args": { + "External id": 701517,"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": 6305203991286.716, "dur": 0.337, + "args": { + "External id": 701518,"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": 6305203991287.806, "dur": 2.655, + "args": { + "External id": 701519,"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": 6305203991294.137, "dur": 0.299, + "args": { + "External id": 701520,"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": 6305203991295.098, "dur": 0.375, + "args": { + "External id": 701521,"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": 6305203991296.082, "dur": 2.678, + "args": { + "External id": 701522,"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": 6305203991301.751, "dur": 0.374, + "args": { + "External id": 701523,"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": 6305203991303.016, "dur": 0.360, + "args": { + "External id": 701524,"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": 6305203991308.464, "dur": 0.378, + "args": { + "External id": 701525,"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": 6305203991309.886, "dur": 0.339, + "args": { + "External id": 701526,"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": 6305203991310.943, "dur": 2.519, + "args": { + "External id": 701527,"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": 6305203991316.951, "dur": 0.298, + "args": { + "External id": 701528,"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": 6305203991317.773, "dur": 0.314, + "args": { + "External id": 701529,"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": 6305203991318.784, "dur": 2.619, + "args": { + "External id": 701530,"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": 6305203991324.293, "dur": 0.359, + "args": { + "External id": 701531,"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": 6305203991325.564, "dur": 0.465, + "args": { + "External id": 701532,"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": 6305203991330.317, "dur": 0.399, + "args": { + "External id": 701533,"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": 6305203991331.797, "dur": 0.249, + "args": { + "External id": 701534,"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": 6305203991332.623, "dur": 2.037, + "args": { + "External id": 701535,"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": 6305203991338.560, "dur": 0.246, + "args": { + "External id": 701536,"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": 6305203991339.541, "dur": 0.266, + "args": { + "External id": 701537,"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": 6305203991340.441, "dur": 2.612, + "args": { + "External id": 701538,"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": 6305203991390.483, "dur": 165.055, + "args": { + "External id": 701539,"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": 6305203991627.490, "dur": 336.603, + "args": { + "External id": 701540,"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": 6305203991643.446, "dur": 5.710, + "args": { + "External id": 701541,"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": 6305203991656.544, "dur": 15.948, + "args": { + "External id": 701542,"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": 6305203991661.351, "dur": 10.704, + "args": { + "External id": 701543,"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": 6305203991667.278, "dur": 0.875, + "args": { + "External id": 701544,"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": 6305203991681.049, "dur": 128.671, + "args": { + "External id": 701545,"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": 6305203991683.260, "dur": 0.502, + "args": { + "External id": 701546,"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": 6305203991684.969, "dur": 0.460, + "args": { + "External id": 701547,"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": 6305203991688.297, "dur": 2.372, + "args": { + "External id": 701548,"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": 6305203991691.297, "dur": 1.032, + "args": { + "External id": 701549,"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": 6305203991694.840, "dur": 0.405, + "args": { + "External id": 701550,"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": 6305203991696.084, "dur": 0.419, + "args": { + "External id": 701551,"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": 6305203991697.868, "dur": 0.429, + "args": { + "External id": 701552,"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": 6305203991701.312, "dur": 0.506, + "args": { + "External id": 701553,"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": 6305203991702.740, "dur": 0.731, + "args": { + "External id": 701554,"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": 6305203991704.093, "dur": 0.307, + "args": { + "External id": 701555,"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": 6305203991707.106, "dur": 2.194, + "args": { + "External id": 701556,"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": 6305203991710.336, "dur": 0.400, + "args": { + "External id": 701557,"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": 6305203991713.629, "dur": 2.314, + "args": { + "External id": 701558,"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": 6305203991716.704, "dur": 0.338, + "args": { + "External id": 701559,"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": 6305203991717.873, "dur": 0.394, + "args": { + "External id": 701560,"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": 6305203991723.251, "dur": 0.310, + "args": { + "External id": 701561,"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": 6305203991724.590, "dur": 0.306, + "args": { + "External id": 701562,"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": 6305203991725.656, "dur": 0.292, + "args": { + "External id": 701563,"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": 6305203991731.027, "dur": 2.233, + "args": { + "External id": 701564,"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": 6305203991733.953, "dur": 0.367, + "args": { + "External id": 701565,"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": 6305203991737.483, "dur": 2.655, + "args": { + "External id": 701566,"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": 6305203991741.169, "dur": 0.319, + "args": { + "External id": 701567,"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": 6305203991742.149, "dur": 0.382, + "args": { + "External id": 701568,"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": 6305203991747.657, "dur": 0.234, + "args": { + "External id": 701569,"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": 6305203991748.855, "dur": 0.316, + "args": { + "External id": 701570,"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": 6305203991749.597, "dur": 0.376, + "args": { + "External id": 701571,"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": 6305203991755.448, "dur": 2.079, + "args": { + "External id": 701572,"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": 6305203991758.423, "dur": 0.357, + "args": { + "External id": 701573,"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": 6305203991761.997, "dur": 2.116, + "args": { + "External id": 701574,"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": 6305203991764.786, "dur": 0.271, + "args": { + "External id": 701575,"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": 6305203991766.107, "dur": 0.257, + "args": { + "External id": 701576,"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": 6305203991771.422, "dur": 0.233, + "args": { + "External id": 701577,"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": 6305203991772.330, "dur": 0.443, + "args": { + "External id": 701578,"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": 6305203991773.541, "dur": 0.239, + "args": { + "External id": 701579,"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": 6305203991779.597, "dur": 2.194, + "args": { + "External id": 701580,"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": 6305203991782.501, "dur": 0.295, + "args": { + "External id": 701581,"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": 6305203991786.088, "dur": 2.619, + "args": { + "External id": 701582,"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": 6305203991789.401, "dur": 0.297, + "args": { + "External id": 701583,"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": 6305203991790.613, "dur": 0.257, + "args": { + "External id": 701584,"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": 6305203991830.765, "dur": 115.380, + "args": { + "External id": 701585,"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": 6305203992023.569, "dur": 347.128, + "args": { + "External id": 701586,"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": 6305203992096.998, "dur": 267.597, + "args": { + "External id": 701587,"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": 6305203992109.323, "dur": 249.233, + "args": { + "External id": 701588,"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": 6305203992397.166, "dur": 2.124, + "args": { + "External id": 701589,"Record function id": 0, "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": 6305203992504.561, "dur": 12532.298, + "args": { + "External id": 701590,"Record function id": 0, "Ev Idx": 11994 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6305203992713.985, "dur": 7.376, + "args": { + "External id": 701591,"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": 6305203992725.586, "dur": 1.305, + "args": { + "External id": 701592,"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": 6305203992728.629, "dur": 0.916, + "args": { + "External id": 701593,"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": 6305203992731.469, "dur": 3.189, + "args": { + "External id": 701594,"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": 6305203992736.198, "dur": 0.794, + "args": { + "External id": 701595,"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": 6305203992738.812, "dur": 0.977, + "args": { + "External id": 701596,"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": 6305203992743.332, "dur": 0.872, + "args": { + "External id": 701597,"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": 6305203992745.702, "dur": 3.557, + "args": { + "External id": 701598,"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": 6305203992752.834, "dur": 0.815, + "args": { + "External id": 701599,"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": 6305203992755.054, "dur": 0.998, + "args": { + "External id": 701600,"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": 6305203992759.667, "dur": 0.829, + "args": { + "External id": 701601,"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": 6305203992761.991, "dur": 3.027, + "args": { + "External id": 701602,"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": 6305203992766.574, "dur": 0.933, + "args": { + "External id": 701603,"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": 6305203992769.018, "dur": 1.034, + "args": { + "External id": 701604,"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": 6305203992773.890, "dur": 0.923, + "args": { + "External id": 701605,"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": 6305203992776.373, "dur": 2.668, + "args": { + "External id": 701606,"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": 6305203992782.787, "dur": 0.700, + "args": { + "External id": 701607,"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": 6305203992784.941, "dur": 0.849, + "args": { + "External id": 701608,"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": 6305203992789.820, "dur": 0.890, + "args": { + "External id": 701609,"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": 6305203992792.112, "dur": 3.177, + "args": { + "External id": 701610,"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": 6305203992796.568, "dur": 0.906, + "args": { + "External id": 701611,"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": 6305203992799.296, "dur": 0.810, + "args": { + "External id": 701612,"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": 6305203992803.809, "dur": 0.953, + "args": { + "External id": 701613,"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": 6305203992806.234, "dur": 2.353, + "args": { + "External id": 701614,"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": 6305203992827.651, "dur": 0.686, + "args": { + "External id": 701615,"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": 6305203992829.741, "dur": 0.876, + "args": { + "External id": 701616,"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": 6305203992833.964, "dur": 0.696, + "args": { + "External id": 701617,"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": 6305203992836.001, "dur": 3.181, + "args": { + "External id": 701618,"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": 6305203992840.404, "dur": 1.395, + "args": { + "External id": 701619,"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": 6305203992843.308, "dur": 0.993, + "args": { + "External id": 701620,"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": 6305203992847.961, "dur": 0.755, + "args": { + "External id": 701621,"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": 6305203992850.297, "dur": 2.886, + "args": { + "External id": 701622,"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": 6305203992856.761, "dur": 0.933, + "args": { + "External id": 701623,"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": 6305203992859.171, "dur": 1.009, + "args": { + "External id": 701624,"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": 6305203992863.801, "dur": 0.606, + "args": { + "External id": 701625,"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": 6305203992865.790, "dur": 3.203, + "args": { + "External id": 701626,"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": 6305203992870.331, "dur": 0.839, + "args": { + "External id": 701627,"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": 6305203992872.322, "dur": 1.191, + "args": { + "External id": 701628,"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": 6305203992876.634, "dur": 0.747, + "args": { + "External id": 701629,"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": 6305203992878.881, "dur": 2.535, + "args": { + "External id": 701630,"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": 6305203992909.198, "dur": 12066.839, + "args": { + "External id": 701631,"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": 6305203992933.772, "dur": 12031.654, + "args": { + "External id": 701632,"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": 6305203992957.143, "dur": 5.395, + "args": { + "External id": 701633,"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": 6305203992968.270, "dur": 11953.596, + "args": { + "External id": 701634,"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": 6305203992973.331, "dur": 11947.923, + "args": { + "External id": 701635,"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": 6305203992981.358, "dur": 5.702, + "args": { + "External id": 701636,"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": 6305203992988.788, "dur": 11928.932, + "args": { + "External id": 701637,"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": 6305204005349.459, "dur": 39.859, + "args": { + "External id": 701638,"Record function id": 0, "Ev Idx": 12042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 0/0", "pid": 2338707, "tid": 2338707, + "ts": 6305204005391.169, "dur": 243.709, + "args": { + "External id": 701639,"Record function id": 0, "Ev Idx": 12043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305204005436.469, "dur": 188.495, + "args": { + "External id": 701640,"Sequence number": 7674390, "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": 6305204005436.469, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_embedding_0", "pid": 2338707, "tid": 2338707, + "ts": 6305204005529.804, "dur": 53.945, + "args": { + "External id": 701641,"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": 6305204005696.593, "dur": 56.667, + "args": { + "External id": 701642,"Record function id": 0, "Ev Idx": 12046 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.0)", "pid": 2338707, "tid": 2338707, + "ts": 6305204005764.556, "dur": 8547.685, + "args": { + "External id": 701643,"Record function id": 0, "Ev Idx": 12047 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.0)", "pid": 2338707, "tid": 2338707, + "ts": 6305204005772.563, "dur": 887.767, + "args": { + "External id": 701644,"Record function id": 0, "Ev Idx": 12048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6305204005844.465, "dur": 12.670, + "args": { + "External id": 701645,"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": 6305204005869.653, "dur": 48.504, + "args": { + "External id": 701646,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305204005879.662, "dur": 2.667, + "args": { + "External id": 701647,"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": 6305204005884.195, "dur": 0.448, + "args": { + "External id": 701648,"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": 6305204005885.445, "dur": 2.881, + "args": { + "External id": 701649,"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": 6305204005892.213, "dur": 0.593, + "args": { + "External id": 701650,"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": 6305204005893.619, "dur": 0.563, + "args": { + "External id": 701651,"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": 6305204005900.242, "dur": 0.244, + "args": { + "External id": 701652,"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": 6305204005901.170, "dur": 0.587, + "args": { + "External id": 701653,"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": 6305204005902.215, "dur": 2.854, + "args": { + "External id": 701654,"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": 6305204005910.123, "dur": 0.622, + "args": { + "External id": 701655,"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": 6305204005928.495, "dur": 65.028, + "args": { + "External id": 701656,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305204006024.947, "dur": 178.470, + "args": { + "External id": 701657,"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": 6305204006035.909, "dur": 5.295, + "args": { + "External id": 701658,"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": 6305204006046.585, "dur": 50.877, + "args": { + "External id": 701659,"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": 6305204006051.611, "dur": 45.377, + "args": { + "External id": 701660,"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": 6305204006093.742, "dur": 1.069, + "args": { + "External id": 701661,"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": 6305204006105.858, "dur": 34.330, + "args": { + "External id": 701662,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305204006107.983, "dur": 0.627, + "args": { + "External id": 701663,"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": 6305204006112.338, "dur": 0.482, + "args": { + "External id": 701664,"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": 6305204006116.337, "dur": 0.489, + "args": { + "External id": 701665,"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": 6305204006119.970, "dur": 0.606, + "args": { + "External id": 701666,"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": 6305204006121.246, "dur": 2.665, + "args": { + "External id": 701667,"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": 6305204006124.891, "dur": 0.423, + "args": { + "External id": 701668,"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": 6305204006128.413, "dur": 0.467, + "args": { + "External id": 701669,"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": 6305204006132.125, "dur": 0.299, + "args": { + "External id": 701670,"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": 6305204006133.197, "dur": 0.468, + "args": { + "External id": 701671,"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": 6305204006153.744, "dur": 39.254, + "args": { + "External id": 701672,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305204006255.735, "dur": 307.191, + "args": { + "External id": 701673,"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": 6305204006289.013, "dur": 268.582, + "args": { + "External id": 701674,"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": 6305204006298.551, "dur": 252.808, + "args": { + "External id": 701675,"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": 6305204006588.073, "dur": 2.388, + "args": { + "External id": 701676,"Record function id": 0, "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": 6305204006680.197, "dur": 7367.208, + "args": { + "External id": 701677,"Record function id": 0, "Ev Idx": 12081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6305204006774.192, "dur": 6.519, + "args": { + "External id": 701678,"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": 6305204006784.118, "dur": 1.002, + "args": { + "External id": 701679,"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": 6305204006787.191, "dur": 1.111, + "args": { + "External id": 701680,"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": 6305204006789.839, "dur": 4.114, + "args": { + "External id": 701681,"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": 6305204006797.762, "dur": 1.031, + "args": { + "External id": 701682,"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": 6305204006800.026, "dur": 1.143, + "args": { + "External id": 701683,"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": 6305204006802.904, "dur": 1.124, + "args": { + "External id": 701684,"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": 6305204006807.166, "dur": 2.618, + "args": { + "External id": 701685,"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": 6305204006813.986, "dur": 0.802, + "args": { + "External id": 701686,"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": 6305204006816.460, "dur": 1.109, + "args": { + "External id": 701687,"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": 6305204006833.706, "dur": 7170.761, + "args": { + "External id": 701688,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305204006849.727, "dur": 7145.660, + "args": { + "External id": 701689,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305204006875.320, "dur": 14.231, + "args": { + "External id": 701690,"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": 6305204006893.153, "dur": 7068.114, + "args": { + "External id": 701691,"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": 6305204006898.107, "dur": 7062.475, + "args": { + "External id": 701692,"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": 6305204006904.021, "dur": 6.810, + "args": { + "External id": 701693,"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": 6305204006912.656, "dur": 7044.624, + "args": { + "External id": 701694,"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": 6305204014252.431, "dur": 33.910, + "args": { + "External id": 701695,"Sequence number": 7674391, "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": 6305204014252.431, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6305204014269.548, "dur": 11.813, + "args": { + "External id": 701696,"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": 6305204014275.838, "dur": 5.179, + "args": { + "External id": 701697,"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": 6305204014357.996, "dur": 112.123, + "args": { + "External id": 701698,"Record function id": 0, "Ev Idx": 12102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6305204014471.170, "dur": 1213.717, + "args": { + "External id": 701699,"Record function id": 0, "Ev Idx": 12103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305204014536.634, "dur": 1134.087, + "args": { + "External id": 701700,"Sequence number": 7674392, "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": 6305204014536.634, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6305204014615.205, "dur": 54.652, + "args": { + "External id": 701701,"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": 6305204014683.637, "dur": 113.474, + "args": { + "External id": 701702,"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": 6305204014810.658, "dur": 38.005, + "args": { + "External id": 701703,"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": 6305204014857.855, "dur": 29.765, + "args": { + "External id": 701704,"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": 6305204014913.839, "dur": 26.768, + "args": { + "External id": 701705,"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": 6305204014965.848, "dur": 20.947, + "args": { + "External id": 701706,"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": 6305204015010.886, "dur": 185.222, + "args": { + "External id": 701707,"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": 6305204015108.777, "dur": 14.472, + "args": { + "External id": 701708,"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": 6305204015114.076, "dur": 8.116, + "args": { + "External id": 701709,"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": 6305204015125.892, "dur": 3.708, + "args": { + "External id": 701710,"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": 6305204015133.464, "dur": 1.074, + "args": { + "External id": 701711,"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": 6305204015137.570, "dur": 2.917, + "args": { + "External id": 701712,"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": 6305204015207.666, "dur": 56.001, + "args": { + "External id": 701713,"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": 6305204015300.022, "dur": 30.850, + "args": { + "External id": 701714,"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": 6305204015337.596, "dur": 42.141, + "args": { + "External id": 701715,"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": 6305204015388.806, "dur": 34.602, + "args": { + "External id": 701716,"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": 6305204015444.334, "dur": 25.023, + "args": { + "External id": 701717,"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": 6305204015478.139, "dur": 63.312, + "args": { + "External id": 701718,"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": 6305204015571.281, "dur": 21.304, + "args": { + "External id": 701719,"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": 6305204015750.455, "dur": 81.810, + "args": { + "External id": 701720,"Record function id": 0, "Ev Idx": 12124 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6305204015907.337, "dur": 46.821, + "args": { + "External id": 701721,"Record function id": 0, "Ev Idx": 12125 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.1)", "pid": 2338707, "tid": 2338707, + "ts": 6305204015962.875, "dur": 29062.092, + "args": { + "External id": 701722,"Record function id": 0, "Ev Idx": 12126 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.1)", "pid": 2338707, "tid": 2338707, + "ts": 6305204015972.298, "dur": 1001.337, + "args": { + "External id": 701723,"Record function id": 0, "Ev Idx": 12127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6305204016051.494, "dur": 54.827, + "args": { + "External id": 701724,"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": 6305204016122.848, "dur": 47.549, + "args": { + "External id": 701725,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305204016131.275, "dur": 4.922, + "args": { + "External id": 701726,"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": 6305204016137.853, "dur": 0.906, + "args": { + "External id": 701727,"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": 6305204016141.904, "dur": 0.559, + "args": { + "External id": 701728,"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": 6305204016145.606, "dur": 0.377, + "args": { + "External id": 701729,"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": 6305204016147.180, "dur": 2.797, + "args": { + "External id": 701730,"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": 6305204016153.152, "dur": 0.538, + "args": { + "External id": 701731,"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": 6305204016155.622, "dur": 0.563, + "args": { + "External id": 701732,"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": 6305204016157.145, "dur": 0.530, + "args": { + "External id": 701733,"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": 6305204016160.739, "dur": 2.684, + "args": { + "External id": 701734,"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": 6305204016181.956, "dur": 59.900, + "args": { + "External id": 701735,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305204016276.449, "dur": 144.745, + "args": { + "External id": 701736,"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": 6305204016292.055, "dur": 4.242, + "args": { + "External id": 701737,"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": 6305204016302.217, "dur": 10.751, + "args": { + "External id": 701738,"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": 6305204016307.337, "dur": 5.226, + "args": { + "External id": 701739,"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": 6305204016310.813, "dur": 0.492, + "args": { + "External id": 701740,"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": 6305204016319.615, "dur": 39.536, + "args": { + "External id": 701741,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305204016323.857, "dur": 0.784, + "args": { + "External id": 701742,"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": 6305204016326.026, "dur": 2.528, + "args": { + "External id": 701743,"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": 6305204016329.524, "dur": 2.846, + "args": { + "External id": 701744,"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": 6305204016336.673, "dur": 0.332, + "args": { + "External id": 701745,"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": 6305204016338.198, "dur": 0.504, + "args": { + "External id": 701746,"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": 6305204016341.757, "dur": 0.306, + "args": { + "External id": 701747,"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": 6305204016345.615, "dur": 0.525, + "args": { + "External id": 701748,"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": 6305204016346.777, "dur": 0.518, + "args": { + "External id": 701749,"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": 6305204016352.994, "dur": 0.486, + "args": { + "External id": 701750,"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": 6305204016374.571, "dur": 35.795, + "args": { + "External id": 701751,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305204016477.184, "dur": 398.201, + "args": { + "External id": 701752,"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": 6305204016537.561, "dur": 332.435, + "args": { + "External id": 701753,"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": 6305204016549.432, "dur": 314.632, + "args": { + "External id": 701754,"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": 6305204016899.178, "dur": 2.024, + "args": { + "External id": 701755,"Record function id": 0, "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": 6305204016994.627, "dur": 27840.223, + "args": { + "External id": 701756,"Record function id": 0, "Ev Idx": 12160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6305204017138.343, "dur": 7.044, + "args": { + "External id": 701757,"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": 6305204017149.440, "dur": 1.217, + "args": { + "External id": 701758,"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": 6305204017152.507, "dur": 1.051, + "args": { + "External id": 701759,"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": 6305204017155.512, "dur": 1.139, + "args": { + "External id": 701760,"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": 6305204017158.029, "dur": 1.097, + "args": { + "External id": 701761,"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": 6305204017163.771, "dur": 1.144, + "args": { + "External id": 701762,"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": 6305204017168.395, "dur": 1.074, + "args": { + "External id": 701763,"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": 6305204017170.720, "dur": 5.131, + "args": { + "External id": 701764,"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": 6305204017177.039, "dur": 0.995, + "args": { + "External id": 701765,"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": 6305204017181.368, "dur": 3.272, + "args": { + "External id": 701766,"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": 6305204017203.347, "dur": 27586.808, + "args": { + "External id": 701767,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305204017222.362, "dur": 27559.564, + "args": { + "External id": 701768,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305204017315.107, "dur": 15.620, + "args": { + "External id": 701769,"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": 6305204017334.741, "dur": 27407.984, + "args": { + "External id": 701770,"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": 6305204017337.401, "dur": 27404.810, + "args": { + "External id": 701771,"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": 6305204017343.034, "dur": 6.477, + "args": { + "External id": 701772,"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": 6305204017351.552, "dur": 27387.742, + "args": { + "External id": 701773,"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": 6305204044968.581, "dur": 31.797, + "args": { + "External id": 701774,"Sequence number": 7674393, "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": 6305204044968.581, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6305204044985.011, "dur": 10.374, + "args": { + "External id": 701775,"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": 6305204044990.437, "dur": 4.760, + "args": { + "External id": 701776,"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": 6305204045103.563, "dur": 80.883, + "args": { + "External id": 701777,"Record function id": 0, "Ev Idx": 12181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6305204045186.409, "dur": 1145.990, + "args": { + "External id": 701778,"Record function id": 0, "Ev Idx": 12182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305204045225.716, "dur": 1093.061, + "args": { + "External id": 701779,"Sequence number": 7674394, "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": 6305204045225.716, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6305204045306.189, "dur": 52.891, + "args": { + "External id": 701780,"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": 6305204045376.223, "dur": 108.300, + "args": { + "External id": 701781,"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": 6305204045494.836, "dur": 57.682, + "args": { + "External id": 701782,"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": 6305204045561.812, "dur": 31.247, + "args": { + "External id": 701783,"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": 6305204045622.696, "dur": 27.825, + "args": { + "External id": 701784,"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": 6305204045674.369, "dur": 22.084, + "args": { + "External id": 701785,"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": 6305204045714.856, "dur": 137.733, + "args": { + "External id": 701786,"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": 6305204045770.874, "dur": 11.229, + "args": { + "External id": 701787,"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": 6305204045776.097, "dur": 5.143, + "args": { + "External id": 701788,"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": 6305204045786.517, "dur": 6.643, + "args": { + "External id": 701789,"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": 6305204045794.566, "dur": 2.787, + "args": { + "External id": 701790,"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": 6305204045799.612, "dur": 3.002, + "args": { + "External id": 701791,"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": 6305204045864.106, "dur": 50.288, + "args": { + "External id": 701792,"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": 6305204045946.265, "dur": 31.485, + "args": { + "External id": 701793,"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": 6305204045987.896, "dur": 41.191, + "args": { + "External id": 701794,"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": 6305204046036.292, "dur": 75.275, + "args": { + "External id": 701795,"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": 6305204046140.796, "dur": 25.016, + "args": { + "External id": 701796,"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": 6305204046172.234, "dur": 37.793, + "args": { + "External id": 701797,"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": 6305204046229.746, "dur": 20.377, + "args": { + "External id": 701798,"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": 6305204046398.216, "dur": 76.639, + "args": { + "External id": 701799,"Record function id": 0, "Ev Idx": 12203 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6305204046580.264, "dur": 50.198, + "args": { + "External id": 701800,"Record function id": 0, "Ev Idx": 12204 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.2)", "pid": 2338707, "tid": 2338707, + "ts": 6305204046639.976, "dur": 30340.407, + "args": { + "External id": 701801,"Record function id": 0, "Ev Idx": 12205 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.2)", "pid": 2338707, "tid": 2338707, + "ts": 6305204046652.117, "dur": 1002.461, + "args": { + "External id": 701802,"Record function id": 0, "Ev Idx": 12206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6305204046730.113, "dur": 9.786, + "args": { + "External id": 701803,"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": 6305204046754.668, "dur": 43.682, + "args": { + "External id": 701804,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305204046760.108, "dur": 2.455, + "args": { + "External id": 701805,"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": 6305204046766.842, "dur": 0.713, + "args": { + "External id": 701806,"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": 6305204046770.943, "dur": 0.628, + "args": { + "External id": 701807,"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": 6305204046772.614, "dur": 0.660, + "args": { + "External id": 701808,"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": 6305204046776.092, "dur": 0.468, + "args": { + "External id": 701809,"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": 6305204046780.136, "dur": 0.525, + "args": { + "External id": 701810,"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": 6305204046781.240, "dur": 4.704, + "args": { + "External id": 701811,"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": 6305204046788.739, "dur": 0.484, + "args": { + "External id": 701812,"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": 6305204046789.955, "dur": 0.508, + "args": { + "External id": 701813,"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": 6305204046808.692, "dur": 59.404, + "args": { + "External id": 701814,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305204046901.057, "dur": 131.983, + "args": { + "External id": 701815,"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": 6305204046913.784, "dur": 4.226, + "args": { + "External id": 701816,"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": 6305204046923.466, "dur": 10.495, + "args": { + "External id": 701817,"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": 6305204046928.399, "dur": 5.148, + "args": { + "External id": 701818,"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": 6305204046931.552, "dur": 0.720, + "args": { + "External id": 701819,"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": 6305204046940.469, "dur": 38.362, + "args": { + "External id": 701820,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305204046944.053, "dur": 2.746, + "args": { + "External id": 701821,"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": 6305204046947.758, "dur": 0.532, + "args": { + "External id": 701822,"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": 6305204046949.341, "dur": 0.707, + "args": { + "External id": 701823,"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": 6305204046955.082, "dur": 2.428, + "args": { + "External id": 701824,"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": 6305204046958.262, "dur": 0.410, + "args": { + "External id": 701825,"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": 6305204046961.843, "dur": 0.421, + "args": { + "External id": 701826,"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": 6305204046965.097, "dur": 0.566, + "args": { + "External id": 701827,"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": 6305204046966.511, "dur": 0.605, + "args": { + "External id": 701828,"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": 6305204046970.177, "dur": 2.558, + "args": { + "External id": 701829,"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": 6305204046989.580, "dur": 34.426, + "args": { + "External id": 701830,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305204047133.837, "dur": 416.075, + "args": { + "External id": 701831,"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": 6305204047167.621, "dur": 376.878, + "args": { + "External id": 701832,"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": 6305204047179.466, "dur": 355.564, + "args": { + "External id": 701833,"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": 6305204047577.166, "dur": 2.840, + "args": { + "External id": 701834,"Record function id": 0, "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": 6305204047676.024, "dur": 29118.469, + "args": { + "External id": 701835,"Record function id": 0, "Ev Idx": 12239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6305204047777.979, "dur": 6.485, + "args": { + "External id": 701836,"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": 6305204047787.930, "dur": 1.338, + "args": { + "External id": 701837,"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": 6305204047791.538, "dur": 3.710, + "args": { + "External id": 701838,"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": 6305204047797.063, "dur": 1.620, + "args": { + "External id": 701839,"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": 6305204047800.178, "dur": 1.546, + "args": { + "External id": 701840,"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": 6305204047803.048, "dur": 1.075, + "args": { + "External id": 701841,"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": 6305204047808.080, "dur": 0.947, + "args": { + "External id": 701842,"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": 6305204047810.562, "dur": 2.918, + "args": { + "External id": 701843,"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": 6305204047814.830, "dur": 0.925, + "args": { + "External id": 701844,"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": 6305204047817.267, "dur": 1.145, + "args": { + "External id": 701845,"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": 6305204047840.466, "dur": 28912.129, + "args": { + "External id": 701846,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305204047855.539, "dur": 28888.526, + "args": { + "External id": 701847,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305204047875.134, "dur": 15.217, + "args": { + "External id": 701848,"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": 6305204047893.985, "dur": 28816.728, + "args": { + "External id": 701849,"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": 6305204047896.547, "dur": 28813.568, + "args": { + "External id": 701850,"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": 6305204047902.722, "dur": 4.959, + "args": { + "External id": 701851,"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": 6305204047909.637, "dur": 28797.069, + "args": { + "External id": 701852,"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": 6305204076925.837, "dur": 30.311, + "args": { + "External id": 701853,"Sequence number": 7674395, "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": 6305204076925.837, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6305204076943.098, "dur": 8.268, + "args": { + "External id": 701854,"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": 6305204076946.668, "dur": 4.527, + "args": { + "External id": 701855,"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": 6305204077023.072, "dur": 109.753, + "args": { + "External id": 701856,"Record function id": 0, "Ev Idx": 12260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6305204077135.599, "dur": 1138.320, + "args": { + "External id": 701857,"Record function id": 0, "Ev Idx": 12261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305204077178.967, "dur": 1081.090, + "args": { + "External id": 701858,"Sequence number": 7674396, "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": 6305204077178.967, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6305204077250.089, "dur": 50.166, + "args": { + "External id": 701859,"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": 6305204077313.334, "dur": 108.292, + "args": { + "External id": 701860,"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": 6305204077432.823, "dur": 41.392, + "args": { + "External id": 701861,"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": 6305204077483.768, "dur": 46.607, + "args": { + "External id": 701862,"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": 6305204077561.670, "dur": 27.155, + "args": { + "External id": 701863,"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": 6305204077608.458, "dur": 18.046, + "args": { + "External id": 701864,"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": 6305204077650.376, "dur": 135.381, + "args": { + "External id": 701865,"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": 6305204077703.923, "dur": 13.172, + "args": { + "External id": 701866,"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": 6305204077711.298, "dur": 4.941, + "args": { + "External id": 701867,"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": 6305204077719.644, "dur": 5.419, + "args": { + "External id": 701868,"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": 6305204077726.172, "dur": 1.228, + "args": { + "External id": 701869,"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": 6305204077729.960, "dur": 5.899, + "args": { + "External id": 701870,"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": 6305204077796.549, "dur": 52.853, + "args": { + "External id": 701871,"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": 6305204077882.793, "dur": 27.646, + "args": { + "External id": 701872,"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": 6305204077920.408, "dur": 41.306, + "args": { + "External id": 701873,"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": 6305204077970.246, "dur": 34.673, + "args": { + "External id": 701874,"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": 6305204078026.257, "dur": 25.261, + "args": { + "External id": 701875,"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": 6305204078096.265, "dur": 41.527, + "args": { + "External id": 701876,"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": 6305204078162.748, "dur": 20.109, + "args": { + "External id": 701877,"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": 6305204078340.410, "dur": 79.218, + "args": { + "External id": 701878,"Record function id": 0, "Ev Idx": 12282 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6305204078494.465, "dur": 65.030, + "args": { + "External id": 701879,"Record function id": 0, "Ev Idx": 12283 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.3)", "pid": 2338707, "tid": 2338707, + "ts": 6305204078569.509, "dur": 28694.781, + "args": { + "External id": 701880,"Record function id": 0, "Ev Idx": 12284 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.3)", "pid": 2338707, "tid": 2338707, + "ts": 6305204078580.204, "dur": 1032.794, + "args": { + "External id": 701881,"Record function id": 0, "Ev Idx": 12285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6305204078661.101, "dur": 10.632, + "args": { + "External id": 701882,"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": 6305204078684.916, "dur": 47.889, + "args": { + "External id": 701883,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305204078690.527, "dur": 2.599, + "args": { + "External id": 701884,"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": 6305204078699.638, "dur": 0.619, + "args": { + "External id": 701885,"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": 6305204078701.197, "dur": 0.643, + "args": { + "External id": 701886,"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": 6305204078708.134, "dur": 0.552, + "args": { + "External id": 701887,"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": 6305204078713.432, "dur": 0.586, + "args": { + "External id": 701888,"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": 6305204078714.945, "dur": 0.555, + "args": { + "External id": 701889,"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": 6305204078717.993, "dur": 3.388, + "args": { + "External id": 701890,"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": 6305204078721.914, "dur": 0.646, + "args": { + "External id": 701891,"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": 6305204078723.394, "dur": 0.507, + "args": { + "External id": 701892,"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": 6305204078744.997, "dur": 56.527, + "args": { + "External id": 701893,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305204078834.115, "dur": 139.696, + "args": { + "External id": 701894,"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": 6305204078846.330, "dur": 3.816, + "args": { + "External id": 701895,"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": 6305204078855.775, "dur": 10.678, + "args": { + "External id": 701896,"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": 6305204078860.793, "dur": 5.261, + "args": { + "External id": 701897,"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": 6305204078864.299, "dur": 0.502, + "args": { + "External id": 701898,"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": 6305204078874.475, "dur": 36.122, + "args": { + "External id": 701899,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305204078875.978, "dur": 2.444, + "args": { + "External id": 701900,"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": 6305204078879.628, "dur": 0.390, + "args": { + "External id": 701901,"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": 6305204078883.690, "dur": 0.514, + "args": { + "External id": 701902,"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": 6305204078887.384, "dur": 3.084, + "args": { + "External id": 701903,"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": 6305204078893.221, "dur": 0.482, + "args": { + "External id": 701904,"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": 6305204078894.535, "dur": 0.459, + "args": { + "External id": 701905,"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": 6305204078898.184, "dur": 0.444, + "args": { + "External id": 701906,"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": 6305204078901.274, "dur": 0.440, + "args": { + "External id": 701907,"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": 6305204078902.874, "dur": 2.319, + "args": { + "External id": 701908,"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": 6305204078930.551, "dur": 34.953, + "args": { + "External id": 701909,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305204079027.483, "dur": 457.619, + "args": { + "External id": 701910,"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": 6305204079100.028, "dur": 378.481, + "args": { + "External id": 701911,"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": 6305204079117.328, "dur": 355.766, + "args": { + "External id": 701912,"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": 6305204079525.991, "dur": 7.482, + "args": { + "External id": 701913,"Record function id": 0, "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": 6305204079634.527, "dur": 27407.665, + "args": { + "External id": 701914,"Record function id": 0, "Ev Idx": 12318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6305204079738.470, "dur": 6.643, + "args": { + "External id": 701915,"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": 6305204079748.414, "dur": 1.156, + "args": { + "External id": 701916,"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": 6305204079751.322, "dur": 3.541, + "args": { + "External id": 701917,"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": 6305204079756.583, "dur": 1.123, + "args": { + "External id": 701918,"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": 6305204079759.016, "dur": 0.999, + "args": { + "External id": 701919,"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": 6305204079761.344, "dur": 1.085, + "args": { + "External id": 701920,"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": 6305204079769.615, "dur": 0.762, + "args": { + "External id": 701921,"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": 6305204079772.123, "dur": 2.882, + "args": { + "External id": 701922,"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": 6305204079776.270, "dur": 0.844, + "args": { + "External id": 701923,"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": 6305204079778.663, "dur": 1.126, + "args": { + "External id": 701924,"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": 6305204079799.684, "dur": 27196.662, + "args": { + "External id": 701925,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305204079815.240, "dur": 27172.704, + "args": { + "External id": 701926,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305204079834.670, "dur": 16.314, + "args": { + "External id": 701927,"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": 6305204079854.540, "dur": 27097.650, + "args": { + "External id": 701928,"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": 6305204079857.460, "dur": 27094.077, + "args": { + "External id": 701929,"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": 6305204079865.895, "dur": 5.894, + "args": { + "External id": 701930,"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": 6305204079873.832, "dur": 27074.320, + "args": { + "External id": 701931,"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": 6305204107200.059, "dur": 39.259, + "args": { + "External id": 701932,"Sequence number": 7674397, "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": 6305204107200.059, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6305204107224.238, "dur": 10.075, + "args": { + "External id": 701933,"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": 6305204107228.636, "dur": 5.346, + "args": { + "External id": 701934,"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": 6305204107304.680, "dur": 76.017, + "args": { + "External id": 701935,"Record function id": 0, "Ev Idx": 12339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6305204107384.152, "dur": 1170.030, + "args": { + "External id": 701936,"Record function id": 0, "Ev Idx": 12340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305204107422.872, "dur": 1115.322, + "args": { + "External id": 701937,"Sequence number": 7674398, "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": 6305204107422.872, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6305204107489.484, "dur": 62.638, + "args": { + "External id": 701938,"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": 6305204107567.372, "dur": 106.258, + "args": { + "External id": 701939,"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": 6305204107690.026, "dur": 36.650, + "args": { + "External id": 701940,"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": 6305204107733.287, "dur": 30.356, + "args": { + "External id": 701941,"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": 6305204107793.757, "dur": 28.758, + "args": { + "External id": 701942,"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": 6305204107841.842, "dur": 16.850, + "args": { + "External id": 701943,"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": 6305204107881.028, "dur": 134.194, + "args": { + "External id": 701944,"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": 6305204107936.857, "dur": 10.875, + "args": { + "External id": 701945,"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": 6305204107941.772, "dur": 5.223, + "args": { + "External id": 701946,"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": 6305204107950.149, "dur": 3.885, + "args": { + "External id": 701947,"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": 6305204107955.542, "dur": 0.826, + "args": { + "External id": 701948,"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": 6305204107960.842, "dur": 5.131, + "args": { + "External id": 701949,"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": 6305204108025.930, "dur": 88.691, + "args": { + "External id": 701950,"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": 6305204108155.949, "dur": 30.958, + "args": { + "External id": 701951,"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": 6305204108197.977, "dur": 47.158, + "args": { + "External id": 701952,"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": 6305204108284.503, "dur": 36.443, + "args": { + "External id": 701953,"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": 6305204108349.462, "dur": 23.267, + "args": { + "External id": 701954,"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": 6305204108378.523, "dur": 35.304, + "args": { + "External id": 701955,"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": 6305204108431.538, "dur": 19.779, + "args": { + "External id": 701956,"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": 6305204108621.597, "dur": 81.215, + "args": { + "External id": 701957,"Record function id": 0, "Ev Idx": 12361 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6305204108777.063, "dur": 48.568, + "args": { + "External id": 701958,"Record function id": 0, "Ev Idx": 12362 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.4)", "pid": 2338707, "tid": 2338707, + "ts": 6305204108834.995, "dur": 30544.320, + "args": { + "External id": 701959,"Record function id": 0, "Ev Idx": 12363 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.4)", "pid": 2338707, "tid": 2338707, + "ts": 6305204108845.131, "dur": 985.658, + "args": { + "External id": 701960,"Record function id": 0, "Ev Idx": 12364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6305204108926.964, "dur": 8.917, + "args": { + "External id": 701961,"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": 6305204108949.080, "dur": 45.187, + "args": { + "External id": 701962,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305204108956.758, "dur": 2.259, + "args": { + "External id": 701963,"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": 6305204108962.707, "dur": 0.419, + "args": { + "External id": 701964,"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": 6305204108963.937, "dur": 0.573, + "args": { + "External id": 701965,"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": 6305204108967.232, "dur": 0.642, + "args": { + "External id": 701966,"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": 6305204108970.606, "dur": 0.786, + "args": { + "External id": 701967,"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": 6305204108974.692, "dur": 0.790, + "args": { + "External id": 701968,"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": 6305204108976.214, "dur": 5.845, + "args": { + "External id": 701969,"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": 6305204108982.758, "dur": 0.850, + "args": { + "External id": 701970,"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": 6305204108986.443, "dur": 0.409, + "args": { + "External id": 701971,"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": 6305204109004.891, "dur": 101.841, + "args": { + "External id": 701972,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305204109143.855, "dur": 137.843, + "args": { + "External id": 701973,"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": 6305204109157.839, "dur": 5.088, + "args": { + "External id": 701974,"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": 6305204109168.833, "dur": 13.073, + "args": { + "External id": 701975,"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": 6305204109173.537, "dur": 7.956, + "args": { + "External id": 701976,"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": 6305204109179.299, "dur": 0.561, + "args": { + "External id": 701977,"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": 6305204109189.026, "dur": 36.255, + "args": { + "External id": 701978,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305204109190.818, "dur": 2.521, + "args": { + "External id": 701979,"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": 6305204109196.867, "dur": 0.601, + "args": { + "External id": 701980,"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": 6305204109198.795, "dur": 0.406, + "args": { + "External id": 701981,"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": 6305204109204.795, "dur": 2.102, + "args": { + "External id": 701982,"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": 6305204109207.620, "dur": 0.550, + "args": { + "External id": 701983,"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": 6305204109209.171, "dur": 0.425, + "args": { + "External id": 701984,"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": 6305204109215.387, "dur": 0.417, + "args": { + "External id": 701985,"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": 6305204109216.506, "dur": 0.666, + "args": { + "External id": 701986,"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": 6305204109217.870, "dur": 2.249, + "args": { + "External id": 701987,"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": 6305204109237.286, "dur": 35.833, + "args": { + "External id": 701988,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305204109337.058, "dur": 393.322, + "args": { + "External id": 701989,"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": 6305204109373.199, "dur": 351.346, + "args": { + "External id": 701990,"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": 6305204109383.193, "dur": 334.949, + "args": { + "External id": 701991,"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": 6305204109755.708, "dur": 2.433, + "args": { + "External id": 701992,"Record function id": 0, "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": 6305204109852.077, "dur": 29342.910, + "args": { + "External id": 701993,"Record function id": 0, "Ev Idx": 12397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6305204109947.429, "dur": 6.353, + "args": { + "External id": 701994,"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": 6305204109957.108, "dur": 0.905, + "args": { + "External id": 701995,"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": 6305204109959.690, "dur": 3.311, + "args": { + "External id": 701996,"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": 6305204109964.597, "dur": 1.148, + "args": { + "External id": 701997,"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": 6305204109966.945, "dur": 0.985, + "args": { + "External id": 701998,"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": 6305204109969.298, "dur": 1.045, + "args": { + "External id": 701999,"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": 6305204109973.931, "dur": 1.344, + "args": { + "External id": 702000,"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": 6305204109978.778, "dur": 2.205, + "args": { + "External id": 702001,"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": 6305204109982.333, "dur": 1.042, + "args": { + "External id": 702002,"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": 6305204109984.541, "dur": 0.510, + "args": { + "External id": 702003,"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": 6305204110003.642, "dur": 29148.878, + "args": { + "External id": 702004,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305204110021.337, "dur": 29123.242, + "args": { + "External id": 702005,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305204110040.780, "dur": 52.136, + "args": { + "External id": 702006,"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": 6305204110097.724, "dur": 29013.344, + "args": { + "External id": 702007,"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": 6305204110100.439, "dur": 29010.028, + "args": { + "External id": 702008,"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": 6305204110106.755, "dur": 5.392, + "args": { + "External id": 702009,"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": 6305204110113.963, "dur": 28993.552, + "args": { + "External id": 702010,"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": 6305204139324.842, "dur": 30.819, + "args": { + "External id": 702011,"Sequence number": 7674399, "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": 6305204139324.842, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6305204139340.288, "dur": 10.742, + "args": { + "External id": 702012,"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": 6305204139346.100, "dur": 4.720, + "args": { + "External id": 702013,"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": 6305204139421.350, "dur": 71.130, + "args": { + "External id": 702014,"Record function id": 0, "Ev Idx": 12418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6305204139493.770, "dur": 1144.771, + "args": { + "External id": 702015,"Record function id": 0, "Ev Idx": 12419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305204139549.147, "dur": 1074.695, + "args": { + "External id": 702016,"Sequence number": 7674400, "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": 6305204139549.147, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6305204139616.330, "dur": 49.896, + "args": { + "External id": 702017,"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": 6305204139679.271, "dur": 107.641, + "args": { + "External id": 702018,"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": 6305204139798.599, "dur": 36.426, + "args": { + "External id": 702019,"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": 6305204139843.549, "dur": 28.956, + "args": { + "External id": 702020,"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": 6305204139898.069, "dur": 25.657, + "args": { + "External id": 702021,"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": 6305204139946.686, "dur": 16.290, + "args": { + "External id": 702022,"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": 6305204139985.195, "dur": 184.745, + "args": { + "External id": 702023,"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": 6305204140037.654, "dur": 10.672, + "args": { + "External id": 702024,"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": 6305204140042.654, "dur": 4.945, + "args": { + "External id": 702025,"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": 6305204140051.202, "dur": 48.245, + "args": { + "External id": 702026,"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": 6305204140104.607, "dur": 1.306, + "args": { + "External id": 702027,"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": 6305204140108.799, "dur": 5.748, + "args": { + "External id": 702028,"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": 6305204140183.028, "dur": 56.726, + "args": { + "External id": 702029,"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": 6305204140272.373, "dur": 29.367, + "args": { + "External id": 702030,"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": 6305204140311.187, "dur": 44.489, + "args": { + "External id": 702031,"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": 6305204140362.304, "dur": 35.303, + "args": { + "External id": 702032,"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": 6305204140424.686, "dur": 25.283, + "args": { + "External id": 702033,"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": 6305204140457.834, "dur": 35.295, + "args": { + "External id": 702034,"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": 6305204140527.987, "dur": 22.291, + "args": { + "External id": 702035,"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": 6305204140703.976, "dur": 77.318, + "args": { + "External id": 702036,"Record function id": 0, "Ev Idx": 12440 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6305204140852.429, "dur": 47.206, + "args": { + "External id": 702037,"Record function id": 0, "Ev Idx": 12441 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.5)", "pid": 2338707, "tid": 2338707, + "ts": 6305204140908.249, "dur": 29453.151, + "args": { + "External id": 702038,"Record function id": 0, "Ev Idx": 12442 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.5)", "pid": 2338707, "tid": 2338707, + "ts": 6305204140919.761, "dur": 902.954, + "args": { + "External id": 702039,"Record function id": 0, "Ev Idx": 12443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6305204140998.895, "dur": 9.157, + "args": { + "External id": 702040,"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": 6305204141020.502, "dur": 80.028, + "args": { + "External id": 702041,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305204141028.762, "dur": 2.363, + "args": { + "External id": 702042,"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": 6305204141035.989, "dur": 0.423, + "args": { + "External id": 702043,"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": 6305204141038.809, "dur": 0.555, + "args": { + "External id": 702044,"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": 6305204141040.563, "dur": 0.285, + "args": { + "External id": 702045,"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": 6305204141043.538, "dur": 0.520, + "args": { + "External id": 702046,"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": 6305204141047.623, "dur": 0.456, + "args": { + "External id": 702047,"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": 6305204141048.561, "dur": 3.405, + "args": { + "External id": 702048,"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": 6305204141089.290, "dur": 0.555, + "args": { + "External id": 702049,"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": 6305204141093.362, "dur": 0.530, + "args": { + "External id": 702050,"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": 6305204141112.336, "dur": 58.164, + "args": { + "External id": 702051,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305204141206.079, "dur": 137.318, + "args": { + "External id": 702052,"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": 6305204141221.674, "dur": 4.919, + "args": { + "External id": 702053,"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": 6305204141231.837, "dur": 10.561, + "args": { + "External id": 702054,"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": 6305204141236.837, "dur": 5.142, + "args": { + "External id": 702055,"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": 6305204141240.263, "dur": 0.598, + "args": { + "External id": 702056,"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": 6305204141248.912, "dur": 36.830, + "args": { + "External id": 702057,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305204141253.331, "dur": 2.604, + "args": { + "External id": 702058,"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": 6305204141257.052, "dur": 0.334, + "args": { + "External id": 702059,"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": 6305204141258.192, "dur": 0.298, + "args": { + "External id": 702060,"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": 6305204141263.912, "dur": 3.161, + "args": { + "External id": 702061,"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": 6305204141267.798, "dur": 0.439, + "args": { + "External id": 702062,"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": 6305204141269.066, "dur": 0.335, + "args": { + "External id": 702063,"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": 6305204141274.317, "dur": 0.300, + "args": { + "External id": 702064,"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": 6305204141275.310, "dur": 0.506, + "args": { + "External id": 702065,"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": 6305204141278.343, "dur": 2.758, + "args": { + "External id": 702066,"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": 6305204141301.208, "dur": 33.709, + "args": { + "External id": 702067,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305204141397.221, "dur": 328.466, + "args": { + "External id": 702068,"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": 6305204141431.337, "dur": 289.194, + "args": { + "External id": 702069,"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": 6305204141441.497, "dur": 272.533, + "args": { + "External id": 702070,"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": 6305204141749.766, "dur": 2.445, + "args": { + "External id": 702071,"Record function id": 0, "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": 6305204141843.397, "dur": 28329.910, + "args": { + "External id": 702072,"Record function id": 0, "Ev Idx": 12476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6305204141941.444, "dur": 6.130, + "args": { + "External id": 702073,"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": 6305204141951.086, "dur": 1.249, + "args": { + "External id": 702074,"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": 6305204141954.057, "dur": 3.092, + "args": { + "External id": 702075,"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": 6305204141958.766, "dur": 0.949, + "args": { + "External id": 702076,"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": 6305204141961.151, "dur": 0.701, + "args": { + "External id": 702077,"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": 6305204141965.226, "dur": 1.065, + "args": { + "External id": 702078,"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": 6305204141972.866, "dur": 0.877, + "args": { + "External id": 702079,"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": 6305204141974.885, "dur": 2.420, + "args": { + "External id": 702080,"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": 6305204141978.503, "dur": 0.978, + "args": { + "External id": 702081,"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": 6305204141982.701, "dur": 1.011, + "args": { + "External id": 702082,"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": 6305204142000.756, "dur": 28129.253, + "args": { + "External id": 702083,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305204142024.946, "dur": 28096.315, + "args": { + "External id": 702084,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305204142042.868, "dur": 55.614, + "args": { + "External id": 702085,"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": 6305204142103.699, "dur": 27980.734, + "args": { + "External id": 702086,"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": 6305204142106.183, "dur": 27977.327, + "args": { + "External id": 702087,"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": 6305204142112.133, "dur": 5.452, + "args": { + "External id": 702088,"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": 6305204142119.316, "dur": 27930.484, + "args": { + "External id": 702089,"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": 6305204170304.265, "dur": 30.634, + "args": { + "External id": 702090,"Sequence number": 7674401, "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": 6305204170304.265, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6305204170319.731, "dur": 10.315, + "args": { + "External id": 702091,"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": 6305204170325.162, "dur": 4.700, + "args": { + "External id": 702092,"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": 6305204170401.845, "dur": 74.629, + "args": { + "External id": 702093,"Record function id": 0, "Ev Idx": 12497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6305204170477.605, "dur": 1137.014, + "args": { + "External id": 702094,"Record function id": 0, "Ev Idx": 12498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305204170526.716, "dur": 1074.016, + "args": { + "External id": 702095,"Sequence number": 7674402, "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": 6305204170526.716, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6305204170596.122, "dur": 52.177, + "args": { + "External id": 702096,"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": 6305204170661.857, "dur": 107.009, + "args": { + "External id": 702097,"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": 6305204170781.013, "dur": 39.304, + "args": { + "External id": 702098,"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": 6305204170830.301, "dur": 28.858, + "args": { + "External id": 702099,"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": 6305204170885.841, "dur": 28.768, + "args": { + "External id": 702100,"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": 6305204170935.001, "dur": 17.571, + "args": { + "External id": 702101,"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": 6305204170980.894, "dur": 171.481, + "args": { + "External id": 702102,"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": 6305204171032.320, "dur": 10.907, + "args": { + "External id": 702103,"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": 6305204171037.356, "dur": 5.004, + "args": { + "External id": 702104,"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": 6305204171047.565, "dur": 39.322, + "args": { + "External id": 702105,"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": 6305204171089.750, "dur": 1.720, + "args": { + "External id": 702106,"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": 6305204171094.039, "dur": 4.537, + "args": { + "External id": 702107,"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": 6305204171163.629, "dur": 57.370, + "args": { + "External id": 702108,"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": 6305204171256.211, "dur": 31.600, + "args": { + "External id": 702109,"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": 6305204171297.219, "dur": 42.856, + "args": { + "External id": 702110,"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": 6305204171349.268, "dur": 36.456, + "args": { + "External id": 702111,"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": 6305204171406.455, "dur": 26.171, + "args": { + "External id": 702112,"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": 6305204171440.031, "dur": 37.135, + "args": { + "External id": 702113,"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": 6305204171496.148, "dur": 33.985, + "args": { + "External id": 702114,"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": 6305204171680.226, "dur": 73.570, + "args": { + "External id": 702115,"Record function id": 0, "Ev Idx": 12519 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6305204171828.605, "dur": 46.943, + "args": { + "External id": 702116,"Record function id": 0, "Ev Idx": 12520 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.6)", "pid": 2338707, "tid": 2338707, + "ts": 6305204171884.347, "dur": 29467.860, + "args": { + "External id": 702117,"Record function id": 0, "Ev Idx": 12521 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.6)", "pid": 2338707, "tid": 2338707, + "ts": 6305204171894.543, "dur": 927.288, + "args": { + "External id": 702118,"Record function id": 0, "Ev Idx": 12522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6305204171972.812, "dur": 9.415, + "args": { + "External id": 702119,"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": 6305204171995.050, "dur": 39.388, + "args": { + "External id": 702120,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305204172000.677, "dur": 2.253, + "args": { + "External id": 702121,"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": 6305204172006.931, "dur": 0.348, + "args": { + "External id": 702122,"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": 6305204172009.803, "dur": 0.417, + "args": { + "External id": 702123,"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": 6305204172010.859, "dur": 0.520, + "args": { + "External id": 702124,"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": 6305204172015.690, "dur": 0.373, + "args": { + "External id": 702125,"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": 6305204172016.812, "dur": 0.431, + "args": { + "External id": 702126,"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": 6305204172018.275, "dur": 5.175, + "args": { + "External id": 702127,"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": 6305204172025.837, "dur": 0.496, + "args": { + "External id": 702128,"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": 6305204172027.341, "dur": 0.343, + "args": { + "External id": 702129,"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": 6305204172044.973, "dur": 94.123, + "args": { + "External id": 702130,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305204172176.568, "dur": 130.970, + "args": { + "External id": 702131,"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": 6305204172189.370, "dur": 5.308, + "args": { + "External id": 702132,"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": 6305204172200.449, "dur": 11.082, + "args": { + "External id": 702133,"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": 6305204172205.314, "dur": 5.810, + "args": { + "External id": 702134,"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": 6305204172208.568, "dur": 0.850, + "args": { + "External id": 702135,"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": 6305204172218.051, "dur": 34.550, + "args": { + "External id": 702136,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305204172221.622, "dur": 3.375, + "args": { + "External id": 702137,"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": 6305204172225.763, "dur": 0.818, + "args": { + "External id": 702138,"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": 6305204172228.790, "dur": 0.304, + "args": { + "External id": 702139,"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": 6305204172231.679, "dur": 2.285, + "args": { + "External id": 702140,"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": 6305204172235.050, "dur": 0.460, + "args": { + "External id": 702141,"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": 6305204172237.807, "dur": 0.529, + "args": { + "External id": 702142,"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": 6305204172241.177, "dur": 0.573, + "args": { + "External id": 702143,"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": 6305204172242.644, "dur": 0.480, + "args": { + "External id": 702144,"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": 6305204172245.499, "dur": 2.665, + "args": { + "External id": 702145,"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": 6305204172265.932, "dur": 33.005, + "args": { + "External id": 702146,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305204172360.639, "dur": 361.708, + "args": { + "External id": 702147,"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": 6305204172393.586, "dur": 323.070, + "args": { + "External id": 702148,"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": 6305204172404.329, "dur": 306.199, + "args": { + "External id": 702149,"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": 6305204172749.266, "dur": 2.648, + "args": { + "External id": 702150,"Record function id": 0, "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": 6305204172842.362, "dur": 28327.916, + "args": { + "External id": 702151,"Record function id": 0, "Ev Idx": 12555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6305204172937.642, "dur": 6.387, + "args": { + "External id": 702152,"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": 6305204172947.384, "dur": 1.140, + "args": { + "External id": 702153,"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": 6305204172950.069, "dur": 2.859, + "args": { + "External id": 702154,"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": 6305204172954.713, "dur": 0.959, + "args": { + "External id": 702155,"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": 6305204172956.977, "dur": 0.938, + "args": { + "External id": 702156,"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": 6305204172959.146, "dur": 0.999, + "args": { + "External id": 702157,"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": 6305204172963.857, "dur": 1.017, + "args": { + "External id": 702158,"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": 6305204172966.293, "dur": 2.541, + "args": { + "External id": 702159,"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": 6305204172970.036, "dur": 1.032, + "args": { + "External id": 702160,"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": 6305204172972.452, "dur": 1.072, + "args": { + "External id": 702161,"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": 6305204172993.860, "dur": 28132.660, + "args": { + "External id": 702162,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305204173008.943, "dur": 28108.945, + "args": { + "External id": 702163,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305204173027.014, "dur": 15.993, + "args": { + "External id": 702164,"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": 6305204173047.043, "dur": 28032.987, + "args": { + "External id": 702165,"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": 6305204173049.661, "dur": 28029.694, + "args": { + "External id": 702166,"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": 6305204173095.348, "dur": 11.239, + "args": { + "External id": 702167,"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": 6305204173108.603, "dur": 27967.288, + "args": { + "External id": 702168,"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": 6305204201300.086, "dur": 28.606, + "args": { + "External id": 702169,"Sequence number": 7674403, "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": 6305204201300.086, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6305204201315.892, "dur": 8.318, + "args": { + "External id": 702170,"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": 6305204201319.497, "dur": 4.512, + "args": { + "External id": 702171,"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": 6305204201393.461, "dur": 73.965, + "args": { + "External id": 702172,"Record function id": 0, "Ev Idx": 12576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6305204201468.728, "dur": 1359.702, + "args": { + "External id": 702173,"Record function id": 0, "Ev Idx": 12577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305204201521.627, "dur": 1291.616, + "args": { + "External id": 702174,"Sequence number": 7674404, "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": 6305204201521.627, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6305204201593.876, "dur": 51.451, + "args": { + "External id": 702175,"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": 6305204201658.840, "dur": 106.023, + "args": { + "External id": 702176,"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": 6305204201776.671, "dur": 37.822, + "args": { + "External id": 702177,"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": 6305204201823.604, "dur": 29.574, + "args": { + "External id": 702178,"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": 6305204201880.046, "dur": 27.843, + "args": { + "External id": 702179,"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": 6305204201925.909, "dur": 19.114, + "args": { + "External id": 702180,"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": 6305204201969.064, "dur": 192.175, + "args": { + "External id": 702181,"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": 6305204202020.055, "dur": 12.761, + "args": { + "External id": 702182,"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": 6305204202027.016, "dur": 5.085, + "args": { + "External id": 702183,"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": 6305204202035.294, "dur": 3.502, + "args": { + "External id": 702184,"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": 6305204202040.101, "dur": 1.388, + "args": { + "External id": 702185,"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": 6305204202044.012, "dur": 6.554, + "args": { + "External id": 702186,"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": 6305204202336.685, "dur": 71.755, + "args": { + "External id": 702187,"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": 6305204202449.312, "dur": 33.949, + "args": { + "External id": 702188,"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": 6305204202493.859, "dur": 61.438, + "args": { + "External id": 702189,"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": 6305204202567.276, "dur": 36.351, + "args": { + "External id": 702190,"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": 6305204202626.724, "dur": 27.336, + "args": { + "External id": 702191,"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": 6305204202662.643, "dur": 35.813, + "args": { + "External id": 702192,"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": 6305204202719.944, "dur": 17.084, + "args": { + "External id": 702193,"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": 6305204202897.864, "dur": 79.657, + "args": { + "External id": 702194,"Record function id": 0, "Ev Idx": 12598 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6305204203050.923, "dur": 89.102, + "args": { + "External id": 702195,"Record function id": 0, "Ev Idx": 12599 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.7)", "pid": 2338707, "tid": 2338707, + "ts": 6305204203150.558, "dur": 30688.824, + "args": { + "External id": 702196,"Record function id": 0, "Ev Idx": 12600 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.7)", "pid": 2338707, "tid": 2338707, + "ts": 6305204203161.436, "dur": 950.265, + "args": { + "External id": 702197,"Record function id": 0, "Ev Idx": 12601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6305204203247.430, "dur": 10.295, + "args": { + "External id": 702198,"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": 6305204203271.066, "dur": 43.058, + "args": { + "External id": 702199,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305204203276.837, "dur": 2.364, + "args": { + "External id": 702200,"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": 6305204203285.674, "dur": 0.521, + "args": { + "External id": 702201,"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": 6305204203286.932, "dur": 0.725, + "args": { + "External id": 702202,"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": 6305204203288.620, "dur": 0.427, + "args": { + "External id": 702203,"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": 6305204203294.367, "dur": 0.503, + "args": { + "External id": 702204,"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": 6305204203296.010, "dur": 0.669, + "args": { + "External id": 702205,"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": 6305204203298.721, "dur": 5.157, + "args": { + "External id": 702206,"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": 6305204203304.859, "dur": 0.555, + "args": { + "External id": 702207,"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": 6305204203306.067, "dur": 0.586, + "args": { + "External id": 702208,"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": 6305204203326.195, "dur": 54.940, + "args": { + "External id": 702209,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305204203414.205, "dur": 153.176, + "args": { + "External id": 702210,"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": 6305204203426.979, "dur": 3.608, + "args": { + "External id": 702211,"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": 6305204203436.059, "dur": 11.024, + "args": { + "External id": 702212,"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": 6305204203441.272, "dur": 5.402, + "args": { + "External id": 702213,"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": 6305204203444.622, "dur": 0.725, + "args": { + "External id": 702214,"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": 6305204203454.941, "dur": 33.876, + "args": { + "External id": 702215,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305204203456.604, "dur": 2.821, + "args": { + "External id": 702216,"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": 6305204203460.763, "dur": 0.792, + "args": { + "External id": 702217,"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": 6305204203464.120, "dur": 0.781, + "args": { + "External id": 702218,"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": 6305204203468.374, "dur": 2.302, + "args": { + "External id": 702219,"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": 6305204203472.599, "dur": 0.311, + "args": { + "External id": 702220,"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": 6305204203473.912, "dur": 0.410, + "args": { + "External id": 702221,"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": 6305204203477.139, "dur": 0.331, + "args": { + "External id": 702222,"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": 6305204203480.350, "dur": 0.357, + "args": { + "External id": 702223,"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": 6305204203481.147, "dur": 2.839, + "args": { + "External id": 702224,"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": 6305204203501.652, "dur": 55.976, + "args": { + "External id": 702225,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305204203624.541, "dur": 355.066, + "args": { + "External id": 702226,"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": 6305204203659.672, "dur": 314.902, + "args": { + "External id": 702227,"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": 6305204203671.385, "dur": 297.874, + "args": { + "External id": 702228,"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": 6305204204005.007, "dur": 2.550, + "args": { + "External id": 702229,"Record function id": 0, "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": 6305204204135.365, "dur": 29518.858, + "args": { + "External id": 702230,"Record function id": 0, "Ev Idx": 12634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6305204204249.141, "dur": 7.468, + "args": { + "External id": 702231,"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": 6305204204260.286, "dur": 1.023, + "args": { + "External id": 702232,"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": 6305204204263.263, "dur": 3.800, + "args": { + "External id": 702233,"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": 6305204204271.574, "dur": 0.991, + "args": { + "External id": 702234,"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": 6305204204274.020, "dur": 0.895, + "args": { + "External id": 702235,"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": 6305204204276.374, "dur": 0.994, + "args": { + "External id": 702236,"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": 6305204204279.117, "dur": 0.733, + "args": { + "External id": 702237,"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": 6305204204284.048, "dur": 2.062, + "args": { + "External id": 702238,"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": 6305204204287.726, "dur": 0.965, + "args": { + "External id": 702239,"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": 6305204204289.900, "dur": 0.885, + "args": { + "External id": 702240,"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": 6305204204309.397, "dur": 29303.059, + "args": { + "External id": 702241,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305204204327.028, "dur": 29277.578, + "args": { + "External id": 702242,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305204204344.501, "dur": 15.969, + "args": { + "External id": 702243,"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": 6305204204364.336, "dur": 29207.643, + "args": { + "External id": 702244,"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": 6305204204367.023, "dur": 29204.385, + "args": { + "External id": 702245,"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": 6305204204372.991, "dur": 7.016, + "args": { + "External id": 702246,"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": 6305204204381.682, "dur": 29186.832, + "args": { + "External id": 702247,"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": 6305204233782.804, "dur": 33.241, + "args": { + "External id": 702248,"Sequence number": 7674405, "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": 6305204233782.804, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6305204233800.845, "dur": 10.591, + "args": { + "External id": 702249,"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": 6305204233806.730, "dur": 4.476, + "args": { + "External id": 702250,"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": 6305204233879.840, "dur": 73.286, + "args": { + "External id": 702251,"Record function id": 0, "Ev Idx": 12655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6305204233954.565, "dur": 1146.688, + "args": { + "External id": 702252,"Record function id": 0, "Ev Idx": 12656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305204233994.048, "dur": 1057.950, + "args": { + "External id": 702253,"Sequence number": 7674406, "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": 6305204233994.048, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6305204234093.086, "dur": 50.674, + "args": { + "External id": 702254,"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": 6305204234158.851, "dur": 105.788, + "args": { + "External id": 702255,"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": 6305204234277.422, "dur": 38.499, + "args": { + "External id": 702256,"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": 6305204234324.449, "dur": 28.714, + "args": { + "External id": 702257,"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": 6305204234376.293, "dur": 27.028, + "args": { + "External id": 702258,"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": 6305204234426.962, "dur": 18.277, + "args": { + "External id": 702259,"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": 6305204234469.257, "dur": 164.735, + "args": { + "External id": 702260,"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": 6305204234536.954, "dur": 12.068, + "args": { + "External id": 702261,"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": 6305204234542.476, "dur": 5.517, + "args": { + "External id": 702262,"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": 6305204234551.528, "dur": 3.772, + "args": { + "External id": 702263,"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": 6305204234564.417, "dur": 1.243, + "args": { + "External id": 702264,"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": 6305204234570.493, "dur": 7.293, + "args": { + "External id": 702265,"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": 6305204234645.802, "dur": 55.589, + "args": { + "External id": 702266,"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": 6305204234731.687, "dur": 29.766, + "args": { + "External id": 702267,"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": 6305204234772.476, "dur": 41.606, + "args": { + "External id": 702268,"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": 6305204234820.173, "dur": 34.096, + "args": { + "External id": 702269,"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": 6305204234874.615, "dur": 29.119, + "args": { + "External id": 702270,"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": 6305204234908.817, "dur": 35.835, + "args": { + "External id": 702271,"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": 6305204234962.675, "dur": 19.618, + "args": { + "External id": 702272,"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": 6305204235170.007, "dur": 79.632, + "args": { + "External id": 702273,"Record function id": 0, "Ev Idx": 12677 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6305204235328.309, "dur": 47.974, + "args": { + "External id": 702274,"Record function id": 0, "Ev Idx": 12678 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.8)", "pid": 2338707, "tid": 2338707, + "ts": 6305204235384.975, "dur": 29873.975, + "args": { + "External id": 702275,"Record function id": 0, "Ev Idx": 12679 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.8)", "pid": 2338707, "tid": 2338707, + "ts": 6305204235396.137, "dur": 988.842, + "args": { + "External id": 702276,"Record function id": 0, "Ev Idx": 12680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6305204235476.149, "dur": 8.702, + "args": { + "External id": 702277,"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": 6305204235498.021, "dur": 55.653, + "args": { + "External id": 702278,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305204235504.432, "dur": 16.338, + "args": { + "External id": 702279,"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": 6305204235525.632, "dur": 0.695, + "args": { + "External id": 702280,"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": 6305204235528.879, "dur": 0.862, + "args": { + "External id": 702281,"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": 6305204235530.419, "dur": 0.940, + "args": { + "External id": 702282,"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": 6305204235534.027, "dur": 0.451, + "args": { + "External id": 702283,"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": 6305204235536.065, "dur": 0.483, + "args": { + "External id": 702284,"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": 6305204235537.783, "dur": 4.173, + "args": { + "External id": 702285,"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": 6305204235543.747, "dur": 0.546, + "args": { + "External id": 702286,"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": 6305204235546.115, "dur": 0.558, + "args": { + "External id": 702287,"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": 6305204235566.261, "dur": 55.338, + "args": { + "External id": 702288,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305204235656.333, "dur": 135.616, + "args": { + "External id": 702289,"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": 6305204235670.403, "dur": 4.900, + "args": { + "External id": 702290,"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": 6305204235680.657, "dur": 13.506, + "args": { + "External id": 702291,"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": 6305204235687.752, "dur": 6.001, + "args": { + "External id": 702292,"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": 6305204235691.951, "dur": 0.599, + "args": { + "External id": 702293,"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": 6305204235701.622, "dur": 36.428, + "args": { + "External id": 702294,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305204235703.976, "dur": 2.763, + "args": { + "External id": 702295,"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": 6305204235708.367, "dur": 0.693, + "args": { + "External id": 702296,"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": 6305204235710.850, "dur": 0.454, + "args": { + "External id": 702297,"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": 6305204235714.989, "dur": 2.181, + "args": { + "External id": 702298,"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": 6305204235718.923, "dur": 0.325, + "args": { + "External id": 702299,"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": 6305204235720.808, "dur": 0.613, + "args": { + "External id": 702300,"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": 6305204235726.172, "dur": 0.374, + "args": { + "External id": 702301,"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": 6305204235727.863, "dur": 0.532, + "args": { + "External id": 702302,"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": 6305204235730.183, "dur": 3.087, + "args": { + "External id": 702303,"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": 6305204235749.103, "dur": 33.550, + "args": { + "External id": 702304,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305204235848.011, "dur": 432.280, + "args": { + "External id": 702305,"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": 6305204235882.135, "dur": 392.288, + "args": { + "External id": 702306,"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": 6305204235893.122, "dur": 374.754, + "args": { + "External id": 702307,"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": 6305204236308.635, "dur": 2.493, + "args": { + "External id": 702308,"Record function id": 0, "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": 6305204236405.871, "dur": 28626.722, + "args": { + "External id": 702309,"Record function id": 0, "Ev Idx": 12713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6305204236502.324, "dur": 21.546, + "args": { + "External id": 702310,"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": 6305204236530.657, "dur": 1.439, + "args": { + "External id": 702311,"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": 6305204236534.065, "dur": 3.996, + "args": { + "External id": 702312,"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": 6305204236539.855, "dur": 1.029, + "args": { + "External id": 702313,"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": 6305204236542.461, "dur": 0.826, + "args": { + "External id": 702314,"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": 6305204236544.960, "dur": 1.008, + "args": { + "External id": 702315,"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": 6305204236549.632, "dur": 0.804, + "args": { + "External id": 702316,"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": 6305204236552.060, "dur": 2.273, + "args": { + "External id": 702317,"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": 6305204236555.984, "dur": 0.927, + "args": { + "External id": 702318,"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": 6305204236558.400, "dur": 0.846, + "args": { + "External id": 702319,"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": 6305204236591.644, "dur": 28395.753, + "args": { + "External id": 702320,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305204236608.364, "dur": 28370.721, + "args": { + "External id": 702321,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305204236624.968, "dur": 17.704, + "args": { + "External id": 702322,"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": 6305204236646.266, "dur": 28298.237, + "args": { + "External id": 702323,"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": 6305204236648.740, "dur": 28295.298, + "args": { + "External id": 702324,"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": 6305204236654.983, "dur": 5.241, + "args": { + "External id": 702325,"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": 6305204236661.768, "dur": 28279.195, + "args": { + "External id": 702326,"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": 6305204265201.652, "dur": 30.269, + "args": { + "External id": 702327,"Sequence number": 7674407, "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": 6305204265201.652, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6305204265218.054, "dur": 9.007, + "args": { + "External id": 702328,"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": 6305204265222.122, "dur": 4.611, + "args": { + "External id": 702329,"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": 6305204265300.763, "dur": 74.770, + "args": { + "External id": 702330,"Record function id": 0, "Ev Idx": 12734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6305204265377.300, "dur": 1112.997, + "args": { + "External id": 702331,"Record function id": 0, "Ev Idx": 12735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305204265416.647, "dur": 1059.312, + "args": { + "External id": 702332,"Sequence number": 7674408, "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": 6305204265416.647, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6305204265480.920, "dur": 62.193, + "args": { + "External id": 702333,"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": 6305204265558.423, "dur": 104.822, + "args": { + "External id": 702334,"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": 6305204265676.661, "dur": 38.177, + "args": { + "External id": 702335,"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": 6305204265723.390, "dur": 29.950, + "args": { + "External id": 702336,"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": 6305204265779.119, "dur": 29.096, + "args": { + "External id": 702337,"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": 6305204265828.501, "dur": 20.681, + "args": { + "External id": 702338,"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": 6305204265871.661, "dur": 132.538, + "args": { + "External id": 702339,"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": 6305204265923.791, "dur": 11.296, + "args": { + "External id": 702340,"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": 6305204265929.185, "dur": 5.112, + "args": { + "External id": 702341,"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": 6305204265938.049, "dur": 3.647, + "args": { + "External id": 702342,"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": 6305204265942.982, "dur": 1.366, + "args": { + "External id": 702343,"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": 6305204265947.012, "dur": 5.134, + "args": { + "External id": 702344,"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": 6305204266015.216, "dur": 86.828, + "args": { + "External id": 702345,"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": 6305204266139.858, "dur": 33.108, + "args": { + "External id": 702346,"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": 6305204266183.239, "dur": 48.564, + "args": { + "External id": 702347,"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": 6305204266240.449, "dur": 33.900, + "args": { + "External id": 702348,"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": 6305204266297.932, "dur": 24.686, + "args": { + "External id": 702349,"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": 6305204266329.825, "dur": 35.647, + "args": { + "External id": 702350,"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": 6305204266382.588, "dur": 17.704, + "args": { + "External id": 702351,"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": 6305204266575.805, "dur": 76.061, + "args": { + "External id": 702352,"Record function id": 0, "Ev Idx": 12756 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6305204266727.152, "dur": 47.118, + "args": { + "External id": 702353,"Record function id": 0, "Ev Idx": 12757 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.9)", "pid": 2338707, "tid": 2338707, + "ts": 6305204266782.963, "dur": 32231.298, + "args": { + "External id": 702354,"Record function id": 0, "Ev Idx": 12758 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.9)", "pid": 2338707, "tid": 2338707, + "ts": 6305204266790.951, "dur": 979.880, + "args": { + "External id": 702355,"Record function id": 0, "Ev Idx": 12759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6305204266872.360, "dur": 9.305, + "args": { + "External id": 702356,"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": 6305204266895.470, "dur": 41.991, + "args": { + "External id": 702357,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305204266901.459, "dur": 2.453, + "args": { + "External id": 702358,"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": 6305204266908.794, "dur": 0.390, + "args": { + "External id": 702359,"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": 6305204266910.729, "dur": 0.552, + "args": { + "External id": 702360,"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": 6305204266912.989, "dur": 0.556, + "args": { + "External id": 702361,"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": 6305204266917.074, "dur": 0.807, + "args": { + "External id": 702362,"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": 6305204266919.454, "dur": 0.400, + "args": { + "External id": 702363,"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": 6305204266921.761, "dur": 4.607, + "args": { + "External id": 702364,"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": 6305204266928.226, "dur": 0.395, + "args": { + "External id": 702365,"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": 6305204266930.340, "dur": 0.286, + "args": { + "External id": 702366,"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": 6305204266949.372, "dur": 49.153, + "args": { + "External id": 702367,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305204267031.186, "dur": 190.169, + "args": { + "External id": 702368,"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": 6305204267043.979, "dur": 3.902, + "args": { + "External id": 702369,"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": 6305204267088.966, "dur": 14.579, + "args": { + "External id": 702370,"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": 6305204267095.832, "dur": 7.287, + "args": { + "External id": 702371,"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": 6305204267100.461, "dur": 0.720, + "args": { + "External id": 702372,"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": 6305204267112.442, "dur": 38.551, + "args": { + "External id": 702373,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305204267115.123, "dur": 2.717, + "args": { + "External id": 702374,"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": 6305204267123.802, "dur": 0.593, + "args": { + "External id": 702375,"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": 6305204267125.906, "dur": 0.524, + "args": { + "External id": 702376,"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": 6305204267129.920, "dur": 2.762, + "args": { + "External id": 702377,"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": 6305204267134.315, "dur": 0.411, + "args": { + "External id": 702378,"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": 6305204267136.299, "dur": 2.155, + "args": { + "External id": 702379,"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": 6305204267139.770, "dur": 0.410, + "args": { + "External id": 702380,"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": 6305204267142.019, "dur": 0.318, + "args": { + "External id": 702381,"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": 6305204267146.123, "dur": 0.271, + "args": { + "External id": 702382,"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": 6305204267173.123, "dur": 39.569, + "args": { + "External id": 702383,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305204267277.602, "dur": 387.531, + "args": { + "External id": 702384,"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": 6305204267312.210, "dur": 343.819, + "args": { + "External id": 702385,"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": 6305204267324.620, "dur": 325.450, + "args": { + "External id": 702386,"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": 6305204267691.024, "dur": 2.257, + "args": { + "External id": 702387,"Record function id": 0, "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": 6305204267793.035, "dur": 31031.189, + "args": { + "External id": 702388,"Record function id": 0, "Ev Idx": 12792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6305204267891.224, "dur": 6.131, + "args": { + "External id": 702389,"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": 6305204267901.188, "dur": 0.967, + "args": { + "External id": 702390,"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": 6305204267903.984, "dur": 3.209, + "args": { + "External id": 702391,"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": 6305204267909.233, "dur": 0.968, + "args": { + "External id": 702392,"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": 6305204267911.984, "dur": 1.115, + "args": { + "External id": 702393,"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": 6305204267914.799, "dur": 0.925, + "args": { + "External id": 702394,"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": 6305204267919.248, "dur": 0.761, + "args": { + "External id": 702395,"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": 6305204267921.551, "dur": 2.253, + "args": { + "External id": 702396,"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": 6305204267925.579, "dur": 0.814, + "args": { + "External id": 702397,"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": 6305204267928.132, "dur": 0.484, + "args": { + "External id": 702398,"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": 6305204267949.372, "dur": 30829.950, + "args": { + "External id": 702399,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305204267966.434, "dur": 30804.015, + "args": { + "External id": 702400,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305204267983.242, "dur": 16.753, + "args": { + "External id": 702401,"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": 6305204268003.588, "dur": 30731.682, + "args": { + "External id": 702402,"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": 6305204268006.529, "dur": 30728.064, + "args": { + "External id": 702403,"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": 6305204268012.471, "dur": 5.895, + "args": { + "External id": 702404,"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": 6305204268020.297, "dur": 30710.944, + "args": { + "External id": 702405,"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": 6305204298959.353, "dur": 30.076, + "args": { + "External id": 702406,"Sequence number": 7674409, "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": 6305204298959.353, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6305204298975.858, "dur": 8.870, + "args": { + "External id": 702407,"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": 6305204298979.590, "dur": 4.928, + "args": { + "External id": 702408,"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": 6305204299096.118, "dur": 80.323, + "args": { + "External id": 702409,"Record function id": 0, "Ev Idx": 12813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6305204299178.630, "dur": 1124.850, + "args": { + "External id": 702410,"Record function id": 0, "Ev Idx": 12814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305204299222.486, "dur": 1067.093, + "args": { + "External id": 702411,"Sequence number": 7674410, "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": 6305204299222.486, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6305204299291.651, "dur": 50.133, + "args": { + "External id": 702412,"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": 6305204299354.597, "dur": 109.328, + "args": { + "External id": 702413,"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": 6305204299477.055, "dur": 51.454, + "args": { + "External id": 702414,"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": 6305204299539.614, "dur": 32.510, + "args": { + "External id": 702415,"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": 6305204299601.378, "dur": 29.363, + "args": { + "External id": 702416,"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": 6305204299650.746, "dur": 16.987, + "args": { + "External id": 702417,"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": 6305204299691.819, "dur": 130.540, + "args": { + "External id": 702418,"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": 6305204299742.979, "dur": 11.103, + "args": { + "External id": 702419,"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": 6305204299748.571, "dur": 4.618, + "args": { + "External id": 702420,"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": 6305204299757.241, "dur": 5.309, + "args": { + "External id": 702421,"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": 6305204299764.160, "dur": 0.983, + "args": { + "External id": 702422,"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": 6305204299768.113, "dur": 5.265, + "args": { + "External id": 702423,"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": 6305204299833.305, "dur": 48.448, + "args": { + "External id": 702424,"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": 6305204299913.328, "dur": 27.798, + "args": { + "External id": 702425,"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": 6305204299957.994, "dur": 42.903, + "args": { + "External id": 702426,"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": 6305204300009.512, "dur": 34.233, + "args": { + "External id": 702427,"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": 6305204300105.758, "dur": 29.217, + "args": { + "External id": 702428,"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": 6305204300143.970, "dur": 40.135, + "args": { + "External id": 702429,"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": 6305204300204.357, "dur": 18.500, + "args": { + "External id": 702430,"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": 6305204300366.995, "dur": 73.880, + "args": { + "External id": 702431,"Record function id": 0, "Ev Idx": 12835 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6305204300533.708, "dur": 50.550, + "args": { + "External id": 702432,"Record function id": 0, "Ev Idx": 12836 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.10)", "pid": 2338707, "tid": 2338707, + "ts": 6305204300594.111, "dur": 29610.400, + "args": { + "External id": 702433,"Record function id": 0, "Ev Idx": 12837 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.10)", "pid": 2338707, "tid": 2338707, + "ts": 6305204300600.648, "dur": 977.891, + "args": { + "External id": 702434,"Record function id": 0, "Ev Idx": 12838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6305204300682.381, "dur": 9.694, + "args": { + "External id": 702435,"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": 6305204300705.727, "dur": 41.558, + "args": { + "External id": 702436,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305204300711.874, "dur": 2.461, + "args": { + "External id": 702437,"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": 6305204300719.328, "dur": 0.370, + "args": { + "External id": 702438,"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": 6305204300721.294, "dur": 0.348, + "args": { + "External id": 702439,"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": 6305204300723.108, "dur": 0.543, + "args": { + "External id": 702440,"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": 6305204300727.428, "dur": 0.407, + "args": { + "External id": 702441,"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": 6305204300729.709, "dur": 0.524, + "args": { + "External id": 702442,"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": 6305204300731.720, "dur": 4.810, + "args": { + "External id": 702443,"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": 6305204300737.978, "dur": 0.460, + "args": { + "External id": 702444,"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": 6305204300739.997, "dur": 0.397, + "args": { + "External id": 702445,"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": 6305204300759.675, "dur": 58.103, + "args": { + "External id": 702446,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305204300851.838, "dur": 126.751, + "args": { + "External id": 702447,"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": 6305204300864.649, "dur": 4.009, + "args": { + "External id": 702448,"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": 6305204300873.782, "dur": 13.354, + "args": { + "External id": 702449,"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": 6305204300881.029, "dur": 5.709, + "args": { + "External id": 702450,"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": 6305204300884.887, "dur": 0.580, + "args": { + "External id": 702451,"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": 6305204300893.490, "dur": 34.364, + "args": { + "External id": 702452,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305204300895.911, "dur": 2.809, + "args": { + "External id": 702453,"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": 6305204300900.235, "dur": 0.254, + "args": { + "External id": 702454,"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": 6305204300902.217, "dur": 0.458, + "args": { + "External id": 702455,"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": 6305204300906.536, "dur": 2.320, + "args": { + "External id": 702456,"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": 6305204300910.129, "dur": 0.687, + "args": { + "External id": 702457,"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": 6305204300912.407, "dur": 0.714, + "args": { + "External id": 702458,"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": 6305204300916.977, "dur": 0.324, + "args": { + "External id": 702459,"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": 6305204300918.839, "dur": 0.435, + "args": { + "External id": 702460,"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": 6305204300920.749, "dur": 2.303, + "args": { + "External id": 702461,"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": 6305204300938.787, "dur": 31.492, + "args": { + "External id": 702462,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305204301031.656, "dur": 426.755, + "args": { + "External id": 702463,"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": 6305204301099.935, "dur": 352.502, + "args": { + "External id": 702464,"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": 6305204301133.215, "dur": 312.271, + "args": { + "External id": 702465,"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": 6305204301483.337, "dur": 2.203, + "args": { + "External id": 702466,"Record function id": 0, "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": 6305204301601.270, "dur": 28388.449, + "args": { + "External id": 702467,"Record function id": 0, "Ev Idx": 12871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6305204301701.070, "dur": 6.646, + "args": { + "External id": 702468,"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": 6305204301711.680, "dur": 1.249, + "args": { + "External id": 702469,"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": 6305204301714.772, "dur": 3.764, + "args": { + "External id": 702470,"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": 6305204301720.436, "dur": 1.200, + "args": { + "External id": 702471,"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": 6305204301723.060, "dur": 0.721, + "args": { + "External id": 702472,"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": 6305204301725.327, "dur": 0.673, + "args": { + "External id": 702473,"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": 6305204301729.939, "dur": 0.898, + "args": { + "External id": 702474,"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": 6305204301732.228, "dur": 2.678, + "args": { + "External id": 702475,"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": 6305204301736.801, "dur": 0.857, + "args": { + "External id": 702476,"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": 6305204301739.064, "dur": 0.681, + "args": { + "External id": 702477,"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": 6305204301759.907, "dur": 28184.225, + "args": { + "External id": 702478,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305204301776.585, "dur": 28159.315, + "args": { + "External id": 702479,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305204301792.125, "dur": 15.947, + "args": { + "External id": 702480,"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": 6305204301811.554, "dur": 28088.278, + "args": { + "External id": 702481,"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": 6305204301814.483, "dur": 28084.709, + "args": { + "External id": 702482,"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": 6305204301821.088, "dur": 6.271, + "args": { + "External id": 702483,"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": 6305204301829.231, "dur": 28066.895, + "args": { + "External id": 702484,"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": 6305204330148.950, "dur": 30.089, + "args": { + "External id": 702485,"Sequence number": 7674411, "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": 6305204330148.950, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6305204330164.977, "dur": 9.266, + "args": { + "External id": 702486,"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": 6305204330168.843, "dur": 4.957, + "args": { + "External id": 702487,"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": 6305204330246.040, "dur": 76.515, + "args": { + "External id": 702488,"Record function id": 0, "Ev Idx": 12892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6305204330324.235, "dur": 1117.336, + "args": { + "External id": 702489,"Record function id": 0, "Ev Idx": 12893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305204330363.885, "dur": 1062.749, + "args": { + "External id": 702490,"Sequence number": 7674412, "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": 6305204330363.885, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6305204330432.122, "dur": 49.555, + "args": { + "External id": 702491,"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": 6305204330494.306, "dur": 122.083, + "args": { + "External id": 702492,"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": 6305204330633.509, "dur": 38.194, + "args": { + "External id": 702493,"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": 6305204330680.559, "dur": 29.507, + "args": { + "External id": 702494,"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": 6305204330737.612, "dur": 27.804, + "args": { + "External id": 702495,"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": 6305204330786.376, "dur": 16.859, + "args": { + "External id": 702496,"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": 6305204330826.819, "dur": 132.741, + "args": { + "External id": 702497,"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": 6305204330878.051, "dur": 11.850, + "args": { + "External id": 702498,"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": 6305204330883.679, "dur": 5.463, + "args": { + "External id": 702499,"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": 6305204330892.843, "dur": 5.688, + "args": { + "External id": 702500,"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": 6305204330899.960, "dur": 0.960, + "args": { + "External id": 702501,"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": 6305204330903.723, "dur": 4.642, + "args": { + "External id": 702502,"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": 6305204330971.160, "dur": 47.124, + "args": { + "External id": 702503,"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": 6305204331049.408, "dur": 64.956, + "args": { + "External id": 702504,"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": 6305204331127.891, "dur": 48.016, + "args": { + "External id": 702505,"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": 6305204331184.735, "dur": 34.714, + "args": { + "External id": 702506,"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": 6305204331246.861, "dur": 26.683, + "args": { + "External id": 702507,"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": 6305204331281.198, "dur": 36.514, + "args": { + "External id": 702508,"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": 6305204331335.834, "dur": 16.960, + "args": { + "External id": 702509,"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": 6305204331520.346, "dur": 82.863, + "args": { + "External id": 702510,"Record function id": 0, "Ev Idx": 12914 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6305204331682.254, "dur": 47.122, + "args": { + "External id": 702511,"Record function id": 0, "Ev Idx": 12915 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.11)", "pid": 2338707, "tid": 2338707, + "ts": 6305204331738.497, "dur": 29928.046, + "args": { + "External id": 702512,"Record function id": 0, "Ev Idx": 12916 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.11)", "pid": 2338707, "tid": 2338707, + "ts": 6305204331745.727, "dur": 972.506, + "args": { + "External id": 702513,"Record function id": 0, "Ev Idx": 12917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6305204331827.183, "dur": 9.767, + "args": { + "External id": 702514,"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": 6305204331849.936, "dur": 42.526, + "args": { + "External id": 702515,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305204331855.729, "dur": 2.358, + "args": { + "External id": 702516,"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": 6305204331863.115, "dur": 0.371, + "args": { + "External id": 702517,"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": 6305204331865.074, "dur": 0.622, + "args": { + "External id": 702518,"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": 6305204331867.265, "dur": 0.608, + "args": { + "External id": 702519,"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": 6305204331871.781, "dur": 0.744, + "args": { + "External id": 702520,"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": 6305204331873.829, "dur": 0.758, + "args": { + "External id": 702521,"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": 6305204331876.151, "dur": 5.045, + "args": { + "External id": 702522,"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": 6305204331882.783, "dur": 0.543, + "args": { + "External id": 702523,"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": 6305204331884.638, "dur": 0.638, + "args": { + "External id": 702524,"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": 6305204331907.096, "dur": 57.953, + "args": { + "External id": 702525,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305204331997.803, "dur": 177.767, + "args": { + "External id": 702526,"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": 6305204332010.030, "dur": 5.692, + "args": { + "External id": 702527,"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": 6305204332021.240, "dur": 13.775, + "args": { + "External id": 702528,"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": 6305204332028.576, "dur": 6.033, + "args": { + "External id": 702529,"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": 6305204332032.385, "dur": 0.956, + "args": { + "External id": 702530,"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": 6305204332041.479, "dur": 69.468, + "args": { + "External id": 702531,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305204332043.759, "dur": 0.622, + "args": { + "External id": 702532,"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": 6305204332046.124, "dur": 2.599, + "args": { + "External id": 702533,"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": 6305204332050.506, "dur": 0.577, + "args": { + "External id": 702534,"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": 6305204332087.367, "dur": 2.940, + "args": { + "External id": 702535,"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": 6305204332095.020, "dur": 0.486, + "args": { + "External id": 702536,"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": 6305204332096.960, "dur": 0.642, + "args": { + "External id": 702537,"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": 6305204332099.109, "dur": 0.635, + "args": { + "External id": 702538,"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": 6305204332103.370, "dur": 0.339, + "args": { + "External id": 702539,"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": 6305204332104.891, "dur": 0.579, + "args": { + "External id": 702540,"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": 6305204332124.827, "dur": 41.534, + "args": { + "External id": 702541,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305204332232.622, "dur": 384.274, + "args": { + "External id": 702542,"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": 6305204332266.027, "dur": 345.529, + "args": { + "External id": 702543,"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": 6305204332276.711, "dur": 328.634, + "args": { + "External id": 702544,"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": 6305204332645.265, "dur": 2.196, + "args": { + "External id": 702545,"Record function id": 0, "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": 6305204332739.072, "dur": 28721.785, + "args": { + "External id": 702546,"Record function id": 0, "Ev Idx": 12950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6305204332834.999, "dur": 6.290, + "args": { + "External id": 702547,"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": 6305204332845.025, "dur": 1.136, + "args": { + "External id": 702548,"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": 6305204332847.902, "dur": 3.357, + "args": { + "External id": 702549,"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": 6305204332853.366, "dur": 0.980, + "args": { + "External id": 702550,"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": 6305204332855.630, "dur": 1.158, + "args": { + "External id": 702551,"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": 6305204332857.942, "dur": 1.270, + "args": { + "External id": 702552,"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": 6305204332862.876, "dur": 1.417, + "args": { + "External id": 702553,"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": 6305204332865.484, "dur": 2.599, + "args": { + "External id": 702554,"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": 6305204332869.273, "dur": 0.667, + "args": { + "External id": 702555,"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": 6305204332871.452, "dur": 0.867, + "args": { + "External id": 702556,"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": 6305204332891.741, "dur": 28526.453, + "args": { + "External id": 702557,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305204332907.927, "dur": 28501.837, + "args": { + "External id": 702558,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305204332926.042, "dur": 16.011, + "args": { + "External id": 702559,"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": 6305204332945.363, "dur": 28430.796, + "args": { + "External id": 702560,"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": 6305204332948.006, "dur": 28427.487, + "args": { + "External id": 702561,"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": 6305204332953.657, "dur": 5.896, + "args": { + "External id": 702562,"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": 6305204332961.255, "dur": 28411.073, + "args": { + "External id": 702563,"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": 6305204361608.313, "dur": 31.934, + "args": { + "External id": 702564,"Sequence number": 7674413, "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": 6305204361608.313, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6305204361626.057, "dur": 9.181, + "args": { + "External id": 702565,"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": 6305204361629.991, "dur": 4.939, + "args": { + "External id": 702566,"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": 6305204361705.273, "dur": 72.670, + "args": { + "External id": 702567,"Record function id": 0, "Ev Idx": 12971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6305204361779.220, "dur": 1118.793, + "args": { + "External id": 702568,"Record function id": 0, "Ev Idx": 12972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305204361817.347, "dur": 1067.689, + "args": { + "External id": 702569,"Sequence number": 7674414, "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": 6305204361817.347, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6305204361883.155, "dur": 49.428, + "args": { + "External id": 702570,"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": 6305204361944.974, "dur": 106.886, + "args": { + "External id": 702571,"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": 6305204362103.393, "dur": 44.904, + "args": { + "External id": 702572,"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": 6305204362157.564, "dur": 29.506, + "args": { + "External id": 702573,"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": 6305204362215.721, "dur": 31.152, + "args": { + "External id": 702574,"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": 6305204362265.753, "dur": 18.487, + "args": { + "External id": 702575,"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": 6305204362307.194, "dur": 131.409, + "args": { + "External id": 702576,"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": 6305204362358.060, "dur": 11.464, + "args": { + "External id": 702577,"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": 6305204362363.673, "dur": 5.107, + "args": { + "External id": 702578,"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": 6305204362372.453, "dur": 3.660, + "args": { + "External id": 702579,"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": 6305204362377.210, "dur": 1.350, + "args": { + "External id": 702580,"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": 6305204362381.373, "dur": 6.415, + "args": { + "External id": 702581,"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": 6305204362449.124, "dur": 50.492, + "args": { + "External id": 702582,"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": 6305204362551.122, "dur": 31.734, + "args": { + "External id": 702583,"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": 6305204362593.647, "dur": 45.853, + "args": { + "External id": 702584,"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": 6305204362648.571, "dur": 35.594, + "args": { + "External id": 702585,"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": 6305204362703.936, "dur": 26.754, + "args": { + "External id": 702586,"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": 6305204362739.137, "dur": 36.378, + "args": { + "External id": 702587,"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": 6305204362793.704, "dur": 17.626, + "args": { + "External id": 702588,"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": 6305204362962.171, "dur": 76.988, + "args": { + "External id": 702589,"Record function id": 0, "Ev Idx": 12993 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6305204363155.451, "dur": 52.674, + "args": { + "External id": 702590,"Record function id": 0, "Ev Idx": 12994 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.12)", "pid": 2338707, "tid": 2338707, + "ts": 6305204363217.746, "dur": 30931.538, + "args": { + "External id": 702591,"Record function id": 0, "Ev Idx": 12995 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.12)", "pid": 2338707, "tid": 2338707, + "ts": 6305204363227.539, "dur": 951.252, + "args": { + "External id": 702592,"Record function id": 0, "Ev Idx": 12996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6305204363309.829, "dur": 9.849, + "args": { + "External id": 702593,"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": 6305204363335.265, "dur": 40.036, + "args": { + "External id": 702594,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305204363340.913, "dur": 2.257, + "args": { + "External id": 702595,"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": 6305204363347.475, "dur": 0.565, + "args": { + "External id": 702596,"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": 6305204363349.262, "dur": 0.490, + "args": { + "External id": 702597,"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": 6305204363351.321, "dur": 2.471, + "args": { + "External id": 702598,"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": 6305204363355.393, "dur": 0.579, + "args": { + "External id": 702599,"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": 6305204363357.560, "dur": 0.238, + "args": { + "External id": 702600,"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": 6305204363361.752, "dur": 2.606, + "args": { + "External id": 702601,"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": 6305204363365.505, "dur": 0.357, + "args": { + "External id": 702602,"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": 6305204363367.410, "dur": 0.528, + "args": { + "External id": 702603,"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": 6305204363387.129, "dur": 54.127, + "args": { + "External id": 702604,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305204363474.854, "dur": 147.831, + "args": { + "External id": 702605,"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": 6305204363487.917, "dur": 3.894, + "args": { + "External id": 702606,"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": 6305204363497.315, "dur": 30.163, + "args": { + "External id": 702607,"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": 6305204363504.212, "dur": 22.787, + "args": { + "External id": 702608,"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": 6305204363521.700, "dur": 3.322, + "args": { + "External id": 702609,"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": 6305204363535.642, "dur": 30.303, + "args": { + "External id": 702610,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305204363537.743, "dur": 0.482, + "args": { + "External id": 702611,"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": 6305204363539.585, "dur": 1.689, + "args": { + "External id": 702612,"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": 6305204363542.740, "dur": 0.482, + "args": { + "External id": 702613,"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": 6305204363546.472, "dur": 2.763, + "args": { + "External id": 702614,"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": 6305204363550.741, "dur": 0.388, + "args": { + "External id": 702615,"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": 6305204363552.390, "dur": 2.841, + "args": { + "External id": 702616,"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": 6305204363556.280, "dur": 0.293, + "args": { + "External id": 702617,"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": 6305204363557.808, "dur": 0.304, + "args": { + "External id": 702618,"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": 6305204363561.306, "dur": 0.405, + "args": { + "External id": 702619,"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": 6305204363578.324, "dur": 35.849, + "args": { + "External id": 702620,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305204363681.509, "dur": 357.936, + "args": { + "External id": 702621,"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": 6305204363713.901, "dur": 320.597, + "args": { + "External id": 702622,"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": 6305204363724.169, "dur": 304.882, + "args": { + "External id": 702623,"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": 6305204364096.769, "dur": 3.453, + "args": { + "External id": 702624,"Record function id": 0, "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": 6305204364200.799, "dur": 29723.644, + "args": { + "External id": 702625,"Record function id": 0, "Ev Idx": 13029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6305204364304.029, "dur": 6.672, + "args": { + "External id": 702626,"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": 6305204364314.905, "dur": 0.809, + "args": { + "External id": 702627,"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": 6305204364317.718, "dur": 3.775, + "args": { + "External id": 702628,"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": 6305204364323.842, "dur": 1.221, + "args": { + "External id": 702629,"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": 6305204364326.585, "dur": 0.984, + "args": { + "External id": 702630,"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": 6305204364329.106, "dur": 0.802, + "args": { + "External id": 702631,"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": 6305204364333.742, "dur": 0.997, + "args": { + "External id": 702632,"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": 6305204364336.466, "dur": 2.261, + "args": { + "External id": 702633,"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": 6305204364340.122, "dur": 0.905, + "args": { + "External id": 702634,"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": 6305204364342.627, "dur": 0.891, + "args": { + "External id": 702635,"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": 6305204364363.735, "dur": 29515.536, + "args": { + "External id": 702636,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305204364379.342, "dur": 29491.197, + "args": { + "External id": 702637,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305204364398.582, "dur": 15.813, + "args": { + "External id": 702638,"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": 6305204364417.840, "dur": 29418.886, + "args": { + "External id": 702639,"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": 6305204364420.698, "dur": 29415.348, + "args": { + "External id": 702640,"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": 6305204364426.394, "dur": 5.688, + "args": { + "External id": 702641,"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": 6305204364433.641, "dur": 29399.121, + "args": { + "External id": 702642,"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": 6305204394089.151, "dur": 31.920, + "args": { + "External id": 702643,"Sequence number": 7674415, "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": 6305204394089.151, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6305204394106.327, "dur": 9.507, + "args": { + "External id": 702644,"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": 6305204394110.208, "dur": 5.204, + "args": { + "External id": 702645,"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": 6305204394191.144, "dur": 72.488, + "args": { + "External id": 702646,"Record function id": 0, "Ev Idx": 13050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6305204394264.908, "dur": 1117.961, + "args": { + "External id": 702647,"Record function id": 0, "Ev Idx": 13051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305204394305.461, "dur": 1063.912, + "args": { + "External id": 702648,"Sequence number": 7674416, "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": 6305204394305.461, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6305204394373.108, "dur": 49.222, + "args": { + "External id": 702649,"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": 6305204394434.396, "dur": 121.091, + "args": { + "External id": 702650,"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": 6305204394572.225, "dur": 41.067, + "args": { + "External id": 702651,"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": 6305204394622.380, "dur": 29.374, + "args": { + "External id": 702652,"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": 6305204394679.096, "dur": 27.243, + "args": { + "External id": 702653,"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": 6305204394726.755, "dur": 17.226, + "args": { + "External id": 702654,"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": 6305204394767.967, "dur": 130.779, + "args": { + "External id": 702655,"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": 6305204394820.441, "dur": 11.526, + "args": { + "External id": 702656,"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": 6305204394826.006, "dur": 4.916, + "args": { + "External id": 702657,"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": 6305204394834.722, "dur": 4.573, + "args": { + "External id": 702658,"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": 6305204394840.574, "dur": 0.940, + "args": { + "External id": 702659,"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": 6305204394844.047, "dur": 3.810, + "args": { + "External id": 702660,"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": 6305204394910.622, "dur": 47.649, + "args": { + "External id": 702661,"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": 6305204394988.925, "dur": 27.835, + "args": { + "External id": 702662,"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": 6305204395026.170, "dur": 78.698, + "args": { + "External id": 702663,"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": 6305204395118.078, "dur": 38.203, + "args": { + "External id": 702664,"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": 6305204395189.138, "dur": 30.349, + "args": { + "External id": 702665,"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": 6305204395228.318, "dur": 36.417, + "args": { + "External id": 702666,"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": 6305204395282.260, "dur": 19.424, + "args": { + "External id": 702667,"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": 6305204395447.438, "dur": 95.784, + "args": { + "External id": 702668,"Record function id": 0, "Ev Idx": 13072 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6305204395621.649, "dur": 49.801, + "args": { + "External id": 702669,"Record function id": 0, "Ev Idx": 13073 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.13)", "pid": 2338707, "tid": 2338707, + "ts": 6305204395679.669, "dur": 30626.172, + "args": { + "External id": 702670,"Record function id": 0, "Ev Idx": 13074 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.13)", "pid": 2338707, "tid": 2338707, + "ts": 6305204395687.928, "dur": 814.925, + "args": { + "External id": 702671,"Record function id": 0, "Ev Idx": 13075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6305204395772.775, "dur": 9.901, + "args": { + "External id": 702672,"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": 6305204395796.149, "dur": 37.365, + "args": { + "External id": 702673,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305204395802.026, "dur": 2.490, + "args": { + "External id": 702674,"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": 6305204395809.243, "dur": 0.532, + "args": { + "External id": 702675,"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": 6305204395810.656, "dur": 0.508, + "args": { + "External id": 702676,"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": 6305204395812.438, "dur": 0.564, + "args": { + "External id": 702677,"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": 6305204395816.798, "dur": 0.336, + "args": { + "External id": 702678,"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": 6305204395818.495, "dur": 0.402, + "args": { + "External id": 702679,"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": 6305204395820.032, "dur": 4.245, + "args": { + "External id": 702680,"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": 6305204395825.356, "dur": 0.356, + "args": { + "External id": 702681,"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": 6305204395826.572, "dur": 0.392, + "args": { + "External id": 702682,"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": 6305204395844.903, "dur": 52.580, + "args": { + "External id": 702683,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305204395932.691, "dur": 164.393, + "args": { + "External id": 702684,"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": 6305204395944.904, "dur": 3.726, + "args": { + "External id": 702685,"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": 6305204395954.174, "dur": 10.104, + "args": { + "External id": 702686,"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": 6305204395958.646, "dur": 5.223, + "args": { + "External id": 702687,"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": 6305204395962.005, "dur": 0.694, + "args": { + "External id": 702688,"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": 6305204395970.798, "dur": 31.906, + "args": { + "External id": 702689,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305204395972.584, "dur": 2.619, + "args": { + "External id": 702690,"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": 6305204395977.035, "dur": 0.539, + "args": { + "External id": 702691,"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": 6305204395979.241, "dur": 0.458, + "args": { + "External id": 702692,"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": 6305204395983.485, "dur": 2.644, + "args": { + "External id": 702693,"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": 6305204395987.519, "dur": 0.439, + "args": { + "External id": 702694,"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": 6305204395989.482, "dur": 0.432, + "args": { + "External id": 702695,"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": 6305204395991.851, "dur": 0.416, + "args": { + "External id": 702696,"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": 6305204395993.869, "dur": 0.441, + "args": { + "External id": 702697,"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": 6305204395995.665, "dur": 2.418, + "args": { + "External id": 702698,"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": 6305204396017.255, "dur": 33.708, + "args": { + "External id": 702699,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305204396158.303, "dur": 256.594, + "args": { + "External id": 702700,"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": 6305204396192.527, "dur": 217.696, + "args": { + "External id": 702701,"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": 6305204396203.352, "dur": 201.720, + "args": { + "External id": 702702,"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": 6305204396436.312, "dur": 2.240, + "args": { + "External id": 702703,"Record function id": 0, "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": 6305204396540.596, "dur": 29572.257, + "args": { + "External id": 702704,"Record function id": 0, "Ev Idx": 13108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6305204396638.669, "dur": 6.139, + "args": { + "External id": 702705,"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": 6305204396648.554, "dur": 1.031, + "args": { + "External id": 702706,"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": 6305204396651.330, "dur": 3.510, + "args": { + "External id": 702707,"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": 6305204396656.665, "dur": 0.777, + "args": { + "External id": 702708,"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": 6305204396658.872, "dur": 0.839, + "args": { + "External id": 702709,"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": 6305204396660.885, "dur": 1.024, + "args": { + "External id": 702710,"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": 6305204396666.527, "dur": 1.087, + "args": { + "External id": 702711,"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": 6305204396669.335, "dur": 2.550, + "args": { + "External id": 702712,"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": 6305204396673.555, "dur": 0.828, + "args": { + "External id": 702713,"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": 6305204396675.860, "dur": 0.926, + "args": { + "External id": 702714,"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": 6305204396696.572, "dur": 29339.470, + "args": { + "External id": 702715,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305204396712.400, "dur": 29315.142, + "args": { + "External id": 702716,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305204396728.314, "dur": 15.591, + "args": { + "External id": 702717,"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": 6305204396747.541, "dur": 29243.806, + "args": { + "External id": 702718,"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": 6305204396750.000, "dur": 29240.749, + "args": { + "External id": 702719,"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": 6305204396755.494, "dur": 4.866, + "args": { + "External id": 702720,"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": 6305204396762.227, "dur": 29225.330, + "args": { + "External id": 702721,"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": 6305204426249.521, "dur": 32.436, + "args": { + "External id": 702722,"Sequence number": 7674417, "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": 6305204426249.521, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6305204426268.064, "dur": 9.087, + "args": { + "External id": 702723,"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": 6305204426271.956, "dur": 5.020, + "args": { + "External id": 702724,"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": 6305204426346.957, "dur": 73.401, + "args": { + "External id": 702725,"Record function id": 0, "Ev Idx": 13129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6305204426421.597, "dur": 1132.026, + "args": { + "External id": 702726,"Record function id": 0, "Ev Idx": 13130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305204426459.599, "dur": 1078.524, + "args": { + "External id": 702727,"Sequence number": 7674418, "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": 6305204426459.599, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6305204426537.400, "dur": 50.694, + "args": { + "External id": 702728,"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": 6305204426602.038, "dur": 106.273, + "args": { + "External id": 702729,"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": 6305204426720.326, "dur": 40.359, + "args": { + "External id": 702730,"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": 6305204426770.535, "dur": 29.213, + "args": { + "External id": 702731,"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": 6305204426825.083, "dur": 27.221, + "args": { + "External id": 702732,"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": 6305204426871.400, "dur": 17.882, + "args": { + "External id": 702733,"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": 6305204426912.550, "dur": 131.089, + "args": { + "External id": 702734,"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": 6305204426964.269, "dur": 11.870, + "args": { + "External id": 702735,"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": 6305204426969.779, "dur": 5.577, + "args": { + "External id": 702736,"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": 6305204426979.017, "dur": 3.732, + "args": { + "External id": 702737,"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": 6305204426984.212, "dur": 1.001, + "args": { + "External id": 702738,"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": 6305204426987.845, "dur": 5.351, + "args": { + "External id": 702739,"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": 6305204427091.189, "dur": 61.545, + "args": { + "External id": 702740,"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": 6305204427188.975, "dur": 33.206, + "args": { + "External id": 702741,"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": 6305204427233.852, "dur": 43.673, + "args": { + "External id": 702742,"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": 6305204427286.316, "dur": 34.749, + "args": { + "External id": 702743,"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": 6305204427343.781, "dur": 26.261, + "args": { + "External id": 702744,"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": 6305204427378.100, "dur": 35.602, + "args": { + "External id": 702745,"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": 6305204427430.845, "dur": 20.016, + "args": { + "External id": 702746,"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": 6305204427620.353, "dur": 77.512, + "args": { + "External id": 702747,"Record function id": 0, "Ev Idx": 13151 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6305204427774.113, "dur": 49.017, + "args": { + "External id": 702748,"Record function id": 0, "Ev Idx": 13152 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.14)", "pid": 2338707, "tid": 2338707, + "ts": 6305204427832.452, "dur": 32839.943, + "args": { + "External id": 702749,"Record function id": 0, "Ev Idx": 13153 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.14)", "pid": 2338707, "tid": 2338707, + "ts": 6305204427840.359, "dur": 1001.809, + "args": { + "External id": 702750,"Record function id": 0, "Ev Idx": 13154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6305204427922.981, "dur": 8.914, + "args": { + "External id": 702751,"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": 6305204427945.090, "dur": 51.225, + "args": { + "External id": 702752,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305204427955.014, "dur": 2.347, + "args": { + "External id": 702753,"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": 6305204427962.006, "dur": 0.548, + "args": { + "External id": 702754,"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": 6305204427964.232, "dur": 0.610, + "args": { + "External id": 702755,"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": 6305204427966.424, "dur": 2.348, + "args": { + "External id": 702756,"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": 6305204427970.918, "dur": 0.438, + "args": { + "External id": 702757,"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": 6305204427976.022, "dur": 0.445, + "args": { + "External id": 702758,"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": 6305204427980.914, "dur": 2.466, + "args": { + "External id": 702759,"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": 6305204427985.018, "dur": 0.560, + "args": { + "External id": 702760,"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": 6305204427986.997, "dur": 2.532, + "args": { + "External id": 702761,"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": 6305204428007.769, "dur": 93.073, + "args": { + "External id": 702762,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305204428138.443, "dur": 133.242, + "args": { + "External id": 702763,"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": 6305204428151.196, "dur": 5.533, + "args": { + "External id": 702764,"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": 6305204428164.802, "dur": 11.734, + "args": { + "External id": 702765,"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": 6305204428169.542, "dur": 6.567, + "args": { + "External id": 702766,"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": 6305204428173.384, "dur": 1.021, + "args": { + "External id": 702767,"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": 6305204428183.880, "dur": 31.743, + "args": { + "External id": 702768,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305204428186.545, "dur": 0.575, + "args": { + "External id": 702769,"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": 6305204428189.021, "dur": 0.620, + "args": { + "External id": 702770,"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": 6305204428191.088, "dur": 2.441, + "args": { + "External id": 702771,"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": 6305204428194.989, "dur": 2.709, + "args": { + "External id": 702772,"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": 6305204428199.306, "dur": 0.351, + "args": { + "External id": 702773,"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": 6305204428202.978, "dur": 0.385, + "args": { + "External id": 702774,"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": 6305204428204.758, "dur": 0.405, + "args": { + "External id": 702775,"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": 6305204428206.481, "dur": 0.493, + "args": { + "External id": 702776,"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": 6305204428210.187, "dur": 0.456, + "args": { + "External id": 702777,"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": 6305204428227.378, "dur": 35.474, + "args": { + "External id": 702778,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305204428326.174, "dur": 412.028, + "args": { + "External id": 702779,"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": 6305204428357.616, "dur": 375.064, + "args": { + "External id": 702780,"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": 6305204428367.940, "dur": 358.783, + "args": { + "External id": 702781,"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": 6305204428765.100, "dur": 2.591, + "args": { + "External id": 702782,"Record function id": 0, "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": 6305204428863.497, "dur": 31602.104, + "args": { + "External id": 702783,"Record function id": 0, "Ev Idx": 13187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6305204428962.279, "dur": 6.524, + "args": { + "External id": 702784,"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": 6305204428971.864, "dur": 1.378, + "args": { + "External id": 702785,"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": 6305204428974.952, "dur": 3.418, + "args": { + "External id": 702786,"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": 6305204428980.059, "dur": 1.184, + "args": { + "External id": 702787,"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": 6305204428982.778, "dur": 1.047, + "args": { + "External id": 702788,"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": 6305204428985.208, "dur": 1.040, + "args": { + "External id": 702789,"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": 6305204428989.902, "dur": 0.930, + "args": { + "External id": 702790,"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": 6305204428992.618, "dur": 2.535, + "args": { + "External id": 702791,"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": 6305204428996.578, "dur": 0.722, + "args": { + "External id": 702792,"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": 6305204428998.807, "dur": 0.698, + "args": { + "External id": 702793,"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": 6305204429019.905, "dur": 31401.930, + "args": { + "External id": 702794,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305204429036.243, "dur": 31377.471, + "args": { + "External id": 702795,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305204429051.243, "dur": 54.885, + "args": { + "External id": 702796,"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": 6305204429114.326, "dur": 31264.348, + "args": { + "External id": 702797,"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": 6305204429116.817, "dur": 31261.296, + "args": { + "External id": 702798,"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": 6305204429123.861, "dur": 5.716, + "args": { + "External id": 702799,"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": 6305204429131.479, "dur": 31243.595, + "args": { + "External id": 702800,"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": 6305204460613.231, "dur": 32.315, + "args": { + "External id": 702801,"Sequence number": 7674419, "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": 6305204460613.231, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6305204460631.128, "dur": 9.680, + "args": { + "External id": 702802,"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": 6305204460635.405, "dur": 5.068, + "args": { + "External id": 702803,"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": 6305204460713.585, "dur": 74.674, + "args": { + "External id": 702804,"Record function id": 0, "Ev Idx": 13208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6305204460789.702, "dur": 1125.189, + "args": { + "External id": 702805,"Record function id": 0, "Ev Idx": 13209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305204460828.208, "dur": 1072.954, + "args": { + "External id": 702806,"Sequence number": 7674420, "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": 6305204460828.208, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6305204460893.814, "dur": 49.447, + "args": { + "External id": 702807,"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": 6305204460956.243, "dur": 134.472, + "args": { + "External id": 702808,"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": 6305204461106.496, "dur": 44.647, + "args": { + "External id": 702809,"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": 6305204461162.412, "dur": 29.871, + "args": { + "External id": 702810,"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": 6305204461220.423, "dur": 28.797, + "args": { + "External id": 702811,"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": 6305204461269.250, "dur": 18.853, + "args": { + "External id": 702812,"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": 6305204461312.272, "dur": 141.450, + "args": { + "External id": 702813,"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": 6305204461368.382, "dur": 12.114, + "args": { + "External id": 702814,"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": 6305204461374.038, "dur": 5.732, + "args": { + "External id": 702815,"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": 6305204461383.326, "dur": 4.096, + "args": { + "External id": 702816,"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": 6305204461389.218, "dur": 1.368, + "args": { + "External id": 702817,"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": 6305204461395.377, "dur": 4.592, + "args": { + "External id": 702818,"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": 6305204461465.084, "dur": 65.535, + "args": { + "External id": 702819,"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": 6305204461565.713, "dur": 31.409, + "args": { + "External id": 702820,"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": 6305204461607.927, "dur": 47.416, + "args": { + "External id": 702821,"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": 6305204461661.848, "dur": 35.025, + "args": { + "External id": 702822,"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": 6305204461717.826, "dur": 31.749, + "args": { + "External id": 702823,"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": 6305204461754.875, "dur": 35.317, + "args": { + "External id": 702824,"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": 6305204461810.082, "dur": 18.784, + "args": { + "External id": 702825,"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": 6305204461978.844, "dur": 108.559, + "args": { + "External id": 702826,"Record function id": 0, "Ev Idx": 13230 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6305204462168.914, "dur": 49.121, + "args": { + "External id": 702827,"Record function id": 0, "Ev Idx": 13231 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.15)", "pid": 2338707, "tid": 2338707, + "ts": 6305204462226.982, "dur": 32499.618, + "args": { + "External id": 702828,"Record function id": 0, "Ev Idx": 13232 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.15)", "pid": 2338707, "tid": 2338707, + "ts": 6305204462236.056, "dur": 969.837, + "args": { + "External id": 702829,"Record function id": 0, "Ev Idx": 13233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6305204462318.302, "dur": 9.831, + "args": { + "External id": 702830,"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": 6305204462341.427, "dur": 43.940, + "args": { + "External id": 702831,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305204462348.207, "dur": 2.468, + "args": { + "External id": 702832,"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": 6305204462355.739, "dur": 0.638, + "args": { + "External id": 702833,"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": 6305204462358.135, "dur": 0.538, + "args": { + "External id": 702834,"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": 6305204462360.488, "dur": 0.473, + "args": { + "External id": 702835,"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": 6305204462364.320, "dur": 0.593, + "args": { + "External id": 702836,"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": 6305204462367.007, "dur": 0.662, + "args": { + "External id": 702837,"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": 6305204462368.932, "dur": 5.162, + "args": { + "External id": 702838,"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": 6305204462375.801, "dur": 0.543, + "args": { + "External id": 702839,"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": 6305204462377.946, "dur": 0.611, + "args": { + "External id": 702840,"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": 6305204462397.072, "dur": 54.842, + "args": { + "External id": 702841,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305204462487.732, "dur": 164.781, + "args": { + "External id": 702842,"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": 6305204462498.995, "dur": 3.783, + "args": { + "External id": 702843,"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": 6305204462523.300, "dur": 12.122, + "args": { + "External id": 702844,"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": 6305204462527.810, "dur": 7.229, + "args": { + "External id": 702845,"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": 6305204462532.479, "dur": 0.668, + "args": { + "External id": 702846,"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": 6305204462543.707, "dur": 34.034, + "args": { + "External id": 702847,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305204462546.687, "dur": 2.823, + "args": { + "External id": 702848,"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": 6305204462551.512, "dur": 0.536, + "args": { + "External id": 702849,"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": 6305204462553.690, "dur": 0.568, + "args": { + "External id": 702850,"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": 6305204462557.757, "dur": 2.690, + "args": { + "External id": 702851,"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": 6305204462561.901, "dur": 0.333, + "args": { + "External id": 702852,"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": 6305204462563.570, "dur": 0.385, + "args": { + "External id": 702853,"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": 6305204462567.043, "dur": 0.400, + "args": { + "External id": 702854,"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": 6305204462569.095, "dur": 0.435, + "args": { + "External id": 702855,"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": 6305204462570.980, "dur": 2.195, + "args": { + "External id": 702856,"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": 6305204462600.753, "dur": 43.326, + "args": { + "External id": 702857,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305204462709.641, "dur": 390.350, + "args": { + "External id": 702858,"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": 6305204462741.486, "dur": 352.854, + "args": { + "External id": 702859,"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": 6305204462754.744, "dur": 331.337, + "args": { + "External id": 702860,"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": 6305204463126.676, "dur": 2.651, + "args": { + "External id": 702861,"Record function id": 0, "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": 6305204463228.284, "dur": 31300.161, + "args": { + "External id": 702862,"Record function id": 0, "Ev Idx": 13266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6305204463336.337, "dur": 6.780, + "args": { + "External id": 702863,"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": 6305204463346.677, "dur": 1.187, + "args": { + "External id": 702864,"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": 6305204463349.505, "dur": 3.884, + "args": { + "External id": 702865,"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": 6305204463354.864, "dur": 0.969, + "args": { + "External id": 702866,"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": 6305204463356.991, "dur": 0.852, + "args": { + "External id": 702867,"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": 6305204463361.391, "dur": 1.026, + "args": { + "External id": 702868,"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": 6305204463364.062, "dur": 1.052, + "args": { + "External id": 702869,"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": 6305204463366.850, "dur": 2.382, + "args": { + "External id": 702870,"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": 6305204463370.717, "dur": 0.796, + "args": { + "External id": 702871,"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": 6305204463376.067, "dur": 0.884, + "args": { + "External id": 702872,"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": 6305204463395.155, "dur": 31077.306, + "args": { + "External id": 702873,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305204463411.194, "dur": 31052.511, + "args": { + "External id": 702874,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305204463431.556, "dur": 15.486, + "args": { + "External id": 702875,"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": 6305204463450.656, "dur": 30977.372, + "args": { + "External id": 702876,"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": 6305204463453.386, "dur": 30974.032, + "args": { + "External id": 702877,"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": 6305204463460.181, "dur": 5.529, + "args": { + "External id": 702878,"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": 6305204463467.576, "dur": 30956.695, + "args": { + "External id": 702879,"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": 6305204494665.302, "dur": 32.508, + "args": { + "External id": 702880,"Sequence number": 7674421, "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": 6305204494665.302, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6305204494683.956, "dur": 8.913, + "args": { + "External id": 702881,"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": 6305204494687.494, "dur": 5.115, + "args": { + "External id": 702882,"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": 6305204494767.853, "dur": 71.381, + "args": { + "External id": 702883,"Record function id": 0, "Ev Idx": 13287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6305204494840.710, "dur": 1111.727, + "args": { + "External id": 702884,"Record function id": 0, "Ev Idx": 13288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305204494879.523, "dur": 1058.834, + "args": { + "External id": 702885,"Sequence number": 7674422, "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": 6305204494879.523, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6305204494946.400, "dur": 50.720, + "args": { + "External id": 702886,"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": 6305204495009.365, "dur": 134.253, + "args": { + "External id": 702887,"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": 6305204495159.651, "dur": 41.203, + "args": { + "External id": 702888,"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": 6305204495211.804, "dur": 29.986, + "args": { + "External id": 702889,"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": 6305204495271.036, "dur": 27.416, + "args": { + "External id": 702890,"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": 6305204495318.995, "dur": 16.328, + "args": { + "External id": 702891,"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": 6305204495359.186, "dur": 129.487, + "args": { + "External id": 702892,"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": 6305204495410.114, "dur": 12.300, + "args": { + "External id": 702893,"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": 6305204495415.555, "dur": 5.870, + "args": { + "External id": 702894,"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": 6305204495425.481, "dur": 4.142, + "args": { + "External id": 702895,"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": 6305204495431.131, "dur": 1.239, + "args": { + "External id": 702896,"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": 6305204495434.977, "dur": 4.565, + "args": { + "External id": 702897,"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": 6305204495499.357, "dur": 68.318, + "args": { + "External id": 702898,"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": 6305204495604.056, "dur": 30.196, + "args": { + "External id": 702899,"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": 6305204495645.835, "dur": 43.488, + "args": { + "External id": 702900,"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": 6305204495698.799, "dur": 35.603, + "args": { + "External id": 702901,"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": 6305204495758.290, "dur": 24.614, + "args": { + "External id": 702902,"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": 6305204495791.512, "dur": 34.833, + "args": { + "External id": 702903,"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": 6305204495844.760, "dur": 18.112, + "args": { + "External id": 702904,"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": 6305204496019.895, "dur": 113.660, + "args": { + "External id": 702905,"Record function id": 0, "Ev Idx": 13309 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6305204496214.436, "dur": 49.222, + "args": { + "External id": 702906,"Record function id": 0, "Ev Idx": 13310 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.16)", "pid": 2338707, "tid": 2338707, + "ts": 6305204496274.170, "dur": 33609.603, + "args": { + "External id": 702907,"Record function id": 0, "Ev Idx": 13311 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.16)", "pid": 2338707, "tid": 2338707, + "ts": 6305204496281.771, "dur": 960.030, + "args": { + "External id": 702908,"Record function id": 0, "Ev Idx": 13312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6305204496365.216, "dur": 9.586, + "args": { + "External id": 702909,"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": 6305204496389.078, "dur": 41.029, + "args": { + "External id": 702910,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305204496395.325, "dur": 2.469, + "args": { + "External id": 702911,"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": 6305204496402.742, "dur": 0.546, + "args": { + "External id": 702912,"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": 6305204496405.221, "dur": 0.542, + "args": { + "External id": 702913,"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": 6305204496407.357, "dur": 0.360, + "args": { + "External id": 702914,"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": 6305204496411.205, "dur": 0.772, + "args": { + "External id": 702915,"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": 6305204496413.435, "dur": 0.389, + "args": { + "External id": 702916,"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": 6305204496415.151, "dur": 4.481, + "args": { + "External id": 702917,"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": 6305204496421.276, "dur": 0.417, + "args": { + "External id": 702918,"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": 6305204496423.231, "dur": 0.356, + "args": { + "External id": 702919,"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": 6305204496444.376, "dur": 57.909, + "args": { + "External id": 702920,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305204496554.243, "dur": 137.044, + "args": { + "External id": 702921,"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": 6305204496566.530, "dur": 8.187, + "args": { + "External id": 702922,"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": 6305204496582.392, "dur": 11.767, + "args": { + "External id": 702923,"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": 6305204496587.047, "dur": 6.707, + "args": { + "External id": 702924,"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": 6305204496591.516, "dur": 0.583, + "args": { + "External id": 702925,"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": 6305204496601.785, "dur": 35.317, + "args": { + "External id": 702926,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305204496604.221, "dur": 0.573, + "args": { + "External id": 702927,"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": 6305204496606.730, "dur": 2.826, + "args": { + "External id": 702928,"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": 6305204496611.636, "dur": 0.645, + "args": { + "External id": 702929,"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": 6305204496613.716, "dur": 3.170, + "args": { + "External id": 702930,"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": 6305204496621.077, "dur": 0.386, + "args": { + "External id": 702931,"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": 6305204496622.921, "dur": 0.491, + "args": { + "External id": 702932,"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": 6305204496625.367, "dur": 0.471, + "args": { + "External id": 702933,"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": 6305204496629.582, "dur": 0.598, + "args": { + "External id": 702934,"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": 6305204496632.139, "dur": 0.607, + "args": { + "External id": 702935,"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": 6305204496648.868, "dur": 34.370, + "args": { + "External id": 702936,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305204496744.983, "dur": 394.907, + "args": { + "External id": 702937,"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": 6305204496776.886, "dur": 356.214, + "args": { + "External id": 702938,"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": 6305204496786.570, "dur": 340.357, + "args": { + "External id": 702939,"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": 6305204497166.695, "dur": 2.826, + "args": { + "External id": 702940,"Record function id": 0, "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": 6305204497265.056, "dur": 32427.158, + "args": { + "External id": 702941,"Record function id": 0, "Ev Idx": 13345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6305204497368.860, "dur": 6.470, + "args": { + "External id": 702942,"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": 6305204497379.192, "dur": 1.006, + "args": { + "External id": 702943,"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": 6305204497382.050, "dur": 3.364, + "args": { + "External id": 702944,"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": 6305204497387.166, "dur": 1.255, + "args": { + "External id": 702945,"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": 6305204497389.911, "dur": 1.143, + "args": { + "External id": 702946,"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": 6305204497392.612, "dur": 0.720, + "args": { + "External id": 702947,"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": 6305204497397.250, "dur": 0.890, + "args": { + "External id": 702948,"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": 6305204497399.645, "dur": 2.524, + "args": { + "External id": 702949,"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": 6305204497403.741, "dur": 0.813, + "args": { + "External id": 702950,"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": 6305204497406.330, "dur": 0.889, + "args": { + "External id": 702951,"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": 6305204497427.162, "dur": 32221.371, + "args": { + "External id": 702952,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305204497442.979, "dur": 32196.812, + "args": { + "External id": 702953,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305204497464.068, "dur": 17.624, + "args": { + "External id": 702954,"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": 6305204497485.401, "dur": 32117.478, + "args": { + "External id": 702955,"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": 6305204497488.159, "dur": 32114.089, + "args": { + "External id": 702956,"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": 6305204497494.702, "dur": 4.895, + "args": { + "External id": 702957,"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": 6305204497501.122, "dur": 32098.022, + "args": { + "External id": 702958,"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": 6305204529826.489, "dur": 33.202, + "args": { + "External id": 702959,"Sequence number": 7674423, "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": 6305204529826.489, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6305204529844.492, "dur": 9.676, + "args": { + "External id": 702960,"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": 6305204529848.721, "dur": 5.179, + "args": { + "External id": 702961,"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": 6305204529925.340, "dur": 73.182, + "args": { + "External id": 702962,"Record function id": 0, "Ev Idx": 13366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6305204530000.106, "dur": 1200.679, + "args": { + "External id": 702963,"Record function id": 0, "Ev Idx": 13367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305204530040.194, "dur": 1146.888, + "args": { + "External id": 702964,"Sequence number": 7674424, "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": 6305204530040.194, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6305204530142.675, "dur": 50.113, + "args": { + "External id": 702965,"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": 6305204530206.448, "dur": 104.036, + "args": { + "External id": 702966,"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": 6305204530323.075, "dur": 40.546, + "args": { + "External id": 702967,"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": 6305204530374.689, "dur": 28.644, + "args": { + "External id": 702968,"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": 6305204530433.882, "dur": 28.785, + "args": { + "External id": 702969,"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": 6305204530481.514, "dur": 18.105, + "args": { + "External id": 702970,"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": 6305204530540.131, "dur": 138.789, + "args": { + "External id": 702971,"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": 6305204530595.186, "dur": 13.105, + "args": { + "External id": 702972,"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": 6305204530600.901, "dur": 6.392, + "args": { + "External id": 702973,"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": 6305204530611.460, "dur": 4.040, + "args": { + "External id": 702974,"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": 6305204530617.134, "dur": 1.215, + "args": { + "External id": 702975,"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": 6305204530620.967, "dur": 6.624, + "args": { + "External id": 702976,"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": 6305204530711.450, "dur": 60.032, + "args": { + "External id": 702977,"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": 6305204530810.611, "dur": 31.300, + "args": { + "External id": 702978,"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": 6305204530852.186, "dur": 44.725, + "args": { + "External id": 702979,"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": 6305204530907.050, "dur": 34.531, + "args": { + "External id": 702980,"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": 6305204530963.923, "dur": 27.592, + "args": { + "External id": 702981,"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": 6305204530997.199, "dur": 34.779, + "args": { + "External id": 702982,"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": 6305204531088.757, "dur": 23.294, + "args": { + "External id": 702983,"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": 6305204531267.078, "dur": 81.886, + "args": { + "External id": 702984,"Record function id": 0, "Ev Idx": 13388 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6305204531425.067, "dur": 47.193, + "args": { + "External id": 702985,"Record function id": 0, "Ev Idx": 13389 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.17)", "pid": 2338707, "tid": 2338707, + "ts": 6305204531481.361, "dur": 32134.195, + "args": { + "External id": 702986,"Record function id": 0, "Ev Idx": 13390 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.17)", "pid": 2338707, "tid": 2338707, + "ts": 6305204531490.458, "dur": 957.789, + "args": { + "External id": 702987,"Record function id": 0, "Ev Idx": 13391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6305204531591.689, "dur": 10.088, + "args": { + "External id": 702988,"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": 6305204531618.435, "dur": 38.736, + "args": { + "External id": 702989,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305204531624.292, "dur": 2.305, + "args": { + "External id": 702990,"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": 6305204531631.779, "dur": 0.698, + "args": { + "External id": 702991,"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": 6305204531634.022, "dur": 0.407, + "args": { + "External id": 702992,"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": 6305204531636.064, "dur": 0.608, + "args": { + "External id": 702993,"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": 6305204531640.072, "dur": 0.668, + "args": { + "External id": 702994,"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": 6305204531642.085, "dur": 0.495, + "args": { + "External id": 702995,"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": 6305204531644.197, "dur": 2.509, + "args": { + "External id": 702996,"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": 6305204531648.607, "dur": 0.538, + "args": { + "External id": 702997,"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": 6305204531650.692, "dur": 0.417, + "args": { + "External id": 702998,"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": 6305204531671.426, "dur": 54.931, + "args": { + "External id": 702999,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305204531763.066, "dur": 126.660, + "args": { + "External id": 703000,"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": 6305204531774.286, "dur": 4.123, + "args": { + "External id": 703001,"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": 6305204531783.451, "dur": 10.836, + "args": { + "External id": 703002,"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": 6305204531788.309, "dur": 5.599, + "args": { + "External id": 703003,"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": 6305204531792.086, "dur": 0.572, + "args": { + "External id": 703004,"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": 6305204531801.259, "dur": 34.063, + "args": { + "External id": 703005,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305204531803.336, "dur": 2.710, + "args": { + "External id": 703006,"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": 6305204531807.720, "dur": 0.374, + "args": { + "External id": 703007,"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": 6305204531809.730, "dur": 0.431, + "args": { + "External id": 703008,"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": 6305204531814.401, "dur": 2.860, + "args": { + "External id": 703009,"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": 6305204531818.757, "dur": 0.482, + "args": { + "External id": 703010,"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": 6305204531820.960, "dur": 0.383, + "args": { + "External id": 703011,"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": 6305204531824.793, "dur": 0.489, + "args": { + "External id": 703012,"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": 6305204531827.034, "dur": 0.460, + "args": { + "External id": 703013,"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": 6305204531828.887, "dur": 2.153, + "args": { + "External id": 703014,"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": 6305204531849.213, "dur": 32.600, + "args": { + "External id": 703015,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305204531943.282, "dur": 401.466, + "args": { + "External id": 703016,"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": 6305204531975.328, "dur": 363.508, + "args": { + "External id": 703017,"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": 6305204531985.881, "dur": 346.386, + "args": { + "External id": 703018,"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": 6305204532371.506, "dur": 2.517, + "args": { + "External id": 703019,"Record function id": 0, "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": 6305204532470.222, "dur": 30939.470, + "args": { + "External id": 703020,"Record function id": 0, "Ev Idx": 13424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6305204532591.444, "dur": 6.844, + "args": { + "External id": 703021,"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": 6305204532602.098, "dur": 1.204, + "args": { + "External id": 703022,"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": 6305204532604.951, "dur": 3.230, + "args": { + "External id": 703023,"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": 6305204532609.929, "dur": 1.121, + "args": { + "External id": 703024,"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": 6305204532612.523, "dur": 0.952, + "args": { + "External id": 703025,"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": 6305204532614.736, "dur": 1.189, + "args": { + "External id": 703026,"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": 6305204532619.808, "dur": 0.595, + "args": { + "External id": 703027,"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": 6305204532622.087, "dur": 2.322, + "args": { + "External id": 703028,"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": 6305204532626.087, "dur": 0.910, + "args": { + "External id": 703029,"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": 6305204532628.919, "dur": 0.588, + "args": { + "External id": 703030,"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": 6305204532651.013, "dur": 30715.852, + "args": { + "External id": 703031,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305204532667.715, "dur": 30690.789, + "args": { + "External id": 703032,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305204532690.734, "dur": 15.704, + "args": { + "External id": 703033,"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": 6305204532710.069, "dur": 30612.442, + "args": { + "External id": 703034,"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": 6305204532712.683, "dur": 30609.200, + "args": { + "External id": 703035,"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": 6305204532718.837, "dur": 4.975, + "args": { + "External id": 703036,"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": 6305204532725.449, "dur": 30593.333, + "args": { + "External id": 703037,"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": 6305204563557.427, "dur": 32.047, + "args": { + "External id": 703038,"Sequence number": 7674425, "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": 6305204563557.427, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6305204563574.376, "dur": 9.893, + "args": { + "External id": 703039,"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": 6305204563579.035, "dur": 4.901, + "args": { + "External id": 703040,"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": 6305204563657.388, "dur": 75.602, + "args": { + "External id": 703041,"Record function id": 0, "Ev Idx": 13445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6305204563734.623, "dur": 1134.862, + "args": { + "External id": 703042,"Record function id": 0, "Ev Idx": 13446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305204563776.354, "dur": 1079.785, + "args": { + "External id": 703043,"Sequence number": 7674426, "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": 6305204563776.354, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6305204563843.347, "dur": 53.669, + "args": { + "External id": 703044,"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": 6305204563909.801, "dur": 104.629, + "args": { + "External id": 703045,"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": 6305204564025.627, "dur": 74.317, + "args": { + "External id": 703046,"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": 6305204564115.340, "dur": 36.190, + "args": { + "External id": 703047,"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": 6305204564180.365, "dur": 29.902, + "args": { + "External id": 703048,"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": 6305204564230.906, "dur": 18.640, + "args": { + "External id": 703049,"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": 6305204564273.431, "dur": 134.786, + "args": { + "External id": 703050,"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": 6305204564325.719, "dur": 12.870, + "args": { + "External id": 703051,"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": 6305204564331.808, "dur": 5.797, + "args": { + "External id": 703052,"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": 6305204564341.438, "dur": 4.300, + "args": { + "External id": 703053,"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": 6305204564347.374, "dur": 1.151, + "args": { + "External id": 703054,"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": 6305204564351.232, "dur": 5.324, + "args": { + "External id": 703055,"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": 6305204564419.272, "dur": 49.480, + "args": { + "External id": 703056,"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": 6305204564499.987, "dur": 45.295, + "args": { + "External id": 703057,"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": 6305204564558.680, "dur": 46.479, + "args": { + "External id": 703058,"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": 6305204564613.886, "dur": 34.378, + "args": { + "External id": 703059,"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": 6305204564673.797, "dur": 27.698, + "args": { + "External id": 703060,"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": 6305204564709.743, "dur": 35.545, + "args": { + "External id": 703061,"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": 6305204564763.224, "dur": 17.384, + "args": { + "External id": 703062,"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": 6305204564935.943, "dur": 79.876, + "args": { + "External id": 703063,"Record function id": 0, "Ev Idx": 13467 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6305204565132.725, "dur": 49.330, + "args": { + "External id": 703064,"Record function id": 0, "Ev Idx": 13468 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.18)", "pid": 2338707, "tid": 2338707, + "ts": 6305204565192.383, "dur": 33047.594, + "args": { + "External id": 703065,"Record function id": 0, "Ev Idx": 13469 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.18)", "pid": 2338707, "tid": 2338707, + "ts": 6305204565200.501, "dur": 949.520, + "args": { + "External id": 703066,"Record function id": 0, "Ev Idx": 13470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6305204565285.056, "dur": 9.257, + "args": { + "External id": 703067,"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": 6305204565308.190, "dur": 41.780, + "args": { + "External id": 703068,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305204565314.337, "dur": 2.615, + "args": { + "External id": 703069,"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": 6305204565321.781, "dur": 0.427, + "args": { + "External id": 703070,"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": 6305204565323.689, "dur": 0.466, + "args": { + "External id": 703071,"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": 6305204565326.173, "dur": 0.613, + "args": { + "External id": 703072,"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": 6305204565330.976, "dur": 0.558, + "args": { + "External id": 703073,"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": 6305204565332.988, "dur": 0.511, + "args": { + "External id": 703074,"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": 6305204565334.583, "dur": 4.416, + "args": { + "External id": 703075,"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": 6305204565341.088, "dur": 0.395, + "args": { + "External id": 703076,"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": 6305204565342.902, "dur": 0.448, + "args": { + "External id": 703077,"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": 6305204565361.230, "dur": 54.287, + "args": { + "External id": 703078,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305204565449.042, "dur": 151.408, + "args": { + "External id": 703079,"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": 6305204565464.821, "dur": 5.781, + "args": { + "External id": 703080,"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": 6305204565475.950, "dur": 10.857, + "args": { + "External id": 703081,"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": 6305204565480.586, "dur": 5.824, + "args": { + "External id": 703082,"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": 6305204565484.496, "dur": 0.453, + "args": { + "External id": 703083,"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": 6305204565493.679, "dur": 48.577, + "args": { + "External id": 703084,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305204565496.178, "dur": 0.432, + "args": { + "External id": 703085,"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": 6305204565498.622, "dur": 2.119, + "args": { + "External id": 703086,"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": 6305204565502.048, "dur": 0.424, + "args": { + "External id": 703087,"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": 6305204565504.382, "dur": 16.482, + "args": { + "External id": 703088,"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": 6305204565526.426, "dur": 0.600, + "args": { + "External id": 703089,"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": 6305204565528.829, "dur": 0.570, + "args": { + "External id": 703090,"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": 6305204565530.832, "dur": 0.273, + "args": { + "External id": 703091,"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": 6305204565534.837, "dur": 0.403, + "args": { + "External id": 703092,"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": 6305204565536.472, "dur": 0.488, + "args": { + "External id": 703093,"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": 6305204565556.025, "dur": 35.490, + "args": { + "External id": 703094,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305204565656.643, "dur": 356.801, + "args": { + "External id": 703095,"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": 6305204565688.254, "dur": 320.319, + "args": { + "External id": 703096,"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": 6305204565698.966, "dur": 301.926, + "args": { + "External id": 703097,"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": 6305204566037.923, "dur": 2.514, + "args": { + "External id": 703098,"Record function id": 0, "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": 6305204566173.591, "dur": 31842.716, + "args": { + "External id": 703099,"Record function id": 0, "Ev Idx": 13503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6305204566279.147, "dur": 7.011, + "args": { + "External id": 703100,"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": 6305204566289.353, "dur": 1.014, + "args": { + "External id": 703101,"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": 6305204566292.191, "dur": 3.203, + "args": { + "External id": 703102,"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": 6305204566296.977, "dur": 0.994, + "args": { + "External id": 703103,"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": 6305204566299.432, "dur": 0.723, + "args": { + "External id": 703104,"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": 6305204566301.232, "dur": 0.767, + "args": { + "External id": 703105,"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": 6305204566304.016, "dur": 0.691, + "args": { + "External id": 703106,"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": 6305204566306.358, "dur": 1.996, + "args": { + "External id": 703107,"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": 6305204566309.868, "dur": 0.851, + "args": { + "External id": 703108,"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": 6305204566314.597, "dur": 0.900, + "args": { + "External id": 703109,"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": 6305204566333.804, "dur": 31639.754, + "args": { + "External id": 703110,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305204566350.312, "dur": 31614.754, + "args": { + "External id": 703111,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305204566370.129, "dur": 15.247, + "args": { + "External id": 703112,"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": 6305204566389.036, "dur": 31538.905, + "args": { + "External id": 703113,"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": 6305204566391.779, "dur": 31535.510, + "args": { + "External id": 703114,"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": 6305204566398.065, "dur": 5.103, + "args": { + "External id": 703115,"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": 6305204566405.012, "dur": 31519.044, + "args": { + "External id": 703116,"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": 6305204598182.237, "dur": 31.870, + "args": { + "External id": 703117,"Sequence number": 7674427, "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": 6305204598182.237, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6305204598199.768, "dur": 9.283, + "args": { + "External id": 703118,"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": 6305204598203.891, "dur": 4.815, + "args": { + "External id": 703119,"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": 6305204598281.397, "dur": 73.940, + "args": { + "External id": 703120,"Record function id": 0, "Ev Idx": 13524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6305204598356.855, "dur": 1168.498, + "args": { + "External id": 703121,"Record function id": 0, "Ev Idx": 13525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305204598394.361, "dur": 1102.676, + "args": { + "External id": 703122,"Sequence number": 7674428, "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": 6305204598394.361, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6305204598469.470, "dur": 64.286, + "args": { + "External id": 703123,"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": 6305204598551.524, "dur": 104.453, + "args": { + "External id": 703124,"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": 6305204598668.060, "dur": 39.265, + "args": { + "External id": 703125,"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": 6305204598713.898, "dur": 29.299, + "args": { + "External id": 703126,"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": 6305204598773.380, "dur": 28.456, + "args": { + "External id": 703127,"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": 6305204598821.629, "dur": 20.716, + "args": { + "External id": 703128,"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": 6305204598865.051, "dur": 134.470, + "args": { + "External id": 703129,"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": 6305204598916.367, "dur": 11.807, + "args": { + "External id": 703130,"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": 6305204598921.985, "dur": 5.333, + "args": { + "External id": 703131,"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": 6305204598931.415, "dur": 4.236, + "args": { + "External id": 703132,"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": 6305204598936.958, "dur": 3.139, + "args": { + "External id": 703133,"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": 6305204598942.739, "dur": 5.436, + "args": { + "External id": 703134,"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": 6305204599010.011, "dur": 99.796, + "args": { + "External id": 703135,"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": 6305204599149.009, "dur": 35.297, + "args": { + "External id": 703136,"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": 6305204599194.665, "dur": 50.757, + "args": { + "External id": 703137,"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": 6305204599254.093, "dur": 35.439, + "args": { + "External id": 703138,"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": 6305204599313.386, "dur": 28.223, + "args": { + "External id": 703139,"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": 6305204599347.180, "dur": 37.036, + "args": { + "External id": 703140,"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": 6305204599404.436, "dur": 21.639, + "args": { + "External id": 703141,"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": 6305204599594.057, "dur": 76.563, + "args": { + "External id": 703142,"Record function id": 0, "Ev Idx": 13546 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6305204599747.979, "dur": 48.428, + "args": { + "External id": 703143,"Record function id": 0, "Ev Idx": 13547 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.19)", "pid": 2338707, "tid": 2338707, + "ts": 6305204599805.750, "dur": 33868.745, + "args": { + "External id": 703144,"Record function id": 0, "Ev Idx": 13548 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.19)", "pid": 2338707, "tid": 2338707, + "ts": 6305204599814.029, "dur": 1010.362, + "args": { + "External id": 703145,"Record function id": 0, "Ev Idx": 13549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6305204599896.622, "dur": 9.312, + "args": { + "External id": 703146,"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": 6305204599919.505, "dur": 41.070, + "args": { + "External id": 703147,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305204599925.584, "dur": 2.180, + "args": { + "External id": 703148,"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": 6305204599933.370, "dur": 0.381, + "args": { + "External id": 703149,"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": 6305204599935.562, "dur": 0.523, + "args": { + "External id": 703150,"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": 6305204599937.834, "dur": 0.708, + "args": { + "External id": 703151,"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": 6305204599942.118, "dur": 0.640, + "args": { + "External id": 703152,"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": 6305204599944.201, "dur": 0.454, + "args": { + "External id": 703153,"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": 6305204599945.965, "dur": 3.913, + "args": { + "External id": 703154,"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": 6305204599951.769, "dur": 0.398, + "args": { + "External id": 703155,"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": 6305204599953.647, "dur": 0.474, + "args": { + "External id": 703156,"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": 6305204599972.425, "dur": 55.993, + "args": { + "External id": 703157,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305204600097.914, "dur": 141.671, + "args": { + "External id": 703158,"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": 6305204600109.938, "dur": 5.420, + "args": { + "External id": 703159,"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": 6305204600121.382, "dur": 11.286, + "args": { + "External id": 703160,"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": 6305204600125.893, "dur": 6.358, + "args": { + "External id": 703161,"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": 6305204600129.945, "dur": 0.713, + "args": { + "External id": 703162,"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": 6305204600140.206, "dur": 33.950, + "args": { + "External id": 703163,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305204600142.761, "dur": 2.360, + "args": { + "External id": 703164,"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": 6305204600146.655, "dur": 0.900, + "args": { + "External id": 703165,"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": 6305204600149.161, "dur": 0.526, + "args": { + "External id": 703166,"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": 6305204600153.501, "dur": 2.633, + "args": { + "External id": 703167,"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": 6305204600157.507, "dur": 0.332, + "args": { + "External id": 703168,"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": 6305204600159.774, "dur": 0.318, + "args": { + "External id": 703169,"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": 6305204600163.295, "dur": 0.480, + "args": { + "External id": 703170,"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": 6305204600165.284, "dur": 0.294, + "args": { + "External id": 703171,"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": 6305204600166.930, "dur": 2.278, + "args": { + "External id": 703172,"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": 6305204600188.708, "dur": 39.943, + "args": { + "External id": 703173,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305204600299.289, "dur": 420.607, + "args": { + "External id": 703174,"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": 6305204600331.197, "dur": 382.844, + "args": { + "External id": 703175,"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": 6305204600342.116, "dur": 365.520, + "args": { + "External id": 703176,"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": 6305204600746.501, "dur": 2.482, + "args": { + "External id": 703177,"Record function id": 0, "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": 6305204600846.761, "dur": 32609.752, + "args": { + "External id": 703178,"Record function id": 0, "Ev Idx": 13582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6305204600947.825, "dur": 6.971, + "args": { + "External id": 703179,"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": 6305204600972.056, "dur": 1.269, + "args": { + "External id": 703180,"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": 6305204600975.106, "dur": 3.072, + "args": { + "External id": 703181,"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": 6305204600981.776, "dur": 0.865, + "args": { + "External id": 703182,"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": 6305204600983.873, "dur": 0.871, + "args": { + "External id": 703183,"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": 6305204600985.945, "dur": 1.090, + "args": { + "External id": 703184,"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": 6305204600988.525, "dur": 1.056, + "args": { + "External id": 703185,"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": 6305204600993.123, "dur": 1.895, + "args": { + "External id": 703186,"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": 6305204600996.494, "dur": 0.945, + "args": { + "External id": 703187,"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": 6305204600998.976, "dur": 0.826, + "args": { + "External id": 703188,"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": 6305204601020.930, "dur": 32390.941, + "args": { + "External id": 703189,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305204601037.554, "dur": 32365.905, + "args": { + "External id": 703190,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305204601051.770, "dur": 51.828, + "args": { + "External id": 703191,"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": 6305204601109.914, "dur": 32256.198, + "args": { + "External id": 703192,"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": 6305204601112.630, "dur": 32252.785, + "args": { + "External id": 703193,"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": 6305204601119.363, "dur": 5.445, + "args": { + "External id": 703194,"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": 6305204601126.675, "dur": 32235.995, + "args": { + "External id": 703195,"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": 6305204633613.615, "dur": 34.629, + "args": { + "External id": 703196,"Sequence number": 7674429, "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": 6305204633613.615, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6305204633634.015, "dur": 8.937, + "args": { + "External id": 703197,"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": 6305204633637.884, "dur": 4.734, + "args": { + "External id": 703198,"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": 6305204633715.047, "dur": 71.754, + "args": { + "External id": 703199,"Record function id": 0, "Ev Idx": 13603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6305204633788.037, "dur": 1119.323, + "args": { + "External id": 703200,"Record function id": 0, "Ev Idx": 13604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305204633824.959, "dur": 1068.582, + "args": { + "External id": 703201,"Sequence number": 7674430, "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": 6305204633824.959, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6305204633893.384, "dur": 49.895, + "args": { + "External id": 703202,"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": 6305204633956.334, "dur": 134.306, + "args": { + "External id": 703203,"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": 6305204634107.497, "dur": 43.940, + "args": { + "External id": 703204,"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": 6305204634160.968, "dur": 28.834, + "args": { + "External id": 703205,"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": 6305204634217.705, "dur": 28.839, + "args": { + "External id": 703206,"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": 6305204634268.122, "dur": 16.990, + "args": { + "External id": 703207,"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": 6305204634309.850, "dur": 131.990, + "args": { + "External id": 703208,"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": 6305204634363.437, "dur": 11.626, + "args": { + "External id": 703209,"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": 6305204634368.853, "dur": 5.389, + "args": { + "External id": 703210,"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": 6305204634377.933, "dur": 3.946, + "args": { + "External id": 703211,"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": 6305204634383.284, "dur": 1.464, + "args": { + "External id": 703212,"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": 6305204634387.499, "dur": 5.161, + "args": { + "External id": 703213,"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": 6305204634452.045, "dur": 48.989, + "args": { + "External id": 703214,"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": 6305204634550.997, "dur": 31.202, + "args": { + "External id": 703215,"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": 6305204634592.720, "dur": 47.600, + "args": { + "External id": 703216,"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": 6305204634651.118, "dur": 34.544, + "args": { + "External id": 703217,"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": 6305204634707.992, "dur": 28.823, + "args": { + "External id": 703218,"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": 6305204634744.719, "dur": 35.565, + "args": { + "External id": 703219,"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": 6305204634799.306, "dur": 18.255, + "args": { + "External id": 703220,"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": 6305204634973.309, "dur": 113.526, + "args": { + "External id": 703221,"Record function id": 0, "Ev Idx": 13625 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6305204635174.065, "dur": 55.097, + "args": { + "External id": 703222,"Record function id": 0, "Ev Idx": 13626 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.20)", "pid": 2338707, "tid": 2338707, + "ts": 6305204635239.678, "dur": 34120.732, + "args": { + "External id": 703223,"Record function id": 0, "Ev Idx": 13627 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.20)", "pid": 2338707, "tid": 2338707, + "ts": 6305204635247.671, "dur": 901.534, + "args": { + "External id": 703224,"Record function id": 0, "Ev Idx": 13628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6305204635335.780, "dur": 10.057, + "args": { + "External id": 703225,"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": 6305204635359.361, "dur": 41.428, + "args": { + "External id": 703226,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305204635366.049, "dur": 2.448, + "args": { + "External id": 703227,"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": 6305204635373.357, "dur": 0.429, + "args": { + "External id": 703228,"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": 6305204635375.183, "dur": 0.509, + "args": { + "External id": 703229,"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": 6305204635377.114, "dur": 0.644, + "args": { + "External id": 703230,"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": 6305204635381.541, "dur": 0.276, + "args": { + "External id": 703231,"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": 6305204635383.676, "dur": 0.492, + "args": { + "External id": 703232,"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": 6305204635385.850, "dur": 5.025, + "args": { + "External id": 703233,"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": 6305204635392.097, "dur": 0.536, + "args": { + "External id": 703234,"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": 6305204635394.047, "dur": 0.276, + "args": { + "External id": 703235,"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": 6305204635412.606, "dur": 57.331, + "args": { + "External id": 703236,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305204635504.030, "dur": 153.627, + "args": { + "External id": 703237,"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": 6305204635530.972, "dur": 5.461, + "args": { + "External id": 703238,"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": 6305204635542.140, "dur": 11.908, + "args": { + "External id": 703239,"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": 6305204635546.891, "dur": 6.738, + "args": { + "External id": 703240,"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": 6305204635551.130, "dur": 0.932, + "args": { + "External id": 703241,"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": 6305204635562.996, "dur": 37.334, + "args": { + "External id": 703242,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305204635565.549, "dur": 2.894, + "args": { + "External id": 703243,"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": 6305204635569.943, "dur": 0.571, + "args": { + "External id": 703244,"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": 6305204635575.709, "dur": 0.291, + "args": { + "External id": 703245,"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": 6305204635579.967, "dur": 2.659, + "args": { + "External id": 703246,"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": 6305204635584.154, "dur": 0.316, + "args": { + "External id": 703247,"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": 6305204635585.964, "dur": 2.068, + "args": { + "External id": 703248,"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": 6305204635589.213, "dur": 0.268, + "args": { + "External id": 703249,"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": 6305204635591.178, "dur": 0.446, + "args": { + "External id": 703250,"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": 6305204635595.339, "dur": 0.332, + "args": { + "External id": 703251,"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": 6305204635612.823, "dur": 36.137, + "args": { + "External id": 703252,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305204635714.924, "dur": 299.438, + "args": { + "External id": 703253,"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": 6305204635747.363, "dur": 261.844, + "args": { + "External id": 703254,"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": 6305204635757.994, "dur": 245.910, + "args": { + "External id": 703255,"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": 6305204636038.518, "dur": 2.263, + "args": { + "External id": 703256,"Record function id": 0, "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": 6305204636171.509, "dur": 32993.152, + "args": { + "External id": 703257,"Record function id": 0, "Ev Idx": 13661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6305204636272.489, "dur": 6.454, + "args": { + "External id": 703258,"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": 6305204636282.746, "dur": 1.227, + "args": { + "External id": 703259,"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": 6305204636285.943, "dur": 2.986, + "args": { + "External id": 703260,"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": 6305204636290.481, "dur": 1.010, + "args": { + "External id": 703261,"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": 6305204636292.686, "dur": 0.867, + "args": { + "External id": 703262,"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": 6305204636294.899, "dur": 0.805, + "args": { + "External id": 703263,"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": 6305204636297.646, "dur": 0.716, + "args": { + "External id": 703264,"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": 6305204636299.986, "dur": 2.447, + "args": { + "External id": 703265,"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": 6305204636304.128, "dur": 0.672, + "args": { + "External id": 703266,"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": 6305204636308.192, "dur": 0.959, + "args": { + "External id": 703267,"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": 6305204636327.702, "dur": 32794.953, + "args": { + "External id": 703268,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305204636344.032, "dur": 32770.294, + "args": { + "External id": 703269,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305204636363.349, "dur": 15.436, + "args": { + "External id": 703270,"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": 6305204636382.475, "dur": 32662.239, + "args": { + "External id": 703271,"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": 6305204636385.079, "dur": 32659.052, + "args": { + "External id": 703272,"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": 6305204636391.402, "dur": 4.753, + "args": { + "External id": 703273,"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": 6305204636397.879, "dur": 32643.260, + "args": { + "External id": 703274,"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": 6305204669300.018, "dur": 35.147, + "args": { + "External id": 703275,"Sequence number": 7674431, "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": 6305204669300.018, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6305204669321.034, "dur": 9.024, + "args": { + "External id": 703276,"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": 6305204669324.896, "dur": 4.977, + "args": { + "External id": 703277,"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": 6305204669401.100, "dur": 73.199, + "args": { + "External id": 703278,"Record function id": 0, "Ev Idx": 13682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6305204669475.667, "dur": 1134.523, + "args": { + "External id": 703279,"Record function id": 0, "Ev Idx": 13683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305204669526.832, "dur": 1069.823, + "args": { + "External id": 703280,"Sequence number": 7674432, "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": 6305204669526.832, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6305204669599.107, "dur": 52.636, + "args": { + "External id": 703281,"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": 6305204669664.570, "dur": 103.423, + "args": { + "External id": 703282,"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": 6305204669781.833, "dur": 41.009, + "args": { + "External id": 703283,"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": 6305204669829.331, "dur": 28.942, + "args": { + "External id": 703284,"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": 6305204669884.642, "dur": 25.086, + "args": { + "External id": 703285,"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": 6305204669929.193, "dur": 16.902, + "args": { + "External id": 703286,"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": 6305204669968.862, "dur": 179.037, + "args": { + "External id": 703287,"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": 6305204670023.256, "dur": 11.956, + "args": { + "External id": 703288,"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": 6305204670029.083, "dur": 5.297, + "args": { + "External id": 703289,"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": 6305204670038.471, "dur": 4.151, + "args": { + "External id": 703290,"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": 6305204670044.110, "dur": 1.040, + "args": { + "External id": 703291,"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": 6305204670049.969, "dur": 41.812, + "args": { + "External id": 703292,"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": 6305204670160.471, "dur": 55.948, + "args": { + "External id": 703293,"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": 6305204670248.763, "dur": 30.322, + "args": { + "External id": 703294,"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": 6305204670288.684, "dur": 41.926, + "args": { + "External id": 703295,"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": 6305204670341.183, "dur": 34.476, + "args": { + "External id": 703296,"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": 6305204670399.710, "dur": 29.333, + "args": { + "External id": 703297,"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": 6305204670434.681, "dur": 34.728, + "args": { + "External id": 703298,"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": 6305204670489.396, "dur": 30.334, + "args": { + "External id": 703299,"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": 6305204670677.171, "dur": 78.104, + "args": { + "External id": 703300,"Record function id": 0, "Ev Idx": 13704 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6305204670831.468, "dur": 46.482, + "args": { + "External id": 703301,"Record function id": 0, "Ev Idx": 13705 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.21)", "pid": 2338707, "tid": 2338707, + "ts": 6305204670887.012, "dur": 36955.286, + "args": { + "External id": 703302,"Record function id": 0, "Ev Idx": 13706 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.21)", "pid": 2338707, "tid": 2338707, + "ts": 6305204670896.500, "dur": 983.218, + "args": { + "External id": 703303,"Record function id": 0, "Ev Idx": 13707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6305204670982.241, "dur": 9.048, + "args": { + "External id": 703304,"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": 6305204671004.534, "dur": 41.250, + "args": { + "External id": 703305,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305204671011.189, "dur": 2.226, + "args": { + "External id": 703306,"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": 6305204671017.757, "dur": 0.345, + "args": { + "External id": 703307,"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": 6305204671019.608, "dur": 0.529, + "args": { + "External id": 703308,"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": 6305204671021.841, "dur": 0.424, + "args": { + "External id": 703309,"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": 6305204671026.037, "dur": 0.387, + "args": { + "External id": 703310,"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": 6305204671028.479, "dur": 0.705, + "args": { + "External id": 703311,"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": 6305204671030.488, "dur": 5.160, + "args": { + "External id": 703312,"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": 6305204671037.073, "dur": 0.286, + "args": { + "External id": 703313,"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": 6305204671038.968, "dur": 0.557, + "args": { + "External id": 703314,"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": 6305204671094.444, "dur": 55.275, + "args": { + "External id": 703315,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305204671187.026, "dur": 133.500, + "args": { + "External id": 703316,"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": 6305204671198.968, "dur": 5.158, + "args": { + "External id": 703317,"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": 6305204671210.158, "dur": 11.633, + "args": { + "External id": 703318,"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": 6305204671214.867, "dur": 6.545, + "args": { + "External id": 703319,"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": 6305204671218.992, "dur": 0.754, + "args": { + "External id": 703320,"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": 6305204671228.789, "dur": 34.386, + "args": { + "External id": 703321,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305204671231.738, "dur": 2.114, + "args": { + "External id": 703322,"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": 6305204671235.341, "dur": 0.708, + "args": { + "External id": 703323,"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": 6305204671237.926, "dur": 0.520, + "args": { + "External id": 703324,"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": 6305204671241.905, "dur": 2.814, + "args": { + "External id": 703325,"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": 6305204671246.413, "dur": 0.413, + "args": { + "External id": 703326,"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": 6305204671248.766, "dur": 0.325, + "args": { + "External id": 703327,"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": 6305204671252.246, "dur": 0.349, + "args": { + "External id": 703328,"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": 6305204671254.128, "dur": 0.575, + "args": { + "External id": 703329,"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": 6305204671256.353, "dur": 2.533, + "args": { + "External id": 703330,"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": 6305204671278.500, "dur": 34.037, + "args": { + "External id": 703331,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305204671386.197, "dur": 389.978, + "args": { + "External id": 703332,"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": 6305204671427.835, "dur": 342.105, + "args": { + "External id": 703333,"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": 6305204671439.231, "dur": 324.477, + "args": { + "External id": 703334,"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": 6305204671804.884, "dur": 2.605, + "args": { + "External id": 703335,"Record function id": 0, "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": 6305204671902.428, "dur": 35742.647, + "args": { + "External id": 703336,"Record function id": 0, "Ev Idx": 13740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6305204672008.726, "dur": 6.813, + "args": { + "External id": 703337,"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": 6305204672018.968, "dur": 1.277, + "args": { + "External id": 703338,"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": 6305204672021.906, "dur": 3.100, + "args": { + "External id": 703339,"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": 6305204672026.578, "dur": 1.033, + "args": { + "External id": 703340,"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": 6305204672028.882, "dur": 1.076, + "args": { + "External id": 703341,"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": 6305204672031.160, "dur": 0.904, + "args": { + "External id": 703342,"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": 6305204672033.802, "dur": 0.985, + "args": { + "External id": 703343,"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": 6305204672036.395, "dur": 1.920, + "args": { + "External id": 703344,"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": 6305204672039.880, "dur": 0.916, + "args": { + "External id": 703345,"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": 6305204672044.326, "dur": 1.060, + "args": { + "External id": 703346,"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": 6305204672100.278, "dur": 35500.095, + "args": { + "External id": 703347,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305204672118.202, "dur": 35473.779, + "args": { + "External id": 703348,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305204672138.382, "dur": 16.382, + "args": { + "External id": 703349,"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": 6305204672158.435, "dur": 35398.384, + "args": { + "External id": 703350,"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": 6305204672161.212, "dur": 35395.046, + "args": { + "External id": 703351,"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": 6305204672167.834, "dur": 5.959, + "args": { + "External id": 703352,"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": 6305204672175.437, "dur": 35377.713, + "args": { + "External id": 703353,"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": 6305204707786.222, "dur": 32.480, + "args": { + "External id": 703354,"Sequence number": 7674433, "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": 6305204707786.222, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6305204707804.076, "dur": 9.455, + "args": { + "External id": 703355,"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": 6305204707808.421, "dur": 4.786, + "args": { + "External id": 703356,"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": 6305204707883.739, "dur": 74.436, + "args": { + "External id": 703357,"Record function id": 0, "Ev Idx": 13761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6305204707959.853, "dur": 1159.434, + "args": { + "External id": 703358,"Record function id": 0, "Ev Idx": 13762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305204707997.039, "dur": 1106.747, + "args": { + "External id": 703359,"Sequence number": 7674434, "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": 6305204707997.039, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6305204708100.083, "dur": 53.414, + "args": { + "External id": 703360,"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": 6305204708168.437, "dur": 107.478, + "args": { + "External id": 703361,"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": 6305204708287.672, "dur": 38.438, + "args": { + "External id": 703362,"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": 6305204708333.988, "dur": 28.803, + "args": { + "External id": 703363,"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": 6305204708390.807, "dur": 27.214, + "args": { + "External id": 703364,"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": 6305204708437.767, "dur": 17.826, + "args": { + "External id": 703365,"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": 6305204708479.068, "dur": 156.401, + "args": { + "External id": 703366,"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": 6305204708549.572, "dur": 13.982, + "args": { + "External id": 703367,"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": 6305204708556.248, "dur": 6.233, + "args": { + "External id": 703368,"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": 6305204708566.697, "dur": 4.220, + "args": { + "External id": 703369,"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": 6305204708572.295, "dur": 1.345, + "args": { + "External id": 703370,"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": 6305204708576.135, "dur": 5.065, + "args": { + "External id": 703371,"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": 6305204708647.268, "dur": 56.517, + "args": { + "External id": 703372,"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": 6305204708735.833, "dur": 30.837, + "args": { + "External id": 703373,"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": 6305204708776.797, "dur": 42.503, + "args": { + "External id": 703374,"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": 6305204708829.223, "dur": 34.228, + "args": { + "External id": 703375,"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": 6305204708885.094, "dur": 26.939, + "args": { + "External id": 703376,"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": 6305204708919.673, "dur": 34.870, + "args": { + "External id": 703377,"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": 6305204708974.488, "dur": 19.952, + "args": { + "External id": 703378,"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": 6305204709187.349, "dur": 76.040, + "args": { + "External id": 703379,"Record function id": 0, "Ev Idx": 13783 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6305204709338.256, "dur": 46.214, + "args": { + "External id": 703380,"Record function id": 0, "Ev Idx": 13784 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.22)", "pid": 2338707, "tid": 2338707, + "ts": 6305204709393.901, "dur": 32459.010, + "args": { + "External id": 703381,"Record function id": 0, "Ev Idx": 13785 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.22)", "pid": 2338707, "tid": 2338707, + "ts": 6305204709402.776, "dur": 954.377, + "args": { + "External id": 703382,"Record function id": 0, "Ev Idx": 13786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6305204709479.642, "dur": 8.910, + "args": { + "External id": 703383,"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": 6305204709501.964, "dur": 57.363, + "args": { + "External id": 703384,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305204709523.193, "dur": 2.511, + "args": { + "External id": 703385,"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": 6305204709531.231, "dur": 0.492, + "args": { + "External id": 703386,"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": 6305204709533.268, "dur": 0.471, + "args": { + "External id": 703387,"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": 6305204709535.333, "dur": 0.691, + "args": { + "External id": 703388,"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": 6305204709539.539, "dur": 0.556, + "args": { + "External id": 703389,"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": 6305204709541.789, "dur": 0.491, + "args": { + "External id": 703390,"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": 6305204709544.001, "dur": 4.903, + "args": { + "External id": 703391,"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": 6305204709550.826, "dur": 0.341, + "args": { + "External id": 703392,"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": 6305204709552.762, "dur": 0.528, + "args": { + "External id": 703393,"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": 6305204709572.964, "dur": 54.929, + "args": { + "External id": 703394,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305204709663.496, "dur": 135.352, + "args": { + "External id": 703395,"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": 6305204709675.664, "dur": 5.269, + "args": { + "External id": 703396,"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": 6305204709686.104, "dur": 11.218, + "args": { + "External id": 703397,"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": 6305204709690.912, "dur": 5.999, + "args": { + "External id": 703398,"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": 6305204709694.759, "dur": 0.731, + "args": { + "External id": 703399,"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": 6305204709704.767, "dur": 37.811, + "args": { + "External id": 703400,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305204709707.412, "dur": 2.008, + "args": { + "External id": 703401,"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": 6305204709711.121, "dur": 0.736, + "args": { + "External id": 703402,"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": 6305204709713.766, "dur": 0.685, + "args": { + "External id": 703403,"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": 6305204709718.241, "dur": 2.473, + "args": { + "External id": 703404,"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": 6305204709721.969, "dur": 0.544, + "args": { + "External id": 703405,"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": 6305204709724.284, "dur": 0.527, + "args": { + "External id": 703406,"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": 6305204709727.804, "dur": 0.510, + "args": { + "External id": 703407,"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": 6305204709729.950, "dur": 0.583, + "args": { + "External id": 703408,"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": 6305204709735.580, "dur": 2.226, + "args": { + "External id": 703409,"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": 6305204709755.693, "dur": 34.549, + "args": { + "External id": 703410,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305204709855.062, "dur": 395.353, + "args": { + "External id": 703411,"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": 6305204709887.247, "dur": 357.039, + "args": { + "External id": 703412,"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": 6305204709897.465, "dur": 340.383, + "args": { + "External id": 703413,"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": 6305204710279.022, "dur": 2.342, + "args": { + "External id": 703414,"Record function id": 0, "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": 6305204710378.879, "dur": 31276.495, + "args": { + "External id": 703415,"Record function id": 0, "Ev Idx": 13819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6305204710480.913, "dur": 6.971, + "args": { + "External id": 703416,"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": 6305204710491.267, "dur": 1.400, + "args": { + "External id": 703417,"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": 6305204710494.669, "dur": 3.406, + "args": { + "External id": 703418,"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": 6305204710499.557, "dur": 0.983, + "args": { + "External id": 703419,"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": 6305204710502.032, "dur": 0.824, + "args": { + "External id": 703420,"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": 6305204710504.060, "dur": 0.871, + "args": { + "External id": 703421,"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": 6305204710523.231, "dur": 1.307, + "args": { + "External id": 703422,"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": 6305204710526.705, "dur": 2.418, + "args": { + "External id": 703423,"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": 6305204710530.802, "dur": 0.879, + "args": { + "External id": 703424,"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": 6305204710535.277, "dur": 0.683, + "args": { + "External id": 703425,"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": 6305204710556.014, "dur": 31056.867, + "args": { + "External id": 703426,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305204710580.320, "dur": 31024.253, + "args": { + "External id": 703427,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305204710594.670, "dur": 15.790, + "args": { + "External id": 703428,"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": 6305204710614.092, "dur": 30955.162, + "args": { + "External id": 703429,"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": 6305204710616.800, "dur": 30951.903, + "args": { + "External id": 703430,"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": 6305204710623.314, "dur": 5.613, + "args": { + "External id": 703431,"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": 6305204710630.780, "dur": 30934.734, + "args": { + "External id": 703432,"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": 6305204741795.206, "dur": 32.592, + "args": { + "External id": 703433,"Sequence number": 7674435, "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": 6305204741795.206, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6305204741811.839, "dur": 10.887, + "args": { + "External id": 703434,"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": 6305204741817.905, "dur": 4.606, + "args": { + "External id": 703435,"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": 6305204741894.949, "dur": 75.333, + "args": { + "External id": 703436,"Record function id": 0, "Ev Idx": 13840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6305204741971.587, "dur": 1163.412, + "args": { + "External id": 703437,"Record function id": 0, "Ev Idx": 13841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305204742009.388, "dur": 1109.135, + "args": { + "External id": 703438,"Sequence number": 7674436, "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": 6305204742009.388, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6305204742105.756, "dur": 52.968, + "args": { + "External id": 703439,"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": 6305204742173.571, "dur": 104.271, + "args": { + "External id": 703440,"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": 6305204742289.039, "dur": 37.627, + "args": { + "External id": 703441,"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": 6305204742335.682, "dur": 29.141, + "args": { + "External id": 703442,"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": 6305204742392.462, "dur": 28.176, + "args": { + "External id": 703443,"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": 6305204742440.942, "dur": 20.442, + "args": { + "External id": 703444,"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": 6305204742484.671, "dur": 154.707, + "args": { + "External id": 703445,"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": 6305204742554.719, "dur": 13.449, + "args": { + "External id": 703446,"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": 6305204742560.578, "dur": 6.603, + "args": { + "External id": 703447,"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": 6305204742571.062, "dur": 3.975, + "args": { + "External id": 703448,"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": 6305204742576.595, "dur": 1.294, + "args": { + "External id": 703449,"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": 6305204742580.482, "dur": 5.598, + "args": { + "External id": 703450,"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": 6305204742650.390, "dur": 54.709, + "args": { + "External id": 703451,"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": 6305204742737.255, "dur": 31.608, + "args": { + "External id": 703452,"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": 6305204742778.890, "dur": 43.917, + "args": { + "External id": 703453,"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": 6305204742832.552, "dur": 34.442, + "args": { + "External id": 703454,"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": 6305204742890.152, "dur": 37.369, + "args": { + "External id": 703455,"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": 6305204742935.626, "dur": 36.442, + "args": { + "External id": 703456,"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": 6305204742990.139, "dur": 18.455, + "args": { + "External id": 703457,"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": 6305204743202.739, "dur": 77.422, + "args": { + "External id": 703458,"Record function id": 0, "Ev Idx": 13862 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6305204743356.127, "dur": 48.128, + "args": { + "External id": 703459,"Record function id": 0, "Ev Idx": 13863 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.23)", "pid": 2338707, "tid": 2338707, + "ts": 6305204743413.996, "dur": 32967.394, + "args": { + "External id": 703460,"Record function id": 0, "Ev Idx": 13864 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.23)", "pid": 2338707, "tid": 2338707, + "ts": 6305204743423.854, "dur": 985.356, + "args": { + "External id": 703461,"Record function id": 0, "Ev Idx": 13865 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6305204743523.353, "dur": 10.579, + "args": { + "External id": 703462,"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": 6305204743551.034, "dur": 43.714, + "args": { + "External id": 703463,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305204743557.152, "dur": 2.632, + "args": { + "External id": 703464,"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": 6305204743565.279, "dur": 0.803, + "args": { + "External id": 703465,"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": 6305204743567.748, "dur": 0.556, + "args": { + "External id": 703466,"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": 6305204743570.271, "dur": 0.498, + "args": { + "External id": 703467,"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": 6305204743574.574, "dur": 0.756, + "args": { + "External id": 703468,"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": 6305204743577.444, "dur": 0.290, + "args": { + "External id": 703469,"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": 6305204743579.659, "dur": 4.492, + "args": { + "External id": 703470,"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": 6305204743585.940, "dur": 0.344, + "args": { + "External id": 703471,"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": 6305204743588.101, "dur": 0.452, + "args": { + "External id": 703472,"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": 6305204743606.301, "dur": 57.414, + "args": { + "External id": 703473,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305204743698.243, "dur": 154.548, + "args": { + "External id": 703474,"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": 6305204743710.483, "dur": 3.998, + "args": { + "External id": 703475,"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": 6305204743719.759, "dur": 10.902, + "args": { + "External id": 703476,"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": 6305204743724.361, "dur": 5.894, + "args": { + "External id": 703477,"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": 6305204743728.570, "dur": 0.456, + "args": { + "External id": 703478,"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": 6305204743737.360, "dur": 33.583, + "args": { + "External id": 703479,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305204743740.075, "dur": 3.051, + "args": { + "External id": 703480,"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": 6305204743744.569, "dur": 0.477, + "args": { + "External id": 703481,"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": 6305204743746.692, "dur": 0.545, + "args": { + "External id": 703482,"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": 6305204743750.806, "dur": 2.195, + "args": { + "External id": 703483,"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": 6305204743755.064, "dur": 0.504, + "args": { + "External id": 703484,"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": 6305204743757.201, "dur": 0.327, + "args": { + "External id": 703485,"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": 6305204743760.948, "dur": 0.261, + "args": { + "External id": 703486,"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": 6305204743762.438, "dur": 0.414, + "args": { + "External id": 703487,"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": 6305204743764.291, "dur": 2.105, + "args": { + "External id": 703488,"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": 6305204743806.576, "dur": 37.873, + "args": { + "External id": 703489,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305204743908.776, "dur": 395.427, + "args": { + "External id": 703490,"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": 6305204743939.825, "dur": 358.686, + "args": { + "External id": 703491,"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": 6305204743952.276, "dur": 339.809, + "args": { + "External id": 703492,"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": 6305204744332.061, "dur": 2.367, + "args": { + "External id": 703493,"Record function id": 0, "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": 6305204744431.312, "dur": 31757.554, + "args": { + "External id": 703494,"Record function id": 0, "Ev Idx": 13898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6305204744553.819, "dur": 7.265, + "args": { + "External id": 703495,"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": 6305204744564.652, "dur": 1.250, + "args": { + "External id": 703496,"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": 6305204744567.628, "dur": 3.408, + "args": { + "External id": 703497,"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": 6305204744572.782, "dur": 1.053, + "args": { + "External id": 703498,"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": 6305204744575.244, "dur": 0.792, + "args": { + "External id": 703499,"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": 6305204744577.237, "dur": 0.985, + "args": { + "External id": 703500,"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": 6305204744579.819, "dur": 0.838, + "args": { + "External id": 703501,"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": 6305204744582.222, "dur": 2.277, + "args": { + "External id": 703502,"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": 6305204744585.999, "dur": 0.928, + "args": { + "External id": 703503,"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": 6305204744590.177, "dur": 0.737, + "args": { + "External id": 703504,"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": 6305204744611.602, "dur": 31533.270, + "args": { + "External id": 703505,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305204744629.192, "dur": 31507.007, + "args": { + "External id": 703506,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305204744648.037, "dur": 17.322, + "args": { + "External id": 703507,"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": 6305204744668.987, "dur": 31428.122, + "args": { + "External id": 703508,"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": 6305204744671.770, "dur": 31424.829, + "args": { + "External id": 703509,"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": 6305204744678.009, "dur": 5.972, + "args": { + "External id": 703510,"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": 6305204744685.825, "dur": 31407.701, + "args": { + "External id": 703511,"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": 6305204776324.477, "dur": 32.440, + "args": { + "External id": 703512,"Sequence number": 7674437, "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": 6305204776324.477, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6305204776343.667, "dur": 8.714, + "args": { + "External id": 703513,"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": 6305204776347.603, "dur": 4.599, + "args": { + "External id": 703514,"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": 6305204776423.225, "dur": 74.504, + "args": { + "External id": 703515,"Record function id": 0, "Ev Idx": 13919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6305204776498.890, "dur": 1176.622, + "args": { + "External id": 703516,"Record function id": 0, "Ev Idx": 13920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305204776558.640, "dur": 1103.254, + "args": { + "External id": 703517,"Sequence number": 7674438, "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": 6305204776558.640, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6305204776629.369, "dur": 52.168, + "args": { + "External id": 703518,"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": 6305204776694.503, "dur": 106.793, + "args": { + "External id": 703519,"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": 6305204776814.011, "dur": 39.699, + "args": { + "External id": 703520,"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": 6305204776861.869, "dur": 29.169, + "args": { + "External id": 703521,"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": 6305204776915.856, "dur": 29.666, + "args": { + "External id": 703522,"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": 6305204776968.456, "dur": 18.867, + "args": { + "External id": 703523,"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": 6305204777010.518, "dur": 176.628, + "args": { + "External id": 703524,"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": 6305204777101.402, "dur": 14.027, + "args": { + "External id": 703525,"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": 6305204777107.524, "dur": 6.779, + "args": { + "External id": 703526,"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": 6305204777118.403, "dur": 3.859, + "args": { + "External id": 703527,"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": 6305204777123.572, "dur": 1.446, + "args": { + "External id": 703528,"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": 6305204777127.617, "dur": 4.776, + "args": { + "External id": 703529,"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": 6305204777199.860, "dur": 60.072, + "args": { + "External id": 703530,"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": 6305204777293.557, "dur": 34.545, + "args": { + "External id": 703531,"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": 6305204777337.636, "dur": 42.854, + "args": { + "External id": 703532,"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": 6305204777391.574, "dur": 35.744, + "args": { + "External id": 703533,"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": 6305204777450.058, "dur": 30.395, + "args": { + "External id": 703534,"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": 6305204777487.931, "dur": 51.889, + "args": { + "External id": 703535,"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": 6305204777563.912, "dur": 20.559, + "args": { + "External id": 703536,"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": 6305204777742.290, "dur": 79.090, + "args": { + "External id": 703537,"Record function id": 0, "Ev Idx": 13941 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6305204777898.621, "dur": 48.642, + "args": { + "External id": 703538,"Record function id": 0, "Ev Idx": 13942 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.24)", "pid": 2338707, "tid": 2338707, + "ts": 6305204777956.151, "dur": 31509.267, + "args": { + "External id": 703539,"Record function id": 0, "Ev Idx": 13943 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.24)", "pid": 2338707, "tid": 2338707, + "ts": 6305204777965.549, "dur": 1014.937, + "args": { + "External id": 703540,"Record function id": 0, "Ev Idx": 13944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6305204778050.206, "dur": 44.734, + "args": { + "External id": 703541,"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": 6305204778111.706, "dur": 40.740, + "args": { + "External id": 703542,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305204778117.913, "dur": 2.427, + "args": { + "External id": 703543,"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": 6305204778124.701, "dur": 0.523, + "args": { + "External id": 703544,"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": 6305204778126.713, "dur": 0.827, + "args": { + "External id": 703545,"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": 6305204778129.660, "dur": 0.422, + "args": { + "External id": 703546,"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": 6305204778133.000, "dur": 0.598, + "args": { + "External id": 703547,"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": 6305204778135.253, "dur": 0.502, + "args": { + "External id": 703548,"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": 6305204778137.605, "dur": 3.862, + "args": { + "External id": 703549,"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": 6305204778143.296, "dur": 0.464, + "args": { + "External id": 703550,"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": 6305204778145.727, "dur": 0.264, + "args": { + "External id": 703551,"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": 6305204778165.261, "dur": 57.113, + "args": { + "External id": 703552,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305204778257.415, "dur": 128.932, + "args": { + "External id": 703553,"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": 6305204778269.338, "dur": 4.612, + "args": { + "External id": 703554,"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": 6305204778279.229, "dur": 11.043, + "args": { + "External id": 703555,"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": 6305204778283.929, "dur": 5.939, + "args": { + "External id": 703556,"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": 6305204778288.128, "dur": 0.463, + "args": { + "External id": 703557,"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": 6305204778297.689, "dur": 32.299, + "args": { + "External id": 703558,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305204778300.300, "dur": 2.498, + "args": { + "External id": 703559,"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": 6305204778304.123, "dur": 0.511, + "args": { + "External id": 703560,"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": 6305204778306.131, "dur": 0.428, + "args": { + "External id": 703561,"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": 6305204778310.332, "dur": 2.655, + "args": { + "External id": 703562,"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": 6305204778314.236, "dur": 0.642, + "args": { + "External id": 703563,"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": 6305204778316.489, "dur": 0.358, + "args": { + "External id": 703564,"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": 6305204778320.354, "dur": 0.433, + "args": { + "External id": 703565,"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": 6305204778322.427, "dur": 0.364, + "args": { + "External id": 703566,"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": 6305204778324.041, "dur": 2.028, + "args": { + "External id": 703567,"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": 6305204778342.015, "dur": 36.090, + "args": { + "External id": 703568,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305204778441.889, "dur": 431.147, + "args": { + "External id": 703569,"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": 6305204778481.606, "dur": 385.777, + "args": { + "External id": 703570,"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": 6305204778492.866, "dur": 368.450, + "args": { + "External id": 703571,"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": 6305204778903.941, "dur": 2.450, + "args": { + "External id": 703572,"Record function id": 0, "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": 6305204779002.400, "dur": 30265.451, + "args": { + "External id": 703573,"Record function id": 0, "Ev Idx": 13977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6305204779145.813, "dur": 7.097, + "args": { + "External id": 703574,"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": 6305204779162.370, "dur": 1.121, + "args": { + "External id": 703575,"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": 6305204779165.520, "dur": 3.363, + "args": { + "External id": 703576,"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": 6305204779172.808, "dur": 0.697, + "args": { + "External id": 703577,"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": 6305204779174.776, "dur": 0.921, + "args": { + "External id": 703578,"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": 6305204779177.166, "dur": 0.829, + "args": { + "External id": 703579,"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": 6305204779180.107, "dur": 0.833, + "args": { + "External id": 703580,"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": 6305204779184.930, "dur": 1.803, + "args": { + "External id": 703581,"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": 6305204779188.212, "dur": 1.015, + "args": { + "External id": 703582,"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": 6305204779190.841, "dur": 0.813, + "args": { + "External id": 703583,"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": 6305204779214.329, "dur": 30009.551, + "args": { + "External id": 703584,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305204779230.794, "dur": 29984.102, + "args": { + "External id": 703585,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305204779245.563, "dur": 16.957, + "args": { + "External id": 703586,"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": 6305204779268.389, "dur": 29909.347, + "args": { + "External id": 703587,"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": 6305204779271.169, "dur": 29905.973, + "args": { + "External id": 703588,"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": 6305204779277.137, "dur": 4.876, + "args": { + "External id": 703589,"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": 6305204779283.810, "dur": 29890.041, + "args": { + "External id": 703590,"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": 6305204809408.963, "dur": 32.724, + "args": { + "External id": 703591,"Sequence number": 7674439, "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": 6305204809408.963, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6305204809427.697, "dur": 9.040, + "args": { + "External id": 703592,"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": 6305204809431.811, "dur": 4.653, + "args": { + "External id": 703593,"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": 6305204809518.842, "dur": 76.919, + "args": { + "External id": 703594,"Record function id": 0, "Ev Idx": 13998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6305204809597.844, "dur": 1125.240, + "args": { + "External id": 703595,"Record function id": 0, "Ev Idx": 13999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305204809637.267, "dur": 1072.545, + "args": { + "External id": 703596,"Sequence number": 7674440, "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": 6305204809637.267, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6305204809705.501, "dur": 51.335, + "args": { + "External id": 703597,"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": 6305204809769.356, "dur": 105.668, + "args": { + "External id": 703598,"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": 6305204809886.334, "dur": 37.037, + "args": { + "External id": 703599,"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": 6305204809932.184, "dur": 29.363, + "args": { + "External id": 703600,"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": 6305204809986.151, "dur": 28.979, + "args": { + "External id": 703601,"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": 6305204810036.791, "dur": 56.278, + "args": { + "External id": 703602,"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": 6305204810120.054, "dur": 133.236, + "args": { + "External id": 703603,"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": 6305204810171.942, "dur": 12.798, + "args": { + "External id": 703604,"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": 6305204810177.952, "dur": 5.835, + "args": { + "External id": 703605,"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": 6305204810187.809, "dur": 3.540, + "args": { + "External id": 703606,"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": 6305204810192.551, "dur": 1.053, + "args": { + "External id": 703607,"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": 6305204810196.325, "dur": 4.659, + "args": { + "External id": 703608,"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": 6305204810263.251, "dur": 54.100, + "args": { + "External id": 703609,"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": 6305204810348.697, "dur": 29.784, + "args": { + "External id": 703610,"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": 6305204810388.137, "dur": 41.830, + "args": { + "External id": 703611,"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": 6305204810440.184, "dur": 33.534, + "args": { + "External id": 703612,"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": 6305204810505.033, "dur": 46.374, + "args": { + "External id": 703613,"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": 6305204810561.461, "dur": 38.478, + "args": { + "External id": 703614,"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": 6305204810620.772, "dur": 18.553, + "args": { + "External id": 703615,"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": 6305204810789.169, "dur": 78.175, + "args": { + "External id": 703616,"Record function id": 0, "Ev Idx": 14020 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6305204810943.998, "dur": 50.115, + "args": { + "External id": 703617,"Record function id": 0, "Ev Idx": 14021 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.25)", "pid": 2338707, "tid": 2338707, + "ts": 6305204811003.340, "dur": 30842.407, + "args": { + "External id": 703618,"Record function id": 0, "Ev Idx": 14022 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.25)", "pid": 2338707, "tid": 2338707, + "ts": 6305204811012.968, "dur": 947.902, + "args": { + "External id": 703619,"Record function id": 0, "Ev Idx": 14023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6305204811143.241, "dur": 10.161, + "args": { + "External id": 703620,"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": 6305204811167.372, "dur": 41.484, + "args": { + "External id": 703621,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305204811173.677, "dur": 2.503, + "args": { + "External id": 703622,"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": 6305204811181.013, "dur": 0.371, + "args": { + "External id": 703623,"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": 6305204811183.082, "dur": 0.534, + "args": { + "External id": 703624,"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": 6305204811185.145, "dur": 0.572, + "args": { + "External id": 703625,"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": 6305204811189.166, "dur": 0.589, + "args": { + "External id": 703626,"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": 6305204811191.407, "dur": 0.685, + "args": { + "External id": 703627,"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": 6305204811193.698, "dur": 4.270, + "args": { + "External id": 703628,"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": 6305204811199.711, "dur": 0.314, + "args": { + "External id": 703629,"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": 6305204811202.705, "dur": 0.523, + "args": { + "External id": 703630,"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": 6305204811223.145, "dur": 54.891, + "args": { + "External id": 703631,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305204811312.320, "dur": 126.168, + "args": { + "External id": 703632,"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": 6305204811323.556, "dur": 5.000, + "args": { + "External id": 703633,"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": 6305204811333.994, "dur": 10.034, + "args": { + "External id": 703634,"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": 6305204811338.579, "dur": 5.070, + "args": { + "External id": 703635,"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": 6305204811341.847, "dur": 0.516, + "args": { + "External id": 703636,"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": 6305204811351.001, "dur": 30.515, + "args": { + "External id": 703637,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305204811353.064, "dur": 2.654, + "args": { + "External id": 703638,"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": 6305204811357.266, "dur": 0.462, + "args": { + "External id": 703639,"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": 6305204811358.999, "dur": 0.549, + "args": { + "External id": 703640,"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": 6305204811362.650, "dur": 2.528, + "args": { + "External id": 703641,"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": 6305204811366.579, "dur": 0.471, + "args": { + "External id": 703642,"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": 6305204811368.286, "dur": 0.345, + "args": { + "External id": 703643,"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": 6305204811371.841, "dur": 0.394, + "args": { + "External id": 703644,"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": 6305204811373.542, "dur": 0.319, + "args": { + "External id": 703645,"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": 6305204811375.188, "dur": 1.800, + "args": { + "External id": 703646,"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": 6305204811395.108, "dur": 35.074, + "args": { + "External id": 703647,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305204811491.135, "dur": 373.128, + "args": { + "External id": 703648,"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": 6305204811538.130, "dur": 321.009, + "args": { + "External id": 703649,"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": 6305204811550.039, "dur": 303.624, + "args": { + "External id": 703650,"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": 6305204811887.350, "dur": 2.506, + "args": { + "External id": 703651,"Record function id": 0, "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": 6305204811982.378, "dur": 29667.808, + "args": { + "External id": 703652,"Record function id": 0, "Ev Idx": 14056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6305204812123.808, "dur": 7.187, + "args": { + "External id": 703653,"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": 6305204812135.020, "dur": 0.810, + "args": { + "External id": 703654,"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": 6305204812137.799, "dur": 3.376, + "args": { + "External id": 703655,"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": 6305204812142.949, "dur": 0.993, + "args": { + "External id": 703656,"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": 6305204812145.210, "dur": 0.894, + "args": { + "External id": 703657,"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": 6305204812147.325, "dur": 0.896, + "args": { + "External id": 703658,"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": 6305204812151.961, "dur": 0.823, + "args": { + "External id": 703659,"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": 6305204812154.342, "dur": 2.186, + "args": { + "External id": 703660,"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": 6305204812158.217, "dur": 0.784, + "args": { + "External id": 703661,"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": 6305204812160.406, "dur": 0.715, + "args": { + "External id": 703662,"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": 6305204812182.888, "dur": 29422.119, + "args": { + "External id": 703663,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305204812199.229, "dur": 29397.624, + "args": { + "External id": 703664,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305204812222.131, "dur": 16.244, + "args": { + "External id": 703665,"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": 6305204812242.331, "dur": 29320.349, + "args": { + "External id": 703666,"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": 6305204812245.070, "dur": 29317.052, + "args": { + "External id": 703667,"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": 6305204812251.442, "dur": 5.146, + "args": { + "External id": 703668,"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": 6305204812258.240, "dur": 29300.992, + "args": { + "External id": 703669,"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": 6305204841791.513, "dur": 29.629, + "args": { + "External id": 703670,"Sequence number": 7674441, "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": 6305204841791.513, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6305204841808.124, "dur": 8.163, + "args": { + "External id": 703671,"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": 6305204841811.290, "dur": 4.749, + "args": { + "External id": 703672,"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": 6305204841886.285, "dur": 72.700, + "args": { + "External id": 703673,"Record function id": 0, "Ev Idx": 14077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6305204841960.421, "dur": 1129.482, + "args": { + "External id": 703674,"Record function id": 0, "Ev Idx": 14078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305204841999.473, "dur": 1043.736, + "args": { + "External id": 703675,"Sequence number": 7674442, "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": 6305204841999.473, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6305204842094.092, "dur": 51.126, + "args": { + "External id": 703676,"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": 6305204842160.764, "dur": 104.884, + "args": { + "External id": 703677,"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": 6305204842276.708, "dur": 38.057, + "args": { + "External id": 703678,"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": 6305204842323.045, "dur": 28.827, + "args": { + "External id": 703679,"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": 6305204842377.070, "dur": 28.719, + "args": { + "External id": 703680,"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": 6305204842426.158, "dur": 19.135, + "args": { + "External id": 703681,"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": 6305204842467.150, "dur": 146.569, + "args": { + "External id": 703682,"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": 6305204842531.974, "dur": 13.151, + "args": { + "External id": 703683,"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": 6305204842537.979, "dur": 6.255, + "args": { + "External id": 703684,"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": 6305204842547.881, "dur": 3.607, + "args": { + "External id": 703685,"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": 6305204842552.772, "dur": 1.032, + "args": { + "External id": 703686,"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": 6305204842556.536, "dur": 4.776, + "args": { + "External id": 703687,"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": 6305204842625.649, "dur": 53.769, + "args": { + "External id": 703688,"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": 6305204842711.096, "dur": 34.433, + "args": { + "External id": 703689,"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": 6305204842755.175, "dur": 42.395, + "args": { + "External id": 703690,"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": 6305204842806.955, "dur": 34.443, + "args": { + "External id": 703691,"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": 6305204842863.968, "dur": 26.886, + "args": { + "External id": 703692,"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": 6305204842898.168, "dur": 35.869, + "args": { + "External id": 703693,"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": 6305204842951.010, "dur": 19.487, + "args": { + "External id": 703694,"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": 6305204843158.531, "dur": 34.963, + "args": { + "External id": 703695,"Record function id": 0, "Ev Idx": 14099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305204843335.558, "dur": 323.818, + "args": { + "External id": 703696,"Sequence number": 7674443, "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": 6305204843335.558, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6305204843370.860, "dur": 8.649, + "args": { + "External id": 703697,"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": 6305204843373.217, "dur": 5.930, + "args": { + "External id": 703698,"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": 6305204843390.154, "dur": 13.039, + "args": { + "External id": 703699,"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": 6305204843393.589, "dur": 9.118, + "args": { + "External id": 703700,"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": 6305204843413.655, "dur": 4.970, + "args": { + "External id": 703701,"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": 6305204843637.216, "dur": 6.930, + "args": { + "External id": 703702,"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": 6305204843640.524, "dur": 3.279, + "args": { + "External id": 703703,"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": 6305204843688.468, "dur": 146.556, + "args": { + "External id": 703704,"Sequence number": 7674444, "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": 6305204843691.487, "dur": 15.344, + "args": { + "External id": 703705,"Sequence number": 7674444, "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": 6305204843691.487, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6305204843697.092, "dur": 8.088, + "args": { + "External id": 703706,"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": 6305204843702.626, "dur": 2.234, + "args": { + "External id": 703707,"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": 6305204843709.711, "dur": 124.922, + "args": { + "External id": 703708,"Sequence number": 7674445, "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": 6305204843712.804, "dur": 5.586, + "args": { + "External id": 703709,"Sequence number": 7674445, "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": 6305204843713.800, "dur": 4.432, + "args": { + "External id": 703710,"Sequence number": 7674445, "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": 6305204843713.800, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6305204843720.957, "dur": 97.390, + "args": { + "External id": 703711,"Sequence number": 7674446, "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": 6305204843720.957, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6305204843825.129, "dur": 8.567, + "args": { + "External id": 703712,"Sequence number": 7674447, "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": 6305204843825.129, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338707, "tid": 2338707, + "ts": 6305204843846.409, "dur": 71.264, + "args": { + "External id": 703713,"Sequence number": 7674448, "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": 6305204843847.046, "dur": 8.492, + "args": { + "External id": 703714,"Sequence number": 7674448, "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": 6305204843847.046, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6305204843849.392, "dur": 4.801, + "args": { + "External id": 703715,"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": 6305204843853.249, "dur": 0.735, + "args": { + "External id": 703716,"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": 6305204843856.061, "dur": 61.306, + "args": { + "External id": 703717,"Sequence number": 7674449, "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": 6305204843857.287, "dur": 5.013, + "args": { + "External id": 703718,"Sequence number": 7674449, "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": 6305204843858.097, "dur": 4.067, + "args": { + "External id": 703719,"Sequence number": 7674449, "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": 6305204843858.097, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6305204843862.924, "dur": 47.645, + "args": { + "External id": 703720,"Sequence number": 7674450, "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": 6305204843862.924, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6305204843912.810, "dur": 4.178, + "args": { + "External id": 703721,"Sequence number": 7674451, "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": 6305204843912.810, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338707, "tid": 2338707, + "ts": 6305204843926.687, "dur": 63.713, + "args": { + "External id": 703722,"Sequence number": 7674452, "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": 6305204843927.043, "dur": 5.456, + "args": { + "External id": 703723,"Sequence number": 7674452, "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": 6305204843927.043, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6305204843928.798, "dur": 2.547, + "args": { + "External id": 703724,"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": 6305204843930.446, "dur": 0.731, + "args": { + "External id": 703725,"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": 6305204843935.808, "dur": 54.355, + "args": { + "External id": 703726,"Sequence number": 7674453, "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": 6305204843936.556, "dur": 4.733, + "args": { + "External id": 703727,"Sequence number": 7674453, "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": 6305204843937.514, "dur": 3.632, + "args": { + "External id": 703728,"Sequence number": 7674453, "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": 6305204843937.514, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6305204843941.720, "dur": 40.535, + "args": { + "External id": 703729,"Sequence number": 7674454, "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": 6305204843941.720, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6305204843984.073, "dur": 5.761, + "args": { + "External id": 703730,"Sequence number": 7674455, "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": 6305204843984.073, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6305204844017.739, "dur": 3.755, + "args": { + "External id": 703731,"Sequence number": 7674456, "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": 6305204844018.766, "dur": 2.549, + "args": { + "External id": 703732,"Sequence number": 7674456, "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": 6305204844018.766, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6305204844029.804, "dur": 2.901, + "args": { + "External id": 703733,"Sequence number": 7674457, "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": 6305204844030.582, "dur": 2.001, + "args": { + "External id": 703734,"Sequence number": 7674457, "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": 6305204844030.582, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6305204844038.823, "dur": 4.785, + "args": { + "External id": 703735,"Sequence number": 7674458, "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": 6305204844039.813, "dur": 3.635, + "args": { + "External id": 703736,"Sequence number": 7674458, "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": 6305204844039.813, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305204844119.884, "dur": 206.680, + "args": { + "External id": 703737,"Sequence number": 7674459, "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": 6305204844119.884, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338707, "tid": 2338707, + "ts": 6305204844146.927, "dur": 10.501, + "args": { + "External id": 703738,"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": 6305204844150.527, "dur": 6.271, + "args": { + "External id": 703739,"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": 6305204844340.150, "dur": 116.283, + "args": { + "External id": 703740,"Sequence number": 7674460, "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": 6305204844340.150, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338707, "tid": 2338707, + "ts": 6305204844353.924, "dur": 6.745, + "args": { + "External id": 703741,"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": 6305204844356.741, "dur": 3.509, + "args": { + "External id": 703742,"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": 6305204844486.204, "dur": 222.639, + "args": { + "External id": 703743,"Sequence number": 7674461, "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": 6305204844486.204, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338707, "tid": 2338707, + "ts": 6305204844535.568, "dur": 143.681, + "args": { + "External id": 703744,"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": 6305204844591.377, "dur": 8.243, + "args": { + "External id": 703745,"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": 6305204844594.263, "dur": 4.756, + "args": { + "External id": 703746,"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": 6305204844605.636, "dur": 3.917, + "args": { + "External id": 703747,"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": 6305204844612.976, "dur": 1.644, + "args": { + "External id": 703748,"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": 6305204844617.029, "dur": 2.997, + "args": { + "External id": 703749,"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": 6305204844693.106, "dur": 5.585, + "args": { + "External id": 703750,"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": 6305204844714.710, "dur": 6.739, + "args": { + "External id": 703751,"Sequence number": 7674462, "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": 6305204844716.296, "dur": 5.018, + "args": { + "External id": 703752,"Sequence number": 7674462, "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": 6305204844716.296, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338707, "tid": 2338707, + "ts": 6305204844736.693, "dur": 114.659, + "args": { + "External id": 703753,"Sequence number": 7674463, "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": 6305204844738.090, "dur": 9.070, + "args": { + "External id": 703754,"Sequence number": 7674463, "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": 6305204844738.090, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6305204844741.283, "dur": 4.647, + "args": { + "External id": 703755,"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": 6305204844743.922, "dur": 1.614, + "args": { + "External id": 703756,"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": 6305204844748.458, "dur": 102.595, + "args": { + "External id": 703757,"Sequence number": 7674464, "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": 6305204844752.567, "dur": 3.152, + "args": { + "External id": 703758,"Sequence number": 7674464, "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": 6305204844753.309, "dur": 2.276, + "args": { + "External id": 703759,"Sequence number": 7674464, "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": 6305204844753.309, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6305204844756.653, "dur": 87.541, + "args": { + "External id": 703760,"Sequence number": 7674465, "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": 6305204844756.653, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6305204844847.030, "dur": 3.287, + "args": { + "External id": 703761,"Sequence number": 7674466, "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": 6305204844847.030, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305204844887.585, "dur": 277.590, + "args": { + "External id": 703762,"Sequence number": 7674467, "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": 6305204844887.585, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6305204844908.550, "dur": 2.936, + "args": { + "External id": 703763,"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": 6305204844909.844, "dur": 1.473, + "args": { + "External id": 703764,"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": 6305204844917.730, "dur": 7.625, + "args": { + "External id": 703765,"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": 6305204844918.828, "dur": 6.415, + "args": { + "External id": 703766,"Record 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": 6305204844922.046, "dur": 3.104, + "args": { + "External id": 703767,"Record 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": 6305204844933.305, "dur": 5.992, + "args": { + "External id": 703768,"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": 6305204844935.223, "dur": 3.674, + "args": { + "External id": 703769,"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": 6305204844945.179, "dur": 2.539, + "args": { + "External id": 703770,"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": 6305204844953.338, "dur": 2.718, + "args": { + "External id": 703771,"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": 6305204845136.018, "dur": 5.004, + "args": { + "External id": 703772,"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": 6305204845137.609, "dur": 3.091, + "args": { + "External id": 703773,"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": 6305204845146.179, "dur": 2.440, + "args": { + "External id": 703774,"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": 6305204845147.364, "dur": 1.125, + "args": { + "External id": 703775,"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": 6305204845187.601, "dur": 109.162, + "args": { + "External id": 703776,"Sequence number": 7674468, "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": 6305204845188.537, "dur": 8.722, + "args": { + "External id": 703777,"Sequence number": 7674468, "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": 6305204845188.537, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6305204845191.473, "dur": 4.655, + "args": { + "External id": 703778,"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": 6305204845194.100, "dur": 1.585, + "args": { + "External id": 703779,"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": 6305204845200.758, "dur": 95.674, + "args": { + "External id": 703780,"Sequence number": 7674469, "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": 6305204845202.515, "dur": 3.841, + "args": { + "External id": 703781,"Sequence number": 7674469, "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": 6305204845203.341, "dur": 2.891, + "args": { + "External id": 703782,"Sequence number": 7674469, "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": 6305204845203.341, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6305204845207.111, "dur": 76.642, + "args": { + "External id": 703783,"Sequence number": 7674470, "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": 6305204845207.111, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6305204845286.624, "dur": 9.219, + "args": { + "External id": 703784,"Sequence number": 7674471, "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": 6305204845286.624, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338707, "tid": 2338707, + "ts": 6305204845305.908, "dur": 66.457, + "args": { + "External id": 703785,"Sequence number": 7674472, "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": 6305204845306.499, "dur": 5.326, + "args": { + "External id": 703786,"Sequence number": 7674472, "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": 6305204845306.499, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6305204845308.049, "dur": 2.524, + "args": { + "External id": 703787,"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": 6305204845309.731, "dur": 0.668, + "args": { + "External id": 703788,"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": 6305204845312.345, "dur": 59.713, + "args": { + "External id": 703789,"Sequence number": 7674473, "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": 6305204845315.752, "dur": 4.228, + "args": { + "External id": 703790,"Sequence number": 7674473, "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": 6305204845316.509, "dur": 3.336, + "args": { + "External id": 703791,"Sequence number": 7674473, "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": 6305204845316.509, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6305204845320.506, "dur": 47.312, + "args": { + "External id": 703792,"Sequence number": 7674474, "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": 6305204845320.506, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6305204845369.792, "dur": 1.860, + "args": { + "External id": 703793,"Sequence number": 7674475, "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": 6305204845369.792, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305204845398.633, "dur": 196.056, + "args": { + "External id": 703794,"Sequence number": 7674476, "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": 6305204845398.633, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6305204845445.627, "dur": 4.185, + "args": { + "External id": 703795,"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": 6305204845486.985, "dur": 90.891, + "args": { + "External id": 703796,"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": 6305204845487.545, "dur": 7.103, + "args": { + "External id": 703797,"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": 6305204845488.847, "dur": 4.963, + "args": { + "External id": 703798,"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": 6305204845492.855, "dur": 0.766, + "args": { + "External id": 703799,"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": 6305204845498.001, "dur": 79.505, + "args": { + "External id": 703800,"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": 6305204845499.486, "dur": 3.209, + "args": { + "External id": 703801,"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": 6305204845500.928, "dur": 1.662, + "args": { + "External id": 703802,"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": 6305204845503.657, "dur": 68.111, + "args": { + "External id": 703803,"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": 6305204845575.282, "dur": 1.350, + "args": { + "External id": 703804,"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": 6305204845605.646, "dur": 28.673, + "args": { + "External id": 703805,"Sequence number": 7674477, "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": 6305204845605.646, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305204845672.082, "dur": 188.252, + "args": { + "External id": 703806,"Sequence number": 7674478, "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": 6305204845672.082, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6305204845693.515, "dur": 3.605, + "args": { + "External id": 703807,"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": 6305204845694.780, "dur": 2.133, + "args": { + "External id": 703808,"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": 6305204845705.191, "dur": 7.866, + "args": { + "External id": 703809,"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": 6305204845708.437, "dur": 4.241, + "args": { + "External id": 703810,"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": 6305204845718.936, "dur": 3.465, + "args": { + "External id": 703811,"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": 6305204845844.293, "dur": 2.931, + "args": { + "External id": 703812,"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": 6305204845845.460, "dur": 1.577, + "args": { + "External id": 703813,"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": 6305204845879.266, "dur": 87.779, + "args": { + "External id": 703814,"Sequence number": 7674479, "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": 6305204845880.423, "dur": 7.530, + "args": { + "External id": 703815,"Sequence number": 7674479, "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": 6305204845880.423, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6305204845883.129, "dur": 3.678, + "args": { + "External id": 703816,"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": 6305204845885.351, "dur": 1.241, + "args": { + "External id": 703817,"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": 6305204845888.867, "dur": 77.927, + "args": { + "External id": 703818,"Sequence number": 7674480, "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": 6305204845892.389, "dur": 6.144, + "args": { + "External id": 703819,"Sequence number": 7674480, "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": 6305204845893.261, "dur": 5.114, + "args": { + "External id": 703820,"Sequence number": 7674480, "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": 6305204845893.261, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6305204845899.117, "dur": 60.103, + "args": { + "External id": 703821,"Sequence number": 7674481, "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": 6305204845899.117, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6305204845961.487, "dur": 4.599, + "args": { + "External id": 703822,"Sequence number": 7674482, "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": 6305204845961.487, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338707, "tid": 2338707, + "ts": 6305204845974.849, "dur": 71.219, + "args": { + "External id": 703823,"Sequence number": 7674483, "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": 6305204845977.645, "dur": 9.009, + "args": { + "External id": 703824,"Sequence number": 7674483, "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": 6305204845977.645, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6305204845982.307, "dur": 3.099, + "args": { + "External id": 703825,"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": 6305204845984.496, "dur": 0.751, + "args": { + "External id": 703826,"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": 6305204845987.337, "dur": 58.557, + "args": { + "External id": 703827,"Sequence number": 7674484, "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": 6305204845988.783, "dur": 6.131, + "args": { + "External id": 703828,"Sequence number": 7674484, "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": 6305204845991.800, "dur": 2.968, + "args": { + "External id": 703829,"Sequence number": 7674484, "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": 6305204845991.800, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6305204845995.578, "dur": 41.957, + "args": { + "External id": 703830,"Sequence number": 7674485, "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": 6305204845995.578, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6305204846039.420, "dur": 5.911, + "args": { + "External id": 703831,"Sequence number": 7674486, "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": 6305204846039.420, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338707, "tid": 2338707, + "ts": 6305204846089.417, "dur": 69.543, + "args": { + "External id": 703832,"Sequence number": 7674487, "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": 6305204846089.982, "dur": 9.899, + "args": { + "External id": 703833,"Sequence number": 7674487, "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": 6305204846089.982, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6305204846094.882, "dur": 3.336, + "args": { + "External id": 703834,"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": 6305204846096.796, "dur": 1.070, + "args": { + "External id": 703835,"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": 6305204846101.040, "dur": 57.654, + "args": { + "External id": 703836,"Sequence number": 7674488, "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": 6305204846102.217, "dur": 8.492, + "args": { + "External id": 703837,"Sequence number": 7674488, "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": 6305204846103.090, "dur": 7.492, + "args": { + "External id": 703838,"Sequence number": 7674488, "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": 6305204846103.090, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6305204846111.191, "dur": 43.023, + "args": { + "External id": 703839,"Sequence number": 7674489, "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": 6305204846111.191, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6305204846156.173, "dur": 2.128, + "args": { + "External id": 703840,"Sequence number": 7674490, "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": 6305204846156.173, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6305204846176.521, "dur": 4.272, + "args": { + "External id": 703841,"Sequence number": 7674491, "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": 6305204846177.575, "dur": 3.054, + "args": { + "External id": 703842,"Sequence number": 7674491, "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": 6305204846177.575, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6305204846190.194, "dur": 5.595, + "args": { + "External id": 703843,"Sequence number": 7674492, "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": 6305204846191.041, "dur": 4.601, + "args": { + "External id": 703844,"Sequence number": 7674492, "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": 6305204846191.041, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6305204846199.758, "dur": 2.779, + "args": { + "External id": 703845,"Sequence number": 7674493, "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": 6305204846200.351, "dur": 2.056, + "args": { + "External id": 703846,"Sequence number": 7674493, "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": 6305204846200.351, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305204846233.446, "dur": 165.419, + "args": { + "External id": 703847,"Sequence number": 7674494, "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": 6305204846233.446, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338707, "tid": 2338707, + "ts": 6305204846254.102, "dur": 8.798, + "args": { + "External id": 703848,"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": 6305204846257.614, "dur": 4.989, + "args": { + "External id": 703849,"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": 6305204846411.112, "dur": 123.200, + "args": { + "External id": 703850,"Sequence number": 7674495, "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": 6305204846411.112, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338707, "tid": 2338707, + "ts": 6305204846425.107, "dur": 6.044, + "args": { + "External id": 703851,"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": 6305204846427.501, "dur": 3.324, + "args": { + "External id": 703852,"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": 6305204846567.120, "dur": 180.207, + "args": { + "External id": 703853,"Sequence number": 7674496, "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": 6305204846567.120, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338707, "tid": 2338707, + "ts": 6305204846598.089, "dur": 122.534, + "args": { + "External id": 703854,"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": 6305204846642.758, "dur": 10.296, + "args": { + "External id": 703855,"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": 6305204846645.796, "dur": 6.702, + "args": { + "External id": 703856,"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": 6305204846655.683, "dur": 3.826, + "args": { + "External id": 703857,"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": 6305204846661.274, "dur": 1.327, + "args": { + "External id": 703858,"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": 6305204846665.158, "dur": 3.356, + "args": { + "External id": 703859,"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": 6305204846731.366, "dur": 4.791, + "args": { + "External id": 703860,"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": 6305204846752.539, "dur": 5.295, + "args": { + "External id": 703861,"Sequence number": 7674497, "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": 6305204846753.851, "dur": 3.830, + "args": { + "External id": 703862,"Sequence number": 7674497, "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": 6305204846753.851, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338707, "tid": 2338707, + "ts": 6305204846769.080, "dur": 107.483, + "args": { + "External id": 703863,"Sequence number": 7674498, "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": 6305204846770.318, "dur": 8.236, + "args": { + "External id": 703864,"Sequence number": 7674498, "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": 6305204846770.318, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6305204846772.993, "dur": 4.451, + "args": { + "External id": 703865,"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": 6305204846775.632, "dur": 1.568, + "args": { + "External id": 703866,"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": 6305204846782.035, "dur": 94.210, + "args": { + "External id": 703867,"Sequence number": 7674499, "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": 6305204846784.276, "dur": 3.383, + "args": { + "External id": 703868,"Sequence number": 7674499, "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": 6305204846784.961, "dur": 2.515, + "args": { + "External id": 703869,"Sequence number": 7674499, "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": 6305204846784.961, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6305204846788.914, "dur": 78.121, + "args": { + "External id": 703870,"Sequence number": 7674500, "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": 6305204846788.914, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6305204846869.234, "dur": 6.436, + "args": { + "External id": 703871,"Sequence number": 7674501, "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": 6305204846869.234, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305204846920.591, "dur": 261.540, + "args": { + "External id": 703872,"Sequence number": 7674502, "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": 6305204846920.591, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6305204846938.745, "dur": 5.164, + "args": { + "External id": 703873,"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": 6305204846940.082, "dur": 3.579, + "args": { + "External id": 703874,"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": 6305204846947.996, "dur": 6.391, + "args": { + "External id": 703875,"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": 6305204846952.060, "dur": 2.107, + "args": { + "External id": 703876,"Record 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": 6305204846953.159, "dur": 0.906, + "args": { + "External id": 703877,"Record 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": 6305204846962.427, "dur": 7.292, + "args": { + "External id": 703878,"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": 6305204846964.944, "dur": 4.473, + "args": { + "External id": 703879,"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": 6305204846975.851, "dur": 2.451, + "args": { + "External id": 703880,"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": 6305204846981.721, "dur": 3.493, + "args": { + "External id": 703881,"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": 6305204847156.818, "dur": 5.296, + "args": { + "External id": 703882,"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": 6305204847158.367, "dur": 3.215, + "args": { + "External id": 703883,"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": 6305204847165.178, "dur": 2.243, + "args": { + "External id": 703884,"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": 6305204847166.315, "dur": 1.021, + "args": { + "External id": 703885,"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": 6305204847201.680, "dur": 104.120, + "args": { + "External id": 703886,"Sequence number": 7674503, "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": 6305204847203.150, "dur": 10.131, + "args": { + "External id": 703887,"Sequence number": 7674503, "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": 6305204847203.150, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6305204847205.629, "dur": 6.457, + "args": { + "External id": 703888,"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": 6305204847210.130, "dur": 1.615, + "args": { + "External id": 703889,"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": 6305204847214.397, "dur": 91.182, + "args": { + "External id": 703890,"Sequence number": 7674504, "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": 6305204847215.904, "dur": 6.512, + "args": { + "External id": 703891,"Sequence number": 7674504, "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": 6305204847217.378, "dur": 4.922, + "args": { + "External id": 703892,"Sequence number": 7674504, "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": 6305204847217.378, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6305204847225.152, "dur": 74.966, + "args": { + "External id": 703893,"Sequence number": 7674505, "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": 6305204847225.152, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6305204847302.314, "dur": 2.649, + "args": { + "External id": 703894,"Sequence number": 7674506, "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": 6305204847302.314, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338707, "tid": 2338707, + "ts": 6305204847315.358, "dur": 81.086, + "args": { + "External id": 703895,"Sequence number": 7674507, "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": 6305204847316.083, "dur": 17.142, + "args": { + "External id": 703896,"Sequence number": 7674507, "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": 6305204847316.083, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6305204847324.008, "dur": 7.664, + "args": { + "External id": 703897,"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": 6305204847330.563, "dur": 0.955, + "args": { + "External id": 703898,"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": 6305204847334.054, "dur": 62.114, + "args": { + "External id": 703899,"Sequence number": 7674508, "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": 6305204847335.116, "dur": 7.015, + "args": { + "External id": 703900,"Sequence number": 7674508, "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": 6305204847336.017, "dur": 5.961, + "args": { + "External id": 703901,"Sequence number": 7674508, "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": 6305204847336.017, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6305204847342.614, "dur": 45.626, + "args": { + "External id": 703902,"Sequence number": 7674509, "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": 6305204847342.614, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6305204847389.761, "dur": 6.079, + "args": { + "External id": 703903,"Sequence number": 7674510, "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": 6305204847389.761, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305204847417.407, "dur": 173.837, + "args": { + "External id": 703904,"Sequence number": 7674511, "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": 6305204847417.407, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6305204847456.485, "dur": 4.265, + "args": { + "External id": 703905,"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": 6305204847496.043, "dur": 79.760, + "args": { + "External id": 703906,"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": 6305204847496.824, "dur": 4.795, + "args": { + "External id": 703907,"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": 6305204847497.899, "dur": 2.929, + "args": { + "External id": 703908,"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": 6305204847499.579, "dur": 1.017, + "args": { + "External id": 703909,"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": 6305204847502.618, "dur": 72.818, + "args": { + "External id": 703910,"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": 6305204847504.027, "dur": 18.277, + "args": { + "External id": 703911,"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": 6305204847504.958, "dur": 16.916, + "args": { + "External id": 703912,"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": 6305204847523.523, "dur": 48.122, + "args": { + "External id": 703913,"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": 6305204847573.824, "dur": 0.936, + "args": { + "External id": 703914,"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": 6305204847600.714, "dur": 27.630, + "args": { + "External id": 703915,"Sequence number": 7674512, "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": 6305204847600.714, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305204847668.864, "dur": 185.884, + "args": { + "External id": 703916,"Sequence number": 7674513, "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": 6305204847668.864, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6305204847688.086, "dur": 3.369, + "args": { + "External id": 703917,"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": 6305204847689.227, "dur": 1.915, + "args": { + "External id": 703918,"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": 6305204847699.597, "dur": 7.649, + "args": { + "External id": 703919,"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": 6305204847702.606, "dur": 4.266, + "args": { + "External id": 703920,"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": 6305204847713.026, "dur": 5.585, + "args": { + "External id": 703921,"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": 6305204847840.996, "dur": 3.128, + "args": { + "External id": 703922,"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": 6305204847842.198, "dur": 1.735, + "args": { + "External id": 703923,"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": 6305204847872.113, "dur": 85.687, + "args": { + "External id": 703924,"Sequence number": 7674514, "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": 6305204847873.221, "dur": 7.065, + "args": { + "External id": 703925,"Sequence number": 7674514, "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": 6305204847873.221, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6305204847875.736, "dur": 3.362, + "args": { + "External id": 703926,"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": 6305204847877.635, "dur": 1.292, + "args": { + "External id": 703927,"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": 6305204847883.708, "dur": 73.821, + "args": { + "External id": 703928,"Sequence number": 7674515, "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": 6305204847885.168, "dur": 4.086, + "args": { + "External id": 703929,"Sequence number": 7674515, "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": 6305204847886.330, "dur": 2.788, + "args": { + "External id": 703930,"Sequence number": 7674515, "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": 6305204847886.330, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6305204847889.872, "dur": 60.580, + "args": { + "External id": 703931,"Sequence number": 7674516, "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": 6305204847889.872, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6305204847952.520, "dur": 4.336, + "args": { + "External id": 703932,"Sequence number": 7674517, "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": 6305204847952.520, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338707, "tid": 2338707, + "ts": 6305204847966.210, "dur": 61.404, + "args": { + "External id": 703933,"Sequence number": 7674518, "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": 6305204847966.772, "dur": 5.523, + "args": { + "External id": 703934,"Sequence number": 7674518, "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": 6305204847966.772, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6305204847968.654, "dur": 2.477, + "args": { + "External id": 703935,"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": 6305204847970.172, "dur": 0.837, + "args": { + "External id": 703936,"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": 6305204847972.899, "dur": 54.468, + "args": { + "External id": 703937,"Sequence number": 7674519, "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": 6305204847976.780, "dur": 3.435, + "args": { + "External id": 703938,"Sequence number": 7674519, "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": 6305204847977.620, "dur": 2.476, + "args": { + "External id": 703939,"Sequence number": 7674519, "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": 6305204847977.620, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6305204847980.708, "dur": 42.831, + "args": { + "External id": 703940,"Sequence number": 7674520, "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": 6305204847980.708, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6305204848025.016, "dur": 1.980, + "args": { + "External id": 703941,"Sequence number": 7674521, "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": 6305204848025.016, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338707, "tid": 2338707, + "ts": 6305204848034.513, "dur": 104.197, + "args": { + "External id": 703942,"Sequence number": 7674522, "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": 6305204848037.250, "dur": 6.884, + "args": { + "External id": 703943,"Sequence number": 7674522, "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": 6305204848037.250, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6305204848038.934, "dur": 4.025, + "args": { + "External id": 703944,"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": 6305204848040.442, "dur": 2.098, + "args": { + "External id": 703945,"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": 6305204848045.216, "dur": 93.291, + "args": { + "External id": 703946,"Sequence number": 7674523, "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": 6305204848045.934, "dur": 6.696, + "args": { + "External id": 703947,"Sequence number": 7674523, "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": 6305204848049.079, "dur": 3.402, + "args": { + "External id": 703948,"Sequence number": 7674523, "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": 6305204848049.079, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6305204848053.042, "dur": 76.297, + "args": { + "External id": 703949,"Sequence number": 7674524, "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": 6305204848053.042, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6305204848132.516, "dur": 5.479, + "args": { + "External id": 703950,"Sequence number": 7674525, "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": 6305204848132.516, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6305204848156.739, "dur": 6.099, + "args": { + "External id": 703951,"Sequence number": 7674526, "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": 6305204848159.727, "dur": 2.981, + "args": { + "External id": 703952,"Sequence number": 7674526, "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": 6305204848159.727, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6305204848169.731, "dur": 2.528, + "args": { + "External id": 703953,"Sequence number": 7674527, "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": 6305204848170.660, "dur": 1.480, + "args": { + "External id": 703954,"Sequence number": 7674527, "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": 6305204848170.660, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6305204848176.317, "dur": 5.131, + "args": { + "External id": 703955,"Sequence number": 7674528, "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": 6305204848177.126, "dur": 4.217, + "args": { + "External id": 703956,"Sequence number": 7674528, "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": 6305204848177.126, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305204848213.457, "dur": 149.289, + "args": { + "External id": 703957,"Sequence number": 7674529, "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": 6305204848213.457, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338707, "tid": 2338707, + "ts": 6305204848231.374, "dur": 9.646, + "args": { + "External id": 703958,"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": 6305204848234.288, "dur": 6.313, + "args": { + "External id": 703959,"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": 6305204848374.528, "dur": 99.964, + "args": { + "External id": 703960,"Sequence number": 7674530, "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": 6305204848374.528, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338707, "tid": 2338707, + "ts": 6305204848387.339, "dur": 5.977, + "args": { + "External id": 703961,"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": 6305204848389.435, "dur": 3.466, + "args": { + "External id": 703962,"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": 6305204848502.998, "dur": 201.802, + "args": { + "External id": 703963,"Sequence number": 7674531, "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": 6305204848502.998, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338707, "tid": 2338707, + "ts": 6305204848547.034, "dur": 131.874, + "args": { + "External id": 703964,"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": 6305204848596.566, "dur": 8.714, + "args": { + "External id": 703965,"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": 6305204848599.318, "dur": 5.308, + "args": { + "External id": 703966,"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": 6305204848607.736, "dur": 5.683, + "args": { + "External id": 703967,"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": 6305204848614.707, "dur": 1.001, + "args": { + "External id": 703968,"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": 6305204848620.219, "dur": 3.562, + "args": { + "External id": 703969,"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": 6305204848690.474, "dur": 4.798, + "args": { + "External id": 703970,"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": 6305204848709.998, "dur": 5.494, + "args": { + "External id": 703971,"Sequence number": 7674532, "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": 6305204848711.288, "dur": 4.020, + "args": { + "External id": 703972,"Sequence number": 7674532, "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": 6305204848711.288, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338707, "tid": 2338707, + "ts": 6305204848728.670, "dur": 125.354, + "args": { + "External id": 703973,"Sequence number": 7674533, "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": 6305204848729.875, "dur": 13.581, + "args": { + "External id": 703974,"Sequence number": 7674533, "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": 6305204848729.875, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6305204848735.472, "dur": 6.777, + "args": { + "External id": 703975,"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": 6305204848739.833, "dur": 2.131, + "args": { + "External id": 703976,"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": 6305204848744.648, "dur": 109.067, + "args": { + "External id": 703977,"Sequence number": 7674534, "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": 6305204848746.875, "dur": 5.358, + "args": { + "External id": 703978,"Sequence number": 7674534, "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": 6305204848747.717, "dur": 4.394, + "args": { + "External id": 703979,"Sequence number": 7674534, "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": 6305204848747.717, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6305204848755.735, "dur": 88.201, + "args": { + "External id": 703980,"Sequence number": 7674535, "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": 6305204848755.735, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6305204848846.742, "dur": 6.197, + "args": { + "External id": 703981,"Sequence number": 7674536, "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": 6305204848846.742, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305204848888.330, "dur": 270.131, + "args": { + "External id": 703982,"Sequence number": 7674537, "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": 6305204848888.330, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6305204848906.534, "dur": 5.109, + "args": { + "External id": 703983,"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": 6305204848910.110, "dur": 1.300, + "args": { + "External id": 703984,"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": 6305204848915.521, "dur": 2.794, + "args": { + "External id": 703985,"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": 6305204848916.280, "dur": 1.915, + "args": { + "External id": 703986,"Record 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": 6305204848917.283, "dur": 0.812, + "args": { + "External id": 703987,"Record 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": 6305204848925.924, "dur": 16.077, + "args": { + "External id": 703988,"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": 6305204848935.557, "dur": 6.118, + "args": { + "External id": 703989,"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": 6305204848950.257, "dur": 2.540, + "args": { + "External id": 703990,"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": 6305204848956.199, "dur": 4.796, + "args": { + "External id": 703991,"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": 6305204849136.697, "dur": 4.011, + "args": { + "External id": 703992,"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": 6305204849137.652, "dur": 2.726, + "args": { + "External id": 703993,"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": 6305204849143.242, "dur": 1.553, + "args": { + "External id": 703994,"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": 6305204849143.953, "dur": 0.759, + "args": { + "External id": 703995,"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": 6305204849178.588, "dur": 146.565, + "args": { + "External id": 703996,"Sequence number": 7674538, "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": 6305204849179.820, "dur": 11.273, + "args": { + "External id": 703997,"Sequence number": 7674538, "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": 6305204849179.820, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6305204849184.245, "dur": 5.694, + "args": { + "External id": 703998,"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": 6305204849186.352, "dur": 3.299, + "args": { + "External id": 703999,"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": 6305204849191.977, "dur": 132.809, + "args": { + "External id": 704000,"Sequence number": 7674539, "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": 6305204849225.091, "dur": 6.365, + "args": { + "External id": 704001,"Sequence number": 7674539, "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": 6305204849228.270, "dur": 3.081, + "args": { + "External id": 704002,"Sequence number": 7674539, "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": 6305204849228.270, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6305204849232.496, "dur": 85.495, + "args": { + "External id": 704003,"Sequence number": 7674540, "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": 6305204849232.496, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6305204849320.951, "dur": 3.101, + "args": { + "External id": 704004,"Sequence number": 7674541, "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": 6305204849320.951, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338707, "tid": 2338707, + "ts": 6305204849333.915, "dur": 73.072, + "args": { + "External id": 704005,"Sequence number": 7674542, "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": 6305204849334.425, "dur": 9.770, + "args": { + "External id": 704006,"Sequence number": 7674542, "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": 6305204849334.425, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6305204849338.119, "dur": 4.866, + "args": { + "External id": 704007,"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": 6305204849339.564, "dur": 3.172, + "args": { + "External id": 704008,"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": 6305204849344.854, "dur": 61.849, + "args": { + "External id": 704009,"Sequence number": 7674543, "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": 6305204849345.841, "dur": 7.425, + "args": { + "External id": 704010,"Sequence number": 7674543, "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": 6305204849346.356, "dur": 6.769, + "args": { + "External id": 704011,"Sequence number": 7674543, "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": 6305204849346.356, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6305204849353.771, "dur": 45.113, + "args": { + "External id": 704012,"Sequence number": 7674544, "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": 6305204849353.771, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6305204849400.532, "dur": 5.515, + "args": { + "External id": 704013,"Sequence number": 7674545, "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": 6305204849400.532, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305204849429.204, "dur": 177.900, + "args": { + "External id": 704014,"Sequence number": 7674546, "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": 6305204849429.204, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6305204849472.248, "dur": 3.911, + "args": { + "External id": 704015,"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": 6305204849523.368, "dur": 68.769, + "args": { + "External id": 704016,"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": 6305204849524.087, "dur": 6.050, + "args": { + "External id": 704017,"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": 6305204849525.526, "dur": 3.473, + "args": { + "External id": 704018,"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": 6305204849527.225, "dur": 1.260, + "args": { + "External id": 704019,"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": 6305204849530.824, "dur": 60.939, + "args": { + "External id": 704020,"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": 6305204849532.693, "dur": 4.804, + "args": { + "External id": 704021,"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": 6305204849535.956, "dur": 1.428, + "args": { + "External id": 704022,"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": 6305204849538.324, "dur": 47.649, + "args": { + "External id": 704023,"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": 6305204849587.857, "dur": 3.262, + "args": { + "External id": 704024,"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": 6305204849616.853, "dur": 24.852, + "args": { + "External id": 704025,"Sequence number": 7674547, "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": 6305204849616.853, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305204849679.619, "dur": 189.912, + "args": { + "External id": 704026,"Sequence number": 7674548, "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": 6305204849679.619, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6305204849700.719, "dur": 3.046, + "args": { + "External id": 704027,"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": 6305204849701.637, "dur": 2.002, + "args": { + "External id": 704028,"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": 6305204849711.721, "dur": 9.632, + "args": { + "External id": 704029,"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": 6305204849716.614, "dur": 4.353, + "args": { + "External id": 704030,"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": 6305204849727.733, "dur": 3.543, + "args": { + "External id": 704031,"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": 6305204849855.632, "dur": 2.894, + "args": { + "External id": 704032,"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": 6305204849856.727, "dur": 1.615, + "args": { + "External id": 704033,"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": 6305204849888.097, "dur": 93.347, + "args": { + "External id": 704034,"Sequence number": 7674549, "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": 6305204849889.020, "dur": 8.627, + "args": { + "External id": 704035,"Sequence number": 7674549, "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": 6305204849889.020, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6305204849891.073, "dur": 5.373, + "args": { + "External id": 704036,"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": 6305204849895.171, "dur": 1.088, + "args": { + "External id": 704037,"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": 6305204849898.308, "dur": 82.872, + "args": { + "External id": 704038,"Sequence number": 7674550, "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": 6305204849899.447, "dur": 3.219, + "args": { + "External id": 704039,"Sequence number": 7674550, "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": 6305204849900.030, "dur": 2.527, + "args": { + "External id": 704040,"Sequence number": 7674550, "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": 6305204849900.030, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6305204849910.100, "dur": 66.048, + "args": { + "External id": 704041,"Sequence number": 7674551, "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": 6305204849910.100, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6305204849978.147, "dur": 2.254, + "args": { + "External id": 704042,"Sequence number": 7674552, "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": 6305204849978.147, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338707, "tid": 2338707, + "ts": 6305204849990.147, "dur": 58.013, + "args": { + "External id": 704043,"Sequence number": 7674553, "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": 6305204849990.751, "dur": 6.929, + "args": { + "External id": 704044,"Sequence number": 7674553, "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": 6305204849990.751, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6305204849992.133, "dur": 4.594, + "args": { + "External id": 704045,"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": 6305204849995.781, "dur": 0.843, + "args": { + "External id": 704046,"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": 6305204849998.235, "dur": 49.605, + "args": { + "External id": 704047,"Sequence number": 7674554, "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": 6305204849999.077, "dur": 2.548, + "args": { + "External id": 704048,"Sequence number": 7674554, "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": 6305204849999.665, "dur": 1.817, + "args": { + "External id": 704049,"Sequence number": 7674554, "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": 6305204849999.665, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6305204850002.127, "dur": 41.694, + "args": { + "External id": 704050,"Sequence number": 7674555, "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": 6305204850002.127, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6305204850045.531, "dur": 1.886, + "args": { + "External id": 704051,"Sequence number": 7674556, "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": 6305204850045.531, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338707, "tid": 2338707, + "ts": 6305204850055.275, "dur": 106.148, + "args": { + "External id": 704052,"Sequence number": 7674557, "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": 6305204850093.794, "dur": 8.672, + "args": { + "External id": 704053,"Sequence number": 7674557, "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": 6305204850093.794, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6305204850095.913, "dur": 5.085, + "args": { + "External id": 704054,"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": 6305204850097.592, "dur": 2.835, + "args": { + "External id": 704055,"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": 6305204850103.289, "dur": 57.934, + "args": { + "External id": 704056,"Sequence number": 7674558, "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": 6305204850106.468, "dur": 4.487, + "args": { + "External id": 704057,"Sequence number": 7674558, "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": 6305204850107.037, "dur": 3.788, + "args": { + "External id": 704058,"Sequence number": 7674558, "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": 6305204850107.037, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6305204850111.578, "dur": 43.634, + "args": { + "External id": 704059,"Sequence number": 7674559, "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": 6305204850111.578, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6305204850156.681, "dur": 4.059, + "args": { + "External id": 704060,"Sequence number": 7674560, "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": 6305204850156.681, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6305204850181.377, "dur": 3.586, + "args": { + "External id": 704061,"Sequence number": 7674561, "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": 6305204850181.939, "dur": 2.814, + "args": { + "External id": 704062,"Sequence number": 7674561, "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": 6305204850181.939, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6305204850192.142, "dur": 4.343, + "args": { + "External id": 704063,"Sequence number": 7674562, "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": 6305204850192.971, "dur": 3.403, + "args": { + "External id": 704064,"Sequence number": 7674562, "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": 6305204850192.971, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6305204850200.274, "dur": 4.713, + "args": { + "External id": 704065,"Sequence number": 7674563, "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": 6305204850203.169, "dur": 1.709, + "args": { + "External id": 704066,"Sequence number": 7674563, "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": 6305204850203.169, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305204850236.803, "dur": 161.914, + "args": { + "External id": 704067,"Sequence number": 7674564, "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": 6305204850236.803, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338707, "tid": 2338707, + "ts": 6305204850257.275, "dur": 9.444, + "args": { + "External id": 704068,"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": 6305204850259.775, "dur": 6.420, + "args": { + "External id": 704069,"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": 6305204850410.374, "dur": 120.590, + "args": { + "External id": 704070,"Sequence number": 7674565, "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": 6305204850410.374, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338707, "tid": 2338707, + "ts": 6305204850423.134, "dur": 6.380, + "args": { + "External id": 704071,"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": 6305204850425.345, "dur": 3.774, + "args": { + "External id": 704072,"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": 6305204850563.631, "dur": 172.566, + "args": { + "External id": 704073,"Sequence number": 7674566, "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": 6305204850563.631, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338707, "tid": 2338707, + "ts": 6305204850590.369, "dur": 121.373, + "args": { + "External id": 704074,"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": 6305204850640.064, "dur": 7.145, + "args": { + "External id": 704075,"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": 6305204850642.234, "dur": 4.505, + "args": { + "External id": 704076,"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": 6305204850649.583, "dur": 3.677, + "args": { + "External id": 704077,"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": 6305204850654.380, "dur": 1.011, + "args": { + "External id": 704078,"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": 6305204850657.917, "dur": 3.139, + "args": { + "External id": 704079,"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": 6305204850722.715, "dur": 4.682, + "args": { + "External id": 704080,"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": 6305204850741.200, "dur": 5.362, + "args": { + "External id": 704081,"Sequence number": 7674567, "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": 6305204850742.496, "dur": 3.896, + "args": { + "External id": 704082,"Sequence number": 7674567, "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": 6305204850742.496, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338707, "tid": 2338707, + "ts": 6305204850758.751, "dur": 108.254, + "args": { + "External id": 704083,"Sequence number": 7674568, "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": 6305204850760.139, "dur": 9.974, + "args": { + "External id": 704084,"Sequence number": 7674568, "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": 6305204850760.139, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6305204850764.663, "dur": 4.390, + "args": { + "External id": 704085,"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": 6305204850767.071, "dur": 1.743, + "args": { + "External id": 704086,"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": 6305204850771.527, "dur": 95.213, + "args": { + "External id": 704087,"Sequence number": 7674569, "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": 6305204850773.263, "dur": 4.833, + "args": { + "External id": 704088,"Sequence number": 7674569, "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": 6305204850774.207, "dur": 3.744, + "args": { + "External id": 704089,"Sequence number": 7674569, "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": 6305204850774.207, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6305204850778.866, "dur": 79.443, + "args": { + "External id": 704090,"Sequence number": 7674570, "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": 6305204850778.866, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6305204850860.777, "dur": 5.265, + "args": { + "External id": 704091,"Sequence number": 7674571, "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": 6305204850860.777, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305204850900.557, "dur": 262.584, + "args": { + "External id": 704092,"Sequence number": 7674572, "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": 6305204850900.557, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6305204850919.330, "dur": 4.613, + "args": { + "External id": 704093,"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": 6305204850922.289, "dur": 1.462, + "args": { + "External id": 704094,"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": 6305204850927.543, "dur": 4.786, + "args": { + "External id": 704095,"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": 6305204850928.561, "dur": 3.660, + "args": { + "External id": 704096,"Record 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": 6305204850929.306, "dur": 2.824, + "args": { + "External id": 704097,"Record 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": 6305204850939.883, "dur": 5.906, + "args": { + "External id": 704098,"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": 6305204850941.351, "dur": 4.069, + "args": { + "External id": 704099,"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": 6305204850954.131, "dur": 2.774, + "args": { + "External id": 704100,"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": 6305204850960.015, "dur": 2.762, + "args": { + "External id": 704101,"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": 6305204851137.180, "dur": 4.253, + "args": { + "External id": 704102,"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": 6305204851138.158, "dur": 2.924, + "args": { + "External id": 704103,"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": 6305204851144.069, "dur": 1.955, + "args": { + "External id": 704104,"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": 6305204851144.784, "dur": 1.153, + "args": { + "External id": 704105,"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": 6305204851182.255, "dur": 102.336, + "args": { + "External id": 704106,"Sequence number": 7674573, "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": 6305204851183.369, "dur": 7.665, + "args": { + "External id": 704107,"Sequence number": 7674573, "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": 6305204851183.369, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6305204851186.255, "dur": 3.750, + "args": { + "External id": 704108,"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": 6305204851188.109, "dur": 1.655, + "args": { + "External id": 704109,"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": 6305204851192.212, "dur": 92.117, + "args": { + "External id": 704110,"Sequence number": 7674574, "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": 6305204851193.605, "dur": 5.579, + "args": { + "External id": 704111,"Sequence number": 7674574, "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": 6305204851196.601, "dur": 2.448, + "args": { + "External id": 704112,"Sequence number": 7674574, "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": 6305204851196.601, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6305204851200.246, "dur": 77.946, + "args": { + "External id": 704113,"Sequence number": 7674575, "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": 6305204851200.246, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6305204851280.592, "dur": 3.114, + "args": { + "External id": 704114,"Sequence number": 7674576, "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": 6305204851280.592, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338707, "tid": 2338707, + "ts": 6305204851292.675, "dur": 74.979, + "args": { + "External id": 704115,"Sequence number": 7674577, "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": 6305204851293.404, "dur": 10.280, + "args": { + "External id": 704116,"Sequence number": 7674577, "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": 6305204851293.404, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6305204851297.757, "dur": 4.507, + "args": { + "External id": 704117,"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": 6305204851299.244, "dur": 2.814, + "args": { + "External id": 704118,"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": 6305204851304.450, "dur": 63.026, + "args": { + "External id": 704119,"Sequence number": 7674578, "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": 6305204851305.265, "dur": 8.660, + "args": { + "External id": 704120,"Sequence number": 7674578, "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": 6305204851308.618, "dur": 4.960, + "args": { + "External id": 704121,"Sequence number": 7674578, "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": 6305204851308.618, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6305204851315.016, "dur": 46.642, + "args": { + "External id": 704122,"Sequence number": 7674579, "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": 6305204851315.016, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6305204851363.215, "dur": 3.905, + "args": { + "External id": 704123,"Sequence number": 7674580, "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": 6305204851363.215, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305204851389.593, "dur": 167.334, + "args": { + "External id": 704124,"Sequence number": 7674581, "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": 6305204851389.593, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6305204851431.225, "dur": 4.720, + "args": { + "External id": 704125,"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": 6305204851465.456, "dur": 76.709, + "args": { + "External id": 704126,"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": 6305204851466.258, "dur": 4.749, + "args": { + "External id": 704127,"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": 6305204851467.890, "dur": 1.972, + "args": { + "External id": 704128,"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": 6305204851469.074, "dur": 0.605, + "args": { + "External id": 704129,"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": 6305204851471.705, "dur": 70.089, + "args": { + "External id": 704130,"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": 6305204851473.076, "dur": 3.901, + "args": { + "External id": 704131,"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": 6305204851475.767, "dur": 1.126, + "args": { + "External id": 704132,"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": 6305204851477.616, "dur": 58.354, + "args": { + "External id": 704133,"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": 6305204851539.583, "dur": 1.442, + "args": { + "External id": 704134,"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": 6305204851565.977, "dur": 26.055, + "args": { + "External id": 704135,"Sequence number": 7674582, "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": 6305204851565.977, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::stack", "pid": 2338707, "tid": 2338707, + "ts": 6305204851611.911, "dur": 45.629, + "args": { + "External id": 704136,"Sequence number": 7674583, "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": 6305204851611.911, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::cat", "pid": 2338707, "tid": 2338707, + "ts": 6305204851621.987, "dur": 28.448, + "args": { + "External id": 704137,"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": 6305204851652.808, "dur": 3.183, + "args": { + "External id": 704138,"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": 6305204851695.973, "dur": 47.286, + "args": { + "External id": 704139,"Record function id": 0, "Ev Idx": 14543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 2/0", "pid": 2338707, "tid": 2338707, + "ts": 6305204851744.320, "dur": 197.536, + "args": { + "External id": 704140,"Record function id": 0, "Ev Idx": 14544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305204851782.725, "dur": 150.568, + "args": { + "External id": 704141,"Sequence number": 7674584, "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": 6305204851782.725, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6305204851855.613, "dur": 39.544, + "args": { + "External id": 704142,"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": 6305204852032.269, "dur": 75.564, + "args": { + "External id": 704143,"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": 6305204852035.207, "dur": 4.549, + "args": { + "External id": 704144,"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": 6305204852042.260, "dur": 65.060, + "args": { + "External id": 704145,"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": 6305204852045.850, "dur": 60.662, + "args": { + "External id": 704146,"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": 6305204852116.252, "dur": 20.092, + "args": { + "External id": 704147,"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": 6305204852117.429, "dur": 3.497, + "args": { + "External id": 704148,"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": 6305204852123.585, "dur": 12.507, + "args": { + "External id": 704149,"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": 6305204852124.338, "dur": 11.364, + "args": { + "External id": 704150,"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": 6305204852139.563, "dur": 15.797, + "args": { + "External id": 704151,"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": 6305204852140.118, "dur": 4.454, + "args": { + "External id": 704152,"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": 6305204852145.481, "dur": 9.620, + "args": { + "External id": 704153,"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": 6305204852146.086, "dur": 8.701, + "args": { + "External id": 704154,"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": 6305204852164.566, "dur": 0.688, + "args": { + "External id": 704155,"Sequence number": 7674585, "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": 6305204852175.136, "dur": 12.459, + "args": { + "External id": 704156,"Sequence number": 7674585, "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": 6305204852183.136, "dur": 2.305, + "args": { + "External id": 704157,"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": 6305204852193.814, "dur": 9.130, + "args": { + "External id": 704158,"Sequence number": 7674585, "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": 6305204852198.045, "dur": 3.169, + "args": { + "External id": 704159,"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": 6305204852204.623, "dur": 3.676, + "args": { + "External id": 704160,"Sequence number": 7674585, "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": 6305204852206.911, "dur": 0.710, + "args": { + "External id": 704161,"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": 6305204852209.744, "dur": 3.121, + "args": { + "External id": 704162,"Sequence number": 7674585, "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": 6305204852211.939, "dur": 0.414, + "args": { + "External id": 704163,"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": 6305204852216.021, "dur": 3.293, + "args": { + "External id": 704164,"Sequence number": 7674585, "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": 6305204852217.874, "dur": 0.898, + "args": { + "External id": 704165,"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": 6305204852220.446, "dur": 3.534, + "args": { + "External id": 704166,"Sequence number": 7674585, "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": 6305204852222.656, "dur": 0.457, + "args": { + "External id": 704167,"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": 6305204852224.841, "dur": 2.715, + "args": { + "External id": 704168,"Sequence number": 7674585, "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": 6305204852226.712, "dur": 0.350, + "args": { + "External id": 704169,"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": 6305204852231.598, "dur": 5.229, + "args": { + "External id": 704170,"Sequence number": 7674585, "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": 6305204852235.516, "dur": 0.488, + "args": { + "External id": 704171,"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": 6305204852241.094, "dur": 3.300, + "args": { + "External id": 704172,"Sequence number": 7674585, "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": 6305204852243.094, "dur": 0.774, + "args": { + "External id": 704173,"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": 6305204852250.465, "dur": 10.836, + "args": { + "External id": 704174,"Sequence number": 7674585, "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": 6305204852256.841, "dur": 3.310, + "args": { + "External id": 704175,"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": 6305204852262.616, "dur": 2.562, + "args": { + "External id": 704176,"Sequence number": 7674585, "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": 6305204852264.179, "dur": 0.472, + "args": { + "External id": 704177,"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": 6305204852267.689, "dur": 7.807, + "args": { + "External id": 704178,"Sequence number": 7674585, "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": 6305204852267.689, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2338707, + "ts": 6305204852273.116, "dur": 0.782, + "args": { + "External id": 704179,"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": 6305204852276.508, "dur": 5.181, + "args": { + "External id": 704180,"Sequence number": 7674586, "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": 6305204852276.508, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2338707, + "ts": 6305204852280.553, "dur": 0.408, + "args": { + "External id": 704181,"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": 6305204852282.591, "dur": 7.544, + "args": { + "External id": 704182,"Sequence number": 7674587, "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": 6305204852282.591, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2338707, + "ts": 6305204852288.568, "dur": 0.726, + "args": { + "External id": 704183,"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": 6305204852291.205, "dur": 4.807, + "args": { + "External id": 704184,"Sequence number": 7674588, "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": 6305204852291.205, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2338707, + "ts": 6305204852294.231, "dur": 1.050, + "args": { + "External id": 704185,"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": 6305204852299.949, "dur": 38.699, + "args": { + "External id": 704186,"Sequence number": 7674589, "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": 6305204852302.275, "dur": 36.147, + "args": { + "External id": 704187,"Sequence number": 7674589, "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": 6305204852305.436, "dur": 6.578, + "args": { + "External id": 704188,"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": 6305204852307.412, "dur": 4.029, + "args": { + "External id": 704189,"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": 6305204852313.545, "dur": 24.298, + "args": { + "External id": 704190,"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": 6305204852365.031, "dur": 5.783, + "args": { + "External id": 704191,"Sequence number": 7674589, "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": 6305204852365.031, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6305204852375.205, "dur": 3.534, + "args": { + "External id": 704192,"Sequence number": 7674590, "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": 6305204852405.522, "dur": 138606.792, + "args": { + "External id": 704193,"Sequence number": 7674590, "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": 6305204852405.522, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338707, "tid": 2338707, + "ts": 6305204852419.895, "dur": 28.456, + "args": { + "External id": 704194,"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": 6305204852420.849, "dur": 27.307, + "args": { + "External id": 704195,"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": 6305204852422.025, "dur": 5.827, + "args": { + "External id": 704196,"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": 6305204852423.777, "dur": 3.706, + "args": { + "External id": 704197,"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": 6305204852428.841, "dur": 18.833, + "args": { + "External id": 704198,"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": 6305204852467.734, "dur": 25.552, + "args": { + "External id": 704199,"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": 6305204852469.332, "dur": 5.393, + "args": { + "External id": 704200,"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": 6305204852471.481, "dur": 2.915, + "args": { + "External id": 704201,"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": 6305204852475.652, "dur": 17.442, + "args": { + "External id": 704202,"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": 6305204852478.822, "dur": 13.918, + "args": { + "External id": 704203,"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": 6305204852497.304, "dur": 33.546, + "args": { + "External id": 704204,"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": 6305204852498.204, "dur": 5.329, + "args": { + "External id": 704205,"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": 6305204852500.194, "dur": 3.129, + "args": { + "External id": 704206,"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": 6305204852504.346, "dur": 26.309, + "args": { + "External id": 704207,"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": 6305204852504.832, "dur": 25.205, + "args": { + "External id": 704208,"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": 6305204852537.358, "dur": 21.341, + "args": { + "External id": 704209,"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": 6305204852541.422, "dur": 3.420, + "args": { + "External id": 704210,"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": 6305204852545.572, "dur": 12.877, + "args": { + "External id": 704211,"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": 6305204852548.989, "dur": 9.134, + "args": { + "External id": 704212,"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": 6305204852566.414, "dur": 29.757, + "args": { + "External id": 704213,"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": 6305204852600.707, "dur": 68.344, + "args": { + "External id": 704214,"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": 6305204852604.829, "dur": 63.756, + "args": { + "External id": 704215,"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": 6305204852610.245, "dur": 0.947, + "args": { + "External id": 704216,"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": 6305204852613.213, "dur": 33.895, + "args": { + "External id": 704217,"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": 6305204852615.001, "dur": 31.902, + "args": { + "External id": 704218,"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": 6305204852626.265, "dur": 4.286, + "args": { + "External id": 704219,"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": 6305204852631.447, "dur": 15.077, + "args": { + "External id": 704220,"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": 6305204852676.207, "dur": 132364.681, + "args": { + "External id": 704221,"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": 6305204852678.334, "dur": 132360.011, + "args": { + "External id": 704222,"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": 6305204985086.465, "dur": 11.764, + "args": { + "External id": 704223,"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": 6305204985093.584, "dur": 2.049, + "args": { + "External id": 704224,"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": 6305204985105.132, "dur": 127.107, + "args": { + "External id": 704225,"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": 6305204985106.904, "dur": 7.478, + "args": { + "External id": 704226,"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": 6305204985109.893, "dur": 3.432, + "args": { + "External id": 704227,"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": 6305204985112.143, "dur": 0.916, + "args": { + "External id": 704228,"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": 6305204985115.782, "dur": 115.570, + "args": { + "External id": 704229,"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": 6305204985123.835, "dur": 106.537, + "args": { + "External id": 704230,"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": 6305204985236.977, "dur": 4.890, + "args": { + "External id": 704231,"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": 6305204985239.493, "dur": 0.747, + "args": { + "External id": 704232,"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": 6305204985253.234, "dur": 4.205, + "args": { + "External id": 704233,"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": 6305204985271.666, "dur": 8.998, + "args": { + "External id": 704234,"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": 6305204985274.524, "dur": 5.850, + "args": { + "External id": 704235,"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": 6305204985442.282, "dur": 286.166, + "args": { + "External id": 704236,"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": 6305204985447.411, "dur": 2.174, + "args": { + "External id": 704237,"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": 6305204985452.153, "dur": 275.580, + "args": { + "External id": 704238,"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": 6305204985455.566, "dur": 0.898, + "args": { + "External id": 704239,"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": 6305204985459.561, "dur": 33.198, + "args": { + "External id": 704240,"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": 6305204985495.330, "dur": 6.265, + "args": { + "External id": 704241,"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": 6305204985500.186, "dur": 0.887, + "args": { + "External id": 704242,"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": 6305204985503.621, "dur": 49.118, + "args": { + "External id": 704243,"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": 6305204985518.177, "dur": 2.577, + "args": { + "External id": 704244,"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": 6305204985526.068, "dur": 26.339, + "args": { + "External id": 704245,"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": 6305204985531.947, "dur": 3.617, + "args": { + "External id": 704246,"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": 6305204985559.824, "dur": 25.082, + "args": { + "External id": 704247,"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": 6305204985588.019, "dur": 29.719, + "args": { + "External id": 704248,"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": 6305204985623.144, "dur": 18.361, + "args": { + "External id": 704249,"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": 6305204985644.624, "dur": 17.023, + "args": { + "External id": 704250,"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": 6305204985664.508, "dur": 28.354, + "args": { + "External id": 704251,"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": 6305204985667.285, "dur": 1.835, + "args": { + "External id": 704252,"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": 6305204985674.037, "dur": 1.056, + "args": { + "External id": 704253,"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": 6305204985695.276, "dur": 16.261, + "args": { + "External id": 704254,"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": 6305204985713.650, "dur": 12.978, + "args": { + "External id": 704255,"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": 6305204985738.013, "dur": 2.926, + "args": { + "External id": 704256,"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": 6305204985749.113, "dur": 3.910, + "args": { + "External id": 704257,"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": 6305204985751.504, "dur": 0.486, + "args": { + "External id": 704258,"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": 6305204985849.006, "dur": 81.558, + "args": { + "External id": 704259,"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": 6305204985936.340, "dur": 7.848, + "args": { + "External id": 704260,"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": 6305204985941.826, "dur": 0.851, + "args": { + "External id": 704261,"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": 6305204985946.052, "dur": 34.963, + "args": { + "External id": 704262,"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": 6305204985987.621, "dur": 6.559, + "args": { + "External id": 704263,"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": 6305204985989.634, "dur": 3.685, + "args": { + "External id": 704264,"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": 6305204985991.445, "dur": 1.620, + "args": { + "External id": 704265,"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": 6305204985999.190, "dur": 91.591, + "args": { + "External id": 704266,"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": 6305204986002.742, "dur": 86.635, + "args": { + "External id": 704267,"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": 6305204986098.882, "dur": 21.513, + "args": { + "External id": 704268,"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": 6305204986129.563, "dur": 5.800, + "args": { + "External id": 704269,"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": 6305204986132.990, "dur": 1.112, + "args": { + "External id": 704270,"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": 6305204986140.370, "dur": 55.799, + "args": { + "External id": 704271,"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": 6305204986141.173, "dur": 6.420, + "args": { + "External id": 704272,"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": 6305204986142.480, "dur": 4.453, + "args": { + "External id": 704273,"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": 6305204986146.100, "dur": 0.654, + "args": { + "External id": 704274,"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": 6305204986148.678, "dur": 47.061, + "args": { + "External id": 704275,"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": 6305204986149.302, "dur": 45.804, + "args": { + "External id": 704276,"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": 6305204986201.306, "dur": 4.409, + "args": { + "External id": 704277,"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": 6305204986203.742, "dur": 0.542, + "args": { + "External id": 704278,"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": 6305204986213.089, "dur": 2.015, + "args": { + "External id": 704279,"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": 6305204986227.041, "dur": 8.877, + "args": { + "External id": 704280,"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": 6305204986229.413, "dur": 6.206, + "args": { + "External id": 704281,"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": 6305204986343.889, "dur": 216.878, + "args": { + "External id": 704282,"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": 6305204986345.969, "dur": 2.084, + "args": { + "External id": 704283,"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": 6305204986350.598, "dur": 209.737, + "args": { + "External id": 704284,"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": 6305204986352.327, "dur": 0.337, + "args": { + "External id": 704285,"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": 6305204986354.437, "dur": 26.541, + "args": { + "External id": 704286,"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": 6305204986385.390, "dur": 6.056, + "args": { + "External id": 704287,"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": 6305204986388.035, "dur": 2.948, + "args": { + "External id": 704288,"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": 6305204986393.029, "dur": 26.253, + "args": { + "External id": 704289,"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": 6305204986394.259, "dur": 1.281, + "args": { + "External id": 704290,"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": 6305204986397.050, "dur": 21.869, + "args": { + "External id": 704291,"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": 6305204986402.217, "dur": 2.326, + "args": { + "External id": 704292,"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": 6305204986421.144, "dur": 22.246, + "args": { + "External id": 704293,"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": 6305204986445.301, "dur": 14.593, + "args": { + "External id": 704294,"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": 6305204986462.788, "dur": 12.396, + "args": { + "External id": 704295,"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": 6305204986476.974, "dur": 12.340, + "args": { + "External id": 704296,"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": 6305204986491.452, "dur": 39.554, + "args": { + "External id": 704297,"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": 6305204986495.944, "dur": 2.374, + "args": { + "External id": 704298,"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": 6305204986500.737, "dur": 0.488, + "args": { + "External id": 704299,"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": 6305204986533.762, "dur": 13.663, + "args": { + "External id": 704300,"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": 6305204986548.557, "dur": 10.467, + "args": { + "External id": 704301,"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": 6305204986569.641, "dur": 3.014, + "args": { + "External id": 704302,"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": 6305204986583.407, "dur": 3.887, + "args": { + "External id": 704303,"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": 6305204986585.850, "dur": 0.528, + "args": { + "External id": 704304,"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": 6305204986663.684, "dur": 58.000, + "args": { + "External id": 704305,"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": 6305204986727.151, "dur": 5.290, + "args": { + "External id": 704306,"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": 6305204986730.469, "dur": 0.886, + "args": { + "External id": 704307,"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": 6305204986733.986, "dur": 24.602, + "args": { + "External id": 704308,"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": 6305204986763.252, "dur": 7.719, + "args": { + "External id": 704309,"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": 6305204986764.923, "dur": 5.295, + "args": { + "External id": 704310,"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": 6305204986769.203, "dur": 0.806, + "args": { + "External id": 704311,"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": 6305204986773.975, "dur": 42.714, + "args": { + "External id": 704312,"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": 6305204986775.045, "dur": 40.941, + "args": { + "External id": 704313,"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": 6305204986820.985, "dur": 13.113, + "args": { + "External id": 704314,"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": 6305204986840.409, "dur": 4.119, + "args": { + "External id": 704315,"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": 6305204986842.649, "dur": 1.021, + "args": { + "External id": 704316,"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": 6305204986848.746, "dur": 48.280, + "args": { + "External id": 704317,"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": 6305204986851.796, "dur": 6.346, + "args": { + "External id": 704318,"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": 6305204986852.846, "dur": 4.630, + "args": { + "External id": 704319,"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": 6305204986854.108, "dur": 3.132, + "args": { + "External id": 704320,"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": 6305204986859.118, "dur": 37.509, + "args": { + "External id": 704321,"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": 6305204986859.463, "dur": 36.508, + "args": { + "External id": 704322,"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": 6305204986901.165, "dur": 6.181, + "args": { + "External id": 704323,"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": 6305204986903.285, "dur": 2.773, + "args": { + "External id": 704324,"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": 6305204986914.979, "dur": 1.650, + "args": { + "External id": 704325,"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": 6305204986924.725, "dur": 5.646, + "args": { + "External id": 704326,"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": 6305204986926.573, "dur": 3.506, + "args": { + "External id": 704327,"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": 6305204987015.995, "dur": 234.626, + "args": { + "External id": 704328,"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": 6305204987017.913, "dur": 1.708, + "args": { + "External id": 704329,"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": 6305204987021.260, "dur": 228.850, + "args": { + "External id": 704330,"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": 6305204987024.904, "dur": 0.358, + "args": { + "External id": 704331,"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": 6305204987028.152, "dur": 19.846, + "args": { + "External id": 704332,"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": 6305204987049.813, "dur": 37.442, + "args": { + "External id": 704333,"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": 6305204987052.092, "dur": 34.320, + "args": { + "External id": 704334,"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": 6305204987088.956, "dur": 29.874, + "args": { + "External id": 704335,"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": 6305204987090.609, "dur": 3.848, + "args": { + "External id": 704336,"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": 6305204987095.826, "dur": 22.659, + "args": { + "External id": 704337,"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": 6305204987099.216, "dur": 2.910, + "args": { + "External id": 704338,"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": 6305204987120.698, "dur": 23.617, + "args": { + "External id": 704339,"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": 6305204987145.651, "dur": 12.208, + "args": { + "External id": 704340,"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": 6305204987163.206, "dur": 16.375, + "args": { + "External id": 704341,"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": 6305204987181.300, "dur": 13.287, + "args": { + "External id": 704342,"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": 6305204987196.362, "dur": 21.886, + "args": { + "External id": 704343,"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": 6305204987198.506, "dur": 1.415, + "args": { + "External id": 704344,"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": 6305204987202.735, "dur": 0.791, + "args": { + "External id": 704345,"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": 6305204987219.614, "dur": 11.619, + "args": { + "External id": 704346,"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": 6305204987234.738, "dur": 14.282, + "args": { + "External id": 704347,"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": 6305204987259.062, "dur": 2.531, + "args": { + "External id": 704348,"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": 6305204987272.338, "dur": 4.368, + "args": { + "External id": 704349,"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": 6305204987275.158, "dur": 0.551, + "args": { + "External id": 704350,"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": 6305204987348.647, "dur": 61.313, + "args": { + "External id": 704351,"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": 6305204987415.683, "dur": 4.872, + "args": { + "External id": 704352,"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": 6305204987418.651, "dur": 0.662, + "args": { + "External id": 704353,"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": 6305204987422.340, "dur": 25.185, + "args": { + "External id": 704354,"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": 6305204987453.994, "dur": 5.140, + "args": { + "External id": 704355,"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": 6305204987455.553, "dur": 2.750, + "args": { + "External id": 704356,"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": 6305204987457.442, "dur": 0.708, + "args": { + "External id": 704357,"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": 6305204987461.674, "dur": 43.076, + "args": { + "External id": 704358,"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": 6305204987462.881, "dur": 40.940, + "args": { + "External id": 704359,"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": 6305204987525.378, "dur": 17.610, + "args": { + "External id": 704360,"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": 6305204987550.392, "dur": 6.599, + "args": { + "External id": 704361,"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": 6305204987554.994, "dur": 0.839, + "args": { + "External id": 704362,"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": 6305204987560.845, "dur": 54.335, + "args": { + "External id": 704363,"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": 6305204987561.858, "dur": 6.972, + "args": { + "External id": 704364,"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": 6305204987562.902, "dur": 5.298, + "args": { + "External id": 704365,"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": 6305204987567.318, "dur": 0.753, + "args": { + "External id": 704366,"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": 6305204987569.432, "dur": 45.322, + "args": { + "External id": 704367,"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": 6305204987572.471, "dur": 41.663, + "args": { + "External id": 704368,"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": 6305204987619.829, "dur": 3.980, + "args": { + "External id": 704369,"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": 6305204987621.902, "dur": 0.747, + "args": { + "External id": 704370,"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": 6305204987630.532, "dur": 1.904, + "args": { + "External id": 704371,"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": 6305204987640.489, "dur": 6.481, + "args": { + "External id": 704372,"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": 6305204987642.744, "dur": 3.952, + "args": { + "External id": 704373,"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": 6305204987737.235, "dur": 174.543, + "args": { + "External id": 704374,"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": 6305204987739.741, "dur": 4.033, + "args": { + "External id": 704375,"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": 6305204987745.308, "dur": 165.966, + "args": { + "External id": 704376,"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": 6305204987749.242, "dur": 0.388, + "args": { + "External id": 704377,"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": 6305204987751.021, "dur": 19.588, + "args": { + "External id": 704378,"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": 6305204987772.382, "dur": 3.599, + "args": { + "External id": 704379,"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": 6305204987775.160, "dur": 0.616, + "args": { + "External id": 704380,"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": 6305204987777.057, "dur": 23.907, + "args": { + "External id": 704381,"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": 6305204987779.980, "dur": 1.186, + "args": { + "External id": 704382,"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": 6305204987784.823, "dur": 15.872, + "args": { + "External id": 704383,"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": 6305204987787.929, "dur": 2.276, + "args": { + "External id": 704384,"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": 6305204987802.531, "dur": 18.787, + "args": { + "External id": 704385,"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": 6305204987822.583, "dur": 13.625, + "args": { + "External id": 704386,"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": 6305204987838.534, "dur": 12.124, + "args": { + "External id": 704387,"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": 6305204987852.178, "dur": 12.082, + "args": { + "External id": 704388,"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": 6305204987865.855, "dur": 17.856, + "args": { + "External id": 704389,"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": 6305204987868.049, "dur": 1.299, + "args": { + "External id": 704390,"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": 6305204987871.180, "dur": 0.474, + "args": { + "External id": 704391,"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": 6305204987887.288, "dur": 11.200, + "args": { + "External id": 704392,"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": 6305204987899.503, "dur": 10.685, + "args": { + "External id": 704393,"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": 6305204987917.873, "dur": 1.965, + "args": { + "External id": 704394,"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": 6305204987928.827, "dur": 4.273, + "args": { + "External id": 704395,"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": 6305204987931.760, "dur": 0.435, + "args": { + "External id": 704396,"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": 6305204987994.157, "dur": 49.692, + "args": { + "External id": 704397,"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": 6305204988048.794, "dur": 42.443, + "args": { + "External id": 704398,"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": 6305204988051.894, "dur": 37.031, + "args": { + "External id": 704399,"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": 6305204988095.782, "dur": 27.667, + "args": { + "External id": 704400,"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": 6305204988129.263, "dur": 6.113, + "args": { + "External id": 704401,"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": 6305204988130.789, "dur": 3.885, + "args": { + "External id": 704402,"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": 6305204988133.625, "dur": 0.857, + "args": { + "External id": 704403,"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": 6305204988138.779, "dur": 46.326, + "args": { + "External id": 704404,"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": 6305204988139.911, "dur": 44.738, + "args": { + "External id": 704405,"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": 6305204988189.080, "dur": 14.324, + "args": { + "External id": 704406,"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": 6305204988212.922, "dur": 3.852, + "args": { + "External id": 704407,"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": 6305204988215.237, "dur": 0.613, + "args": { + "External id": 704408,"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": 6305204988221.120, "dur": 48.513, + "args": { + "External id": 704409,"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": 6305204988222.014, "dur": 4.510, + "args": { + "External id": 704410,"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": 6305204988222.983, "dur": 2.953, + "args": { + "External id": 704411,"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": 6305204988225.169, "dur": 0.620, + "args": { + "External id": 704412,"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": 6305204988229.713, "dur": 39.574, + "args": { + "External id": 704413,"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": 6305204988230.155, "dur": 38.610, + "args": { + "External id": 704414,"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": 6305204988273.954, "dur": 3.936, + "args": { + "External id": 704415,"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": 6305204988276.160, "dur": 0.402, + "args": { + "External id": 704416,"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": 6305204988284.288, "dur": 1.378, + "args": { + "External id": 704417,"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": 6305204988293.760, "dur": 8.788, + "args": { + "External id": 704418,"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": 6305204988298.541, "dur": 3.750, + "args": { + "External id": 704419,"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": 6305204988389.407, "dur": 208.808, + "args": { + "External id": 704420,"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": 6305204988391.341, "dur": 3.418, + "args": { + "External id": 704421,"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": 6305204988396.132, "dur": 201.448, + "args": { + "External id": 704422,"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": 6305204988397.377, "dur": 0.343, + "args": { + "External id": 704423,"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": 6305204988398.783, "dur": 21.953, + "args": { + "External id": 704424,"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": 6305204988422.249, "dur": 5.125, + "args": { + "External id": 704425,"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": 6305204988426.505, "dur": 0.693, + "args": { + "External id": 704426,"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": 6305204988428.314, "dur": 26.369, + "args": { + "External id": 704427,"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": 6305204988431.599, "dur": 1.295, + "args": { + "External id": 704428,"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": 6305204988434.368, "dur": 20.035, + "args": { + "External id": 704429,"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": 6305204988437.354, "dur": 3.196, + "args": { + "External id": 704430,"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": 6305204988456.076, "dur": 21.802, + "args": { + "External id": 704431,"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": 6305204988479.166, "dur": 13.984, + "args": { + "External id": 704432,"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": 6305204988496.036, "dur": 31.465, + "args": { + "External id": 704433,"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": 6305204988530.020, "dur": 14.054, + "args": { + "External id": 704434,"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": 6305204988546.197, "dur": 23.928, + "args": { + "External id": 704435,"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": 6305204988550.001, "dur": 1.969, + "args": { + "External id": 704436,"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": 6305204988556.085, "dur": 0.969, + "args": { + "External id": 704437,"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": 6305204988571.628, "dur": 11.504, + "args": { + "External id": 704438,"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": 6305204988584.167, "dur": 12.497, + "args": { + "External id": 704439,"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": 6305204988605.914, "dur": 2.480, + "args": { + "External id": 704440,"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": 6305204988617.490, "dur": 4.409, + "args": { + "External id": 704441,"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": 6305204988620.463, "dur": 0.587, + "args": { + "External id": 704442,"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": 6305204988686.344, "dur": 56.960, + "args": { + "External id": 704443,"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": 6305204988750.226, "dur": 4.779, + "args": { + "External id": 704444,"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": 6305204988753.191, "dur": 0.816, + "args": { + "External id": 704445,"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": 6305204988756.578, "dur": 24.513, + "args": { + "External id": 704446,"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": 6305204988785.304, "dur": 6.003, + "args": { + "External id": 704447,"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": 6305204988786.937, "dur": 3.663, + "args": { + "External id": 704448,"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": 6305204988789.330, "dur": 1.130, + "args": { + "External id": 704449,"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": 6305204988796.108, "dur": 40.879, + "args": { + "External id": 704450,"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": 6305204988797.071, "dur": 39.187, + "args": { + "External id": 704451,"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": 6305204988840.462, "dur": 16.117, + "args": { + "External id": 704452,"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": 6305204988861.727, "dur": 3.718, + "args": { + "External id": 704453,"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": 6305204988863.918, "dur": 0.647, + "args": { + "External id": 704454,"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": 6305204988869.280, "dur": 46.580, + "args": { + "External id": 704455,"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": 6305204988869.927, "dur": 6.111, + "args": { + "External id": 704456,"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": 6305204988872.952, "dur": 2.571, + "args": { + "External id": 704457,"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": 6305204988874.814, "dur": 0.580, + "args": { + "External id": 704458,"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": 6305204988876.572, "dur": 38.999, + "args": { + "External id": 704459,"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": 6305204988877.223, "dur": 37.739, + "args": { + "External id": 704460,"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": 6305204988919.734, "dur": 4.326, + "args": { + "External id": 704461,"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": 6305204988922.459, "dur": 0.395, + "args": { + "External id": 704462,"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": 6305204988929.560, "dur": 1.277, + "args": { + "External id": 704463,"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": 6305204988946.132, "dur": 9.294, + "args": { + "External id": 704464,"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": 6305204988948.025, "dur": 7.110, + "args": { + "External id": 704465,"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": 6305204989040.862, "dur": 227.469, + "args": { + "External id": 704466,"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": 6305204989042.925, "dur": 1.845, + "args": { + "External id": 704467,"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": 6305204989046.072, "dur": 221.811, + "args": { + "External id": 704468,"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": 6305204989047.799, "dur": 0.544, + "args": { + "External id": 704469,"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": 6305204989083.993, "dur": 29.810, + "args": { + "External id": 704470,"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": 6305204989116.692, "dur": 3.495, + "args": { + "External id": 704471,"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": 6305204989118.686, "dur": 1.250, + "args": { + "External id": 704472,"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": 6305204989121.014, "dur": 24.090, + "args": { + "External id": 704473,"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": 6305204989122.051, "dur": 1.777, + "args": { + "External id": 704474,"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": 6305204989124.982, "dur": 19.828, + "args": { + "External id": 704475,"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": 6305204989129.814, "dur": 2.212, + "args": { + "External id": 704476,"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": 6305204989146.579, "dur": 20.467, + "args": { + "External id": 704477,"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": 6305204989168.359, "dur": 13.619, + "args": { + "External id": 704478,"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": 6305204989184.733, "dur": 13.120, + "args": { + "External id": 704479,"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": 6305204989199.540, "dur": 14.136, + "args": { + "External id": 704480,"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": 6305204989220.570, "dur": 20.324, + "args": { + "External id": 704481,"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": 6305204989222.644, "dur": 1.414, + "args": { + "External id": 704482,"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": 6305204989225.831, "dur": 0.847, + "args": { + "External id": 704483,"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": 6305204989241.993, "dur": 13.080, + "args": { + "External id": 704484,"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": 6305204989256.045, "dur": 10.717, + "args": { + "External id": 704485,"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": 6305204989277.189, "dur": 2.054, + "args": { + "External id": 704486,"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": 6305204989289.245, "dur": 4.025, + "args": { + "External id": 704487,"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": 6305204989291.679, "dur": 0.640, + "args": { + "External id": 704488,"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": 6305204989367.020, "dur": 64.662, + "args": { + "External id": 704489,"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": 6305204989437.496, "dur": 7.044, + "args": { + "External id": 704490,"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": 6305204989440.433, "dur": 2.842, + "args": { + "External id": 704491,"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": 6305204989446.113, "dur": 25.755, + "args": { + "External id": 704492,"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": 6305204989476.727, "dur": 7.693, + "args": { + "External id": 704493,"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": 6305204989478.762, "dur": 4.810, + "args": { + "External id": 704494,"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": 6305204989482.623, "dur": 0.773, + "args": { + "External id": 704495,"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": 6305204989487.232, "dur": 62.148, + "args": { + "External id": 704496,"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": 6305204989488.660, "dur": 59.743, + "args": { + "External id": 704497,"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": 6305204989555.140, "dur": 17.501, + "args": { + "External id": 704498,"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": 6305204989579.726, "dur": 4.224, + "args": { + "External id": 704499,"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": 6305204989581.875, "dur": 0.839, + "args": { + "External id": 704500,"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": 6305204989588.420, "dur": 51.551, + "args": { + "External id": 704501,"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": 6305204989591.636, "dur": 3.611, + "args": { + "External id": 704502,"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": 6305204989592.650, "dur": 1.969, + "args": { + "External id": 704503,"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": 6305204989593.692, "dur": 0.786, + "args": { + "External id": 704504,"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": 6305204989596.019, "dur": 43.535, + "args": { + "External id": 704505,"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": 6305204989596.791, "dur": 42.269, + "args": { + "External id": 704506,"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": 6305204989644.276, "dur": 3.925, + "args": { + "External id": 704507,"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": 6305204989646.272, "dur": 0.722, + "args": { + "External id": 704508,"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": 6305204989657.234, "dur": 2.007, + "args": { + "External id": 704509,"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": 6305204989667.448, "dur": 6.926, + "args": { + "External id": 704510,"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": 6305204989669.726, "dur": 4.410, + "args": { + "External id": 704511,"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": 6305204989762.534, "dur": 205.320, + "args": { + "External id": 704512,"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": 6305204989782.103, "dur": 3.376, + "args": { + "External id": 704513,"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": 6305204989790.772, "dur": 176.576, + "args": { + "External id": 704514,"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": 6305204989794.468, "dur": 0.337, + "args": { + "External id": 704515,"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": 6305204989796.233, "dur": 21.995, + "args": { + "External id": 704516,"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": 6305204989819.853, "dur": 6.142, + "args": { + "External id": 704517,"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": 6305204989825.135, "dur": 0.690, + "args": { + "External id": 704518,"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": 6305204989827.050, "dur": 21.810, + "args": { + "External id": 704519,"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": 6305204989827.796, "dur": 1.147, + "args": { + "External id": 704520,"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": 6305204989830.007, "dur": 18.543, + "args": { + "External id": 704521,"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": 6305204989832.811, "dur": 2.513, + "args": { + "External id": 704522,"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": 6305204989850.236, "dur": 23.995, + "args": { + "External id": 704523,"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": 6305204989875.667, "dur": 12.693, + "args": { + "External id": 704524,"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": 6305204989893.228, "dur": 12.849, + "args": { + "External id": 704525,"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": 6305204989907.362, "dur": 10.958, + "args": { + "External id": 704526,"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": 6305204989920.311, "dur": 20.553, + "args": { + "External id": 704527,"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": 6305204989922.210, "dur": 1.323, + "args": { + "External id": 704528,"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": 6305204989925.874, "dur": 2.503, + "args": { + "External id": 704529,"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": 6305204989942.160, "dur": 11.154, + "args": { + "External id": 704530,"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": 6305204989956.156, "dur": 10.225, + "args": { + "External id": 704531,"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": 6305204989974.775, "dur": 1.661, + "args": { + "External id": 704532,"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": 6305204989985.063, "dur": 3.785, + "args": { + "External id": 704533,"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": 6305204989987.554, "dur": 0.376, + "args": { + "External id": 704534,"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": 6305204990049.514, "dur": 96.108, + "args": { + "External id": 704535,"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": 6305204990153.436, "dur": 5.849, + "args": { + "External id": 704536,"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": 6305204990157.249, "dur": 0.696, + "args": { + "External id": 704537,"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": 6305204990160.953, "dur": 25.783, + "args": { + "External id": 704538,"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": 6305204990194.298, "dur": 6.003, + "args": { + "External id": 704539,"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": 6305204990195.959, "dur": 3.632, + "args": { + "External id": 704540,"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": 6305204990198.033, "dur": 1.327, + "args": { + "External id": 704541,"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": 6305204990204.088, "dur": 42.693, + "args": { + "External id": 704542,"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": 6305204990205.346, "dur": 40.957, + "args": { + "External id": 704543,"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": 6305204990250.643, "dur": 14.445, + "args": { + "External id": 704544,"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": 6305204990271.196, "dur": 5.558, + "args": { + "External id": 704545,"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": 6305204990275.378, "dur": 0.597, + "args": { + "External id": 704546,"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": 6305204990281.417, "dur": 46.622, + "args": { + "External id": 704547,"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": 6305204990282.258, "dur": 4.035, + "args": { + "External id": 704548,"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": 6305204990283.032, "dur": 2.687, + "args": { + "External id": 704549,"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": 6305204990284.946, "dur": 0.644, + "args": { + "External id": 704550,"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": 6305204990286.828, "dur": 40.708, + "args": { + "External id": 704551,"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": 6305204990289.683, "dur": 37.412, + "args": { + "External id": 704552,"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": 6305204990331.952, "dur": 3.803, + "args": { + "External id": 704553,"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": 6305204990334.002, "dur": 0.590, + "args": { + "External id": 704554,"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": 6305204990342.121, "dur": 1.580, + "args": { + "External id": 704555,"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": 6305204990351.942, "dur": 6.137, + "args": { + "External id": 704556,"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": 6305204990353.929, "dur": 3.886, + "args": { + "External id": 704557,"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": 6305204990444.259, "dur": 196.721, + "args": { + "External id": 704558,"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": 6305204990448.561, "dur": 3.971, + "args": { + "External id": 704559,"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": 6305204990454.453, "dur": 185.950, + "args": { + "External id": 704560,"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": 6305204990456.104, "dur": 0.346, + "args": { + "External id": 704561,"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": 6305204990457.653, "dur": 20.402, + "args": { + "External id": 704562,"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": 6305204990479.577, "dur": 5.036, + "args": { + "External id": 704563,"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": 6305204990483.966, "dur": 0.454, + "args": { + "External id": 704564,"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": 6305204990485.480, "dur": 38.864, + "args": { + "External id": 704565,"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": 6305204990486.603, "dur": 1.391, + "args": { + "External id": 704566,"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": 6305204990491.603, "dur": 32.126, + "args": { + "External id": 704567,"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": 6305204990494.598, "dur": 1.977, + "args": { + "External id": 704568,"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": 6305204990526.326, "dur": 21.404, + "args": { + "External id": 704569,"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": 6305204990549.295, "dur": 14.598, + "args": { + "External id": 704570,"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": 6305204990566.135, "dur": 12.936, + "args": { + "External id": 704571,"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": 6305204990580.509, "dur": 10.826, + "args": { + "External id": 704572,"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": 6305204990593.584, "dur": 19.060, + "args": { + "External id": 704573,"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": 6305204990595.498, "dur": 1.577, + "args": { + "External id": 704574,"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": 6305204990599.358, "dur": 0.530, + "args": { + "External id": 704575,"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": 6305204990616.117, "dur": 11.658, + "args": { + "External id": 704576,"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": 6305204990628.752, "dur": 10.740, + "args": { + "External id": 704577,"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": 6305204990648.900, "dur": 2.026, + "args": { + "External id": 704578,"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": 6305204990659.977, "dur": 3.755, + "args": { + "External id": 704579,"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": 6305204990662.498, "dur": 0.386, + "args": { + "External id": 704580,"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": 6305204990733.599, "dur": 55.949, + "args": { + "External id": 704581,"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": 6305204990794.441, "dur": 4.110, + "args": { + "External id": 704582,"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": 6305204990796.887, "dur": 0.779, + "args": { + "External id": 704583,"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": 6305204990802.545, "dur": 24.355, + "args": { + "External id": 704584,"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": 6305204990831.339, "dur": 5.855, + "args": { + "External id": 704585,"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": 6305204990832.846, "dur": 3.666, + "args": { + "External id": 704586,"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": 6305204990835.151, "dur": 1.178, + "args": { + "External id": 704587,"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": 6305204990839.625, "dur": 39.594, + "args": { + "External id": 704588,"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": 6305204990840.344, "dur": 38.207, + "args": { + "External id": 704589,"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": 6305204990882.779, "dur": 15.489, + "args": { + "External id": 704590,"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": 6305204990905.471, "dur": 25.493, + "args": { + "External id": 704591,"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": 6305204990907.411, "dur": 23.103, + "args": { + "External id": 704592,"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": 6305204990911.984, "dur": 1.807, + "args": { + "External id": 704593,"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": 6305204990936.638, "dur": 29.707, + "args": { + "External id": 704594,"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": 6305204990938.568, "dur": 27.544, + "args": { + "External id": 704595,"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": 6305204990943.195, "dur": 3.731, + "args": { + "External id": 704596,"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": 6305204990948.215, "dur": 17.393, + "args": { + "External id": 704597,"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": 6305204990979.831, "dur": 7.843, + "args": { + "External id": 704598,"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": 6305204990984.266, "dur": 3.124, + "args": { + "External id": 704599,"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": 6305204990988.914, "dur": 0.896, + "args": { + "External id": 704600,"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": 6305204990989.234, "dur": 0.498, + "args": { + "External id": 704601,"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": 6305204991031.373, "dur": 100.630, + "args": { + "External id": 704602,"Sequence number": 7674591, "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": 6305204991031.373, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338707, "tid": 2338707, + "ts": 6305204991141.585, "dur": 7.356, + "args": { + "External id": 704603,"Sequence number": 7674592, "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": 6305204991145.839, "dur": 1.200, + "args": { + "External id": 704604,"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": 6305204991151.475, "dur": 8.619, + "args": { + "External id": 704605,"Sequence number": 7674592, "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": 6305204991158.442, "dur": 0.379, + "args": { + "External id": 704606,"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": 6305204991161.279, "dur": 2.713, + "args": { + "External id": 704607,"Sequence number": 7674592, "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": 6305204991162.808, "dur": 0.534, + "args": { + "External id": 704608,"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": 6305204991169.001, "dur": 6.825, + "args": { + "External id": 704609,"Sequence number": 7674592, "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": 6305204991169.001, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2338707, + "ts": 6305204991173.096, "dur": 0.893, + "args": { + "External id": 704610,"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": 6305204991178.911, "dur": 4.797, + "args": { + "External id": 704611,"Sequence number": 7674593, "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": 6305204991178.911, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2338707, + "ts": 6305204991182.424, "dur": 0.453, + "args": { + "External id": 704612,"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": 6305204991184.726, "dur": 4.864, + "args": { + "External id": 704613,"Sequence number": 7674594, "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": 6305204991184.726, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2338707, + "ts": 6305204991188.133, "dur": 0.588, + "args": { + "External id": 704614,"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": 6305204991190.526, "dur": 7.655, + "args": { + "External id": 704615,"Sequence number": 7674595, "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": 6305204991190.526, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2338707, + "ts": 6305204991194.172, "dur": 3.262, + "args": { + "External id": 704616,"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": 6305204991202.055, "dur": 44.566, + "args": { + "External id": 704617,"Sequence number": 7674596, "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": 6305204991206.096, "dur": 40.248, + "args": { + "External id": 704618,"Sequence number": 7674596, "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": 6305204991208.922, "dur": 10.370, + "args": { + "External id": 704619,"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": 6305204991213.508, "dur": 5.057, + "args": { + "External id": 704620,"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": 6305204991220.381, "dur": 25.504, + "args": { + "External id": 704621,"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": 6305204991273.856, "dur": 4.046, + "args": { + "External id": 704622,"Sequence number": 7674596, "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": 6305204991273.856, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6305204991280.239, "dur": 1.025, + "args": { + "External id": 704623,"Sequence number": 7674597, "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": 6305204991316.071, "dur": 47413.209, + "args": { + "External id": 704624,"Sequence number": 7674597, "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": 6305204991316.071, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338707, "tid": 2338707, + "ts": 6305204991332.566, "dur": 23.135, + "args": { + "External id": 704625,"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": 6305204991333.272, "dur": 22.212, + "args": { + "External id": 704626,"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": 6305204991334.899, "dur": 4.593, + "args": { + "External id": 704627,"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": 6305204991336.172, "dur": 2.896, + "args": { + "External id": 704628,"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": 6305204991340.128, "dur": 14.869, + "args": { + "External id": 704629,"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": 6305204991372.001, "dur": 27.278, + "args": { + "External id": 704630,"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": 6305204991373.054, "dur": 6.172, + "args": { + "External id": 704631,"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": 6305204991375.750, "dur": 3.181, + "args": { + "External id": 704632,"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": 6305204991380.405, "dur": 18.629, + "args": { + "External id": 704633,"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": 6305204991382.144, "dur": 16.440, + "args": { + "External id": 704634,"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": 6305204991402.982, "dur": 21.643, + "args": { + "External id": 704635,"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": 6305204991403.863, "dur": 6.877, + "args": { + "External id": 704636,"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": 6305204991406.997, "dur": 3.482, + "args": { + "External id": 704637,"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": 6305204991411.280, "dur": 13.133, + "args": { + "External id": 704638,"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": 6305204991411.726, "dur": 12.242, + "args": { + "External id": 704639,"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": 6305204991430.970, "dur": 16.089, + "args": { + "External id": 704640,"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": 6305204991432.412, "dur": 2.436, + "args": { + "External id": 704641,"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": 6305204991435.728, "dur": 11.062, + "args": { + "External id": 704642,"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": 6305204991436.509, "dur": 10.010, + "args": { + "External id": 704643,"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": 6305204991454.367, "dur": 23.493, + "args": { + "External id": 704644,"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": 6305204991480.760, "dur": 65.695, + "args": { + "External id": 704645,"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": 6305204991482.853, "dur": 63.178, + "args": { + "External id": 704646,"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": 6305204991486.860, "dur": 2.308, + "args": { + "External id": 704647,"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": 6305204991490.240, "dur": 36.986, + "args": { + "External id": 704648,"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": 6305204991491.924, "dur": 35.100, + "args": { + "External id": 704649,"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": 6305204991494.635, "dur": 2.698, + "args": { + "External id": 704650,"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": 6305204991498.057, "dur": 28.304, + "args": { + "External id": 704651,"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": 6305204991551.387, "dur": 41434.132, + "args": { + "External id": 704652,"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": 6305204991552.971, "dur": 41431.038, + "args": { + "External id": 704653,"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": 6305205032998.928, "dur": 10.362, + "args": { + "External id": 704654,"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": 6305205033006.136, "dur": 1.146, + "args": { + "External id": 704655,"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": 6305205033014.892, "dur": 146.589, + "args": { + "External id": 704656,"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": 6305205033016.472, "dur": 6.576, + "args": { + "External id": 704657,"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": 6305205033019.072, "dur": 3.107, + "args": { + "External id": 704658,"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": 6305205033021.139, "dur": 0.744, + "args": { + "External id": 704659,"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": 6305205033024.274, "dur": 136.175, + "args": { + "External id": 704660,"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": 6305205033028.500, "dur": 130.482, + "args": { + "External id": 704661,"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": 6305205033167.469, "dur": 6.180, + "args": { + "External id": 704662,"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": 6305205033170.814, "dur": 0.882, + "args": { + "External id": 704663,"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": 6305205033181.927, "dur": 2.503, + "args": { + "External id": 704664,"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": 6305205033196.030, "dur": 6.924, + "args": { + "External id": 704665,"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": 6305205033198.025, "dur": 4.664, + "args": { + "External id": 704666,"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": 6305205033339.256, "dur": 222.539, + "args": { + "External id": 704667,"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": 6305205033343.593, "dur": 3.905, + "args": { + "External id": 704668,"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": 6305205033349.286, "dur": 211.831, + "args": { + "External id": 704669,"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": 6305205033350.993, "dur": 0.442, + "args": { + "External id": 704670,"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": 6305205033353.107, "dur": 27.082, + "args": { + "External id": 704671,"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": 6305205033382.502, "dur": 5.486, + "args": { + "External id": 704672,"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": 6305205033386.764, "dur": 0.840, + "args": { + "External id": 704673,"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": 6305205033389.250, "dur": 26.341, + "args": { + "External id": 704674,"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": 6305205033390.354, "dur": 0.933, + "args": { + "External id": 704675,"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": 6305205033395.249, "dur": 20.068, + "args": { + "External id": 704676,"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": 6305205033398.841, "dur": 3.029, + "args": { + "External id": 704677,"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": 6305205033417.511, "dur": 24.133, + "args": { + "External id": 704678,"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": 6305205033443.950, "dur": 17.299, + "args": { + "External id": 704679,"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": 6305205033464.268, "dur": 16.103, + "args": { + "External id": 704680,"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": 6305205033481.876, "dur": 12.869, + "args": { + "External id": 704681,"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": 6305205033496.503, "dur": 35.440, + "args": { + "External id": 704682,"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": 6305205033498.699, "dur": 1.471, + "args": { + "External id": 704683,"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": 6305205033503.940, "dur": 0.493, + "args": { + "External id": 704684,"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": 6305205033534.635, "dur": 12.958, + "args": { + "External id": 704685,"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": 6305205033549.094, "dur": 10.973, + "args": { + "External id": 704686,"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": 6305205033570.577, "dur": 2.300, + "args": { + "External id": 704687,"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": 6305205033580.457, "dur": 3.757, + "args": { + "External id": 704688,"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": 6305205033582.646, "dur": 0.564, + "args": { + "External id": 704689,"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": 6305205033660.127, "dur": 73.668, + "args": { + "External id": 704690,"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": 6305205033739.499, "dur": 9.386, + "args": { + "External id": 704691,"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": 6305205033745.322, "dur": 0.915, + "args": { + "External id": 704692,"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": 6305205033750.611, "dur": 26.961, + "args": { + "External id": 704693,"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": 6305205033783.067, "dur": 9.312, + "args": { + "External id": 704694,"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": 6305205033785.331, "dur": 6.373, + "args": { + "External id": 704695,"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": 6305205033787.546, "dur": 3.873, + "args": { + "External id": 704696,"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": 6305205033795.506, "dur": 48.419, + "args": { + "External id": 704697,"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": 6305205033799.034, "dur": 44.271, + "args": { + "External id": 704698,"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": 6305205033850.702, "dur": 14.861, + "args": { + "External id": 704699,"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": 6305205033872.259, "dur": 3.380, + "args": { + "External id": 704700,"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": 6305205033874.209, "dur": 0.392, + "args": { + "External id": 704701,"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": 6305205033879.836, "dur": 47.628, + "args": { + "External id": 704702,"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": 6305205033880.991, "dur": 6.518, + "args": { + "External id": 704703,"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": 6305205033884.798, "dur": 2.092, + "args": { + "External id": 704704,"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": 6305205033886.071, "dur": 0.478, + "args": { + "External id": 704705,"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": 6305205033888.044, "dur": 39.017, + "args": { + "External id": 704706,"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": 6305205033888.455, "dur": 38.067, + "args": { + "External id": 704707,"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": 6305205033931.509, "dur": 4.124, + "args": { + "External id": 704708,"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": 6305205033933.670, "dur": 0.378, + "args": { + "External id": 704709,"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": 6305205033941.404, "dur": 1.563, + "args": { + "External id": 704710,"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": 6305205033953.379, "dur": 7.885, + "args": { + "External id": 704711,"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": 6305205033955.183, "dur": 5.788, + "args": { + "External id": 704712,"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": 6305205034091.503, "dur": 187.509, + "args": { + "External id": 704713,"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": 6305205034093.952, "dur": 2.700, + "args": { + "External id": 704714,"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": 6305205034098.604, "dur": 180.000, + "args": { + "External id": 704715,"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": 6305205034100.326, "dur": 0.332, + "args": { + "External id": 704716,"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": 6305205034104.178, "dur": 28.951, + "args": { + "External id": 704717,"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": 6305205034134.659, "dur": 3.374, + "args": { + "External id": 704718,"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": 6305205034136.703, "dur": 0.770, + "args": { + "External id": 704719,"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": 6305205034139.231, "dur": 25.471, + "args": { + "External id": 704720,"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": 6305205034140.189, "dur": 3.513, + "args": { + "External id": 704721,"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": 6305205034145.286, "dur": 19.119, + "args": { + "External id": 704722,"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": 6305205034150.286, "dur": 2.275, + "args": { + "External id": 704723,"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": 6305205034166.259, "dur": 20.450, + "args": { + "External id": 704724,"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": 6305205034188.362, "dur": 13.843, + "args": { + "External id": 704725,"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": 6305205034205.164, "dur": 12.095, + "args": { + "External id": 704726,"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": 6305205034218.652, "dur": 11.147, + "args": { + "External id": 704727,"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": 6305205034233.594, "dur": 19.550, + "args": { + "External id": 704728,"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": 6305205034235.942, "dur": 2.050, + "args": { + "External id": 704729,"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": 6305205034239.841, "dur": 0.577, + "args": { + "External id": 704730,"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": 6305205034254.542, "dur": 11.180, + "args": { + "External id": 704731,"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": 6305205034266.653, "dur": 10.893, + "args": { + "External id": 704732,"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": 6305205034286.879, "dur": 2.107, + "args": { + "External id": 704733,"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": 6305205034300.055, "dur": 4.217, + "args": { + "External id": 704734,"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": 6305205034302.952, "dur": 0.474, + "args": { + "External id": 704735,"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": 6305205034384.593, "dur": 59.594, + "args": { + "External id": 704736,"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": 6305205034449.715, "dur": 6.778, + "args": { + "External id": 704737,"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": 6305205034452.775, "dur": 2.633, + "args": { + "External id": 704738,"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": 6305205034457.881, "dur": 24.115, + "args": { + "External id": 704739,"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": 6305205034486.438, "dur": 7.421, + "args": { + "External id": 704740,"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": 6305205034488.306, "dur": 4.871, + "args": { + "External id": 704741,"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": 6305205034492.302, "dur": 0.629, + "args": { + "External id": 704742,"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": 6305205034496.568, "dur": 60.535, + "args": { + "External id": 704743,"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": 6305205034497.739, "dur": 58.518, + "args": { + "External id": 704744,"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": 6305205034562.405, "dur": 15.528, + "args": { + "External id": 704745,"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": 6305205034584.807, "dur": 3.874, + "args": { + "External id": 704746,"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": 6305205034587.032, "dur": 0.650, + "args": { + "External id": 704747,"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": 6305205034593.156, "dur": 47.089, + "args": { + "External id": 704748,"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": 6305205034596.501, "dur": 3.532, + "args": { + "External id": 704749,"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": 6305205034597.567, "dur": 1.870, + "args": { + "External id": 704750,"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": 6305205034598.867, "dur": 0.444, + "args": { + "External id": 704751,"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": 6305205034600.607, "dur": 39.308, + "args": { + "External id": 704752,"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": 6305205034601.218, "dur": 38.125, + "args": { + "External id": 704753,"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": 6305205034650.467, "dur": 8.276, + "args": { + "External id": 704754,"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": 6305205034654.520, "dur": 2.796, + "args": { + "External id": 704755,"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": 6305205034667.927, "dur": 1.692, + "args": { + "External id": 704756,"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": 6305205034678.177, "dur": 7.903, + "args": { + "External id": 704757,"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": 6305205034680.040, "dur": 5.707, + "args": { + "External id": 704758,"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": 6305205034778.374, "dur": 189.481, + "args": { + "External id": 704759,"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": 6305205034780.335, "dur": 1.639, + "args": { + "External id": 704760,"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": 6305205034783.449, "dur": 184.001, + "args": { + "External id": 704761,"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": 6305205034787.695, "dur": 0.365, + "args": { + "External id": 704762,"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": 6305205034788.958, "dur": 22.057, + "args": { + "External id": 704763,"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": 6305205034812.488, "dur": 2.790, + "args": { + "External id": 704764,"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": 6305205034814.528, "dur": 0.511, + "args": { + "External id": 704765,"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": 6305205034816.267, "dur": 22.536, + "args": { + "External id": 704766,"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": 6305205034817.711, "dur": 1.235, + "args": { + "External id": 704767,"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": 6305205034820.020, "dur": 18.422, + "args": { + "External id": 704768,"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": 6305205034824.780, "dur": 2.697, + "args": { + "External id": 704769,"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": 6305205034840.209, "dur": 24.541, + "args": { + "External id": 704770,"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": 6305205034866.331, "dur": 12.694, + "args": { + "External id": 704771,"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": 6305205034883.774, "dur": 15.909, + "args": { + "External id": 704772,"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": 6305205034901.107, "dur": 13.175, + "args": { + "External id": 704773,"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": 6305205034915.762, "dur": 19.353, + "args": { + "External id": 704774,"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": 6305205034917.739, "dur": 1.315, + "args": { + "External id": 704775,"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": 6305205034920.830, "dur": 0.703, + "args": { + "External id": 704776,"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": 6305205034936.381, "dur": 13.713, + "args": { + "External id": 704777,"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": 6305205034953.396, "dur": 13.186, + "args": { + "External id": 704778,"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": 6305205034974.060, "dur": 1.558, + "args": { + "External id": 704779,"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": 6305205034983.641, "dur": 3.528, + "args": { + "External id": 704780,"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": 6305205034985.896, "dur": 0.408, + "args": { + "External id": 704781,"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": 6305205035052.315, "dur": 97.762, + "args": { + "External id": 704782,"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": 6305205035157.219, "dur": 6.361, + "args": { + "External id": 704783,"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": 6305205035160.650, "dur": 1.326, + "args": { + "External id": 704784,"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": 6305205035165.180, "dur": 33.223, + "args": { + "External id": 704785,"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": 6305205035205.204, "dur": 4.943, + "args": { + "External id": 704786,"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": 6305205035206.804, "dur": 2.685, + "args": { + "External id": 704787,"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": 6305205035208.495, "dur": 0.743, + "args": { + "External id": 704788,"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": 6305205035213.336, "dur": 68.893, + "args": { + "External id": 704789,"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": 6305205035214.438, "dur": 67.284, + "args": { + "External id": 704790,"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": 6305205035286.131, "dur": 29.347, + "args": { + "External id": 704791,"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": 6305205035321.136, "dur": 5.691, + "args": { + "External id": 704792,"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": 6305205035325.478, "dur": 0.483, + "args": { + "External id": 704793,"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": 6305205035331.045, "dur": 50.578, + "args": { + "External id": 704794,"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": 6305205035331.854, "dur": 5.033, + "args": { + "External id": 704795,"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": 6305205035332.847, "dur": 3.436, + "args": { + "External id": 704796,"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": 6305205035333.984, "dur": 2.064, + "args": { + "External id": 704797,"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": 6305205035337.543, "dur": 43.592, + "args": { + "External id": 704798,"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": 6305205035340.923, "dur": 39.626, + "args": { + "External id": 704799,"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": 6305205035385.926, "dur": 3.444, + "args": { + "External id": 704800,"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": 6305205035387.867, "dur": 0.310, + "args": { + "External id": 704801,"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": 6305205035395.432, "dur": 1.438, + "args": { + "External id": 704802,"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": 6305205035404.920, "dur": 5.908, + "args": { + "External id": 704803,"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": 6305205035406.823, "dur": 3.733, + "args": { + "External id": 704804,"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": 6305205035522.221, "dur": 182.937, + "args": { + "External id": 704805,"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": 6305205035525.133, "dur": 4.433, + "args": { + "External id": 704806,"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": 6305205035531.310, "dur": 173.452, + "args": { + "External id": 704807,"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": 6305205035532.516, "dur": 0.340, + "args": { + "External id": 704808,"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": 6305205035536.127, "dur": 24.278, + "args": { + "External id": 704809,"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": 6305205035562.097, "dur": 2.965, + "args": { + "External id": 704810,"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": 6305205035563.943, "dur": 0.794, + "args": { + "External id": 704811,"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": 6305205035565.811, "dur": 23.881, + "args": { + "External id": 704812,"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": 6305205035566.797, "dur": 2.821, + "args": { + "External id": 704813,"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": 6305205035573.117, "dur": 16.163, + "args": { + "External id": 704814,"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": 6305205035575.940, "dur": 2.151, + "args": { + "External id": 704815,"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": 6305205035591.191, "dur": 19.837, + "args": { + "External id": 704816,"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": 6305205035612.736, "dur": 13.423, + "args": { + "External id": 704817,"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": 6305205035628.698, "dur": 12.212, + "args": { + "External id": 704818,"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": 6305205035642.571, "dur": 11.454, + "args": { + "External id": 704819,"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": 6305205035655.650, "dur": 18.085, + "args": { + "External id": 704820,"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": 6305205035657.885, "dur": 1.569, + "args": { + "External id": 704821,"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": 6305205035661.173, "dur": 0.532, + "args": { + "External id": 704822,"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": 6305205035677.354, "dur": 13.983, + "args": { + "External id": 704823,"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": 6305205035692.363, "dur": 11.381, + "args": { + "External id": 704824,"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": 6305205035712.693, "dur": 2.132, + "args": { + "External id": 704825,"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": 6305205035723.775, "dur": 3.517, + "args": { + "External id": 704826,"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": 6305205035725.950, "dur": 0.457, + "args": { + "External id": 704827,"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": 6305205035798.473, "dur": 56.685, + "args": { + "External id": 704828,"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": 6305205035860.487, "dur": 4.967, + "args": { + "External id": 704829,"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": 6305205035863.580, "dur": 0.804, + "args": { + "External id": 704830,"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": 6305205035869.177, "dur": 25.795, + "args": { + "External id": 704831,"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": 6305205035899.018, "dur": 6.414, + "args": { + "External id": 704832,"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": 6305205035900.704, "dur": 4.011, + "args": { + "External id": 704833,"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": 6305205035902.178, "dur": 2.353, + "args": { + "External id": 704834,"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": 6305205035907.856, "dur": 42.079, + "args": { + "External id": 704835,"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": 6305205035908.833, "dur": 40.219, + "args": { + "External id": 704836,"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": 6305205035953.759, "dur": 14.543, + "args": { + "External id": 704837,"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": 6305205035976.294, "dur": 3.378, + "args": { + "External id": 704838,"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": 6305205035978.459, "dur": 0.428, + "args": { + "External id": 704839,"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": 6305205035983.671, "dur": 44.936, + "args": { + "External id": 704840,"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": 6305205035984.298, "dur": 3.393, + "args": { + "External id": 704841,"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": 6305205035984.918, "dur": 2.084, + "args": { + "External id": 704842,"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": 6305205035986.277, "dur": 0.568, + "args": { + "External id": 704843,"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": 6305205035990.657, "dur": 37.509, + "args": { + "External id": 704844,"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": 6305205035991.120, "dur": 36.467, + "args": { + "External id": 704845,"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": 6305205036032.565, "dur": 3.723, + "args": { + "External id": 704846,"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": 6305205036034.880, "dur": 0.289, + "args": { + "External id": 704847,"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": 6305205036041.163, "dur": 1.401, + "args": { + "External id": 704848,"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": 6305205036050.182, "dur": 46.356, + "args": { + "External id": 704849,"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": 6305205036087.987, "dur": 7.971, + "args": { + "External id": 704850,"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": 6305205036190.656, "dur": 173.260, + "args": { + "External id": 704851,"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": 6305205036192.863, "dur": 1.657, + "args": { + "External id": 704852,"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": 6305205036197.864, "dur": 165.555, + "args": { + "External id": 704853,"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": 6305205036199.045, "dur": 0.455, + "args": { + "External id": 704854,"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": 6305205036200.447, "dur": 24.011, + "args": { + "External id": 704855,"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": 6305205036226.037, "dur": 4.459, + "args": { + "External id": 704856,"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": 6305205036228.215, "dur": 2.034, + "args": { + "External id": 704857,"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": 6305205036231.436, "dur": 24.009, + "args": { + "External id": 704858,"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": 6305205036234.787, "dur": 1.187, + "args": { + "External id": 704859,"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": 6305205036237.277, "dur": 17.879, + "args": { + "External id": 704860,"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": 6305205036240.145, "dur": 3.055, + "args": { + "External id": 704861,"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": 6305205036256.770, "dur": 19.353, + "args": { + "External id": 704862,"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": 6305205036277.391, "dur": 12.107, + "args": { + "External id": 704863,"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": 6305205036291.966, "dur": 12.887, + "args": { + "External id": 704864,"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": 6305205036306.361, "dur": 10.205, + "args": { + "External id": 704865,"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": 6305205036318.287, "dur": 20.152, + "args": { + "External id": 704866,"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": 6305205036320.617, "dur": 1.255, + "args": { + "External id": 704867,"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": 6305205036325.453, "dur": 0.668, + "args": { + "External id": 704868,"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": 6305205036339.620, "dur": 11.337, + "args": { + "External id": 704869,"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": 6305205036351.988, "dur": 10.597, + "args": { + "External id": 704870,"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": 6305205036370.315, "dur": 2.250, + "args": { + "External id": 704871,"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": 6305205036381.619, "dur": 3.679, + "args": { + "External id": 704872,"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": 6305205036384.005, "dur": 0.388, + "args": { + "External id": 704873,"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": 6305205036446.966, "dur": 56.214, + "args": { + "External id": 704874,"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": 6305205036526.113, "dur": 7.685, + "args": { + "External id": 704875,"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": 6305205036529.527, "dur": 2.608, + "args": { + "External id": 704876,"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": 6305205036535.211, "dur": 27.376, + "args": { + "External id": 704877,"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": 6305205036567.934, "dur": 5.311, + "args": { + "External id": 704878,"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": 6305205036569.569, "dur": 2.911, + "args": { + "External id": 704879,"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": 6305205036571.532, "dur": 0.755, + "args": { + "External id": 704880,"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": 6305205036578.182, "dur": 44.485, + "args": { + "External id": 704881,"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": 6305205036579.299, "dur": 42.851, + "args": { + "External id": 704882,"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": 6305205036632.141, "dur": 15.637, + "args": { + "External id": 704883,"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": 6305205036654.089, "dur": 3.633, + "args": { + "External id": 704884,"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": 6305205036656.339, "dur": 0.407, + "args": { + "External id": 704885,"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": 6305205036661.727, "dur": 46.916, + "args": { + "External id": 704886,"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": 6305205036662.404, "dur": 7.439, + "args": { + "External id": 704887,"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": 6305205036665.284, "dur": 3.919, + "args": { + "External id": 704888,"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": 6305205036666.226, "dur": 2.841, + "args": { + "External id": 704889,"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": 6305205036670.610, "dur": 37.650, + "args": { + "External id": 704890,"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": 6305205036670.999, "dur": 36.754, + "args": { + "External id": 704891,"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": 6305205036713.150, "dur": 3.659, + "args": { + "External id": 704892,"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": 6305205036714.905, "dur": 0.558, + "args": { + "External id": 704893,"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": 6305205036722.667, "dur": 1.422, + "args": { + "External id": 704894,"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": 6305205036733.807, "dur": 7.939, + "args": { + "External id": 704895,"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": 6305205036735.875, "dur": 5.565, + "args": { + "External id": 704896,"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": 6305205036826.459, "dur": 189.569, + "args": { + "External id": 704897,"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": 6305205036828.581, "dur": 1.697, + "args": { + "External id": 704898,"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": 6305205036831.505, "dur": 184.007, + "args": { + "External id": 704899,"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": 6305205036833.156, "dur": 0.526, + "args": { + "External id": 704900,"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": 6305205036837.114, "dur": 23.831, + "args": { + "External id": 704901,"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": 6305205036862.406, "dur": 3.308, + "args": { + "External id": 704902,"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": 6305205036864.954, "dur": 0.554, + "args": { + "External id": 704903,"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": 6305205036866.486, "dur": 31.104, + "args": { + "External id": 704904,"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": 6305205036867.352, "dur": 1.220, + "args": { + "External id": 704905,"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": 6305205036869.723, "dur": 27.519, + "args": { + "External id": 704906,"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": 6305205036874.521, "dur": 1.955, + "args": { + "External id": 704907,"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": 6305205036898.836, "dur": 24.427, + "args": { + "External id": 704908,"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": 6305205036924.783, "dur": 14.604, + "args": { + "External id": 704909,"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": 6305205036941.635, "dur": 13.110, + "args": { + "External id": 704910,"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": 6305205036956.134, "dur": 11.094, + "args": { + "External id": 704911,"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": 6305205036971.934, "dur": 18.346, + "args": { + "External id": 704912,"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": 6305205036973.765, "dur": 1.364, + "args": { + "External id": 704913,"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": 6305205036977.574, "dur": 0.737, + "args": { + "External id": 704914,"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": 6305205036991.516, "dur": 11.414, + "args": { + "External id": 704915,"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": 6305205037003.881, "dur": 10.818, + "args": { + "External id": 704916,"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": 6305205037022.261, "dur": 1.671, + "args": { + "External id": 704917,"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": 6305205037032.635, "dur": 3.803, + "args": { + "External id": 704918,"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": 6305205037035.068, "dur": 0.522, + "args": { + "External id": 704919,"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": 6305205037144.427, "dur": 58.511, + "args": { + "External id": 704920,"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": 6305205037208.858, "dur": 5.992, + "args": { + "External id": 704921,"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": 6305205037212.228, "dur": 1.022, + "args": { + "External id": 704922,"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": 6305205037216.221, "dur": 24.692, + "args": { + "External id": 704923,"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": 6305205037245.501, "dur": 8.111, + "args": { + "External id": 704924,"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": 6305205037247.386, "dur": 5.362, + "args": { + "External id": 704925,"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": 6305205037251.535, "dur": 1.047, + "args": { + "External id": 704926,"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": 6305205037256.291, "dur": 40.940, + "args": { + "External id": 704927,"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": 6305205037257.529, "dur": 39.001, + "args": { + "External id": 704928,"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": 6305205037301.092, "dur": 14.446, + "args": { + "External id": 704929,"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": 6305205037321.356, "dur": 3.868, + "args": { + "External id": 704930,"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": 6305205037323.836, "dur": 0.558, + "args": { + "External id": 704931,"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": 6305205037329.314, "dur": 46.680, + "args": { + "External id": 704932,"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": 6305205037332.365, "dur": 5.256, + "args": { + "External id": 704933,"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": 6305205037333.186, "dur": 3.781, + "args": { + "External id": 704934,"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": 6305205037334.436, "dur": 2.325, + "args": { + "External id": 704935,"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": 6305205037338.453, "dur": 37.031, + "args": { + "External id": 704936,"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": 6305205037338.950, "dur": 35.966, + "args": { + "External id": 704937,"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": 6305205037380.209, "dur": 6.162, + "args": { + "External id": 704938,"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": 6305205037382.144, "dur": 2.988, + "args": { + "External id": 704939,"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": 6305205037394.947, "dur": 1.551, + "args": { + "External id": 704940,"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": 6305205037404.029, "dur": 8.267, + "args": { + "External id": 704941,"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": 6305205037408.746, "dur": 3.272, + "args": { + "External id": 704942,"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": 6305205037488.588, "dur": 195.389, + "args": { + "External id": 704943,"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": 6305205037492.432, "dur": 1.678, + "args": { + "External id": 704944,"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": 6305205037495.250, "dur": 188.218, + "args": { + "External id": 704945,"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": 6305205037498.616, "dur": 0.344, + "args": { + "External id": 704946,"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": 6305205037499.983, "dur": 38.056, + "args": { + "External id": 704947,"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": 6305205037540.923, "dur": 4.680, + "args": { + "External id": 704948,"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": 6305205037544.534, "dur": 0.805, + "args": { + "External id": 704949,"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": 6305205037546.535, "dur": 21.270, + "args": { + "External id": 704950,"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": 6305205037547.520, "dur": 1.646, + "args": { + "External id": 704951,"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": 6305205037550.421, "dur": 17.083, + "args": { + "External id": 704952,"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": 6305205037553.579, "dur": 2.949, + "args": { + "External id": 704953,"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": 6305205037569.264, "dur": 21.358, + "args": { + "External id": 704954,"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": 6305205037592.019, "dur": 14.023, + "args": { + "External id": 704955,"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": 6305205037611.367, "dur": 13.537, + "args": { + "External id": 704956,"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": 6305205037626.353, "dur": 11.277, + "args": { + "External id": 704957,"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": 6305205037639.253, "dur": 18.387, + "args": { + "External id": 704958,"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": 6305205037640.993, "dur": 1.484, + "args": { + "External id": 704959,"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": 6305205037644.275, "dur": 0.466, + "args": { + "External id": 704960,"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": 6305205037658.932, "dur": 10.883, + "args": { + "External id": 704961,"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": 6305205037672.713, "dur": 9.790, + "args": { + "External id": 704962,"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": 6305205037691.872, "dur": 2.418, + "args": { + "External id": 704963,"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": 6305205037703.770, "dur": 3.977, + "args": { + "External id": 704964,"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": 6305205037706.443, "dur": 0.455, + "args": { + "External id": 704965,"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": 6305205037770.627, "dur": 53.597, + "args": { + "External id": 704966,"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": 6305205037829.077, "dur": 4.669, + "args": { + "External id": 704967,"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": 6305205037832.169, "dur": 0.703, + "args": { + "External id": 704968,"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": 6305205037834.999, "dur": 22.436, + "args": { + "External id": 704969,"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": 6305205037863.935, "dur": 5.496, + "args": { + "External id": 704970,"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": 6305205037865.585, "dur": 3.241, + "args": { + "External id": 704971,"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": 6305205037867.642, "dur": 1.040, + "args": { + "External id": 704972,"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": 6305205037871.592, "dur": 40.803, + "args": { + "External id": 704973,"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": 6305205037872.618, "dur": 39.113, + "args": { + "External id": 704974,"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": 6305205037916.021, "dur": 14.503, + "args": { + "External id": 704975,"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": 6305205037936.048, "dur": 5.044, + "args": { + "External id": 704976,"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": 6305205037940.079, "dur": 0.316, + "args": { + "External id": 704977,"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": 6305205037944.680, "dur": 46.923, + "args": { + "External id": 704978,"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": 6305205037948.490, "dur": 3.219, + "args": { + "External id": 704979,"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": 6305205037949.367, "dur": 1.778, + "args": { + "External id": 704980,"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": 6305205037950.490, "dur": 0.519, + "args": { + "External id": 704981,"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": 6305205037952.206, "dur": 38.976, + "args": { + "External id": 704982,"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": 6305205037955.063, "dur": 35.589, + "args": { + "External id": 704983,"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": 6305205037995.703, "dur": 3.172, + "args": { + "External id": 704984,"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": 6305205037997.384, "dur": 0.402, + "args": { + "External id": 704985,"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": 6305205038003.698, "dur": 1.350, + "args": { + "External id": 704986,"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": 6305205038012.140, "dur": 7.931, + "args": { + "External id": 704987,"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": 6305205038014.549, "dur": 5.215, + "args": { + "External id": 704988,"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": 6305205038140.160, "dur": 176.428, + "args": { + "External id": 704989,"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": 6305205038142.747, "dur": 5.132, + "args": { + "External id": 704990,"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": 6305205038149.171, "dur": 166.807, + "args": { + "External id": 704991,"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": 6305205038150.928, "dur": 0.388, + "args": { + "External id": 704992,"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": 6305205038152.551, "dur": 25.721, + "args": { + "External id": 704993,"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": 6305205038179.751, "dur": 3.502, + "args": { + "External id": 704994,"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": 6305205038182.260, "dur": 0.765, + "args": { + "External id": 704995,"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": 6305205038184.079, "dur": 25.213, + "args": { + "External id": 704996,"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": 6305205038185.112, "dur": 1.350, + "args": { + "External id": 704997,"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": 6305205038189.770, "dur": 19.119, + "args": { + "External id": 704998,"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": 6305205038194.457, "dur": 2.410, + "args": { + "External id": 704999,"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": 6305205038210.651, "dur": 19.243, + "args": { + "External id": 705000,"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": 6305205038231.264, "dur": 12.316, + "args": { + "External id": 705001,"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": 6305205038245.810, "dur": 11.329, + "args": { + "External id": 705002,"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": 6305205038258.450, "dur": 11.034, + "args": { + "External id": 705003,"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": 6305205038271.159, "dur": 17.507, + "args": { + "External id": 705004,"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": 6305205038272.957, "dur": 1.414, + "args": { + "External id": 705005,"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": 6305205038276.245, "dur": 0.528, + "args": { + "External id": 705006,"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": 6305205038292.073, "dur": 11.078, + "args": { + "External id": 705007,"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": 6305205038304.032, "dur": 10.926, + "args": { + "External id": 705008,"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": 6305205038323.079, "dur": 1.925, + "args": { + "External id": 705009,"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": 6305205038333.758, "dur": 3.866, + "args": { + "External id": 705010,"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": 6305205038336.357, "dur": 0.435, + "args": { + "External id": 705011,"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": 6305205038400.718, "dur": 55.403, + "args": { + "External id": 705012,"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": 6305205038461.052, "dur": 4.771, + "args": { + "External id": 705013,"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": 6305205038464.041, "dur": 0.758, + "args": { + "External id": 705014,"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": 6305205038469.393, "dur": 22.488, + "args": { + "External id": 705015,"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": 6305205038496.061, "dur": 5.187, + "args": { + "External id": 705016,"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": 6305205038497.646, "dur": 2.875, + "args": { + "External id": 705017,"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": 6305205038499.517, "dur": 0.838, + "args": { + "External id": 705018,"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": 6305205038503.508, "dur": 62.403, + "args": { + "External id": 705019,"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": 6305205038504.799, "dur": 60.140, + "args": { + "External id": 705020,"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": 6305205038570.963, "dur": 16.394, + "args": { + "External id": 705021,"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": 6305205038594.328, "dur": 29.692, + "args": { + "External id": 705022,"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": 6305205038596.887, "dur": 26.632, + "args": { + "External id": 705023,"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": 6305205038603.673, "dur": 0.686, + "args": { + "External id": 705024,"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": 6305205038652.008, "dur": 31.280, + "args": { + "External id": 705025,"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": 6305205038653.939, "dur": 29.096, + "args": { + "External id": 705026,"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": 6305205038661.526, "dur": 3.986, + "args": { + "External id": 705027,"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": 6305205038666.787, "dur": 15.763, + "args": { + "External id": 705028,"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": 6305205038696.213, "dur": 7.167, + "args": { + "External id": 705029,"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": 6305205038700.155, "dur": 2.913, + "args": { + "External id": 705030,"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": 6305205038704.308, "dur": 0.842, + "args": { + "External id": 705031,"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": 6305205038704.661, "dur": 0.407, + "args": { + "External id": 705032,"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": 6305205038747.051, "dur": 21.480, + "args": { + "External id": 705033,"Sequence number": 7674598, "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": 6305205038770.259, "dur": 14.515, + "args": { + "External id": 705034,"Sequence number": 7674599, "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": 6305205038770.259, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338707, "tid": 2338707, + "ts": 6305205038791.304, "dur": 7.132, + "args": { + "External id": 705035,"Sequence number": 7674600, "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": 6305205038795.841, "dur": 1.007, + "args": { + "External id": 705036,"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": 6305205038800.919, "dur": 8.521, + "args": { + "External id": 705037,"Sequence number": 7674600, "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": 6305205038807.665, "dur": 0.379, + "args": { + "External id": 705038,"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": 6305205038810.624, "dur": 2.796, + "args": { + "External id": 705039,"Sequence number": 7674600, "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": 6305205038812.608, "dur": 0.240, + "args": { + "External id": 705040,"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": 6305205038817.486, "dur": 5.774, + "args": { + "External id": 705041,"Sequence number": 7674600, "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": 6305205038817.486, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2338707, + "ts": 6305205038820.861, "dur": 0.784, + "args": { + "External id": 705042,"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": 6305205038826.515, "dur": 5.919, + "args": { + "External id": 705043,"Sequence number": 7674601, "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": 6305205038826.515, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2338707, + "ts": 6305205038831.309, "dur": 0.287, + "args": { + "External id": 705044,"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": 6305205038833.340, "dur": 4.772, + "args": { + "External id": 705045,"Sequence number": 7674602, "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": 6305205038833.340, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2338707, + "ts": 6305205038836.821, "dur": 0.481, + "args": { + "External id": 705046,"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": 6305205038839.091, "dur": 6.105, + "args": { + "External id": 705047,"Sequence number": 7674603, "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": 6305205038839.091, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2338707, + "ts": 6305205038841.451, "dur": 3.016, + "args": { + "External id": 705048,"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": 6305205038849.138, "dur": 31.708, + "args": { + "External id": 705049,"Sequence number": 7674604, "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": 6305205038852.821, "dur": 27.803, + "args": { + "External id": 705050,"Sequence number": 7674604, "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": 6305205038855.371, "dur": 6.263, + "args": { + "External id": 705051,"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": 6305205038857.797, "dur": 3.304, + "args": { + "External id": 705052,"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": 6305205038862.468, "dur": 17.689, + "args": { + "External id": 705053,"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": 6305205038907.407, "dur": 3.554, + "args": { + "External id": 705054,"Sequence number": 7674604, "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": 6305205038907.407, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6305205038913.373, "dur": 0.946, + "args": { + "External id": 705055,"Sequence number": 7674605, "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": 6305205038949.412, "dur": 48152.055, + "args": { + "External id": 705056,"Sequence number": 7674605, "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": 6305205038949.412, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338707, "tid": 2338707, + "ts": 6305205038964.460, "dur": 24.443, + "args": { + "External id": 705057,"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": 6305205038965.128, "dur": 23.586, + "args": { + "External id": 705058,"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": 6305205038966.312, "dur": 4.719, + "args": { + "External id": 705059,"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": 6305205038967.737, "dur": 2.956, + "args": { + "External id": 705060,"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": 6305205038971.649, "dur": 16.692, + "args": { + "External id": 705061,"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": 6305205039004.959, "dur": 26.949, + "args": { + "External id": 705062,"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": 6305205039006.274, "dur": 5.534, + "args": { + "External id": 705063,"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": 6305205039008.336, "dur": 3.188, + "args": { + "External id": 705064,"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": 6305205039013.085, "dur": 18.552, + "args": { + "External id": 705065,"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": 6305205039017.030, "dur": 14.258, + "args": { + "External id": 705066,"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": 6305205039035.487, "dur": 19.830, + "args": { + "External id": 705067,"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": 6305205039036.270, "dur": 4.567, + "args": { + "External id": 705068,"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": 6305205039037.968, "dur": 2.631, + "args": { + "External id": 705069,"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": 6305205039041.268, "dur": 13.853, + "args": { + "External id": 705070,"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": 6305205039041.715, "dur": 13.041, + "args": { + "External id": 705071,"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": 6305205039100.688, "dur": 31.719, + "args": { + "External id": 705072,"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": 6305205039102.420, "dur": 3.735, + "args": { + "External id": 705073,"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": 6305205039107.039, "dur": 25.069, + "args": { + "External id": 705074,"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": 6305205039111.692, "dur": 20.021, + "args": { + "External id": 705075,"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": 6305205039137.692, "dur": 24.670, + "args": { + "External id": 705076,"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": 6305205039165.044, "dur": 48.289, + "args": { + "External id": 705077,"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": 6305205039167.060, "dur": 45.771, + "args": { + "External id": 705078,"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": 6305205039171.764, "dur": 0.856, + "args": { + "External id": 705079,"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": 6305205039173.708, "dur": 24.412, + "args": { + "External id": 705080,"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": 6305205039175.352, "dur": 22.537, + "args": { + "External id": 705081,"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": 6305205039179.703, "dur": 2.759, + "args": { + "External id": 705082,"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": 6305205039183.180, "dur": 14.386, + "args": { + "External id": 705083,"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": 6305205039219.215, "dur": 42329.557, + "args": { + "External id": 705084,"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": 6305205039220.648, "dur": 42327.006, + "args": { + "External id": 705085,"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": 6305205081561.059, "dur": 6.914, + "args": { + "External id": 705086,"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": 6305205081565.420, "dur": 0.949, + "args": { + "External id": 705087,"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": 6305205081573.091, "dur": 101.962, + "args": { + "External id": 705088,"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": 6305205081574.717, "dur": 6.346, + "args": { + "External id": 705089,"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": 6305205081577.006, "dur": 3.190, + "args": { + "External id": 705090,"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": 6305205081579.266, "dur": 0.647, + "args": { + "External id": 705091,"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": 6305205081584.511, "dur": 89.918, + "args": { + "External id": 705092,"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": 6305205081586.415, "dur": 87.240, + "args": { + "External id": 705093,"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": 6305205081679.002, "dur": 4.399, + "args": { + "External id": 705094,"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": 6305205081681.538, "dur": 0.555, + "args": { + "External id": 705095,"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": 6305205081690.507, "dur": 2.011, + "args": { + "External id": 705096,"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": 6305205081703.147, "dur": 7.626, + "args": { + "External id": 705097,"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": 6305205081706.953, "dur": 3.571, + "args": { + "External id": 705098,"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": 6305205081836.317, "dur": 188.547, + "args": { + "External id": 705099,"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": 6305205081839.376, "dur": 1.671, + "args": { + "External id": 705100,"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": 6305205081842.703, "dur": 181.677, + "args": { + "External id": 705101,"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": 6305205081844.275, "dur": 0.551, + "args": { + "External id": 705102,"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": 6305205081848.767, "dur": 25.327, + "args": { + "External id": 705103,"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": 6305205081875.970, "dur": 3.277, + "args": { + "External id": 705104,"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": 6305205081878.199, "dur": 0.617, + "args": { + "External id": 705105,"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": 6305205081880.160, "dur": 27.427, + "args": { + "External id": 705106,"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": 6305205081883.791, "dur": 3.278, + "args": { + "External id": 705107,"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": 6305205081888.445, "dur": 18.885, + "args": { + "External id": 705108,"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": 6305205081891.694, "dur": 3.169, + "args": { + "External id": 705109,"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": 6305205081909.045, "dur": 20.114, + "args": { + "External id": 705110,"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": 6305205081931.119, "dur": 14.016, + "args": { + "External id": 705111,"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": 6305205081948.445, "dur": 13.446, + "args": { + "External id": 705112,"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": 6305205081963.488, "dur": 12.166, + "args": { + "External id": 705113,"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": 6305205081977.172, "dur": 21.446, + "args": { + "External id": 705114,"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": 6305205081979.512, "dur": 1.293, + "args": { + "External id": 705115,"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": 6305205081985.203, "dur": 0.413, + "args": { + "External id": 705116,"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": 6305205082000.005, "dur": 11.669, + "args": { + "External id": 705117,"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": 6305205082013.258, "dur": 10.318, + "args": { + "External id": 705118,"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": 6305205082032.069, "dur": 1.764, + "args": { + "External id": 705119,"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": 6305205082040.004, "dur": 3.797, + "args": { + "External id": 705120,"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": 6305205082042.297, "dur": 0.421, + "args": { + "External id": 705121,"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": 6305205082153.995, "dur": 70.250, + "args": { + "External id": 705122,"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": 6305205082232.358, "dur": 7.994, + "args": { + "External id": 705123,"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": 6305205082236.382, "dur": 1.096, + "args": { + "External id": 705124,"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": 6305205082241.796, "dur": 31.809, + "args": { + "External id": 705125,"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": 6305205082279.260, "dur": 6.274, + "args": { + "External id": 705126,"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": 6305205082281.182, "dur": 3.446, + "args": { + "External id": 705127,"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": 6305205082283.201, "dur": 1.231, + "args": { + "External id": 705128,"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": 6305205082291.220, "dur": 45.389, + "args": { + "External id": 705129,"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": 6305205082292.409, "dur": 43.673, + "args": { + "External id": 705130,"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": 6305205082340.815, "dur": 18.301, + "args": { + "External id": 705131,"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": 6305205082365.294, "dur": 4.017, + "args": { + "External id": 705132,"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": 6305205082367.707, "dur": 0.544, + "args": { + "External id": 705133,"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": 6305205082373.765, "dur": 47.427, + "args": { + "External id": 705134,"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": 6305205082374.715, "dur": 7.230, + "args": { + "External id": 705135,"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": 6305205082377.482, "dur": 3.779, + "args": { + "External id": 705136,"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": 6305205082380.704, "dur": 0.405, + "args": { + "External id": 705137,"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": 6305205082382.664, "dur": 38.016, + "args": { + "External id": 705138,"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": 6305205082383.267, "dur": 36.969, + "args": { + "External id": 705139,"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": 6305205082425.246, "dur": 3.670, + "args": { + "External id": 705140,"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": 6305205082427.363, "dur": 0.479, + "args": { + "External id": 705141,"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": 6305205082437.458, "dur": 1.695, + "args": { + "External id": 705142,"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": 6305205082447.522, "dur": 6.145, + "args": { + "External id": 705143,"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": 6305205082449.527, "dur": 3.829, + "args": { + "External id": 705144,"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": 6305205082564.781, "dur": 179.747, + "args": { + "External id": 705145,"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": 6305205082567.101, "dur": 3.130, + "args": { + "External id": 705146,"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": 6305205082571.989, "dur": 172.041, + "args": { + "External id": 705147,"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": 6305205082577.860, "dur": 0.409, + "args": { + "External id": 705148,"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": 6305205082579.648, "dur": 22.219, + "args": { + "External id": 705149,"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": 6305205082603.613, "dur": 5.266, + "args": { + "External id": 705150,"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": 6305205082605.743, "dur": 2.916, + "args": { + "External id": 705151,"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": 6305205082609.936, "dur": 22.660, + "args": { + "External id": 705152,"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": 6305205082613.342, "dur": 1.038, + "args": { + "External id": 705153,"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": 6305205082615.629, "dur": 16.630, + "args": { + "External id": 705154,"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": 6305205082619.024, "dur": 2.673, + "args": { + "External id": 705155,"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": 6305205082633.920, "dur": 20.291, + "args": { + "External id": 705156,"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": 6305205082655.850, "dur": 11.986, + "args": { + "External id": 705157,"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": 6305205082672.596, "dur": 12.680, + "args": { + "External id": 705158,"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": 6305205082686.936, "dur": 11.726, + "args": { + "External id": 705159,"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": 6305205082700.367, "dur": 19.140, + "args": { + "External id": 705160,"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": 6305205082702.430, "dur": 1.991, + "args": { + "External id": 705161,"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": 6305205082706.613, "dur": 0.544, + "args": { + "External id": 705162,"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": 6305205082720.760, "dur": 10.597, + "args": { + "External id": 705163,"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": 6305205082732.355, "dur": 10.638, + "args": { + "External id": 705164,"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": 6305205082753.609, "dur": 1.891, + "args": { + "External id": 705165,"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": 6305205082765.545, "dur": 3.466, + "args": { + "External id": 705166,"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": 6305205082767.708, "dur": 0.522, + "args": { + "External id": 705167,"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": 6305205082833.980, "dur": 56.417, + "args": { + "External id": 705168,"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": 6305205082895.668, "dur": 6.247, + "args": { + "External id": 705169,"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": 6305205082898.884, "dur": 1.876, + "args": { + "External id": 705170,"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": 6305205082903.301, "dur": 25.618, + "args": { + "External id": 705171,"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": 6305205082933.663, "dur": 7.626, + "args": { + "External id": 705172,"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": 6305205082935.412, "dur": 5.132, + "args": { + "External id": 705173,"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": 6305205082939.611, "dur": 0.725, + "args": { + "External id": 705174,"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": 6305205082944.062, "dur": 40.944, + "args": { + "External id": 705175,"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": 6305205082945.184, "dur": 39.272, + "args": { + "External id": 705176,"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": 6305205082988.302, "dur": 15.923, + "args": { + "External id": 705177,"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": 6305205083012.537, "dur": 3.348, + "args": { + "External id": 705178,"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": 6305205083014.196, "dur": 0.687, + "args": { + "External id": 705179,"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": 6305205083022.525, "dur": 82.417, + "args": { + "External id": 705180,"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": 6305205083023.373, "dur": 3.591, + "args": { + "External id": 705181,"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": 6305205083024.125, "dur": 2.232, + "args": { + "External id": 705182,"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": 6305205083025.638, "dur": 0.584, + "args": { + "External id": 705183,"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": 6305205083027.551, "dur": 76.889, + "args": { + "External id": 705184,"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": 6305205083028.298, "dur": 74.967, + "args": { + "External id": 705185,"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": 6305205083111.782, "dur": 7.065, + "args": { + "External id": 705186,"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": 6305205083114.537, "dur": 2.780, + "args": { + "External id": 705187,"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": 6305205083128.050, "dur": 1.975, + "args": { + "External id": 705188,"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": 6305205083138.981, "dur": 8.093, + "args": { + "External id": 705189,"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": 6305205083140.765, "dur": 5.985, + "args": { + "External id": 705190,"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": 6305205083240.833, "dur": 188.941, + "args": { + "External id": 705191,"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": 6305205083242.892, "dur": 1.652, + "args": { + "External id": 705192,"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": 6305205083246.317, "dur": 183.086, + "args": { + "External id": 705193,"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": 6305205083250.552, "dur": 0.460, + "args": { + "External id": 705194,"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": 6305205083252.034, "dur": 25.847, + "args": { + "External id": 705195,"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": 6305205083279.847, "dur": 2.962, + "args": { + "External id": 705196,"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": 6305205083281.890, "dur": 0.735, + "args": { + "External id": 705197,"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": 6305205083283.640, "dur": 23.656, + "args": { + "External id": 705198,"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": 6305205083284.959, "dur": 1.162, + "args": { + "External id": 705199,"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": 6305205083287.376, "dur": 19.562, + "args": { + "External id": 705200,"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": 6305205083292.537, "dur": 2.669, + "args": { + "External id": 705201,"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": 6305205083308.852, "dur": 20.798, + "args": { + "External id": 705202,"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": 6305205083331.294, "dur": 14.936, + "args": { + "External id": 705203,"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": 6305205083351.543, "dur": 13.435, + "args": { + "External id": 705204,"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": 6305205083366.337, "dur": 12.802, + "args": { + "External id": 705205,"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": 6305205083380.852, "dur": 19.523, + "args": { + "External id": 705206,"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": 6305205083382.786, "dur": 1.358, + "args": { + "External id": 705207,"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": 6305205083385.990, "dur": 0.535, + "args": { + "External id": 705208,"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": 6305205083401.799, "dur": 13.566, + "args": { + "External id": 705209,"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": 6305205083418.726, "dur": 9.740, + "args": { + "External id": 705210,"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": 6305205083436.532, "dur": 1.789, + "args": { + "External id": 705211,"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": 6305205083446.883, "dur": 3.562, + "args": { + "External id": 705212,"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": 6305205083449.211, "dur": 0.415, + "args": { + "External id": 705213,"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": 6305205083523.654, "dur": 62.296, + "args": { + "External id": 705214,"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": 6305205083591.849, "dur": 6.528, + "args": { + "External id": 705215,"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": 6305205083595.726, "dur": 1.128, + "args": { + "External id": 705216,"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": 6305205083600.023, "dur": 27.123, + "args": { + "External id": 705217,"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": 6305205083634.292, "dur": 5.194, + "args": { + "External id": 705218,"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": 6305205083635.956, "dur": 2.898, + "args": { + "External id": 705219,"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": 6305205083637.970, "dur": 0.699, + "args": { + "External id": 705220,"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": 6305205083642.229, "dur": 41.865, + "args": { + "External id": 705221,"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": 6305205083643.045, "dur": 40.441, + "args": { + "External id": 705222,"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": 6305205083687.867, "dur": 16.090, + "args": { + "External id": 705223,"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": 6305205083709.639, "dur": 6.829, + "args": { + "External id": 705224,"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": 6305205083714.876, "dur": 0.631, + "args": { + "External id": 705225,"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": 6305205083720.882, "dur": 79.901, + "args": { + "External id": 705226,"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": 6305205083721.890, "dur": 5.770, + "args": { + "External id": 705227,"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": 6305205083723.040, "dur": 4.002, + "args": { + "External id": 705228,"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": 6305205083724.317, "dur": 2.535, + "args": { + "External id": 705229,"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": 6305205083728.327, "dur": 71.968, + "args": { + "External id": 705230,"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": 6305205083734.783, "dur": 64.984, + "args": { + "External id": 705231,"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": 6305205083804.720, "dur": 3.548, + "args": { + "External id": 705232,"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": 6305205083806.533, "dur": 0.493, + "args": { + "External id": 705233,"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": 6305205083813.960, "dur": 1.614, + "args": { + "External id": 705234,"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": 6305205083823.740, "dur": 8.040, + "args": { + "External id": 705235,"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": 6305205083827.833, "dur": 3.641, + "args": { + "External id": 705236,"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": 6305205083917.890, "dur": 211.260, + "args": { + "External id": 705237,"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": 6305205083922.247, "dur": 3.389, + "args": { + "External id": 705238,"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": 6305205083927.184, "dur": 201.210, + "args": { + "External id": 705239,"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": 6305205083928.527, "dur": 0.488, + "args": { + "External id": 705240,"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": 6305205083929.874, "dur": 19.552, + "args": { + "External id": 705241,"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": 6305205083950.731, "dur": 4.690, + "args": { + "External id": 705242,"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": 6305205083954.272, "dur": 0.989, + "args": { + "External id": 705243,"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": 6305205083956.148, "dur": 21.938, + "args": { + "External id": 705244,"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": 6305205083960.101, "dur": 0.951, + "args": { + "External id": 705245,"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": 6305205083962.118, "dur": 15.716, + "args": { + "External id": 705246,"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": 6305205083964.807, "dur": 2.489, + "args": { + "External id": 705247,"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": 6305205083979.412, "dur": 19.581, + "args": { + "External id": 705248,"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": 6305205084000.570, "dur": 14.512, + "args": { + "External id": 705249,"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": 6305205084017.377, "dur": 12.476, + "args": { + "External id": 705250,"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": 6305205084031.165, "dur": 11.281, + "args": { + "External id": 705251,"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": 6305205084043.792, "dur": 57.298, + "args": { + "External id": 705252,"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": 6305205084046.120, "dur": 1.243, + "args": { + "External id": 705253,"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": 6305205084051.076, "dur": 0.603, + "args": { + "External id": 705254,"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": 6305205084103.459, "dur": 11.947, + "args": { + "External id": 705255,"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": 6305205084116.451, "dur": 10.455, + "args": { + "External id": 705256,"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": 6305205084137.383, "dur": 2.312, + "args": { + "External id": 705257,"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": 6305205084149.276, "dur": 4.014, + "args": { + "External id": 705258,"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": 6305205084151.772, "dur": 0.618, + "args": { + "External id": 705259,"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": 6305205084217.584, "dur": 59.208, + "args": { + "External id": 705260,"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": 6305205084281.477, "dur": 7.183, + "args": { + "External id": 705261,"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": 6305205084286.955, "dur": 0.519, + "args": { + "External id": 705262,"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": 6305205084290.094, "dur": 25.394, + "args": { + "External id": 705263,"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": 6305205084319.558, "dur": 5.412, + "args": { + "External id": 705264,"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": 6305205084321.220, "dur": 3.162, + "args": { + "External id": 705265,"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": 6305205084323.194, "dur": 0.927, + "args": { + "External id": 705266,"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": 6305205084327.335, "dur": 39.939, + "args": { + "External id": 705267,"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": 6305205084328.366, "dur": 38.226, + "args": { + "External id": 705268,"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": 6305205084371.088, "dur": 13.884, + "args": { + "External id": 705269,"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": 6305205084392.015, "dur": 3.715, + "args": { + "External id": 705270,"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": 6305205084394.269, "dur": 0.574, + "args": { + "External id": 705271,"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": 6305205084399.538, "dur": 45.905, + "args": { + "External id": 705272,"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": 6305205084400.322, "dur": 5.398, + "args": { + "External id": 705273,"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": 6305205084401.055, "dur": 4.101, + "args": { + "External id": 705274,"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": 6305205084404.458, "dur": 0.569, + "args": { + "External id": 705275,"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": 6305205084406.689, "dur": 38.406, + "args": { + "External id": 705276,"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": 6305205084407.230, "dur": 37.333, + "args": { + "External id": 705277,"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": 6305205084449.334, "dur": 4.056, + "args": { + "External id": 705278,"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": 6305205084451.699, "dur": 0.456, + "args": { + "External id": 705279,"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": 6305205084458.480, "dur": 1.409, + "args": { + "External id": 705280,"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": 6305205084467.653, "dur": 9.475, + "args": { + "External id": 705281,"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": 6305205084472.026, "dur": 4.801, + "args": { + "External id": 705282,"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": 6305205084577.752, "dur": 188.523, + "args": { + "External id": 705283,"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": 6305205084580.058, "dur": 2.782, + "args": { + "External id": 705284,"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": 6305205084585.067, "dur": 180.714, + "args": { + "External id": 705285,"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": 6305205084586.442, "dur": 0.347, + "args": { + "External id": 705286,"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": 6305205084587.961, "dur": 24.280, + "args": { + "External id": 705287,"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": 6305205084613.612, "dur": 3.177, + "args": { + "External id": 705288,"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": 6305205084615.552, "dur": 0.809, + "args": { + "External id": 705289,"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": 6305205084617.396, "dur": 26.175, + "args": { + "External id": 705290,"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": 6305205084621.211, "dur": 1.296, + "args": { + "External id": 705291,"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": 6305205084623.667, "dur": 19.615, + "args": { + "External id": 705292,"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": 6305205084628.138, "dur": 2.697, + "args": { + "External id": 705293,"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": 6305205084645.337, "dur": 21.433, + "args": { + "External id": 705294,"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": 6305205084668.231, "dur": 15.461, + "args": { + "External id": 705295,"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": 6305205084686.218, "dur": 13.179, + "args": { + "External id": 705296,"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": 6305205084700.794, "dur": 13.217, + "args": { + "External id": 705297,"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": 6305205084715.930, "dur": 22.625, + "args": { + "External id": 705298,"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": 6305205084718.346, "dur": 1.551, + "args": { + "External id": 705299,"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": 6305205084724.072, "dur": 0.618, + "args": { + "External id": 705300,"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": 6305205084739.932, "dur": 12.904, + "args": { + "External id": 705301,"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": 6305205084753.765, "dur": 11.194, + "args": { + "External id": 705302,"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": 6305205084772.730, "dur": 1.873, + "args": { + "External id": 705303,"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": 6305205084783.157, "dur": 3.564, + "args": { + "External id": 705304,"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": 6305205084785.383, "dur": 0.485, + "args": { + "External id": 705305,"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": 6305205084847.704, "dur": 52.277, + "args": { + "External id": 705306,"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": 6305205084907.766, "dur": 5.193, + "args": { + "External id": 705307,"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": 6305205084910.791, "dur": 1.035, + "args": { + "External id": 705308,"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": 6305205084914.355, "dur": 23.549, + "args": { + "External id": 705309,"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": 6305205084942.231, "dur": 4.964, + "args": { + "External id": 705310,"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": 6305205084943.797, "dur": 2.645, + "args": { + "External id": 705311,"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": 6305205084945.408, "dur": 0.899, + "args": { + "External id": 705312,"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": 6305205084951.537, "dur": 39.697, + "args": { + "External id": 705313,"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": 6305205084952.812, "dur": 37.617, + "args": { + "External id": 705314,"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": 6305205084994.964, "dur": 13.338, + "args": { + "External id": 705315,"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": 6305205085013.508, "dur": 3.742, + "args": { + "External id": 705316,"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": 6305205085015.837, "dur": 0.453, + "args": { + "External id": 705317,"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": 6305205085021.052, "dur": 84.906, + "args": { + "External id": 705318,"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": 6305205085021.753, "dur": 8.181, + "args": { + "External id": 705319,"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": 6305205085025.048, "dur": 4.349, + "args": { + "External id": 705320,"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": 6305205085026.303, "dur": 2.954, + "args": { + "External id": 705321,"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": 6305205085030.453, "dur": 74.806, + "args": { + "External id": 705322,"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": 6305205085030.915, "dur": 73.315, + "args": { + "External id": 705323,"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": 6305205085112.598, "dur": 4.746, + "args": { + "External id": 705324,"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": 6305205085115.188, "dur": 0.503, + "args": { + "External id": 705325,"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": 6305205085125.901, "dur": 1.778, + "args": { + "External id": 705326,"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": 6305205085135.595, "dur": 8.265, + "args": { + "External id": 705327,"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": 6305205085137.265, "dur": 6.329, + "args": { + "External id": 705328,"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": 6305205085226.894, "dur": 186.017, + "args": { + "External id": 705329,"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": 6305205085229.415, "dur": 1.569, + "args": { + "External id": 705330,"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": 6305205085232.772, "dur": 179.680, + "args": { + "External id": 705331,"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": 6305205085236.318, "dur": 0.628, + "args": { + "External id": 705332,"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": 6305205085239.872, "dur": 23.200, + "args": { + "External id": 705333,"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": 6305205085264.706, "dur": 2.570, + "args": { + "External id": 705334,"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": 6305205085266.294, "dur": 0.757, + "args": { + "External id": 705335,"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": 6305205085268.031, "dur": 23.473, + "args": { + "External id": 705336,"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": 6305205085269.431, "dur": 2.277, + "args": { + "External id": 705337,"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": 6305205085272.845, "dur": 18.254, + "args": { + "External id": 705338,"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": 6305205085275.717, "dur": 2.609, + "args": { + "External id": 705339,"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": 6305205085292.820, "dur": 20.758, + "args": { + "External id": 705340,"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": 6305205085314.858, "dur": 13.730, + "args": { + "External id": 705341,"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": 6305205085333.011, "dur": 15.113, + "args": { + "External id": 705342,"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": 6305205085349.520, "dur": 12.844, + "args": { + "External id": 705343,"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": 6305205085363.717, "dur": 21.480, + "args": { + "External id": 705344,"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": 6305205085365.975, "dur": 1.964, + "args": { + "External id": 705345,"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": 6305205085370.128, "dur": 0.675, + "args": { + "External id": 705346,"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": 6305205085386.259, "dur": 12.556, + "args": { + "External id": 705347,"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": 6305205085399.775, "dur": 11.730, + "args": { + "External id": 705348,"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": 6305205085420.582, "dur": 1.642, + "args": { + "External id": 705349,"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": 6305205085429.947, "dur": 3.549, + "args": { + "External id": 705350,"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": 6305205085432.157, "dur": 0.451, + "args": { + "External id": 705351,"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": 6305205085492.267, "dur": 75.471, + "args": { + "External id": 705352,"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": 6305205085574.503, "dur": 6.348, + "args": { + "External id": 705353,"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": 6305205085578.177, "dur": 1.206, + "args": { + "External id": 705354,"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": 6305205085582.412, "dur": 26.819, + "args": { + "External id": 705355,"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": 6305205085614.466, "dur": 9.118, + "args": { + "External id": 705356,"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": 6305205085616.111, "dur": 6.781, + "args": { + "External id": 705357,"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": 6305205085620.226, "dur": 2.507, + "args": { + "External id": 705358,"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": 6305205085626.525, "dur": 41.788, + "args": { + "External id": 705359,"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": 6305205085627.519, "dur": 40.047, + "args": { + "External id": 705360,"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": 6305205085671.882, "dur": 16.145, + "args": { + "External id": 705361,"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": 6305205085693.812, "dur": 3.678, + "args": { + "External id": 705362,"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": 6305205085696.177, "dur": 0.477, + "args": { + "External id": 705363,"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": 6305205085703.720, "dur": 44.908, + "args": { + "External id": 705364,"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": 6305205085704.832, "dur": 3.360, + "args": { + "External id": 705365,"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": 6305205085705.640, "dur": 2.114, + "args": { + "External id": 705366,"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": 6305205085706.962, "dur": 0.662, + "args": { + "External id": 705367,"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": 6305205085708.723, "dur": 39.530, + "args": { + "External id": 705368,"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": 6305205085709.311, "dur": 38.474, + "args": { + "External id": 705369,"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": 6305205085752.382, "dur": 3.606, + "args": { + "External id": 705370,"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": 6305205085754.357, "dur": 0.541, + "args": { + "External id": 705371,"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": 6305205085763.457, "dur": 1.513, + "args": { + "External id": 705372,"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": 6305205085772.281, "dur": 5.912, + "args": { + "External id": 705373,"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": 6305205085773.958, "dur": 3.971, + "args": { + "External id": 705374,"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": 6305205085857.503, "dur": 184.735, + "args": { + "External id": 705375,"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": 6305205085859.304, "dur": 1.819, + "args": { + "External id": 705376,"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": 6305205085864.011, "dur": 177.885, + "args": { + "External id": 705377,"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": 6305205085868.058, "dur": 0.515, + "args": { + "External id": 705378,"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": 6305205085869.535, "dur": 21.091, + "args": { + "External id": 705379,"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": 6305205085892.249, "dur": 4.197, + "args": { + "External id": 705380,"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": 6305205085894.466, "dur": 1.713, + "args": { + "External id": 705381,"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": 6305205085897.317, "dur": 21.063, + "args": { + "External id": 705382,"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": 6305205085898.653, "dur": 1.060, + "args": { + "External id": 705383,"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": 6305205085900.973, "dur": 17.171, + "args": { + "External id": 705384,"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": 6305205085903.197, "dur": 2.509, + "args": { + "External id": 705385,"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": 6305205085919.813, "dur": 20.847, + "args": { + "External id": 705386,"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": 6305205085942.185, "dur": 14.900, + "args": { + "External id": 705387,"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": 6305205085961.480, "dur": 13.669, + "args": { + "External id": 705388,"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": 6305205085976.524, "dur": 13.118, + "args": { + "External id": 705389,"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": 6305205085991.161, "dur": 21.051, + "args": { + "External id": 705390,"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": 6305205085993.421, "dur": 1.259, + "args": { + "External id": 705391,"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": 6305205085996.440, "dur": 1.940, + "args": { + "External id": 705392,"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": 6305205086013.619, "dur": 13.562, + "args": { + "External id": 705393,"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": 6305205086030.636, "dur": 10.378, + "args": { + "External id": 705394,"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": 6305205086048.494, "dur": 1.408, + "args": { + "External id": 705395,"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": 6305205086093.778, "dur": 4.422, + "args": { + "External id": 705396,"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": 6305205086096.505, "dur": 0.540, + "args": { + "External id": 705397,"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": 6305205086165.335, "dur": 56.544, + "args": { + "External id": 705398,"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": 6305205086226.961, "dur": 5.137, + "args": { + "External id": 705399,"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": 6305205086230.407, "dur": 0.612, + "args": { + "External id": 705400,"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": 6305205086233.711, "dur": 25.209, + "args": { + "External id": 705401,"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": 6305205086265.181, "dur": 5.948, + "args": { + "External id": 705402,"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": 6305205086266.706, "dur": 3.809, + "args": { + "External id": 705403,"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": 6305205086268.724, "dur": 1.592, + "args": { + "External id": 705404,"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": 6305205086273.608, "dur": 41.620, + "args": { + "External id": 705405,"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": 6305205086274.693, "dur": 39.825, + "args": { + "External id": 705406,"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": 6305205086318.503, "dur": 15.645, + "args": { + "External id": 705407,"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": 6305205086339.917, "dur": 6.212, + "args": { + "External id": 705408,"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": 6305205086344.542, "dur": 0.576, + "args": { + "External id": 705409,"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": 6305205086349.910, "dur": 45.483, + "args": { + "External id": 705410,"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": 6305205086351.101, "dur": 3.466, + "args": { + "External id": 705411,"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": 6305205086351.715, "dur": 2.350, + "args": { + "External id": 705412,"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": 6305205086353.167, "dur": 0.742, + "args": { + "External id": 705413,"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": 6305205086355.193, "dur": 39.686, + "args": { + "External id": 705414,"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": 6305205086358.349, "dur": 36.053, + "args": { + "External id": 705415,"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": 6305205086398.847, "dur": 4.060, + "args": { + "External id": 705416,"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": 6305205086400.964, "dur": 0.756, + "args": { + "External id": 705417,"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": 6305205086408.098, "dur": 1.724, + "args": { + "External id": 705418,"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": 6305205086417.690, "dur": 11.305, + "args": { + "External id": 705419,"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": 6305205086422.075, "dur": 6.626, + "args": { + "External id": 705420,"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": 6305205086525.658, "dur": 188.356, + "args": { + "External id": 705421,"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": 6305205086529.651, "dur": 2.806, + "args": { + "External id": 705422,"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": 6305205086534.322, "dur": 179.282, + "args": { + "External id": 705423,"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": 6305205086535.713, "dur": 0.402, + "args": { + "External id": 705424,"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": 6305205086537.185, "dur": 25.537, + "args": { + "External id": 705425,"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": 6305205086564.452, "dur": 4.624, + "args": { + "External id": 705426,"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": 6305205086567.963, "dur": 0.893, + "args": { + "External id": 705427,"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": 6305205086572.036, "dur": 22.316, + "args": { + "External id": 705428,"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": 6305205086573.454, "dur": 1.127, + "args": { + "External id": 705429,"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": 6305205086576.044, "dur": 18.058, + "args": { + "External id": 705430,"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": 6305205086579.242, "dur": 2.174, + "args": { + "External id": 705431,"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": 6305205086595.589, "dur": 22.237, + "args": { + "External id": 705432,"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": 6305205086619.123, "dur": 13.721, + "args": { + "External id": 705433,"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": 6305205086635.098, "dur": 14.778, + "args": { + "External id": 705434,"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": 6305205086651.751, "dur": 12.361, + "args": { + "External id": 705435,"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": 6305205086665.796, "dur": 22.466, + "args": { + "External id": 705436,"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": 6305205086669.469, "dur": 1.588, + "args": { + "External id": 705437,"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": 6305205086675.250, "dur": 0.617, + "args": { + "External id": 705438,"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": 6305205086689.680, "dur": 11.333, + "args": { + "External id": 705439,"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": 6305205086702.144, "dur": 10.573, + "args": { + "External id": 705440,"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": 6305205086721.639, "dur": 1.883, + "args": { + "External id": 705441,"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": 6305205086732.388, "dur": 4.454, + "args": { + "External id": 705442,"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": 6305205086735.156, "dur": 0.799, + "args": { + "External id": 705443,"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": 6305205086798.396, "dur": 55.097, + "args": { + "External id": 705444,"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": 6305205086858.595, "dur": 6.776, + "args": { + "External id": 705445,"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": 6305205086863.480, "dur": 0.692, + "args": { + "External id": 705446,"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": 6305205086866.790, "dur": 25.804, + "args": { + "External id": 705447,"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": 6305205086897.011, "dur": 5.475, + "args": { + "External id": 705448,"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": 6305205086898.649, "dur": 3.120, + "args": { + "External id": 705449,"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": 6305205086900.857, "dur": 0.733, + "args": { + "External id": 705450,"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": 6305205086904.830, "dur": 42.114, + "args": { + "External id": 705451,"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": 6305205086907.809, "dur": 38.445, + "args": { + "External id": 705452,"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": 6305205086950.418, "dur": 12.592, + "args": { + "External id": 705453,"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": 6305205086967.375, "dur": 21.489, + "args": { + "External id": 705454,"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": 6305205086969.986, "dur": 18.476, + "args": { + "External id": 705455,"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": 6305205086974.590, "dur": 0.701, + "args": { + "External id": 705456,"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": 6305205086993.713, "dur": 25.784, + "args": { + "External id": 705457,"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": 6305205086995.737, "dur": 23.509, + "args": { + "External id": 705458,"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": 6305205087000.037, "dur": 3.226, + "args": { + "External id": 705459,"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": 6305205087004.332, "dur": 14.412, + "args": { + "External id": 705460,"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": 6305205087032.522, "dur": 4.694, + "args": { + "External id": 705461,"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": 6305205087034.409, "dur": 2.514, + "args": { + "External id": 705462,"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": 6305205087038.322, "dur": 1.222, + "args": { + "External id": 705463,"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": 6305205087038.762, "dur": 0.716, + "args": { + "External id": 705464,"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": 6305205087123.644, "dur": 28.292, + "args": { + "External id": 705465,"Sequence number": 7674606, "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": 6305205087155.936, "dur": 12.913, + "args": { + "External id": 705466,"Sequence number": 7674607, "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": 6305205087155.936, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338707, "tid": 2338707, + "ts": 6305205087175.560, "dur": 7.158, + "args": { + "External id": 705467,"Sequence number": 7674608, "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": 6305205087179.468, "dur": 1.527, + "args": { + "External id": 705468,"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": 6305205087185.180, "dur": 5.961, + "args": { + "External id": 705469,"Sequence number": 7674608, "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": 6305205087189.289, "dur": 0.540, + "args": { + "External id": 705470,"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": 6305205087192.438, "dur": 4.326, + "args": { + "External id": 705471,"Sequence number": 7674608, "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": 6305205087195.898, "dur": 0.248, + "args": { + "External id": 705472,"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": 6305205087200.991, "dur": 6.082, + "args": { + "External id": 705473,"Sequence number": 7674608, "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": 6305205087200.991, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2338707, + "ts": 6305205087204.649, "dur": 0.885, + "args": { + "External id": 705474,"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": 6305205087208.171, "dur": 4.442, + "args": { + "External id": 705475,"Sequence number": 7674609, "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": 6305205087208.171, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2338707, + "ts": 6305205087211.317, "dur": 0.551, + "args": { + "External id": 705476,"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": 6305205087213.679, "dur": 12.138, + "args": { + "External id": 705477,"Sequence number": 7674610, "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": 6305205087213.679, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2338707, + "ts": 6305205087222.104, "dur": 2.802, + "args": { + "External id": 705478,"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": 6305205087226.864, "dur": 5.385, + "args": { + "External id": 705479,"Sequence number": 7674611, "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": 6305205087226.864, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2338707, + "ts": 6305205087229.233, "dur": 1.970, + "args": { + "External id": 705480,"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": 6305205087236.277, "dur": 30.195, + "args": { + "External id": 705481,"Sequence number": 7674612, "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": 6305205087237.851, "dur": 28.380, + "args": { + "External id": 705482,"Sequence number": 7674612, "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": 6305205087240.478, "dur": 7.937, + "args": { + "External id": 705483,"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": 6305205087243.193, "dur": 4.636, + "args": { + "External id": 705484,"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": 6305205087249.451, "dur": 16.293, + "args": { + "External id": 705485,"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": 6305205087294.291, "dur": 3.531, + "args": { + "External id": 705486,"Sequence number": 7674612, "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": 6305205087294.291, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6305205087300.418, "dur": 1.121, + "args": { + "External id": 705487,"Sequence number": 7674613, "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": 6305205087333.634, "dur": 47639.519, + "args": { + "External id": 705488,"Sequence number": 7674613, "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": 6305205087333.634, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338707, "tid": 2338707, + "ts": 6305205087349.386, "dur": 29.769, + "args": { + "External id": 705489,"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": 6305205087349.885, "dur": 29.067, + "args": { + "External id": 705490,"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": 6305205087351.124, "dur": 8.826, + "args": { + "External id": 705491,"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": 6305205087354.417, "dur": 4.963, + "args": { + "External id": 705492,"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": 6305205087360.741, "dur": 17.785, + "args": { + "External id": 705493,"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": 6305205087395.262, "dur": 25.283, + "args": { + "External id": 705494,"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": 6305205087396.378, "dur": 6.274, + "args": { + "External id": 705495,"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": 6305205087398.675, "dur": 3.686, + "args": { + "External id": 705496,"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": 6305205087404.107, "dur": 16.221, + "args": { + "External id": 705497,"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": 6305205087405.808, "dur": 13.988, + "args": { + "External id": 705498,"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": 6305205087429.522, "dur": 20.023, + "args": { + "External id": 705499,"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": 6305205087430.114, "dur": 4.287, + "args": { + "External id": 705500,"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": 6305205087431.213, "dur": 2.976, + "args": { + "External id": 705501,"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": 6305205087437.284, "dur": 12.062, + "args": { + "External id": 705502,"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": 6305205087437.887, "dur": 11.158, + "args": { + "External id": 705503,"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": 6305205087455.920, "dur": 18.410, + "args": { + "External id": 705504,"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": 6305205087457.688, "dur": 5.521, + "args": { + "External id": 705505,"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": 6305205087463.845, "dur": 10.119, + "args": { + "External id": 705506,"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": 6305205087464.824, "dur": 8.876, + "args": { + "External id": 705507,"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": 6305205087480.153, "dur": 21.646, + "args": { + "External id": 705508,"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": 6305205087504.886, "dur": 69.961, + "args": { + "External id": 705509,"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": 6305205087525.013, "dur": 49.198, + "args": { + "External id": 705510,"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": 6305205087530.290, "dur": 1.460, + "args": { + "External id": 705511,"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": 6305205087533.155, "dur": 24.999, + "args": { + "External id": 705512,"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": 6305205087534.513, "dur": 23.446, + "args": { + "External id": 705513,"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": 6305205087538.849, "dur": 2.884, + "args": { + "External id": 705514,"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": 6305205087542.515, "dur": 14.996, + "args": { + "External id": 705515,"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": 6305205087579.558, "dur": 41596.582, + "args": { + "External id": 705516,"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": 6305205087581.291, "dur": 41593.719, + "args": { + "External id": 705517,"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": 6305205129188.602, "dur": 7.667, + "args": { + "External id": 705518,"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": 6305205129193.315, "dur": 1.095, + "args": { + "External id": 705519,"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": 6305205129204.035, "dur": 105.067, + "args": { + "External id": 705520,"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": 6305205129205.651, "dur": 6.589, + "args": { + "External id": 705521,"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": 6305205129208.238, "dur": 2.947, + "args": { + "External id": 705522,"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": 6305205129210.215, "dur": 0.684, + "args": { + "External id": 705523,"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": 6305205129213.477, "dur": 94.824, + "args": { + "External id": 705524,"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": 6305205129215.181, "dur": 92.032, + "args": { + "External id": 705525,"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": 6305205129312.622, "dur": 4.291, + "args": { + "External id": 705526,"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": 6305205129315.009, "dur": 0.640, + "args": { + "External id": 705527,"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": 6305205129327.376, "dur": 2.015, + "args": { + "External id": 705528,"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": 6305205129340.248, "dur": 6.858, + "args": { + "External id": 705529,"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": 6305205129342.581, "dur": 4.244, + "args": { + "External id": 705530,"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": 6305205129481.835, "dur": 259.174, + "args": { + "External id": 705531,"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": 6305205129484.741, "dur": 4.074, + "args": { + "External id": 705532,"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": 6305205129492.229, "dur": 248.322, + "args": { + "External id": 705533,"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": 6305205129496.286, "dur": 0.493, + "args": { + "External id": 705534,"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": 6305205129498.829, "dur": 38.113, + "args": { + "External id": 705535,"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": 6305205129539.827, "dur": 41.375, + "args": { + "External id": 705536,"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": 6305205129578.561, "dur": 2.311, + "args": { + "External id": 705537,"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": 6305205129582.404, "dur": 24.660, + "args": { + "External id": 705538,"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": 6305205129583.891, "dur": 1.571, + "args": { + "External id": 705539,"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": 6305205129586.789, "dur": 20.007, + "args": { + "External id": 705540,"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": 6305205129590.951, "dur": 3.232, + "args": { + "External id": 705541,"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": 6305205129611.194, "dur": 22.522, + "args": { + "External id": 705542,"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": 6305205129635.958, "dur": 14.235, + "args": { + "External id": 705543,"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": 6305205129653.959, "dur": 14.297, + "args": { + "External id": 705544,"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": 6305205129669.730, "dur": 12.601, + "args": { + "External id": 705545,"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": 6305205129684.074, "dur": 23.173, + "args": { + "External id": 705546,"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": 6305205129686.429, "dur": 1.387, + "args": { + "External id": 705547,"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": 6305205129689.938, "dur": 2.232, + "args": { + "External id": 705548,"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": 6305205129711.671, "dur": 13.748, + "args": { + "External id": 705549,"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": 6305205129726.692, "dur": 12.827, + "args": { + "External id": 705550,"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": 6305205129750.091, "dur": 2.505, + "args": { + "External id": 705551,"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": 6305205129760.698, "dur": 3.970, + "args": { + "External id": 705552,"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": 6305205129763.241, "dur": 0.375, + "args": { + "External id": 705553,"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": 6305205129844.507, "dur": 74.996, + "args": { + "External id": 705554,"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": 6305205129925.683, "dur": 6.640, + "args": { + "External id": 705555,"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": 6305205129929.043, "dur": 0.712, + "args": { + "External id": 705556,"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": 6305205129936.030, "dur": 29.630, + "args": { + "External id": 705557,"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": 6305205129971.137, "dur": 7.166, + "args": { + "External id": 705558,"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": 6305205129973.565, "dur": 3.882, + "args": { + "External id": 705559,"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": 6305205129975.759, "dur": 1.424, + "args": { + "External id": 705560,"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": 6305205129981.671, "dur": 44.501, + "args": { + "External id": 705561,"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": 6305205129982.843, "dur": 42.601, + "args": { + "External id": 705562,"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": 6305205130030.817, "dur": 14.733, + "args": { + "External id": 705563,"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": 6305205130104.256, "dur": 5.982, + "args": { + "External id": 705564,"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": 6305205130107.747, "dur": 0.907, + "args": { + "External id": 705565,"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": 6305205130116.466, "dur": 58.535, + "args": { + "External id": 705566,"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": 6305205130117.572, "dur": 5.966, + "args": { + "External id": 705567,"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": 6305205130118.470, "dur": 4.488, + "args": { + "External id": 705568,"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": 6305205130120.070, "dur": 2.761, + "args": { + "External id": 705569,"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": 6305205130126.278, "dur": 48.288, + "args": { + "External id": 705570,"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": 6305205130127.305, "dur": 46.620, + "args": { + "External id": 705571,"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": 6305205130180.107, "dur": 3.870, + "args": { + "External id": 705572,"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": 6305205130182.186, "dur": 0.628, + "args": { + "External id": 705573,"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": 6305205130191.163, "dur": 1.914, + "args": { + "External id": 705574,"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": 6305205130202.251, "dur": 9.803, + "args": { + "External id": 705575,"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": 6305205130207.285, "dur": 4.520, + "args": { + "External id": 705576,"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": 6305205130314.033, "dur": 213.548, + "args": { + "External id": 705577,"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": 6305205130317.524, "dur": 1.543, + "args": { + "External id": 705578,"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": 6305205130320.697, "dur": 206.282, + "args": { + "External id": 705579,"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": 6305205130322.530, "dur": 1.317, + "args": { + "External id": 705580,"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": 6305205130325.761, "dur": 22.747, + "args": { + "External id": 705581,"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": 6305205130350.205, "dur": 5.553, + "args": { + "External id": 705582,"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": 6305205130354.954, "dur": 0.600, + "args": { + "External id": 705583,"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": 6305205130358.960, "dur": 21.731, + "args": { + "External id": 705584,"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": 6305205130360.203, "dur": 0.924, + "args": { + "External id": 705585,"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": 6305205130362.687, "dur": 17.632, + "args": { + "External id": 705586,"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": 6305205130366.067, "dur": 2.132, + "args": { + "External id": 705587,"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": 6305205130382.086, "dur": 24.867, + "args": { + "External id": 705588,"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": 6305205130408.474, "dur": 18.456, + "args": { + "External id": 705589,"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": 6305205130429.945, "dur": 14.266, + "args": { + "External id": 705590,"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": 6305205130445.858, "dur": 13.751, + "args": { + "External id": 705591,"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": 6305205130461.480, "dur": 23.616, + "args": { + "External id": 705592,"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": 6305205130463.656, "dur": 2.229, + "args": { + "External id": 705593,"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": 6305205130470.687, "dur": 0.698, + "args": { + "External id": 705594,"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": 6305205130486.678, "dur": 11.268, + "args": { + "External id": 705595,"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": 6305205130499.047, "dur": 25.524, + "args": { + "External id": 705596,"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": 6305205130537.172, "dur": 3.051, + "args": { + "External id": 705597,"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": 6305205130550.553, "dur": 4.720, + "args": { + "External id": 705598,"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": 6305205130553.916, "dur": 0.435, + "args": { + "External id": 705599,"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": 6305205130625.640, "dur": 60.076, + "args": { + "External id": 705600,"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": 6305205130691.583, "dur": 6.953, + "args": { + "External id": 705601,"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": 6305205130696.675, "dur": 0.817, + "args": { + "External id": 705602,"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": 6305205130700.086, "dur": 26.526, + "args": { + "External id": 705603,"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": 6305205130731.584, "dur": 6.288, + "args": { + "External id": 705604,"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": 6305205130733.378, "dur": 3.885, + "args": { + "External id": 705605,"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": 6305205130735.511, "dur": 1.530, + "args": { + "External id": 705606,"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": 6305205130749.272, "dur": 44.227, + "args": { + "External id": 705607,"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": 6305205130752.610, "dur": 40.293, + "args": { + "External id": 705608,"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": 6305205130797.486, "dur": 14.745, + "args": { + "External id": 705609,"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": 6305205130817.730, "dur": 4.008, + "args": { + "External id": 705610,"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": 6305205130820.151, "dur": 0.605, + "args": { + "External id": 705611,"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": 6305205130825.813, "dur": 46.502, + "args": { + "External id": 705612,"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": 6305205130826.674, "dur": 6.251, + "args": { + "External id": 705613,"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": 6305205130827.558, "dur": 4.789, + "args": { + "External id": 705614,"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": 6305205130831.436, "dur": 0.770, + "args": { + "External id": 705615,"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": 6305205130833.677, "dur": 38.225, + "args": { + "External id": 705616,"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": 6305205130834.076, "dur": 37.070, + "args": { + "External id": 705617,"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": 6305205130876.541, "dur": 4.031, + "args": { + "External id": 705618,"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": 6305205130878.880, "dur": 0.406, + "args": { + "External id": 705619,"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": 6305205130885.971, "dur": 1.678, + "args": { + "External id": 705620,"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": 6305205130895.941, "dur": 11.338, + "args": { + "External id": 705621,"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": 6305205130900.167, "dur": 6.800, + "args": { + "External id": 705622,"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": 6305205130993.859, "dur": 252.945, + "args": { + "External id": 705623,"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": 6305205130996.284, "dur": 1.658, + "args": { + "External id": 705624,"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": 6305205130999.288, "dur": 247.086, + "args": { + "External id": 705625,"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": 6305205131000.879, "dur": 0.349, + "args": { + "External id": 705626,"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": 6305205131002.780, "dur": 24.276, + "args": { + "External id": 705627,"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": 6305205131028.883, "dur": 3.405, + "args": { + "External id": 705628,"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": 6305205131031.614, "dur": 0.467, + "args": { + "External id": 705629,"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": 6305205131035.803, "dur": 78.167, + "args": { + "External id": 705630,"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": 6305205131036.662, "dur": 1.515, + "args": { + "External id": 705631,"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": 6305205131039.649, "dur": 73.683, + "args": { + "External id": 705632,"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": 6305205131044.621, "dur": 2.290, + "args": { + "External id": 705633,"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": 6305205131116.149, "dur": 27.524, + "args": { + "External id": 705634,"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": 6305205131145.187, "dur": 15.067, + "args": { + "External id": 705635,"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": 6305205131163.250, "dur": 14.682, + "args": { + "External id": 705636,"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": 6305205131179.403, "dur": 14.124, + "args": { + "External id": 705637,"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": 6305205131195.849, "dur": 24.043, + "args": { + "External id": 705638,"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": 6305205131200.554, "dur": 1.593, + "args": { + "External id": 705639,"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": 6305205131204.661, "dur": 0.923, + "args": { + "External id": 705640,"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": 6305205131221.320, "dur": 12.013, + "args": { + "External id": 705641,"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": 6305205131234.749, "dur": 10.532, + "args": { + "External id": 705642,"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": 6305205131255.457, "dur": 2.399, + "args": { + "External id": 705643,"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": 6305205131267.962, "dur": 4.282, + "args": { + "External id": 705644,"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": 6305205131270.844, "dur": 0.475, + "args": { + "External id": 705645,"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": 6305205131345.049, "dur": 66.857, + "args": { + "External id": 705646,"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": 6305205131417.195, "dur": 5.107, + "args": { + "External id": 705647,"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": 6305205131420.128, "dur": 1.078, + "args": { + "External id": 705648,"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": 6305205131423.859, "dur": 26.659, + "args": { + "External id": 705649,"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": 6305205131454.922, "dur": 7.354, + "args": { + "External id": 705650,"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": 6305205131456.710, "dur": 4.953, + "args": { + "External id": 705651,"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": 6305205131460.636, "dur": 0.839, + "args": { + "External id": 705652,"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": 6305205131464.752, "dur": 57.590, + "args": { + "External id": 705653,"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": 6305205131465.888, "dur": 55.465, + "args": { + "External id": 705654,"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": 6305205131527.995, "dur": 16.221, + "args": { + "External id": 705655,"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": 6305205131551.187, "dur": 6.256, + "args": { + "External id": 705656,"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": 6305205131555.623, "dur": 0.667, + "args": { + "External id": 705657,"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": 6305205131561.534, "dur": 51.230, + "args": { + "External id": 705658,"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": 6305205131564.699, "dur": 5.971, + "args": { + "External id": 705659,"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": 6305205131565.707, "dur": 4.341, + "args": { + "External id": 705660,"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": 6305205131567.473, "dur": 2.356, + "args": { + "External id": 705661,"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": 6305205131571.269, "dur": 41.049, + "args": { + "External id": 705662,"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": 6305205131572.199, "dur": 39.649, + "args": { + "External id": 705663,"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": 6305205131617.059, "dur": 3.838, + "args": { + "External id": 705664,"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": 6305205131619.043, "dur": 0.632, + "args": { + "External id": 705665,"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": 6305205131629.196, "dur": 1.553, + "args": { + "External id": 705666,"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": 6305205131638.870, "dur": 8.188, + "args": { + "External id": 705667,"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": 6305205131641.142, "dur": 5.629, + "args": { + "External id": 705668,"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": 6305205131733.648, "dur": 175.206, + "args": { + "External id": 705669,"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": 6305205131736.036, "dur": 1.402, + "args": { + "External id": 705670,"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": 6305205131740.599, "dur": 167.869, + "args": { + "External id": 705671,"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": 6305205131742.166, "dur": 0.346, + "args": { + "External id": 705672,"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": 6305205131745.311, "dur": 19.864, + "args": { + "External id": 705673,"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": 6305205131766.670, "dur": 3.878, + "args": { + "External id": 705674,"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": 6305205131769.585, "dur": 0.789, + "args": { + "External id": 705675,"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": 6305205131771.595, "dur": 22.393, + "args": { + "External id": 705676,"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": 6305205131772.631, "dur": 2.932, + "args": { + "External id": 705677,"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": 6305205131776.985, "dur": 16.635, + "args": { + "External id": 705678,"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": 6305205131779.851, "dur": 2.157, + "args": { + "External id": 705679,"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": 6305205131795.510, "dur": 18.591, + "args": { + "External id": 705680,"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": 6305205131815.400, "dur": 13.019, + "args": { + "External id": 705681,"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": 6305205131833.509, "dur": 14.052, + "args": { + "External id": 705682,"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": 6305205131849.166, "dur": 13.168, + "args": { + "External id": 705683,"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": 6305205131863.945, "dur": 18.196, + "args": { + "External id": 705684,"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": 6305205131866.059, "dur": 1.477, + "args": { + "External id": 705685,"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": 6305205131869.509, "dur": 0.594, + "args": { + "External id": 705686,"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": 6305205131883.390, "dur": 11.076, + "args": { + "External id": 705687,"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": 6305205131897.611, "dur": 9.593, + "args": { + "External id": 705688,"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": 6305205131915.463, "dur": 1.410, + "args": { + "External id": 705689,"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": 6305205131925.862, "dur": 3.540, + "args": { + "External id": 705690,"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": 6305205131927.927, "dur": 0.545, + "args": { + "External id": 705691,"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": 6305205131990.955, "dur": 50.808, + "args": { + "External id": 705692,"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": 6305205132046.771, "dur": 52.718, + "args": { + "External id": 705693,"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": 6305205132050.308, "dur": 0.694, + "args": { + "External id": 705694,"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": 6305205132102.228, "dur": 29.083, + "args": { + "External id": 705695,"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": 6305205132138.077, "dur": 9.413, + "args": { + "External id": 705696,"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": 6305205132142.803, "dur": 3.932, + "args": { + "External id": 705697,"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": 6305205132145.248, "dur": 1.182, + "args": { + "External id": 705698,"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": 6305205132150.632, "dur": 47.734, + "args": { + "External id": 705699,"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": 6305205132152.088, "dur": 45.668, + "args": { + "External id": 705700,"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": 6305205132202.633, "dur": 15.302, + "args": { + "External id": 705701,"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": 6305205132224.518, "dur": 6.557, + "args": { + "External id": 705702,"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": 6305205132229.216, "dur": 0.744, + "args": { + "External id": 705703,"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": 6305205132236.075, "dur": 47.753, + "args": { + "External id": 705704,"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": 6305205132237.124, "dur": 5.693, + "args": { + "External id": 705705,"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": 6305205132238.112, "dur": 4.059, + "args": { + "External id": 705706,"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": 6305205132241.501, "dur": 0.510, + "args": { + "External id": 705707,"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": 6305205132243.737, "dur": 39.651, + "args": { + "External id": 705708,"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": 6305205132244.395, "dur": 38.465, + "args": { + "External id": 705709,"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": 6305205132288.877, "dur": 4.154, + "args": { + "External id": 705710,"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": 6305205132291.051, "dur": 0.673, + "args": { + "External id": 705711,"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": 6305205132301.424, "dur": 2.018, + "args": { + "External id": 705712,"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": 6305205132311.584, "dur": 6.631, + "args": { + "External id": 705713,"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": 6305205132313.662, "dur": 4.290, + "args": { + "External id": 705714,"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": 6305205132410.265, "dur": 216.269, + "args": { + "External id": 705715,"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": 6305205132412.815, "dur": 2.010, + "args": { + "External id": 705716,"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": 6305205132418.459, "dur": 207.542, + "args": { + "External id": 705717,"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": 6305205132421.836, "dur": 0.343, + "args": { + "External id": 705718,"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": 6305205132423.231, "dur": 19.994, + "args": { + "External id": 705719,"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": 6305205132444.975, "dur": 3.044, + "args": { + "External id": 705720,"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": 6305205132447.258, "dur": 0.567, + "args": { + "External id": 705721,"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": 6305205132448.847, "dur": 23.312, + "args": { + "External id": 705722,"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": 6305205132452.344, "dur": 1.114, + "args": { + "External id": 705723,"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": 6305205132454.968, "dur": 16.923, + "args": { + "External id": 705724,"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": 6305205132457.968, "dur": 3.103, + "args": { + "External id": 705725,"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": 6305205132475.831, "dur": 23.661, + "args": { + "External id": 705726,"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": 6305205132501.332, "dur": 30.910, + "args": { + "External id": 705727,"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": 6305205132536.663, "dur": 16.188, + "args": { + "External id": 705728,"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": 6305205132554.518, "dur": 14.176, + "args": { + "External id": 705729,"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": 6305205132570.579, "dur": 22.819, + "args": { + "External id": 705730,"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": 6305205132572.944, "dur": 1.867, + "args": { + "External id": 705731,"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": 6305205132577.279, "dur": 0.638, + "args": { + "External id": 705732,"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": 6305205132597.715, "dur": 13.651, + "args": { + "External id": 705733,"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": 6305205132612.768, "dur": 12.204, + "args": { + "External id": 705734,"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": 6305205132635.486, "dur": 2.038, + "args": { + "External id": 705735,"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": 6305205132647.095, "dur": 3.817, + "args": { + "External id": 705736,"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": 6305205132649.560, "dur": 0.455, + "args": { + "External id": 705737,"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": 6305205132722.286, "dur": 59.195, + "args": { + "External id": 705738,"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": 6305205132786.027, "dur": 6.537, + "args": { + "External id": 705739,"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": 6305205132789.175, "dur": 2.189, + "args": { + "External id": 705740,"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": 6305205132796.491, "dur": 27.957, + "args": { + "External id": 705741,"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": 6305205132828.837, "dur": 4.708, + "args": { + "External id": 705742,"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": 6305205132830.191, "dur": 2.722, + "args": { + "External id": 705743,"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": 6305205132831.951, "dur": 0.664, + "args": { + "External id": 705744,"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": 6305205132835.920, "dur": 40.652, + "args": { + "External id": 705745,"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": 6305205132837.014, "dur": 38.959, + "args": { + "External id": 705746,"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": 6305205132880.360, "dur": 14.772, + "args": { + "External id": 705747,"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": 6305205132903.060, "dur": 3.696, + "args": { + "External id": 705748,"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": 6305205132905.327, "dur": 0.586, + "args": { + "External id": 705749,"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": 6305205132910.520, "dur": 48.091, + "args": { + "External id": 705750,"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": 6305205132911.226, "dur": 3.571, + "args": { + "External id": 705751,"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": 6305205132911.765, "dur": 2.456, + "args": { + "External id": 705752,"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": 6305205132913.257, "dur": 0.843, + "args": { + "External id": 705753,"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": 6305205132917.206, "dur": 41.065, + "args": { + "External id": 705754,"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": 6305205132917.986, "dur": 39.609, + "args": { + "External id": 705755,"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": 6305205132962.110, "dur": 3.877, + "args": { + "External id": 705756,"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": 6305205132964.404, "dur": 0.455, + "args": { + "External id": 705757,"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": 6305205132971.145, "dur": 1.527, + "args": { + "External id": 705758,"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": 6305205132980.901, "dur": 10.123, + "args": { + "External id": 705759,"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": 6305205132985.046, "dur": 5.707, + "args": { + "External id": 705760,"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": 6305205133125.655, "dur": 180.560, + "args": { + "External id": 705761,"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": 6305205133127.956, "dur": 4.878, + "args": { + "External id": 705762,"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": 6305205133134.720, "dur": 170.979, + "args": { + "External id": 705763,"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": 6305205133136.293, "dur": 0.528, + "args": { + "External id": 705764,"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": 6305205133137.785, "dur": 21.774, + "args": { + "External id": 705765,"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": 6305205133161.326, "dur": 5.400, + "args": { + "External id": 705766,"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": 6305205133165.254, "dur": 1.219, + "args": { + "External id": 705767,"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": 6305205133170.324, "dur": 20.727, + "args": { + "External id": 705768,"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": 6305205133171.505, "dur": 0.955, + "args": { + "External id": 705769,"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": 6305205133174.197, "dur": 16.562, + "args": { + "External id": 705770,"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": 6305205133177.097, "dur": 2.204, + "args": { + "External id": 705771,"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": 6305205133192.481, "dur": 19.266, + "args": { + "External id": 705772,"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": 6305205133213.454, "dur": 13.040, + "args": { + "External id": 705773,"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": 6305205133229.122, "dur": 12.409, + "args": { + "External id": 705774,"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": 6305205133243.013, "dur": 11.264, + "args": { + "External id": 705775,"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": 6305205133255.916, "dur": 22.704, + "args": { + "External id": 705776,"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": 6305205133259.852, "dur": 1.432, + "args": { + "External id": 705777,"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": 6305205133265.464, "dur": 0.693, + "args": { + "External id": 705778,"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": 6305205133280.074, "dur": 12.620, + "args": { + "External id": 705779,"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": 6305205133293.658, "dur": 10.959, + "args": { + "External id": 705780,"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": 6305205133313.828, "dur": 2.210, + "args": { + "External id": 705781,"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": 6305205133325.961, "dur": 3.910, + "args": { + "External id": 705782,"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": 6305205133328.432, "dur": 0.515, + "args": { + "External id": 705783,"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": 6305205133398.311, "dur": 57.094, + "args": { + "External id": 705784,"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": 6305205133460.428, "dur": 6.407, + "args": { + "External id": 705785,"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": 6305205133465.194, "dur": 0.573, + "args": { + "External id": 705786,"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": 6305205133468.365, "dur": 24.757, + "args": { + "External id": 705787,"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": 6305205133497.454, "dur": 5.666, + "args": { + "External id": 705788,"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": 6305205133499.032, "dur": 3.358, + "args": { + "External id": 705789,"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": 6305205133501.173, "dur": 1.055, + "args": { + "External id": 705790,"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": 6305205133520.288, "dur": 49.686, + "args": { + "External id": 705791,"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": 6305205133523.605, "dur": 45.457, + "args": { + "External id": 705792,"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": 6305205133574.568, "dur": 14.803, + "args": { + "External id": 705793,"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": 6305205133595.505, "dur": 4.221, + "args": { + "External id": 705794,"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": 6305205133598.069, "dur": 0.497, + "args": { + "External id": 705795,"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": 6305205133603.973, "dur": 44.897, + "args": { + "External id": 705796,"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": 6305205133604.653, "dur": 5.942, + "args": { + "External id": 705797,"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": 6305205133605.771, "dur": 4.202, + "args": { + "External id": 705798,"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": 6305205133609.157, "dur": 0.688, + "args": { + "External id": 705799,"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": 6305205133611.135, "dur": 37.251, + "args": { + "External id": 705800,"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": 6305205133611.642, "dur": 35.918, + "args": { + "External id": 705801,"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": 6305205133653.749, "dur": 5.720, + "args": { + "External id": 705802,"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": 6305205133656.037, "dur": 2.435, + "args": { + "External id": 705803,"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": 6305205133666.132, "dur": 1.583, + "args": { + "External id": 705804,"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": 6305205133676.199, "dur": 8.338, + "args": { + "External id": 705805,"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": 6305205133680.769, "dur": 3.520, + "args": { + "External id": 705806,"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": 6305205133767.315, "dur": 171.977, + "args": { + "External id": 705807,"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": 6305205133770.436, "dur": 1.701, + "args": { + "External id": 705808,"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": 6305205133773.729, "dur": 165.127, + "args": { + "External id": 705809,"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": 6305205133775.167, "dur": 0.349, + "args": { + "External id": 705810,"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": 6305205133776.422, "dur": 19.395, + "args": { + "External id": 705811,"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": 6305205133797.677, "dur": 4.370, + "args": { + "External id": 705812,"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": 6305205133801.132, "dur": 0.749, + "args": { + "External id": 705813,"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": 6305205133805.532, "dur": 20.090, + "args": { + "External id": 705814,"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": 6305205133806.737, "dur": 1.019, + "args": { + "External id": 705815,"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": 6305205133808.848, "dur": 16.420, + "args": { + "External id": 705816,"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": 6305205133811.360, "dur": 3.222, + "args": { + "External id": 705817,"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": 6305205133827.171, "dur": 20.811, + "args": { + "External id": 705818,"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": 6305205133849.427, "dur": 13.455, + "args": { + "External id": 705819,"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": 6305205133865.556, "dur": 13.737, + "args": { + "External id": 705820,"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": 6305205133880.840, "dur": 11.085, + "args": { + "External id": 705821,"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": 6305205133893.169, "dur": 20.298, + "args": { + "External id": 705822,"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": 6305205133897.699, "dur": 1.324, + "args": { + "External id": 705823,"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": 6305205133900.938, "dur": 0.671, + "args": { + "External id": 705824,"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": 6305205133914.877, "dur": 11.305, + "args": { + "External id": 705825,"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": 6305205133926.997, "dur": 10.754, + "args": { + "External id": 705826,"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": 6305205133945.336, "dur": 1.657, + "args": { + "External id": 705827,"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": 6305205133955.066, "dur": 3.593, + "args": { + "External id": 705828,"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": 6305205133957.348, "dur": 0.529, + "args": { + "External id": 705829,"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": 6305205134021.262, "dur": 86.506, + "args": { + "External id": 705830,"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": 6305205134115.785, "dur": 6.868, + "args": { + "External id": 705831,"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": 6305205134119.582, "dur": 1.280, + "args": { + "External id": 705832,"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": 6305205134124.113, "dur": 29.119, + "args": { + "External id": 705833,"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": 6305205134158.471, "dur": 8.640, + "args": { + "External id": 705834,"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": 6305205134160.007, "dur": 6.382, + "args": { + "External id": 705835,"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": 6305205134164.928, "dur": 1.202, + "args": { + "External id": 705836,"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": 6305205134170.122, "dur": 45.386, + "args": { + "External id": 705837,"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": 6305205134171.515, "dur": 43.533, + "args": { + "External id": 705838,"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": 6305205134219.264, "dur": 17.418, + "args": { + "External id": 705839,"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": 6305205134242.649, "dur": 3.803, + "args": { + "External id": 705840,"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": 6305205134245.063, "dur": 0.574, + "args": { + "External id": 705841,"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": 6305205134250.366, "dur": 46.387, + "args": { + "External id": 705842,"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": 6305205134253.571, "dur": 4.280, + "args": { + "External id": 705843,"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": 6305205134254.257, "dur": 2.988, + "args": { + "External id": 705844,"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": 6305205134256.507, "dur": 0.617, + "args": { + "External id": 705845,"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": 6305205134258.630, "dur": 37.634, + "args": { + "External id": 705846,"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": 6305205134259.048, "dur": 36.537, + "args": { + "External id": 705847,"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": 6305205134300.437, "dur": 3.325, + "args": { + "External id": 705848,"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": 6305205134302.256, "dur": 0.503, + "args": { + "External id": 705849,"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": 6305205134312.364, "dur": 1.456, + "args": { + "External id": 705850,"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": 6305205134321.524, "dur": 7.590, + "args": { + "External id": 705851,"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": 6305205134323.261, "dur": 5.557, + "args": { + "External id": 705852,"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": 6305205134411.302, "dur": 204.314, + "args": { + "External id": 705853,"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": 6305205134413.251, "dur": 3.778, + "args": { + "External id": 705854,"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": 6305205134420.885, "dur": 194.330, + "args": { + "External id": 705855,"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": 6305205134422.425, "dur": 0.319, + "args": { + "External id": 705856,"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": 6305205134423.635, "dur": 21.628, + "args": { + "External id": 705857,"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": 6305205134447.122, "dur": 2.981, + "args": { + "External id": 705858,"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": 6305205134449.004, "dur": 0.912, + "args": { + "External id": 705859,"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": 6305205134451.211, "dur": 22.414, + "args": { + "External id": 705860,"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": 6305205134452.333, "dur": 1.406, + "args": { + "External id": 705861,"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": 6305205134455.500, "dur": 17.854, + "args": { + "External id": 705862,"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": 6305205134460.176, "dur": 2.737, + "args": { + "External id": 705863,"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": 6305205134474.907, "dur": 18.564, + "args": { + "External id": 705864,"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": 6305205134494.977, "dur": 29.061, + "args": { + "External id": 705865,"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": 6305205134529.807, "dur": 13.546, + "args": { + "External id": 705866,"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": 6305205134544.832, "dur": 16.900, + "args": { + "External id": 705867,"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": 6305205134563.745, "dur": 21.517, + "args": { + "External id": 705868,"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": 6305205134565.700, "dur": 1.725, + "args": { + "External id": 705869,"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": 6305205134569.318, "dur": 0.678, + "args": { + "External id": 705870,"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": 6305205134586.519, "dur": 13.726, + "args": { + "External id": 705871,"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": 6305205134603.869, "dur": 10.364, + "args": { + "External id": 705872,"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": 6305205134623.065, "dur": 2.170, + "args": { + "External id": 705873,"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": 6305205134633.753, "dur": 4.000, + "args": { + "External id": 705874,"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": 6305205134636.303, "dur": 0.614, + "args": { + "External id": 705875,"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": 6305205134704.288, "dur": 55.404, + "args": { + "External id": 705876,"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": 6305205134764.322, "dur": 4.783, + "args": { + "External id": 705877,"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": 6305205134767.389, "dur": 0.733, + "args": { + "External id": 705878,"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": 6305205134770.381, "dur": 25.832, + "args": { + "External id": 705879,"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": 6305205134800.665, "dur": 7.588, + "args": { + "External id": 705880,"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": 6305205134804.178, "dur": 3.269, + "args": { + "External id": 705881,"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": 6305205134806.289, "dur": 0.982, + "args": { + "External id": 705882,"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": 6305205134810.783, "dur": 39.719, + "args": { + "External id": 705883,"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": 6305205134811.896, "dur": 37.978, + "args": { + "External id": 705884,"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": 6305205134853.886, "dur": 15.018, + "args": { + "External id": 705885,"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": 6305205134873.133, "dur": 23.828, + "args": { + "External id": 705886,"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": 6305205134875.585, "dur": 20.967, + "args": { + "External id": 705887,"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": 6305205134881.889, "dur": 0.412, + "args": { + "External id": 705888,"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": 6305205134901.504, "dur": 27.386, + "args": { + "External id": 705889,"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": 6305205134905.972, "dur": 22.714, + "args": { + "External id": 705890,"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": 6305205134910.265, "dur": 3.578, + "args": { + "External id": 705891,"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": 6305205134915.171, "dur": 13.074, + "args": { + "External id": 705892,"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": 6305205134940.270, "dur": 5.084, + "args": { + "External id": 705893,"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": 6305205134942.510, "dur": 2.546, + "args": { + "External id": 705894,"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": 6305205134946.679, "dur": 3.967, + "args": { + "External id": 705895,"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": 6305205134949.667, "dur": 0.672, + "args": { + "External id": 705896,"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": 6305205134991.836, "dur": 22.176, + "args": { + "External id": 705897,"Sequence number": 7674614, "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": 6305205135015.949, "dur": 13.916, + "args": { + "External id": 705898,"Sequence number": 7674615, "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": 6305205135015.949, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward", "pid": 2338707, "tid": 2338707, + "ts": 6305205135182.335, "dur": 41.575, + "args": { + "External id": 705899,"Record function id": 0, "Ev Idx": 16303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::div", "pid": 2338707, "tid": 2338707, + "ts": 6305205135328.786, "dur": 41.718, + "args": { + "External id": 705900,"Sequence number": 7674616, "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": 6305205135328.786, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ones_like", "pid": 2338707, "tid": 2338707, + "ts": 6305205135448.075, "dur": 36.822, + "args": { + "External id": 705901,"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": 6305205135457.417, "dur": 9.975, + "args": { + "External id": 705902,"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": 6305205135461.900, "dur": 4.727, + "args": { + "External id": 705903,"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": 6305205135469.151, "dur": 15.451, + "args": { + "External id": 705904,"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": 6305207235882.267, "dur": 47.515, + "args": { + "External id": 705905,"Sequence number": 7674617, "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": 6305207235937.984, "dur": 16.797, + "args": { + "External id": 705906,"Sequence number": 7674618, "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": 6305207235984.578, "dur": 2713.041, + "args": { + "External id": 705907,"Record function id": 0, "Ev Idx": 16311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6305207237529.194, "dur": 7.176, + "args": { + "External id": 705908,"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": 6305207237550.909, "dur": 7.440, + "args": { + "External id": 705909,"Sequence number": 7674619, "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": 6305207238099.229, "dur": 4.772, + "args": { + "External id": 705910,"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": 6305207238109.505, "dur": 2.448, + "args": { + "External id": 705911,"Sequence number": 7674619, "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": 6305207238566.156, "dur": 1.869, + "args": { + "External id": 705912,"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": 6305207238574.954, "dur": 2.065, + "args": { + "External id": 705913,"Sequence number": 7674619, "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": 6305207239110.918, "dur": 13.494, + "args": { + "External id": 705914,"Sequence number": 7674619, "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": 6305207239118.144, "dur": 2.309, + "args": { + "External id": 705915,"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": 6305207239126.642, "dur": 4.077, + "args": { + "External id": 705916,"Sequence number": 7674619, "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": 6305207239128.505, "dur": 1.190, + "args": { + "External id": 705917,"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": 6305207239158.747, "dur": 15714.389, + "args": { + "External id": 705918,"Sequence number": 7674619, "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": 6305207239164.855, "dur": 15707.458, + "args": { + "External id": 705919,"Sequence number": 7674619, "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": 6305207239170.679, "dur": 9.332, + "args": { + "External id": 705920,"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": 6305207239181.839, "dur": 15688.975, + "args": { + "External id": 705921,"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": 6305207239191.048, "dur": 0.531, + "args": { + "External id": 705922,"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": 6305207239194.296, "dur": 9.665, + "args": { + "External id": 705923,"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": 6305207239196.994, "dur": 6.752, + "args": { + "External id": 705924,"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": 6305207239202.777, "dur": 0.717, + "args": { + "External id": 705925,"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": 6305207239206.106, "dur": 151.740, + "args": { + "External id": 705926,"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": 6305207239207.684, "dur": 149.830, + "args": { + "External id": 705927,"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": 6305207239209.805, "dur": 6.174, + "args": { + "External id": 705928,"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": 6305207239211.856, "dur": 3.644, + "args": { + "External id": 705929,"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": 6305207239216.772, "dur": 140.426, + "args": { + "External id": 705930,"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": 6305207239359.484, "dur": 15505.999, + "args": { + "External id": 705931,"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": 6305207254893.775, "dur": 388.037, + "args": { + "External id": 705932,"Sequence number": 7674619, "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": 6305207254896.083, "dur": 385.241, + "args": { + "External id": 705933,"Sequence number": 7674619, "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": 6305207254901.651, "dur": 9.039, + "args": { + "External id": 705934,"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": 6305207254911.998, "dur": 367.413, + "args": { + "External id": 705935,"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": 6305207255307.254, "dur": 50.364, + "args": { + "External id": 705936,"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": 6305207255312.419, "dur": 6.818, + "args": { + "External id": 705937,"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": 6305207255322.178, "dur": 35.076, + "args": { + "External id": 705938,"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": 6305207255326.948, "dur": 5.928, + "args": { + "External id": 705939,"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": 6305207255371.983, "dur": 65.698, + "args": { + "External id": 705940,"Sequence number": 7674619, "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": 6305207255377.335, "dur": 5.382, + "args": { + "External id": 705941,"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": 6305207255380.444, "dur": 1.995, + "args": { + "External id": 705942,"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": 6305207255384.130, "dur": 2.501, + "args": { + "External id": 705943,"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": 6305207255388.481, "dur": 1.874, + "args": { + "External id": 705944,"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": 6305207255394.875, "dur": 6.757, + "args": { + "External id": 705945,"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": 6305207255400.565, "dur": 0.905, + "args": { + "External id": 705946,"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": 6305207255402.518, "dur": 2.774, + "args": { + "External id": 705947,"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": 6305207255404.315, "dur": 0.890, + "args": { + "External id": 705948,"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": 6305207255407.262, "dur": 4.393, + "args": { + "External id": 705949,"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": 6305207255408.955, "dur": 2.572, + "args": { + "External id": 705950,"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": 6305207255410.385, "dur": 1.020, + "args": { + "External id": 705951,"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": 6305207255412.784, "dur": 24.251, + "args": { + "External id": 705952,"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": 6305207255445.748, "dur": 28.759, + "args": { + "External id": 705953,"Sequence number": 7674619, "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": 6305207255447.322, "dur": 26.997, + "args": { + "External id": 705954,"Sequence number": 7674619, "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": 6305207255452.581, "dur": 2.990, + "args": { + "External id": 705955,"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": 6305207255456.482, "dur": 17.284, + "args": { + "External id": 705956,"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": 6305207255603.612, "dur": 148.007, + "args": { + "External id": 705957,"Record function id": 0, "Ev Idx": 16361 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::inputs_to_device", "pid": 2338707, "tid": 2338707, + "ts": 6305207255683.415, "dur": 56.851, + "args": { + "External id": 705958,"Record function id": 0, "Ev Idx": 16362 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6305207255758.119, "dur": 44.270, + "args": { + "External id": 705959,"Record function id": 0, "Ev Idx": 16363 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward", "pid": 2338707, "tid": 2338707, + "ts": 6305207255810.352, "dur": 14088.497, + "args": { + "External id": 705960,"Record function id": 0, "Ev Idx": 16364 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather", "pid": 2338707, "tid": 2338707, + "ts": 6305207255817.121, "dur": 1600.721, + "args": { + "External id": 705961,"Record function id": 0, "Ev Idx": 16365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6305207255919.895, "dur": 11.320, + "args": { + "External id": 705962,"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": 6305207255946.931, "dur": 162.401, + "args": { + "External id": 705963,"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": 6305207255952.038, "dur": 2.095, + "args": { + "External id": 705964,"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": 6305207255958.040, "dur": 0.514, + "args": { + "External id": 705965,"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": 6305207255959.982, "dur": 0.338, + "args": { + "External id": 705966,"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": 6305207255961.788, "dur": 2.709, + "args": { + "External id": 705967,"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": 6305207255965.793, "dur": 0.354, + "args": { + "External id": 705968,"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": 6305207255967.235, "dur": 0.269, + "args": { + "External id": 705969,"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": 6305207255970.794, "dur": 0.254, + "args": { + "External id": 705970,"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": 6305207255972.168, "dur": 2.513, + "args": { + "External id": 705971,"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": 6305207255975.865, "dur": 0.686, + "args": { + "External id": 705972,"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": 6305207255979.947, "dur": 0.633, + "args": { + "External id": 705973,"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": 6305207255981.988, "dur": 0.524, + "args": { + "External id": 705974,"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": 6305207255983.778, "dur": 2.047, + "args": { + "External id": 705975,"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": 6305207255987.195, "dur": 0.501, + "args": { + "External id": 705976,"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": 6305207255988.989, "dur": 0.235, + "args": { + "External id": 705977,"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": 6305207255992.360, "dur": 0.287, + "args": { + "External id": 705978,"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": 6305207255993.800, "dur": 2.537, + "args": { + "External id": 705979,"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": 6305207255997.617, "dur": 0.584, + "args": { + "External id": 705980,"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": 6305207256001.371, "dur": 0.643, + "args": { + "External id": 705981,"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": 6305207256003.286, "dur": 0.498, + "args": { + "External id": 705982,"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": 6305207256005.309, "dur": 2.096, + "args": { + "External id": 705983,"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": 6305207256008.613, "dur": 0.287, + "args": { + "External id": 705984,"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": 6305207256009.737, "dur": 0.378, + "args": { + "External id": 705985,"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": 6305207256013.040, "dur": 0.247, + "args": { + "External id": 705986,"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": 6305207256014.527, "dur": 2.288, + "args": { + "External id": 705987,"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": 6305207256017.971, "dur": 0.267, + "args": { + "External id": 705988,"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": 6305207256021.761, "dur": 0.279, + "args": { + "External id": 705989,"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": 6305207256023.237, "dur": 0.445, + "args": { + "External id": 705990,"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": 6305207256024.976, "dur": 2.162, + "args": { + "External id": 705991,"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": 6305207256028.548, "dur": 0.371, + "args": { + "External id": 705992,"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": 6305207256029.942, "dur": 0.333, + "args": { + "External id": 705993,"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": 6305207256033.871, "dur": 0.244, + "args": { + "External id": 705994,"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": 6305207256035.187, "dur": 2.324, + "args": { + "External id": 705995,"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": 6305207256038.565, "dur": 0.279, + "args": { + "External id": 705996,"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": 6305207256041.837, "dur": 0.658, + "args": { + "External id": 705997,"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": 6305207256043.840, "dur": 0.331, + "args": { + "External id": 705998,"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": 6305207256045.407, "dur": 1.786, + "args": { + "External id": 705999,"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": 6305207256048.233, "dur": 0.506, + "args": { + "External id": 706000,"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": 6305207256049.831, "dur": 0.385, + "args": { + "External id": 706001,"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": 6305207256090.507, "dur": 0.829, + "args": { + "External id": 706002,"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": 6305207256139.989, "dur": 139.566, + "args": { + "External id": 706003,"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": 6305207256349.675, "dur": 396.405, + "args": { + "External id": 706004,"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": 6305207256366.901, "dur": 7.734, + "args": { + "External id": 706005,"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": 6305207256380.783, "dur": 14.687, + "args": { + "External id": 706006,"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": 6305207256387.689, "dur": 7.354, + "args": { + "External id": 706007,"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": 6305207256391.548, "dur": 0.705, + "args": { + "External id": 706008,"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": 6305207256404.117, "dur": 139.653, + "args": { + "External id": 706009,"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": 6305207256406.320, "dur": 0.438, + "args": { + "External id": 706010,"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": 6305207256408.349, "dur": 2.459, + "args": { + "External id": 706011,"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": 6305207256412.024, "dur": 0.659, + "args": { + "External id": 706012,"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": 6305207256413.835, "dur": 0.503, + "args": { + "External id": 706013,"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": 6305207256417.959, "dur": 0.258, + "args": { + "External id": 706014,"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": 6305207256419.375, "dur": 0.396, + "args": { + "External id": 706015,"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": 6305207256420.808, "dur": 2.796, + "args": { + "External id": 706016,"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": 6305207256426.261, "dur": 0.385, + "args": { + "External id": 706017,"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": 6305207256427.875, "dur": 0.268, + "args": { + "External id": 706018,"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": 6305207256429.617, "dur": 2.218, + "args": { + "External id": 706019,"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": 6305207256432.941, "dur": 0.370, + "args": { + "External id": 706020,"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": 6305207256434.364, "dur": 0.664, + "args": { + "External id": 706021,"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": 6305207256438.164, "dur": 0.343, + "args": { + "External id": 706022,"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": 6305207256439.511, "dur": 0.449, + "args": { + "External id": 706023,"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": 6305207256441.088, "dur": 2.853, + "args": { + "External id": 706024,"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": 6305207256447.031, "dur": 0.292, + "args": { + "External id": 706025,"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": 6305207256448.385, "dur": 0.397, + "args": { + "External id": 706026,"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": 6305207256450.247, "dur": 2.445, + "args": { + "External id": 706027,"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": 6305207256453.780, "dur": 0.360, + "args": { + "External id": 706028,"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": 6305207256455.377, "dur": 0.446, + "args": { + "External id": 706029,"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": 6305207256458.751, "dur": 0.295, + "args": { + "External id": 706030,"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": 6305207256460.179, "dur": 0.387, + "args": { + "External id": 706031,"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": 6305207256461.813, "dur": 2.708, + "args": { + "External id": 706032,"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": 6305207256467.151, "dur": 0.379, + "args": { + "External id": 706033,"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": 6305207256468.894, "dur": 0.339, + "args": { + "External id": 706034,"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": 6305207256470.528, "dur": 1.664, + "args": { + "External id": 706035,"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": 6305207256473.093, "dur": 0.395, + "args": { + "External id": 706036,"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": 6305207256475.037, "dur": 0.323, + "args": { + "External id": 706037,"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": 6305207256479.115, "dur": 0.260, + "args": { + "External id": 706038,"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": 6305207256480.493, "dur": 0.271, + "args": { + "External id": 706039,"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": 6305207256481.819, "dur": 2.789, + "args": { + "External id": 706040,"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": 6305207256487.433, "dur": 0.361, + "args": { + "External id": 706041,"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": 6305207256489.252, "dur": 0.357, + "args": { + "External id": 706042,"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": 6305207256490.947, "dur": 2.053, + "args": { + "External id": 706043,"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": 6305207256494.340, "dur": 0.215, + "args": { + "External id": 706044,"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": 6305207256495.736, "dur": 0.294, + "args": { + "External id": 706045,"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": 6305207256499.187, "dur": 0.351, + "args": { + "External id": 706046,"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": 6305207256500.307, "dur": 0.248, + "args": { + "External id": 706047,"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": 6305207256501.385, "dur": 2.302, + "args": { + "External id": 706048,"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": 6305207256612.934, "dur": 116.742, + "args": { + "External id": 712193,"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": 6305207256807.767, "dur": 474.387, + "args": { + "External id": 712194,"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": 6305207256845.739, "dur": 430.623, + "args": { + "External id": 712195,"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": 6305207256858.336, "dur": 407.697, + "args": { + "External id": 712196,"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": 6305207257316.157, "dur": 2.602, + "args": { + "External id": 712197,"Record function id": 0, "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": 6305207257433.402, "dur": 12274.863, + "args": { + "External id": 712198,"Record function id": 0, "Ev Idx": 16458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6305207257642.837, "dur": 7.278, + "args": { + "External id": 712199,"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": 6305207257654.462, "dur": 1.110, + "args": { + "External id": 712200,"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": 6305207257657.261, "dur": 1.344, + "args": { + "External id": 712201,"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": 6305207257661.246, "dur": 1.174, + "args": { + "External id": 712202,"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": 6305207257663.956, "dur": 1.081, + "args": { + "External id": 712203,"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": 6305207257666.421, "dur": 1.137, + "args": { + "External id": 712204,"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": 6305207257671.099, "dur": 0.943, + "args": { + "External id": 712205,"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": 6305207257673.849, "dur": 5.109, + "args": { + "External id": 712206,"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": 6305207257680.554, "dur": 0.971, + "args": { + "External id": 712207,"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": 6305207257683.116, "dur": 0.936, + "args": { + "External id": 712208,"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": 6305207257688.147, "dur": 0.948, + "args": { + "External id": 712209,"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": 6305207257690.692, "dur": 0.932, + "args": { + "External id": 712210,"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": 6305207257692.945, "dur": 0.787, + "args": { + "External id": 712211,"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": 6305207257695.263, "dur": 0.677, + "args": { + "External id": 712212,"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": 6305207257699.025, "dur": 0.735, + "args": { + "External id": 712213,"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": 6305207257701.576, "dur": 3.884, + "args": { + "External id": 712214,"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": 6305207257706.845, "dur": 0.694, + "args": { + "External id": 712215,"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": 6305207257708.817, "dur": 0.736, + "args": { + "External id": 712216,"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": 6305207257716.120, "dur": 1.057, + "args": { + "External id": 712217,"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": 6305207257718.674, "dur": 0.884, + "args": { + "External id": 712218,"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": 6305207257720.902, "dur": 0.841, + "args": { + "External id": 712219,"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": 6305207257723.645, "dur": 1.106, + "args": { + "External id": 712220,"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": 6305207257728.059, "dur": 0.734, + "args": { + "External id": 712221,"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": 6305207257730.336, "dur": 4.103, + "args": { + "External id": 712222,"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": 6305207257735.755, "dur": 0.695, + "args": { + "External id": 712223,"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": 6305207257738.000, "dur": 0.960, + "args": { + "External id": 712224,"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": 6305207257742.649, "dur": 0.997, + "args": { + "External id": 712225,"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": 6305207257745.180, "dur": 1.050, + "args": { + "External id": 712226,"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": 6305207257747.496, "dur": 1.011, + "args": { + "External id": 712227,"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": 6305207257749.993, "dur": 0.846, + "args": { + "External id": 712228,"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": 6305207257754.412, "dur": 0.560, + "args": { + "External id": 712229,"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": 6305207257756.789, "dur": 3.841, + "args": { + "External id": 712230,"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": 6305207257761.855, "dur": 0.838, + "args": { + "External id": 712231,"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": 6305207257764.207, "dur": 1.093, + "args": { + "External id": 712232,"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": 6305207257769.152, "dur": 0.734, + "args": { + "External id": 712233,"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": 6305207257771.636, "dur": 1.282, + "args": { + "External id": 712234,"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": 6305207257774.136, "dur": 0.864, + "args": { + "External id": 712235,"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": 6305207257776.666, "dur": 1.049, + "args": { + "External id": 712236,"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": 6305207257780.919, "dur": 0.613, + "args": { + "External id": 712237,"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": 6305207257782.745, "dur": 4.313, + "args": { + "External id": 712238,"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": 6305207257816.024, "dur": 11834.067, + "args": { + "External id": 712239,"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": 6305207257841.248, "dur": 11797.876, + "args": { + "External id": 712240,"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": 6305207257865.205, "dur": 15.264, + "args": { + "External id": 712241,"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": 6305207257887.768, "dur": 11707.987, + "args": { + "External id": 712242,"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": 6305207257890.449, "dur": 11704.554, + "args": { + "External id": 712243,"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": 6305207257896.019, "dur": 5.182, + "args": { + "External id": 712244,"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": 6305207257905.039, "dur": 11686.438, + "args": { + "External id": 712245,"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": 6305207269987.848, "dur": 39.309, + "args": { + "External id": 712246,"Record function id": 0, "Ev Idx": 16506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 0/0", "pid": 2338707, "tid": 2338707, + "ts": 6305207270028.558, "dur": 252.765, + "args": { + "External id": 712247,"Record function id": 0, "Ev Idx": 16507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305207270104.406, "dur": 167.306, + "args": { + "External id": 712248,"Sequence number": 7674619, "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": 6305207270104.406, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_embedding_0", "pid": 2338707, "tid": 2338707, + "ts": 6305207270180.652, "dur": 52.981, + "args": { + "External id": 712249,"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": 6305207270344.339, "dur": 54.741, + "args": { + "External id": 712250,"Record function id": 0, "Ev Idx": 16510 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.0)", "pid": 2338707, "tid": 2338707, + "ts": 6305207270409.449, "dur": 8742.199, + "args": { + "External id": 712251,"Record function id": 0, "Ev Idx": 16511 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.0)", "pid": 2338707, "tid": 2338707, + "ts": 6305207270418.779, "dur": 885.054, + "args": { + "External id": 712252,"Record function id": 0, "Ev Idx": 16512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6305207270492.240, "dur": 9.564, + "args": { + "External id": 712253,"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": 6305207270536.181, "dur": 40.978, + "args": { + "External id": 712254,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305207270543.727, "dur": 2.830, + "args": { + "External id": 712255,"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": 6305207270548.847, "dur": 0.814, + "args": { + "External id": 712256,"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": 6305207270551.047, "dur": 2.746, + "args": { + "External id": 712257,"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": 6305207270555.305, "dur": 2.536, + "args": { + "External id": 712258,"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": 6305207270558.907, "dur": 0.754, + "args": { + "External id": 712259,"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": 6305207270563.157, "dur": 0.246, + "args": { + "External id": 712260,"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": 6305207270564.341, "dur": 0.398, + "args": { + "External id": 712261,"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": 6305207270566.027, "dur": 0.590, + "args": { + "External id": 712262,"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": 6305207270569.554, "dur": 0.540, + "args": { + "External id": 712263,"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": 6305207270588.575, "dur": 65.959, + "args": { + "External id": 712264,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305207270687.526, "dur": 130.895, + "args": { + "External id": 712265,"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": 6305207270698.951, "dur": 6.023, + "args": { + "External id": 712266,"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": 6305207270710.305, "dur": 10.451, + "args": { + "External id": 712267,"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": 6305207270715.350, "dur": 5.008, + "args": { + "External id": 712268,"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": 6305207270718.609, "dur": 0.509, + "args": { + "External id": 712269,"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": 6305207270726.889, "dur": 33.626, + "args": { + "External id": 712270,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305207270728.700, "dur": 3.180, + "args": { + "External id": 712271,"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": 6305207270734.657, "dur": 0.620, + "args": { + "External id": 712272,"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": 6305207270738.459, "dur": 0.451, + "args": { + "External id": 712273,"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": 6305207270740.259, "dur": 0.516, + "args": { + "External id": 712274,"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": 6305207270741.574, "dur": 2.726, + "args": { + "External id": 712275,"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": 6305207270745.246, "dur": 1.495, + "args": { + "External id": 712276,"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": 6305207270747.812, "dur": 0.348, + "args": { + "External id": 712277,"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": 6305207270751.484, "dur": 0.386, + "args": { + "External id": 712278,"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": 6305207270752.688, "dur": 2.551, + "args": { + "External id": 712279,"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": 6305207270773.283, "dur": 35.989, + "args": { + "External id": 712280,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305207270871.701, "dur": 334.739, + "args": { + "External id": 712281,"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": 6305207270904.553, "dur": 296.000, + "args": { + "External id": 712282,"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": 6305207270914.299, "dur": 279.994, + "args": { + "External id": 712283,"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": 6305207271230.677, "dur": 2.183, + "args": { + "External id": 712284,"Record function id": 0, "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": 6305207271324.003, "dur": 7601.253, + "args": { + "External id": 712285,"Record function id": 0, "Ev Idx": 16545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6305207271418.547, "dur": 6.556, + "args": { + "External id": 712286,"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": 6305207271428.484, "dur": 0.848, + "args": { + "External id": 712287,"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": 6305207271431.372, "dur": 0.922, + "args": { + "External id": 712288,"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": 6305207271433.985, "dur": 1.152, + "args": { + "External id": 712289,"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": 6305207271436.743, "dur": 1.310, + "args": { + "External id": 712290,"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": 6305207271441.568, "dur": 1.255, + "args": { + "External id": 712291,"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": 6305207271444.601, "dur": 1.088, + "args": { + "External id": 712292,"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": 6305207271447.090, "dur": 4.554, + "args": { + "External id": 712293,"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": 6305207271453.468, "dur": 0.825, + "args": { + "External id": 712294,"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": 6305207271458.034, "dur": 0.835, + "args": { + "External id": 712295,"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": 6305207271482.920, "dur": 7403.342, + "args": { + "External id": 712296,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305207271498.184, "dur": 7379.934, + "args": { + "External id": 712297,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305207271529.764, "dur": 14.973, + "args": { + "External id": 712298,"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": 6305207271548.754, "dur": 7293.946, + "args": { + "External id": 712299,"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": 6305207271551.584, "dur": 7290.588, + "args": { + "External id": 712300,"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": 6305207271557.484, "dur": 5.731, + "args": { + "External id": 712301,"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": 6305207271565.231, "dur": 7274.310, + "args": { + "External id": 712302,"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": 6305207279092.337, "dur": 33.582, + "args": { + "External id": 712303,"Sequence number": 7674620, "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": 6305207279092.337, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6305207279112.025, "dur": 9.022, + "args": { + "External id": 712304,"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": 6305207279115.662, "dur": 4.993, + "args": { + "External id": 712305,"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": 6305207279195.666, "dur": 89.543, + "args": { + "External id": 712306,"Record function id": 0, "Ev Idx": 16566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6305207279286.403, "dur": 1147.129, + "args": { + "External id": 712307,"Record function id": 0, "Ev Idx": 16567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305207279326.281, "dur": 1092.353, + "args": { + "External id": 712308,"Sequence number": 7674621, "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": 6305207279326.281, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6305207279401.163, "dur": 50.302, + "args": { + "External id": 712309,"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": 6305207279464.085, "dur": 126.495, + "args": { + "External id": 712310,"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": 6305207279602.934, "dur": 39.226, + "args": { + "External id": 712311,"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": 6305207279650.804, "dur": 30.499, + "args": { + "External id": 712312,"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": 6305207279712.298, "dur": 26.438, + "args": { + "External id": 712313,"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": 6305207279759.697, "dur": 18.477, + "args": { + "External id": 712314,"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": 6305207279799.899, "dur": 133.628, + "args": { + "External id": 712315,"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": 6305207279854.703, "dur": 15.198, + "args": { + "External id": 712316,"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": 6305207279860.217, "dur": 8.839, + "args": { + "External id": 712317,"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": 6305207279872.580, "dur": 3.807, + "args": { + "External id": 712318,"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": 6305207279877.601, "dur": 1.043, + "args": { + "External id": 712319,"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": 6305207279881.353, "dur": 2.925, + "args": { + "External id": 712320,"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": 6305207279944.562, "dur": 48.855, + "args": { + "External id": 712321,"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": 6305207280023.703, "dur": 28.544, + "args": { + "External id": 712322,"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": 6305207280102.580, "dur": 50.737, + "args": { + "External id": 712323,"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": 6305207280163.223, "dur": 34.487, + "args": { + "External id": 712324,"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": 6305207280225.174, "dur": 27.915, + "args": { + "External id": 712325,"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": 6305207280261.425, "dur": 41.454, + "args": { + "External id": 712326,"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": 6305207280321.077, "dur": 18.159, + "args": { + "External id": 712327,"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": 6305207280500.696, "dur": 105.611, + "args": { + "External id": 712328,"Record function id": 0, "Ev Idx": 16588 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6305207280681.984, "dur": 49.182, + "args": { + "External id": 712329,"Record function id": 0, "Ev Idx": 16589 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.1)", "pid": 2338707, "tid": 2338707, + "ts": 6305207280739.531, "dur": 28947.320, + "args": { + "External id": 712330,"Record function id": 0, "Ev Idx": 16590 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.1)", "pid": 2338707, "tid": 2338707, + "ts": 6305207280746.814, "dur": 960.710, + "args": { + "External id": 712331,"Record function id": 0, "Ev Idx": 16591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6305207280827.996, "dur": 10.020, + "args": { + "External id": 712332,"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": 6305207280850.986, "dur": 38.473, + "args": { + "External id": 712333,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305207280856.871, "dur": 4.723, + "args": { + "External id": 712334,"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": 6305207280863.501, "dur": 0.615, + "args": { + "External id": 712335,"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": 6305207280865.186, "dur": 0.546, + "args": { + "External id": 712336,"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": 6305207280869.055, "dur": 0.537, + "args": { + "External id": 712337,"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": 6305207280870.733, "dur": 0.773, + "args": { + "External id": 712338,"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": 6305207280872.317, "dur": 0.556, + "args": { + "External id": 712339,"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": 6305207280876.205, "dur": 2.527, + "args": { + "External id": 712340,"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": 6305207280879.626, "dur": 0.368, + "args": { + "External id": 712341,"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": 6305207280881.177, "dur": 0.776, + "args": { + "External id": 712342,"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": 6305207280909.726, "dur": 54.317, + "args": { + "External id": 712343,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305207280997.355, "dur": 167.667, + "args": { + "External id": 712344,"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": 6305207281008.628, "dur": 5.863, + "args": { + "External id": 712345,"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": 6305207281019.838, "dur": 10.511, + "args": { + "External id": 712346,"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": 6305207281024.706, "dur": 5.237, + "args": { + "External id": 712347,"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": 6305207281027.784, "dur": 0.693, + "args": { + "External id": 712348,"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": 6305207281036.888, "dur": 66.954, + "args": { + "External id": 712349,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305207281038.883, "dur": 0.574, + "args": { + "External id": 712350,"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": 6305207281040.723, "dur": 2.493, + "args": { + "External id": 712351,"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": 6305207281044.428, "dur": 0.645, + "args": { + "External id": 712352,"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": 6305207281046.033, "dur": 3.173, + "args": { + "External id": 712353,"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": 6305207281052.041, "dur": 0.542, + "args": { + "External id": 712354,"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": 6305207281090.328, "dur": 0.742, + "args": { + "External id": 712355,"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": 6305207281093.392, "dur": 0.545, + "args": { + "External id": 712356,"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": 6305207281096.968, "dur": 0.354, + "args": { + "External id": 712357,"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": 6305207281098.483, "dur": 0.561, + "args": { + "External id": 712358,"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": 6305207281118.845, "dur": 37.536, + "args": { + "External id": 712359,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305207281222.264, "dur": 386.585, + "args": { + "External id": 712360,"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": 6305207281255.262, "dur": 347.828, + "args": { + "External id": 712361,"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": 6305207281265.382, "dur": 331.658, + "args": { + "External id": 712362,"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": 6305207281635.659, "dur": 2.749, + "args": { + "External id": 712363,"Record function id": 0, "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": 6305207281727.764, "dur": 27749.594, + "args": { + "External id": 712364,"Record function id": 0, "Ev Idx": 16624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6305207281825.622, "dur": 6.060, + "args": { + "External id": 712365,"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": 6305207281834.678, "dur": 1.114, + "args": { + "External id": 712366,"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": 6305207281837.542, "dur": 3.168, + "args": { + "External id": 712367,"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": 6305207281842.492, "dur": 0.921, + "args": { + "External id": 712368,"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": 6305207281844.726, "dur": 1.099, + "args": { + "External id": 712369,"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": 6305207281849.571, "dur": 1.056, + "args": { + "External id": 712370,"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": 6305207281852.117, "dur": 0.820, + "args": { + "External id": 712371,"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": 6305207281854.638, "dur": 2.539, + "args": { + "External id": 712372,"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": 6305207281858.730, "dur": 0.579, + "args": { + "External id": 712373,"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": 6305207281862.663, "dur": 0.770, + "args": { + "External id": 712374,"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": 6305207281880.346, "dur": 27552.737, + "args": { + "External id": 712375,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305207281895.304, "dur": 27529.280, + "args": { + "External id": 712376,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305207281910.792, "dur": 15.294, + "args": { + "External id": 712377,"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": 6305207281929.618, "dur": 27458.362, + "args": { + "External id": 712378,"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": 6305207281932.195, "dur": 27454.943, + "args": { + "External id": 712379,"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": 6305207281937.711, "dur": 5.290, + "args": { + "External id": 712380,"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": 6305207281944.715, "dur": 27438.980, + "args": { + "External id": 712381,"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": 6305207309625.265, "dur": 36.223, + "args": { + "External id": 712382,"Sequence number": 7674622, "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": 6305207309625.265, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6305207309644.129, "dur": 12.272, + "args": { + "External id": 712383,"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": 6305207309650.858, "dur": 5.205, + "args": { + "External id": 712384,"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": 6305207309729.169, "dur": 78.446, + "args": { + "External id": 712385,"Record function id": 0, "Ev Idx": 16645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6305207309809.106, "dur": 1093.913, + "args": { + "External id": 712386,"Record function id": 0, "Ev Idx": 16646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305207309846.893, "dur": 1042.528, + "args": { + "External id": 712387,"Sequence number": 7674623, "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": 6305207309846.893, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6305207309913.580, "dur": 50.560, + "args": { + "External id": 712388,"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": 6305207309976.846, "dur": 133.150, + "args": { + "External id": 712389,"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": 6305207310127.551, "dur": 42.316, + "args": { + "External id": 712390,"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": 6305207310176.810, "dur": 29.716, + "args": { + "External id": 712391,"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": 6305207310235.268, "dur": 25.531, + "args": { + "External id": 712392,"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": 6305207310277.363, "dur": 16.537, + "args": { + "External id": 712393,"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": 6305207310316.724, "dur": 134.434, + "args": { + "External id": 712394,"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": 6305207310368.008, "dur": 13.042, + "args": { + "External id": 712395,"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": 6305207310373.616, "dur": 6.648, + "args": { + "External id": 712396,"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": 6305207310383.984, "dur": 3.858, + "args": { + "External id": 712397,"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": 6305207310389.087, "dur": 1.239, + "args": { + "External id": 712398,"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": 6305207310394.266, "dur": 5.190, + "args": { + "External id": 712399,"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": 6305207310462.364, "dur": 66.294, + "args": { + "External id": 712400,"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": 6305207310564.653, "dur": 27.372, + "args": { + "External id": 712401,"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": 6305207310602.609, "dur": 45.562, + "args": { + "External id": 712402,"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": 6305207310654.778, "dur": 34.349, + "args": { + "External id": 712403,"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": 6305207310713.658, "dur": 26.318, + "args": { + "External id": 712404,"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": 6305207310746.571, "dur": 35.616, + "args": { + "External id": 712405,"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": 6305207310801.642, "dur": 17.512, + "args": { + "External id": 712406,"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": 6305207310967.962, "dur": 79.268, + "args": { + "External id": 712407,"Record function id": 0, "Ev Idx": 16667 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6305207311164.619, "dur": 49.913, + "args": { + "External id": 712408,"Record function id": 0, "Ev Idx": 16668 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.2)", "pid": 2338707, "tid": 2338707, + "ts": 6305207311223.810, "dur": 29345.850, + "args": { + "External id": 712409,"Record function id": 0, "Ev Idx": 16669 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.2)", "pid": 2338707, "tid": 2338707, + "ts": 6305207311232.460, "dur": 958.489, + "args": { + "External id": 712410,"Record function id": 0, "Ev Idx": 16670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6305207311314.149, "dur": 10.288, + "args": { + "External id": 712411,"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": 6305207311338.134, "dur": 37.841, + "args": { + "External id": 712412,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305207311344.192, "dur": 2.101, + "args": { + "External id": 712413,"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": 6305207311350.954, "dur": 0.463, + "args": { + "External id": 712414,"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": 6305207311352.441, "dur": 0.509, + "args": { + "External id": 712415,"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": 6305207311354.337, "dur": 0.687, + "args": { + "External id": 712416,"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": 6305207311357.896, "dur": 0.653, + "args": { + "External id": 712417,"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": 6305207311359.460, "dur": 0.624, + "args": { + "External id": 712418,"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": 6305207311361.073, "dur": 4.914, + "args": { + "External id": 712419,"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": 6305207311367.063, "dur": 0.737, + "args": { + "External id": 712420,"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": 6305207311368.793, "dur": 0.329, + "args": { + "External id": 712421,"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": 6305207311387.261, "dur": 53.889, + "args": { + "External id": 712422,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305207311473.060, "dur": 147.383, + "args": { + "External id": 712423,"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": 6305207311483.572, "dur": 4.147, + "args": { + "External id": 712424,"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": 6305207311492.850, "dur": 10.777, + "args": { + "External id": 712425,"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": 6305207311497.970, "dur": 5.265, + "args": { + "External id": 712426,"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": 6305207311501.341, "dur": 0.766, + "args": { + "External id": 712427,"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": 6305207311526.924, "dur": 32.031, + "args": { + "External id": 712428,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305207311529.623, "dur": 3.064, + "args": { + "External id": 712429,"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": 6305207311534.094, "dur": 0.666, + "args": { + "External id": 712430,"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": 6305207311535.881, "dur": 0.311, + "args": { + "External id": 712431,"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": 6305207311539.974, "dur": 2.366, + "args": { + "External id": 712432,"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": 6305207311543.443, "dur": 0.521, + "args": { + "External id": 712433,"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": 6305207311545.148, "dur": 0.599, + "args": { + "External id": 712434,"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": 6305207311548.501, "dur": 0.478, + "args": { + "External id": 712435,"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": 6305207311550.673, "dur": 0.539, + "args": { + "External id": 712436,"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": 6305207311552.524, "dur": 2.237, + "args": { + "External id": 712437,"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": 6305207311574.258, "dur": 37.588, + "args": { + "External id": 712438,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305207311676.537, "dur": 373.295, + "args": { + "External id": 712439,"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": 6305207311708.448, "dur": 336.879, + "args": { + "External id": 712440,"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": 6305207311722.874, "dur": 317.147, + "args": { + "External id": 712441,"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": 6305207312113.061, "dur": 3.339, + "args": { + "External id": 712442,"Record function id": 0, "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": 6305207312211.847, "dur": 28156.774, + "args": { + "External id": 712443,"Record function id": 0, "Ev Idx": 16703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6305207312312.936, "dur": 7.340, + "args": { + "External id": 712444,"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": 6305207312323.330, "dur": 0.758, + "args": { + "External id": 712445,"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": 6305207312325.769, "dur": 3.526, + "args": { + "External id": 712446,"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": 6305207312331.413, "dur": 1.120, + "args": { + "External id": 712447,"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": 6305207312333.788, "dur": 1.094, + "args": { + "External id": 712448,"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": 6305207312335.930, "dur": 1.006, + "args": { + "External id": 712449,"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": 6305207312340.850, "dur": 0.900, + "args": { + "External id": 712450,"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": 6305207312343.049, "dur": 2.394, + "args": { + "External id": 712451,"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": 6305207312347.177, "dur": 0.979, + "args": { + "External id": 712452,"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": 6305207312349.609, "dur": 0.764, + "args": { + "External id": 712453,"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": 6305207312369.578, "dur": 27956.586, + "args": { + "External id": 712454,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305207312385.355, "dur": 27933.234, + "args": { + "External id": 712455,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305207312399.910, "dur": 16.282, + "args": { + "External id": 712456,"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": 6305207312420.075, "dur": 27865.692, + "args": { + "External id": 712457,"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": 6305207312422.786, "dur": 27862.389, + "args": { + "External id": 712458,"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": 6305207312429.230, "dur": 5.424, + "args": { + "External id": 712459,"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": 6305207312436.943, "dur": 27844.708, + "args": { + "External id": 712460,"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": 6305207340497.491, "dur": 44.007, + "args": { + "External id": 712461,"Sequence number": 7674624, "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": 6305207340497.491, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6305207340527.570, "dur": 8.905, + "args": { + "External id": 712462,"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": 6305207340531.230, "dur": 4.903, + "args": { + "External id": 712463,"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": 6305207340612.070, "dur": 73.769, + "args": { + "External id": 712464,"Record function id": 0, "Ev Idx": 16724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6305207340687.388, "dur": 1100.977, + "args": { + "External id": 712465,"Record function id": 0, "Ev Idx": 16725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305207340726.169, "dur": 1049.943, + "args": { + "External id": 712466,"Sequence number": 7674625, "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": 6305207340726.169, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6305207340793.553, "dur": 48.760, + "args": { + "External id": 712467,"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": 6305207340855.859, "dur": 107.118, + "args": { + "External id": 712468,"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": 6305207340974.485, "dur": 36.786, + "args": { + "External id": 712469,"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": 6305207341020.249, "dur": 29.125, + "args": { + "External id": 712470,"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": 6305207341114.582, "dur": 28.885, + "args": { + "External id": 712471,"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": 6305207341164.172, "dur": 18.018, + "args": { + "External id": 712472,"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": 6305207341206.204, "dur": 134.939, + "args": { + "External id": 712473,"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": 6305207341260.248, "dur": 11.537, + "args": { + "External id": 712474,"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": 6305207341265.734, "dur": 5.303, + "args": { + "External id": 712475,"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": 6305207341275.080, "dur": 4.784, + "args": { + "External id": 712476,"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": 6305207341281.587, "dur": 0.856, + "args": { + "External id": 712477,"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": 6305207341285.186, "dur": 7.058, + "args": { + "External id": 712478,"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": 6305207341351.816, "dur": 53.640, + "args": { + "External id": 712479,"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": 6305207341435.675, "dur": 26.719, + "args": { + "External id": 712480,"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": 6305207341471.926, "dur": 54.850, + "args": { + "External id": 712481,"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": 6305207341538.623, "dur": 38.526, + "args": { + "External id": 712482,"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": 6305207341601.906, "dur": 28.354, + "args": { + "External id": 712483,"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": 6305207341638.145, "dur": 35.482, + "args": { + "External id": 712484,"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": 6305207341690.750, "dur": 16.549, + "args": { + "External id": 712485,"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": 6305207341852.430, "dur": 74.446, + "args": { + "External id": 712486,"Record function id": 0, "Ev Idx": 16746 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6305207342000.166, "dur": 45.831, + "args": { + "External id": 712487,"Record function id": 0, "Ev Idx": 16747 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.3)", "pid": 2338707, "tid": 2338707, + "ts": 6305207342096.229, "dur": 30108.518, + "args": { + "External id": 712488,"Record function id": 0, "Ev Idx": 16748 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.3)", "pid": 2338707, "tid": 2338707, + "ts": 6305207342105.187, "dur": 926.742, + "args": { + "External id": 712489,"Record function id": 0, "Ev Idx": 16749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6305207342187.213, "dur": 9.771, + "args": { + "External id": 712490,"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": 6305207342210.573, "dur": 42.586, + "args": { + "External id": 712491,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305207342217.007, "dur": 2.758, + "args": { + "External id": 712492,"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": 6305207342224.214, "dur": 0.357, + "args": { + "External id": 712493,"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": 6305207342226.221, "dur": 0.611, + "args": { + "External id": 712494,"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": 6305207342228.148, "dur": 0.672, + "args": { + "External id": 712495,"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": 6305207342232.520, "dur": 0.599, + "args": { + "External id": 712496,"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": 6305207342234.703, "dur": 0.580, + "args": { + "External id": 712497,"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": 6305207342236.594, "dur": 5.062, + "args": { + "External id": 712498,"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": 6305207342243.120, "dur": 0.634, + "args": { + "External id": 712499,"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": 6305207342245.640, "dur": 0.552, + "args": { + "External id": 712500,"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": 6305207342264.625, "dur": 56.712, + "args": { + "External id": 712501,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305207342353.220, "dur": 127.720, + "args": { + "External id": 712502,"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": 6305207342363.973, "dur": 3.835, + "args": { + "External id": 712503,"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": 6305207342373.345, "dur": 10.773, + "args": { + "External id": 712504,"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": 6305207342378.307, "dur": 5.414, + "args": { + "External id": 712505,"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": 6305207342381.918, "dur": 0.622, + "args": { + "External id": 712506,"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": 6305207342391.701, "dur": 37.007, + "args": { + "External id": 712507,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305207342394.205, "dur": 2.655, + "args": { + "External id": 712508,"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": 6305207342399.116, "dur": 0.311, + "args": { + "External id": 712509,"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": 6305207342401.205, "dur": 0.507, + "args": { + "External id": 712510,"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": 6305207342405.736, "dur": 2.698, + "args": { + "External id": 712511,"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": 6305207342409.941, "dur": 0.542, + "args": { + "External id": 712512,"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": 6305207342411.805, "dur": 0.431, + "args": { + "External id": 712513,"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": 6305207342415.904, "dur": 0.559, + "args": { + "External id": 712514,"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": 6305207342417.914, "dur": 0.722, + "args": { + "External id": 712515,"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": 6305207342420.392, "dur": 3.134, + "args": { + "External id": 712516,"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": 6305207342441.501, "dur": 32.150, + "args": { + "External id": 712517,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305207342554.918, "dur": 377.502, + "args": { + "External id": 712518,"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": 6305207342590.024, "dur": 337.138, + "args": { + "External id": 712519,"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": 6305207342602.152, "dur": 319.213, + "args": { + "External id": 712520,"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": 6305207342957.742, "dur": 2.483, + "args": { + "External id": 712521,"Record function id": 0, "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": 6305207343051.772, "dur": 28935.223, + "args": { + "External id": 712522,"Record function id": 0, "Ev Idx": 16782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6305207343205.944, "dur": 7.104, + "args": { + "External id": 712523,"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": 6305207343217.120, "dur": 1.311, + "args": { + "External id": 712524,"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": 6305207343220.203, "dur": 3.209, + "args": { + "External id": 712525,"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": 6305207343225.401, "dur": 0.837, + "args": { + "External id": 712526,"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": 6305207343227.630, "dur": 0.928, + "args": { + "External id": 712527,"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": 6305207343230.107, "dur": 0.743, + "args": { + "External id": 712528,"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": 6305207343235.302, "dur": 1.168, + "args": { + "External id": 712529,"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": 6305207343238.490, "dur": 2.407, + "args": { + "External id": 712530,"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": 6305207343242.329, "dur": 1.152, + "args": { + "External id": 712531,"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": 6305207343245.304, "dur": 0.677, + "args": { + "External id": 712532,"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": 6305207343267.317, "dur": 28675.294, + "args": { + "External id": 712533,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305207343283.414, "dur": 28650.962, + "args": { + "External id": 712534,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305207343299.404, "dur": 15.316, + "args": { + "External id": 712535,"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": 6305207343318.518, "dur": 28582.171, + "args": { + "External id": 712536,"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": 6305207343321.098, "dur": 28578.971, + "args": { + "External id": 712537,"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": 6305207343327.798, "dur": 5.209, + "args": { + "External id": 712538,"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": 6305207343334.735, "dur": 28562.237, + "args": { + "External id": 712539,"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": 6305207372147.731, "dur": 30.595, + "args": { + "External id": 712540,"Sequence number": 7674626, "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": 6305207372147.731, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6305207372164.489, "dur": 8.942, + "args": { + "External id": 712541,"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": 6305207372167.837, "dur": 5.252, + "args": { + "External id": 712542,"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": 6305207372246.398, "dur": 74.467, + "args": { + "External id": 712543,"Record function id": 0, "Ev Idx": 16803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6305207372322.354, "dur": 1097.932, + "args": { + "External id": 712544,"Record function id": 0, "Ev Idx": 16804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305207372361.531, "dur": 1044.992, + "args": { + "External id": 712545,"Sequence number": 7674627, "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": 6305207372361.531, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6305207372425.479, "dur": 50.344, + "args": { + "External id": 712546,"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": 6305207372491.806, "dur": 120.302, + "args": { + "External id": 712547,"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": 6305207372627.106, "dur": 38.393, + "args": { + "External id": 712548,"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": 6305207372674.974, "dur": 29.613, + "args": { + "External id": 712549,"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": 6305207372733.280, "dur": 26.021, + "args": { + "External id": 712550,"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": 6305207372779.078, "dur": 15.368, + "args": { + "External id": 712551,"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": 6305207372818.373, "dur": 128.645, + "args": { + "External id": 712552,"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": 6305207372870.109, "dur": 10.805, + "args": { + "External id": 712553,"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": 6305207372875.328, "dur": 4.762, + "args": { + "External id": 712554,"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": 6305207372883.965, "dur": 4.333, + "args": { + "External id": 712555,"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": 6305207372889.915, "dur": 1.328, + "args": { + "External id": 712556,"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": 6305207372893.858, "dur": 5.320, + "args": { + "External id": 712557,"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": 6305207372957.540, "dur": 47.853, + "args": { + "External id": 712558,"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": 6305207373038.470, "dur": 67.751, + "args": { + "External id": 712559,"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": 6305207373119.624, "dur": 46.963, + "args": { + "External id": 712560,"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": 6305207373175.250, "dur": 34.245, + "args": { + "External id": 712561,"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": 6305207373232.055, "dur": 26.056, + "args": { + "External id": 712562,"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": 6305207373265.188, "dur": 35.927, + "args": { + "External id": 712563,"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": 6305207373321.346, "dur": 18.779, + "args": { + "External id": 712564,"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": 6305207373485.812, "dur": 92.181, + "args": { + "External id": 712565,"Record function id": 0, "Ev Idx": 16825 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6305207373654.447, "dur": 49.970, + "args": { + "External id": 712566,"Record function id": 0, "Ev Idx": 16826 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.4)", "pid": 2338707, "tid": 2338707, + "ts": 6305207373713.379, "dur": 29909.372, + "args": { + "External id": 712567,"Record function id": 0, "Ev Idx": 16827 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.4)", "pid": 2338707, "tid": 2338707, + "ts": 6305207373721.106, "dur": 996.646, + "args": { + "External id": 712568,"Record function id": 0, "Ev Idx": 16828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6305207373800.148, "dur": 9.235, + "args": { + "External id": 712569,"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": 6305207373823.011, "dur": 41.482, + "args": { + "External id": 712570,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305207373828.861, "dur": 2.402, + "args": { + "External id": 712571,"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": 6305207373836.314, "dur": 0.769, + "args": { + "External id": 712572,"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": 6305207373838.159, "dur": 0.399, + "args": { + "External id": 712573,"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": 6305207373840.191, "dur": 0.614, + "args": { + "External id": 712574,"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": 6305207373844.122, "dur": 0.486, + "args": { + "External id": 712575,"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": 6305207373846.315, "dur": 0.670, + "args": { + "External id": 712576,"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": 6305207373848.574, "dur": 4.739, + "args": { + "External id": 712577,"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": 6305207373855.110, "dur": 0.534, + "args": { + "External id": 712578,"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": 6305207373857.041, "dur": 0.518, + "args": { + "External id": 712579,"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": 6305207373876.411, "dur": 56.379, + "args": { + "External id": 712580,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305207373968.459, "dur": 165.980, + "args": { + "External id": 712581,"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": 6305207373979.101, "dur": 5.041, + "args": { + "External id": 712582,"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": 6305207373990.021, "dur": 10.904, + "args": { + "External id": 712583,"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": 6305207373995.131, "dur": 5.385, + "args": { + "External id": 712584,"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": 6305207373998.647, "dur": 0.663, + "args": { + "External id": 712585,"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": 6305207374007.604, "dur": 33.872, + "args": { + "External id": 712586,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305207374009.797, "dur": 0.653, + "args": { + "External id": 712587,"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": 6305207374012.408, "dur": 3.027, + "args": { + "External id": 712588,"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": 6305207374017.241, "dur": 0.306, + "args": { + "External id": 712589,"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": 6305207374019.038, "dur": 2.843, + "args": { + "External id": 712590,"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": 6305207374025.744, "dur": 0.259, + "args": { + "External id": 712591,"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": 6305207374028.125, "dur": 0.301, + "args": { + "External id": 712592,"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": 6305207374029.991, "dur": 0.372, + "args": { + "External id": 712593,"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": 6305207374033.954, "dur": 0.426, + "args": { + "External id": 712594,"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": 6305207374036.045, "dur": 0.274, + "args": { + "External id": 712595,"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": 6305207374051.270, "dur": 72.278, + "args": { + "External id": 712596,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305207374188.357, "dur": 426.503, + "args": { + "External id": 712597,"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": 6305207374222.981, "dur": 386.071, + "args": { + "External id": 712598,"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": 6305207374233.678, "dur": 368.352, + "args": { + "External id": 712599,"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": 6305207374641.484, "dur": 2.359, + "args": { + "External id": 712600,"Record function id": 0, "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": 6305207374740.062, "dur": 28677.929, + "args": { + "External id": 712601,"Record function id": 0, "Ev Idx": 16861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6305207374841.506, "dur": 6.731, + "args": { + "External id": 712602,"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": 6305207374851.654, "dur": 1.117, + "args": { + "External id": 712603,"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": 6305207374854.778, "dur": 3.449, + "args": { + "External id": 712604,"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": 6305207374860.050, "dur": 0.764, + "args": { + "External id": 712605,"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": 6305207374862.614, "dur": 1.066, + "args": { + "External id": 712606,"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": 6305207374865.054, "dur": 1.053, + "args": { + "External id": 712607,"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": 6305207374870.199, "dur": 0.874, + "args": { + "External id": 712608,"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": 6305207374872.636, "dur": 2.058, + "args": { + "External id": 712609,"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": 6305207374876.192, "dur": 0.677, + "args": { + "External id": 712610,"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": 6305207374878.663, "dur": 0.900, + "args": { + "External id": 712611,"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": 6305207374899.472, "dur": 28472.494, + "args": { + "External id": 712612,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305207374915.161, "dur": 28448.053, + "args": { + "External id": 712613,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305207374930.448, "dur": 15.753, + "args": { + "External id": 712614,"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": 6305207374949.761, "dur": 28378.897, + "args": { + "External id": 712615,"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": 6305207374952.412, "dur": 28375.572, + "args": { + "External id": 712616,"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": 6305207374958.255, "dur": 5.538, + "args": { + "External id": 712617,"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": 6305207374965.934, "dur": 28358.403, + "args": { + "External id": 712618,"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": 6305207403565.004, "dur": 31.352, + "args": { + "External id": 712619,"Sequence number": 7674628, "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": 6305207403565.004, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6305207403581.998, "dur": 9.337, + "args": { + "External id": 712620,"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": 6305207403586.011, "dur": 4.920, + "args": { + "External id": 712621,"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": 6305207403665.153, "dur": 73.646, + "args": { + "External id": 712622,"Record function id": 0, "Ev Idx": 16882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6305207403739.967, "dur": 1131.776, + "args": { + "External id": 712623,"Record function id": 0, "Ev Idx": 16883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305207403779.695, "dur": 1078.503, + "args": { + "External id": 712624,"Sequence number": 7674629, "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": 6305207403779.695, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6305207403848.340, "dur": 48.124, + "args": { + "External id": 712625,"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": 6305207403908.307, "dur": 109.274, + "args": { + "External id": 712626,"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": 6305207404028.575, "dur": 78.072, + "args": { + "External id": 712627,"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": 6305207404120.800, "dur": 34.593, + "args": { + "External id": 712628,"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": 6305207404184.477, "dur": 29.930, + "args": { + "External id": 712629,"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": 6305207404234.995, "dur": 18.613, + "args": { + "External id": 712630,"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": 6305207404277.415, "dur": 133.019, + "args": { + "External id": 712631,"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": 6305207404327.778, "dur": 11.337, + "args": { + "External id": 712632,"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": 6305207404333.307, "dur": 5.073, + "args": { + "External id": 712633,"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": 6305207404342.204, "dur": 4.175, + "args": { + "External id": 712634,"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": 6305207404347.556, "dur": 1.314, + "args": { + "External id": 712635,"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": 6305207404351.815, "dur": 6.979, + "args": { + "External id": 712636,"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": 6305207404421.198, "dur": 49.676, + "args": { + "External id": 712637,"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": 6305207404501.685, "dur": 45.998, + "args": { + "External id": 712638,"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": 6305207404560.856, "dur": 46.362, + "args": { + "External id": 712639,"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": 6305207404617.253, "dur": 34.534, + "args": { + "External id": 712640,"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": 6305207404677.834, "dur": 28.686, + "args": { + "External id": 712641,"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": 6305207404714.300, "dur": 36.229, + "args": { + "External id": 712642,"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": 6305207404769.603, "dur": 18.775, + "args": { + "External id": 712643,"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": 6305207404936.858, "dur": 78.316, + "args": { + "External id": 712644,"Record function id": 0, "Ev Idx": 16904 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6305207405131.690, "dur": 49.981, + "args": { + "External id": 712645,"Record function id": 0, "Ev Idx": 16905 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.5)", "pid": 2338707, "tid": 2338707, + "ts": 6305207405191.494, "dur": 30240.904, + "args": { + "External id": 712646,"Record function id": 0, "Ev Idx": 16906 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.5)", "pid": 2338707, "tid": 2338707, + "ts": 6305207405200.505, "dur": 960.225, + "args": { + "External id": 712647,"Record function id": 0, "Ev Idx": 16907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6305207405281.797, "dur": 10.137, + "args": { + "External id": 712648,"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": 6305207405305.448, "dur": 47.067, + "args": { + "External id": 712649,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305207405311.390, "dur": 2.635, + "args": { + "External id": 712650,"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": 6305207405319.221, "dur": 0.387, + "args": { + "External id": 712651,"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": 6305207405321.094, "dur": 0.644, + "args": { + "External id": 712652,"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": 6305207405322.975, "dur": 0.450, + "args": { + "External id": 712653,"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": 6305207405327.739, "dur": 0.489, + "args": { + "External id": 712654,"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": 6305207405329.660, "dur": 0.560, + "args": { + "External id": 712655,"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": 6305207405332.031, "dur": 5.124, + "args": { + "External id": 712656,"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": 6305207405338.212, "dur": 0.701, + "args": { + "External id": 712657,"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": 6305207405344.985, "dur": 0.508, + "args": { + "External id": 712658,"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": 6305207405363.588, "dur": 58.491, + "args": { + "External id": 712659,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305207405454.493, "dur": 152.393, + "args": { + "External id": 712660,"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": 6305207405465.566, "dur": 3.679, + "args": { + "External id": 712661,"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": 6305207405474.658, "dur": 14.238, + "args": { + "External id": 712662,"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": 6305207405479.912, "dur": 8.578, + "args": { + "External id": 712663,"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": 6305207405484.059, "dur": 3.071, + "args": { + "External id": 712664,"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": 6305207405495.619, "dur": 49.823, + "args": { + "External id": 712665,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305207405497.999, "dur": 0.887, + "args": { + "External id": 712666,"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": 6305207405499.990, "dur": 0.826, + "args": { + "External id": 712667,"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": 6305207405502.599, "dur": 0.537, + "args": { + "External id": 712668,"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": 6305207405522.350, "dur": 3.157, + "args": { + "External id": 712669,"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": 6305207405527.803, "dur": 0.606, + "args": { + "External id": 712670,"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": 6305207405529.685, "dur": 2.850, + "args": { + "External id": 712671,"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": 6305207405534.047, "dur": 0.532, + "args": { + "External id": 712672,"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": 6305207405535.723, "dur": 0.664, + "args": { + "External id": 712673,"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": 6305207405540.539, "dur": 0.522, + "args": { + "External id": 712674,"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": 6305207405561.953, "dur": 36.925, + "args": { + "External id": 712675,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305207405661.906, "dur": 365.047, + "args": { + "External id": 712676,"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": 6305207405694.156, "dur": 327.852, + "args": { + "External id": 712677,"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": 6305207405704.916, "dur": 311.486, + "args": { + "External id": 712678,"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": 6305207406048.858, "dur": 2.314, + "args": { + "External id": 712679,"Record function id": 0, "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": 6305207406180.978, "dur": 29059.879, + "args": { + "External id": 712680,"Record function id": 0, "Ev Idx": 16940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6305207406279.099, "dur": 7.028, + "args": { + "External id": 712681,"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": 6305207406290.323, "dur": 1.072, + "args": { + "External id": 712682,"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": 6305207406293.550, "dur": 3.349, + "args": { + "External id": 712683,"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": 6305207406298.788, "dur": 0.964, + "args": { + "External id": 712684,"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": 6305207406301.121, "dur": 0.627, + "args": { + "External id": 712685,"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": 6305207406305.462, "dur": 1.014, + "args": { + "External id": 712686,"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": 6305207406307.892, "dur": 0.888, + "args": { + "External id": 712687,"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": 6305207406310.692, "dur": 2.340, + "args": { + "External id": 712688,"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": 6305207406314.271, "dur": 1.145, + "args": { + "External id": 712689,"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": 6305207406319.016, "dur": 0.913, + "args": { + "External id": 712690,"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": 6305207406337.435, "dur": 28859.687, + "args": { + "External id": 712691,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305207406352.689, "dur": 28836.271, + "args": { + "External id": 712692,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305207406366.843, "dur": 17.129, + "args": { + "External id": 712693,"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": 6305207406387.435, "dur": 28764.294, + "args": { + "External id": 712694,"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": 6305207406390.216, "dur": 28760.825, + "args": { + "External id": 712695,"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": 6305207406397.126, "dur": 5.707, + "args": { + "External id": 712696,"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": 6305207406404.687, "dur": 28743.095, + "args": { + "External id": 712697,"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": 6305207435372.971, "dur": 32.902, + "args": { + "External id": 712698,"Sequence number": 7674630, "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": 6305207435372.971, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6305207435391.750, "dur": 9.216, + "args": { + "External id": 712699,"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": 6305207435395.996, "dur": 4.792, + "args": { + "External id": 712700,"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": 6305207435474.085, "dur": 87.143, + "args": { + "External id": 712701,"Record function id": 0, "Ev Idx": 16961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6305207435564.484, "dur": 1155.846, + "args": { + "External id": 712702,"Record function id": 0, "Ev Idx": 16962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305207435604.372, "dur": 1102.780, + "args": { + "External id": 712703,"Sequence number": 7674631, "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": 6305207435604.372, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6305207435672.279, "dur": 51.550, + "args": { + "External id": 712704,"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": 6305207435757.058, "dur": 107.065, + "args": { + "External id": 712705,"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": 6305207435876.495, "dur": 38.025, + "args": { + "External id": 712706,"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": 6305207435924.934, "dur": 29.102, + "args": { + "External id": 712707,"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": 6305207435983.234, "dur": 28.689, + "args": { + "External id": 712708,"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": 6305207436034.616, "dur": 17.559, + "args": { + "External id": 712709,"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": 6305207436114.590, "dur": 139.496, + "args": { + "External id": 712710,"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": 6305207436166.500, "dur": 12.342, + "args": { + "External id": 712711,"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": 6305207436171.991, "dur": 5.588, + "args": { + "External id": 712712,"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": 6305207436181.724, "dur": 4.514, + "args": { + "External id": 712713,"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": 6305207436187.429, "dur": 0.850, + "args": { + "External id": 712714,"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": 6305207436190.518, "dur": 9.258, + "args": { + "External id": 712715,"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": 6305207436265.046, "dur": 58.666, + "args": { + "External id": 712716,"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": 6305207436358.423, "dur": 30.041, + "args": { + "External id": 712717,"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": 6305207436398.906, "dur": 44.016, + "args": { + "External id": 712718,"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": 6305207436449.280, "dur": 34.409, + "args": { + "External id": 712719,"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": 6305207436522.887, "dur": 28.440, + "args": { + "External id": 712720,"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": 6305207436561.556, "dur": 38.909, + "args": { + "External id": 712721,"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": 6305207436619.290, "dur": 17.568, + "args": { + "External id": 712722,"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": 6305207436785.918, "dur": 79.390, + "args": { + "External id": 712723,"Record function id": 0, "Ev Idx": 16983 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6305207436937.498, "dur": 49.108, + "args": { + "External id": 712724,"Record function id": 0, "Ev Idx": 16984 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.6)", "pid": 2338707, "tid": 2338707, + "ts": 6305207436995.404, "dur": 30050.908, + "args": { + "External id": 712725,"Record function id": 0, "Ev Idx": 16985 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.6)", "pid": 2338707, "tid": 2338707, + "ts": 6305207437002.698, "dur": 952.554, + "args": { + "External id": 712726,"Record function id": 0, "Ev Idx": 16986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6305207437123.395, "dur": 9.963, + "args": { + "External id": 712727,"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": 6305207437148.151, "dur": 42.658, + "args": { + "External id": 712728,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305207437154.081, "dur": 2.121, + "args": { + "External id": 712729,"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": 6305207437160.812, "dur": 0.550, + "args": { + "External id": 712730,"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": 6305207437163.142, "dur": 0.470, + "args": { + "External id": 712731,"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": 6305207437165.298, "dur": 0.564, + "args": { + "External id": 712732,"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": 6305207437169.488, "dur": 0.430, + "args": { + "External id": 712733,"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": 6305207437174.798, "dur": 0.389, + "args": { + "External id": 712734,"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": 6305207437176.418, "dur": 4.700, + "args": { + "External id": 712735,"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": 6305207437182.335, "dur": 0.324, + "args": { + "External id": 712736,"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": 6305207437183.998, "dur": 0.248, + "args": { + "External id": 712737,"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": 6305207437202.382, "dur": 54.097, + "args": { + "External id": 712738,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305207437290.081, "dur": 124.802, + "args": { + "External id": 712739,"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": 6305207437301.397, "dur": 3.979, + "args": { + "External id": 712740,"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": 6305207437311.035, "dur": 10.850, + "args": { + "External id": 712741,"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": 6305207437315.776, "dur": 5.696, + "args": { + "External id": 712742,"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": 6305207437319.698, "dur": 0.511, + "args": { + "External id": 712743,"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": 6305207437328.382, "dur": 33.246, + "args": { + "External id": 712744,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305207437330.665, "dur": 2.876, + "args": { + "External id": 712745,"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": 6305207437335.208, "dur": 0.675, + "args": { + "External id": 712746,"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": 6305207437337.262, "dur": 0.541, + "args": { + "External id": 712747,"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": 6305207437341.457, "dur": 3.018, + "args": { + "External id": 712748,"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": 6305207437345.599, "dur": 0.289, + "args": { + "External id": 712749,"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": 6305207437347.656, "dur": 0.359, + "args": { + "External id": 712750,"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": 6305207437350.716, "dur": 0.289, + "args": { + "External id": 712751,"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": 6305207437352.776, "dur": 0.360, + "args": { + "External id": 712752,"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": 6305207437354.683, "dur": 2.429, + "args": { + "External id": 712753,"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": 6305207437374.394, "dur": 32.193, + "args": { + "External id": 712754,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305207437468.808, "dur": 388.066, + "args": { + "External id": 712755,"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": 6305207437499.261, "dur": 351.881, + "args": { + "External id": 712756,"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": 6305207437525.914, "dur": 319.408, + "args": { + "External id": 712757,"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": 6305207437882.157, "dur": 2.265, + "args": { + "External id": 712758,"Record function id": 0, "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": 6305207437975.488, "dur": 28882.148, + "args": { + "External id": 712759,"Record function id": 0, "Ev Idx": 17019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6305207438109.718, "dur": 6.821, + "args": { + "External id": 712760,"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": 6305207438120.399, "dur": 0.933, + "args": { + "External id": 712761,"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": 6305207438122.764, "dur": 3.053, + "args": { + "External id": 712762,"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": 6305207438127.754, "dur": 0.753, + "args": { + "External id": 712763,"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": 6305207438129.888, "dur": 0.757, + "args": { + "External id": 712764,"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": 6305207438132.101, "dur": 0.863, + "args": { + "External id": 712765,"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": 6305207438136.821, "dur": 0.758, + "args": { + "External id": 712766,"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": 6305207438139.579, "dur": 1.657, + "args": { + "External id": 712767,"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": 6305207438142.839, "dur": 0.906, + "args": { + "External id": 712768,"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": 6305207438145.632, "dur": 0.958, + "args": { + "External id": 712769,"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": 6305207438167.825, "dur": 28647.151, + "args": { + "External id": 712770,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305207438183.635, "dur": 28623.416, + "args": { + "External id": 712771,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305207438202.735, "dur": 16.431, + "args": { + "External id": 712772,"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": 6305207438222.774, "dur": 28550.298, + "args": { + "External id": 712773,"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": 6305207438225.363, "dur": 28547.223, + "args": { + "External id": 712774,"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": 6305207438232.215, "dur": 7.311, + "args": { + "External id": 712775,"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": 6305207438241.139, "dur": 28528.251, + "args": { + "External id": 712776,"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": 6305207466988.294, "dur": 32.686, + "args": { + "External id": 712777,"Sequence number": 7674632, "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": 6305207466988.294, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6305207467008.256, "dur": 8.283, + "args": { + "External id": 712778,"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": 6305207467011.856, "dur": 4.435, + "args": { + "External id": 712779,"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": 6305207467115.150, "dur": 77.859, + "args": { + "External id": 712780,"Record function id": 0, "Ev Idx": 17040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6305207467194.646, "dur": 1116.039, + "args": { + "External id": 712781,"Record function id": 0, "Ev Idx": 17041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305207467235.400, "dur": 1061.263, + "args": { + "External id": 712782,"Sequence number": 7674633, "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": 6305207467235.400, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6305207467301.018, "dur": 49.944, + "args": { + "External id": 712783,"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": 6305207467364.241, "dur": 105.221, + "args": { + "External id": 712784,"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": 6305207467482.287, "dur": 53.460, + "args": { + "External id": 712785,"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": 6305207467548.232, "dur": 31.706, + "args": { + "External id": 712786,"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": 6305207467608.016, "dur": 26.349, + "args": { + "External id": 712787,"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": 6305207467654.073, "dur": 18.044, + "args": { + "External id": 712788,"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": 6305207467696.574, "dur": 133.117, + "args": { + "External id": 712789,"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": 6305207467750.973, "dur": 11.318, + "args": { + "External id": 712790,"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": 6305207467756.355, "dur": 4.957, + "args": { + "External id": 712791,"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": 6305207467764.842, "dur": 4.092, + "args": { + "External id": 712792,"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": 6305207467770.483, "dur": 1.198, + "args": { + "External id": 712793,"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": 6305207467774.384, "dur": 6.157, + "args": { + "External id": 712794,"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": 6305207467840.954, "dur": 48.908, + "args": { + "External id": 712795,"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": 6305207467921.830, "dur": 27.154, + "args": { + "External id": 712796,"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": 6305207467959.241, "dur": 41.405, + "args": { + "External id": 712797,"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": 6305207468010.235, "dur": 34.252, + "args": { + "External id": 712798,"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": 6305207468105.887, "dur": 30.239, + "args": { + "External id": 712799,"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": 6305207468146.414, "dur": 40.762, + "args": { + "External id": 712800,"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": 6305207468208.755, "dur": 18.477, + "args": { + "External id": 712801,"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": 6305207468374.121, "dur": 78.297, + "args": { + "External id": 712802,"Record function id": 0, "Ev Idx": 17062 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6305207468546.565, "dur": 51.696, + "args": { + "External id": 712803,"Record function id": 0, "Ev Idx": 17063 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.7)", "pid": 2338707, "tid": 2338707, + "ts": 6305207468607.788, "dur": 31791.637, + "args": { + "External id": 712804,"Record function id": 0, "Ev Idx": 17064 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.7)", "pid": 2338707, "tid": 2338707, + "ts": 6305207468615.474, "dur": 953.740, + "args": { + "External id": 712805,"Record function id": 0, "Ev Idx": 17065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6305207468698.558, "dur": 9.555, + "args": { + "External id": 712806,"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": 6305207468721.625, "dur": 38.198, + "args": { + "External id": 712807,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305207468727.634, "dur": 2.337, + "args": { + "External id": 712808,"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": 6305207468734.218, "dur": 0.362, + "args": { + "External id": 712809,"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": 6305207468736.445, "dur": 0.453, + "args": { + "External id": 712810,"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": 6305207468738.083, "dur": 0.457, + "args": { + "External id": 712811,"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": 6305207468742.636, "dur": 0.649, + "args": { + "External id": 712812,"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": 6305207468744.536, "dur": 0.490, + "args": { + "External id": 712813,"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": 6305207468746.851, "dur": 3.307, + "args": { + "External id": 712814,"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": 6305207468751.653, "dur": 0.390, + "args": { + "External id": 712815,"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": 6305207468753.323, "dur": 0.279, + "args": { + "External id": 712816,"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": 6305207468770.975, "dur": 52.759, + "args": { + "External id": 712817,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305207468861.582, "dur": 126.639, + "args": { + "External id": 712818,"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": 6305207468872.693, "dur": 5.492, + "args": { + "External id": 712819,"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": 6305207468883.725, "dur": 10.539, + "args": { + "External id": 712820,"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": 6305207468888.372, "dur": 5.513, + "args": { + "External id": 712821,"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": 6305207468892.050, "dur": 0.549, + "args": { + "External id": 712822,"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": 6305207468900.874, "dur": 31.176, + "args": { + "External id": 712823,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305207468902.663, "dur": 0.389, + "args": { + "External id": 712824,"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": 6305207468904.468, "dur": 2.675, + "args": { + "External id": 712825,"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": 6305207468908.603, "dur": 0.374, + "args": { + "External id": 712826,"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": 6305207468910.683, "dur": 2.614, + "args": { + "External id": 712827,"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": 6305207468917.344, "dur": 0.375, + "args": { + "External id": 712828,"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": 6305207468919.042, "dur": 0.297, + "args": { + "External id": 712829,"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": 6305207468921.310, "dur": 0.293, + "args": { + "External id": 712830,"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": 6305207468925.890, "dur": 0.311, + "args": { + "External id": 712831,"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": 6305207468927.548, "dur": 0.362, + "args": { + "External id": 712832,"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": 6305207468948.255, "dur": 32.293, + "args": { + "External id": 712833,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305207469040.583, "dur": 412.157, + "args": { + "External id": 712834,"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": 6305207469108.649, "dur": 338.326, + "args": { + "External id": 712835,"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": 6305207469121.027, "dur": 318.291, + "args": { + "External id": 712836,"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": 6305207469477.620, "dur": 2.218, + "args": { + "External id": 712837,"Record function id": 0, "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": 6305207469591.746, "dur": 30617.807, + "args": { + "External id": 712838,"Record function id": 0, "Ev Idx": 17098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6305207469693.597, "dur": 6.658, + "args": { + "External id": 712839,"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": 6305207469704.095, "dur": 0.937, + "args": { + "External id": 712840,"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": 6305207469706.656, "dur": 3.234, + "args": { + "External id": 712841,"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": 6305207469711.536, "dur": 0.965, + "args": { + "External id": 712842,"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": 6305207469714.056, "dur": 0.885, + "args": { + "External id": 712843,"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": 6305207469716.178, "dur": 1.123, + "args": { + "External id": 712844,"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": 6305207469720.761, "dur": 0.734, + "args": { + "External id": 712845,"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": 6305207469723.007, "dur": 2.167, + "args": { + "External id": 712846,"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": 6305207469726.922, "dur": 0.766, + "args": { + "External id": 712847,"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": 6305207469729.121, "dur": 0.827, + "args": { + "External id": 712848,"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": 6305207469749.661, "dur": 30413.776, + "args": { + "External id": 712849,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305207469765.181, "dur": 30389.828, + "args": { + "External id": 712850,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305207469781.683, "dur": 15.440, + "args": { + "External id": 712851,"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": 6305207469800.782, "dur": 30317.125, + "args": { + "External id": 712852,"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": 6305207469803.237, "dur": 30314.023, + "args": { + "External id": 712853,"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": 6305207469810.319, "dur": 6.972, + "args": { + "External id": 712854,"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": 6305207469819.136, "dur": 30294.896, + "args": { + "External id": 712855,"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": 6305207500343.866, "dur": 30.465, + "args": { + "External id": 712856,"Sequence number": 7674634, "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": 6305207500343.866, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6305207500360.841, "dur": 8.600, + "args": { + "External id": 712857,"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": 6305207500364.556, "dur": 4.601, + "args": { + "External id": 712858,"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": 6305207500441.292, "dur": 86.573, + "args": { + "External id": 712859,"Record function id": 0, "Ev Idx": 17119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6305207500530.680, "dur": 1126.551, + "args": { + "External id": 712860,"Record function id": 0, "Ev Idx": 17120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305207500573.551, "dur": 1070.617, + "args": { + "External id": 712861,"Sequence number": 7674635, "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": 6305207500573.551, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6305207500640.750, "dur": 52.172, + "args": { + "External id": 712862,"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": 6305207500706.163, "dur": 103.732, + "args": { + "External id": 712863,"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": 6305207500821.655, "dur": 41.450, + "args": { + "External id": 712864,"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": 6305207500871.708, "dur": 29.479, + "args": { + "External id": 712865,"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": 6305207500924.901, "dur": 26.714, + "args": { + "External id": 712866,"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": 6305207500971.441, "dur": 17.169, + "args": { + "External id": 712867,"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": 6305207501010.763, "dur": 180.847, + "args": { + "External id": 712868,"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": 6305207501099.989, "dur": 12.203, + "args": { + "External id": 712869,"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": 6305207501104.903, "dur": 6.300, + "args": { + "External id": 712870,"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": 6305207501114.923, "dur": 4.654, + "args": { + "External id": 712871,"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": 6305207501120.749, "dur": 0.995, + "args": { + "External id": 712872,"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": 6305207501126.504, "dur": 7.079, + "args": { + "External id": 712873,"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": 6305207501203.541, "dur": 58.033, + "args": { + "External id": 712874,"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": 6305207501295.931, "dur": 29.791, + "args": { + "External id": 712875,"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": 6305207501335.709, "dur": 42.420, + "args": { + "External id": 712876,"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": 6305207501387.107, "dur": 34.562, + "args": { + "External id": 712877,"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": 6305207501449.835, "dur": 26.830, + "args": { + "External id": 712878,"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": 6305207501482.041, "dur": 48.940, + "args": { + "External id": 712879,"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": 6305207501554.488, "dur": 22.103, + "args": { + "External id": 712880,"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": 6305207501722.473, "dur": 76.170, + "args": { + "External id": 712881,"Record function id": 0, "Ev Idx": 17141 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6305207501872.949, "dur": 49.255, + "args": { + "External id": 712882,"Record function id": 0, "Ev Idx": 17142 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.8)", "pid": 2338707, "tid": 2338707, + "ts": 6305207501931.099, "dur": 31173.007, + "args": { + "External id": 712883,"Record function id": 0, "Ev Idx": 17143 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.8)", "pid": 2338707, "tid": 2338707, + "ts": 6305207501940.927, "dur": 972.775, + "args": { + "External id": 712884,"Record function id": 0, "Ev Idx": 17144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6305207502018.774, "dur": 7.980, + "args": { + "External id": 712885,"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": 6305207502039.769, "dur": 90.158, + "args": { + "External id": 712886,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305207502045.506, "dur": 2.265, + "args": { + "External id": 712887,"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": 6305207502100.948, "dur": 1.032, + "args": { + "External id": 712888,"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": 6305207502105.387, "dur": 0.522, + "args": { + "External id": 712889,"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": 6305207502107.044, "dur": 0.427, + "args": { + "External id": 712890,"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": 6305207502111.493, "dur": 0.435, + "args": { + "External id": 712891,"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": 6305207502113.258, "dur": 0.529, + "args": { + "External id": 712892,"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": 6305207502115.001, "dur": 4.478, + "args": { + "External id": 712893,"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": 6305207502120.651, "dur": 0.281, + "args": { + "External id": 712894,"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": 6305207502122.128, "dur": 0.380, + "args": { + "External id": 712895,"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": 6305207502144.368, "dur": 60.035, + "args": { + "External id": 712896,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305207502241.697, "dur": 133.117, + "args": { + "External id": 712897,"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": 6305207502253.855, "dur": 5.399, + "args": { + "External id": 712898,"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": 6305207502265.011, "dur": 13.173, + "args": { + "External id": 712899,"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": 6305207502272.315, "dur": 5.473, + "args": { + "External id": 712900,"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": 6305207502275.850, "dur": 0.533, + "args": { + "External id": 712901,"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": 6305207502285.230, "dur": 34.822, + "args": { + "External id": 712902,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305207502287.863, "dur": 2.430, + "args": { + "External id": 712903,"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": 6305207502292.340, "dur": 0.332, + "args": { + "External id": 712904,"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": 6305207502293.846, "dur": 0.333, + "args": { + "External id": 712905,"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": 6305207502298.626, "dur": 3.420, + "args": { + "External id": 712906,"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": 6305207502303.301, "dur": 0.318, + "args": { + "External id": 712907,"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": 6305207502305.417, "dur": 0.369, + "args": { + "External id": 712908,"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": 6305207502308.853, "dur": 0.420, + "args": { + "External id": 712909,"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": 6305207502311.057, "dur": 0.291, + "args": { + "External id": 712910,"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": 6305207502312.786, "dur": 2.353, + "args": { + "External id": 712911,"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": 6305207502331.449, "dur": 34.985, + "args": { + "External id": 712912,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305207502430.727, "dur": 382.428, + "args": { + "External id": 712913,"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": 6305207502462.864, "dur": 344.926, + "args": { + "External id": 712914,"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": 6305207502473.534, "dur": 327.659, + "args": { + "External id": 712915,"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": 6305207502838.711, "dur": 2.491, + "args": { + "External id": 712916,"Record function id": 0, "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": 6305207502934.417, "dur": 29948.929, + "args": { + "External id": 712917,"Record function id": 0, "Ev Idx": 17177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6305207503028.951, "dur": 6.664, + "args": { + "External id": 712918,"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": 6305207503039.337, "dur": 0.952, + "args": { + "External id": 712919,"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": 6305207503042.124, "dur": 4.071, + "args": { + "External id": 712920,"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": 6305207503048.102, "dur": 0.866, + "args": { + "External id": 712921,"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": 6305207503050.371, "dur": 0.800, + "args": { + "External id": 712922,"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": 6305207503087.152, "dur": 1.612, + "args": { + "External id": 712923,"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": 6305207503094.250, "dur": 0.650, + "args": { + "External id": 712924,"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": 6305207503096.539, "dur": 2.254, + "args": { + "External id": 712925,"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": 6305207503100.508, "dur": 0.947, + "args": { + "External id": 712926,"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": 6305207503102.810, "dur": 0.854, + "args": { + "External id": 712927,"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": 6305207503125.068, "dur": 29714.311, + "args": { + "External id": 712928,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305207503140.800, "dur": 29690.646, + "args": { + "External id": 712929,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305207503159.703, "dur": 17.039, + "args": { + "External id": 712930,"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": 6305207503180.574, "dur": 29616.976, + "args": { + "External id": 712931,"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": 6305207503183.430, "dur": 29613.518, + "args": { + "External id": 712932,"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": 6305207503189.685, "dur": 5.806, + "args": { + "External id": 712933,"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": 6305207503197.378, "dur": 29596.453, + "args": { + "External id": 712934,"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": 6305207533018.324, "dur": 31.599, + "args": { + "External id": 712935,"Sequence number": 7674636, "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": 6305207533018.324, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6305207533036.256, "dur": 8.914, + "args": { + "External id": 712936,"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": 6305207533040.025, "dur": 4.929, + "args": { + "External id": 712937,"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": 6305207533150.194, "dur": 74.007, + "args": { + "External id": 712938,"Record function id": 0, "Ev Idx": 17198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6305207533225.281, "dur": 1113.794, + "args": { + "External id": 712939,"Record function id": 0, "Ev Idx": 17199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305207533265.793, "dur": 1059.429, + "args": { + "External id": 712940,"Sequence number": 7674637, "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": 6305207533265.793, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6305207533336.173, "dur": 50.086, + "args": { + "External id": 712941,"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": 6305207533400.225, "dur": 121.812, + "args": { + "External id": 712942,"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": 6305207533538.729, "dur": 41.173, + "args": { + "External id": 712943,"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": 6305207533588.973, "dur": 28.718, + "args": { + "External id": 712944,"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": 6305207533645.941, "dur": 26.314, + "args": { + "External id": 712945,"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": 6305207533691.964, "dur": 16.844, + "args": { + "External id": 712946,"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": 6305207533733.029, "dur": 130.483, + "args": { + "External id": 712947,"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": 6305207533783.468, "dur": 10.955, + "args": { + "External id": 712948,"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": 6305207533788.501, "dur": 5.126, + "args": { + "External id": 712949,"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": 6305207533797.799, "dur": 4.051, + "args": { + "External id": 712950,"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": 6305207533803.071, "dur": 0.848, + "args": { + "External id": 712951,"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": 6305207533806.464, "dur": 5.552, + "args": { + "External id": 712952,"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": 6305207533873.975, "dur": 48.360, + "args": { + "External id": 712953,"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": 6305207533954.493, "dur": 27.663, + "args": { + "External id": 712954,"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": 6305207533991.566, "dur": 42.218, + "args": { + "External id": 712955,"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": 6305207534042.741, "dur": 70.081, + "args": { + "External id": 712956,"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": 6305207534141.193, "dur": 26.198, + "args": { + "External id": 712957,"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": 6305207534176.649, "dur": 39.015, + "args": { + "External id": 712958,"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": 6305207534235.053, "dur": 17.158, + "args": { + "External id": 712959,"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": 6305207534404.653, "dur": 74.940, + "args": { + "External id": 712960,"Record function id": 0, "Ev Idx": 17220 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6305207534573.809, "dur": 51.296, + "args": { + "External id": 712961,"Record function id": 0, "Ev Idx": 17221 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.9)", "pid": 2338707, "tid": 2338707, + "ts": 6305207534634.346, "dur": 33120.325, + "args": { + "External id": 712962,"Record function id": 0, "Ev Idx": 17222 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.9)", "pid": 2338707, "tid": 2338707, + "ts": 6305207534642.498, "dur": 993.816, + "args": { + "External id": 712963,"Record function id": 0, "Ev Idx": 17223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6305207534724.367, "dur": 10.292, + "args": { + "External id": 712964,"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": 6305207534747.335, "dur": 40.020, + "args": { + "External id": 712965,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305207534753.729, "dur": 2.502, + "args": { + "External id": 712966,"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": 6305207534760.927, "dur": 0.451, + "args": { + "External id": 712967,"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": 6305207534763.302, "dur": 0.331, + "args": { + "External id": 712968,"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": 6305207534764.805, "dur": 0.385, + "args": { + "External id": 712969,"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": 6305207534769.464, "dur": 0.505, + "args": { + "External id": 712970,"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": 6305207534770.764, "dur": 0.389, + "args": { + "External id": 712971,"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": 6305207534772.359, "dur": 4.737, + "args": { + "External id": 712972,"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": 6305207534778.400, "dur": 0.418, + "args": { + "External id": 712973,"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": 6305207534780.428, "dur": 0.451, + "args": { + "External id": 712974,"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": 6305207534798.085, "dur": 56.177, + "args": { + "External id": 712975,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305207534886.697, "dur": 126.401, + "args": { + "External id": 712976,"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": 6305207534897.880, "dur": 4.146, + "args": { + "External id": 712977,"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": 6305207534907.462, "dur": 13.269, + "args": { + "External id": 712978,"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": 6305207534914.593, "dur": 5.712, + "args": { + "External id": 712979,"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": 6305207534918.452, "dur": 0.621, + "args": { + "External id": 712980,"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": 6305207534926.662, "dur": 31.647, + "args": { + "External id": 712981,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305207534928.920, "dur": 2.243, + "args": { + "External id": 712982,"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": 6305207534932.420, "dur": 0.315, + "args": { + "External id": 712983,"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": 6305207534934.125, "dur": 0.502, + "args": { + "External id": 712984,"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": 6305207534938.260, "dur": 2.393, + "args": { + "External id": 712985,"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": 6305207534942.440, "dur": 0.345, + "args": { + "External id": 712986,"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": 6305207534943.861, "dur": 0.339, + "args": { + "External id": 712987,"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": 6305207534948.363, "dur": 0.382, + "args": { + "External id": 712988,"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": 6305207534949.749, "dur": 0.364, + "args": { + "External id": 712989,"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": 6305207534951.700, "dur": 2.323, + "args": { + "External id": 712990,"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": 6305207534970.900, "dur": 34.193, + "args": { + "External id": 712991,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305207535102.858, "dur": 423.641, + "args": { + "External id": 712992,"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": 6305207535136.625, "dur": 368.162, + "args": { + "External id": 712993,"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": 6305207535148.653, "dur": 350.562, + "args": { + "External id": 712994,"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": 6305207535553.696, "dur": 3.378, + "args": { + "External id": 712995,"Record function id": 0, "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": 6305207535658.706, "dur": 31906.843, + "args": { + "External id": 712996,"Record function id": 0, "Ev Idx": 17256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6305207535755.907, "dur": 6.464, + "args": { + "External id": 712997,"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": 6305207535765.785, "dur": 0.879, + "args": { + "External id": 712998,"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": 6305207535768.259, "dur": 3.558, + "args": { + "External id": 712999,"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": 6305207535773.620, "dur": 0.740, + "args": { + "External id": 713000,"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": 6305207535775.789, "dur": 0.738, + "args": { + "External id": 713001,"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": 6305207535778.384, "dur": 0.756, + "args": { + "External id": 713002,"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": 6305207535782.922, "dur": 0.663, + "args": { + "External id": 713003,"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": 6305207535785.425, "dur": 1.992, + "args": { + "External id": 713004,"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": 6305207535788.916, "dur": 0.573, + "args": { + "External id": 713005,"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": 6305207535791.049, "dur": 0.527, + "args": { + "External id": 713006,"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": 6305207535811.207, "dur": 31711.301, + "args": { + "External id": 713007,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305207535827.729, "dur": 31676.784, + "args": { + "External id": 713008,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305207535843.332, "dur": 15.563, + "args": { + "External id": 713009,"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": 6305207535862.436, "dur": 31608.270, + "args": { + "External id": 713010,"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": 6305207535865.170, "dur": 31604.937, + "args": { + "External id": 713011,"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": 6305207535872.363, "dur": 5.927, + "args": { + "External id": 713012,"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": 6305207535880.014, "dur": 31586.758, + "args": { + "External id": 713013,"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": 6305207567700.298, "dur": 29.514, + "args": { + "External id": 713014,"Sequence number": 7674638, "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": 6305207567700.298, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6305207567716.854, "dur": 8.228, + "args": { + "External id": 713015,"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": 6305207567720.323, "dur": 4.590, + "args": { + "External id": 713016,"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": 6305207567795.894, "dur": 77.292, + "args": { + "External id": 713017,"Record function id": 0, "Ev Idx": 17277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6305207567874.654, "dur": 1115.530, + "args": { + "External id": 713018,"Record function id": 0, "Ev Idx": 17278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305207567915.907, "dur": 1061.141, + "args": { + "External id": 713019,"Sequence number": 7674639, "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": 6305207567915.907, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6305207567980.758, "dur": 48.721, + "args": { + "External id": 713020,"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": 6305207568042.168, "dur": 131.605, + "args": { + "External id": 713021,"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": 6305207568191.121, "dur": 38.617, + "args": { + "External id": 713022,"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": 6305207568239.421, "dur": 28.942, + "args": { + "External id": 713023,"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": 6305207568296.795, "dur": 28.050, + "args": { + "External id": 713024,"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": 6305207568345.829, "dur": 16.562, + "args": { + "External id": 713025,"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": 6305207568389.093, "dur": 153.140, + "args": { + "External id": 713026,"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": 6305207568442.479, "dur": 10.805, + "args": { + "External id": 713027,"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": 6305207568447.557, "dur": 4.802, + "args": { + "External id": 713028,"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": 6305207568456.142, "dur": 4.497, + "args": { + "External id": 713029,"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": 6305207568462.538, "dur": 0.881, + "args": { + "External id": 713030,"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": 6305207568465.825, "dur": 5.595, + "args": { + "External id": 713031,"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": 6305207568557.642, "dur": 57.118, + "args": { + "External id": 713032,"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": 6305207568651.519, "dur": 30.668, + "args": { + "External id": 713033,"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": 6305207568692.092, "dur": 42.231, + "args": { + "External id": 713034,"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": 6305207568743.467, "dur": 34.448, + "args": { + "External id": 713035,"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": 6305207568802.409, "dur": 27.558, + "args": { + "External id": 713036,"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": 6305207568835.686, "dur": 36.144, + "args": { + "External id": 713037,"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": 6305207568890.610, "dur": 18.758, + "args": { + "External id": 713038,"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": 6305207569088.164, "dur": 80.670, + "args": { + "External id": 713039,"Record function id": 0, "Ev Idx": 17299 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6305207569247.305, "dur": 46.670, + "args": { + "External id": 713040,"Record function id": 0, "Ev Idx": 17300 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.10)", "pid": 2338707, "tid": 2338707, + "ts": 6305207569302.601, "dur": 31266.449, + "args": { + "External id": 713041,"Record function id": 0, "Ev Idx": 17301 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.10)", "pid": 2338707, "tid": 2338707, + "ts": 6305207569310.769, "dur": 976.348, + "args": { + "External id": 713042,"Record function id": 0, "Ev Idx": 17302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6305207569390.070, "dur": 8.663, + "args": { + "External id": 713043,"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": 6305207569411.729, "dur": 39.429, + "args": { + "External id": 713044,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305207569417.557, "dur": 2.257, + "args": { + "External id": 713045,"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": 6305207569424.766, "dur": 0.491, + "args": { + "External id": 713046,"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": 6305207569426.800, "dur": 0.443, + "args": { + "External id": 713047,"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": 6305207569428.531, "dur": 0.755, + "args": { + "External id": 713048,"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": 6305207569432.812, "dur": 0.742, + "args": { + "External id": 713049,"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": 6305207569434.479, "dur": 0.473, + "args": { + "External id": 713050,"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": 6305207569436.776, "dur": 4.674, + "args": { + "External id": 713051,"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": 6305207569442.529, "dur": 0.488, + "args": { + "External id": 713052,"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": 6305207569444.213, "dur": 0.284, + "args": { + "External id": 713053,"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": 6305207569462.325, "dur": 73.916, + "args": { + "External id": 713054,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305207569571.984, "dur": 140.858, + "args": { + "External id": 713055,"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": 6305207569583.466, "dur": 13.995, + "args": { + "External id": 713056,"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": 6305207569604.459, "dur": 14.282, + "args": { + "External id": 713057,"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": 6305207569611.533, "dur": 6.746, + "args": { + "External id": 713058,"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": 6305207569615.953, "dur": 0.652, + "args": { + "External id": 713059,"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": 6305207569626.173, "dur": 30.036, + "args": { + "External id": 713060,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305207569628.089, "dur": 2.743, + "args": { + "External id": 713061,"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": 6305207569632.805, "dur": 0.315, + "args": { + "External id": 713062,"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": 6305207569634.350, "dur": 0.236, + "args": { + "External id": 713063,"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": 6305207569638.552, "dur": 2.756, + "args": { + "External id": 713064,"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": 6305207569642.588, "dur": 0.352, + "args": { + "External id": 713065,"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": 6305207569644.563, "dur": 0.268, + "args": { + "External id": 713066,"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": 6305207569645.990, "dur": 0.370, + "args": { + "External id": 713067,"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": 6305207569648.088, "dur": 0.388, + "args": { + "External id": 713068,"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": 6305207569649.699, "dur": 2.233, + "args": { + "External id": 713069,"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": 6305207569667.144, "dur": 37.597, + "args": { + "External id": 713070,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305207569767.433, "dur": 413.291, + "args": { + "External id": 713071,"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": 6305207569798.720, "dur": 376.271, + "args": { + "External id": 713072,"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": 6305207569809.445, "dur": 358.281, + "args": { + "External id": 713073,"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": 6305207570207.622, "dur": 2.186, + "args": { + "External id": 713074,"Record function id": 0, "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": 6305207570308.936, "dur": 30054.850, + "args": { + "External id": 713075,"Record function id": 0, "Ev Idx": 17335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6305207570409.399, "dur": 6.430, + "args": { + "External id": 713076,"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": 6305207570419.343, "dur": 0.725, + "args": { + "External id": 713077,"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": 6305207570421.629, "dur": 3.066, + "args": { + "External id": 713078,"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": 6305207570426.453, "dur": 0.689, + "args": { + "External id": 713079,"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": 6305207570428.425, "dur": 1.001, + "args": { + "External id": 713080,"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": 6305207570430.780, "dur": 0.954, + "args": { + "External id": 713081,"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": 6305207570435.540, "dur": 0.612, + "args": { + "External id": 713082,"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": 6305207570437.586, "dur": 1.948, + "args": { + "External id": 713083,"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": 6305207570440.809, "dur": 0.680, + "args": { + "External id": 713084,"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": 6305207570443.061, "dur": 0.773, + "args": { + "External id": 713085,"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": 6305207570463.423, "dur": 29856.709, + "args": { + "External id": 713086,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305207570478.840, "dur": 29833.005, + "args": { + "External id": 713087,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305207570495.466, "dur": 32.519, + "args": { + "External id": 713088,"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": 6305207570532.765, "dur": 29743.801, + "args": { + "External id": 713089,"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": 6305207570535.575, "dur": 29740.365, + "args": { + "External id": 713090,"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": 6305207570545.389, "dur": 6.426, + "args": { + "External id": 713091,"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": 6305207570553.411, "dur": 29719.470, + "args": { + "External id": 713092,"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": 6305207600495.015, "dur": 46.729, + "args": { + "External id": 713093,"Sequence number": 7674640, "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": 6305207600495.015, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6305207600527.442, "dur": 9.145, + "args": { + "External id": 713094,"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": 6305207600531.037, "dur": 5.184, + "args": { + "External id": 713095,"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": 6305207600611.138, "dur": 72.670, + "args": { + "External id": 713096,"Record function id": 0, "Ev Idx": 17356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6305207600684.994, "dur": 1125.099, + "args": { + "External id": 713097,"Record function id": 0, "Ev Idx": 17357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305207600723.863, "dur": 1072.390, + "args": { + "External id": 713098,"Sequence number": 7674641, "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": 6305207600723.863, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6305207600792.721, "dur": 50.978, + "args": { + "External id": 713099,"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": 6305207600855.432, "dur": 104.329, + "args": { + "External id": 713100,"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": 6305207600972.303, "dur": 38.550, + "args": { + "External id": 713101,"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": 6305207601019.866, "dur": 29.753, + "args": { + "External id": 713102,"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": 6305207601115.828, "dur": 30.927, + "args": { + "External id": 713103,"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": 6305207601167.890, "dur": 18.485, + "args": { + "External id": 713104,"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": 6305207601209.317, "dur": 131.772, + "args": { + "External id": 713105,"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": 6305207601262.562, "dur": 11.340, + "args": { + "External id": 713106,"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": 6305207601268.046, "dur": 5.197, + "args": { + "External id": 713107,"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": 6305207601277.271, "dur": 4.218, + "args": { + "External id": 713108,"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": 6305207601282.928, "dur": 0.828, + "args": { + "External id": 713109,"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": 6305207601286.376, "dur": 5.723, + "args": { + "External id": 713110,"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": 6305207601351.275, "dur": 56.478, + "args": { + "External id": 713111,"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": 6305207601440.879, "dur": 30.713, + "args": { + "External id": 713112,"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": 6305207601480.674, "dur": 59.703, + "args": { + "External id": 713113,"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": 6305207601553.124, "dur": 38.505, + "args": { + "External id": 713114,"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": 6305207601616.428, "dur": 29.182, + "args": { + "External id": 713115,"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": 6305207601653.119, "dur": 35.958, + "args": { + "External id": 713116,"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": 6305207601707.268, "dur": 18.722, + "args": { + "External id": 713117,"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": 6305207601875.191, "dur": 77.649, + "args": { + "External id": 713118,"Record function id": 0, "Ev Idx": 17378 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6305207602026.321, "dur": 103.816, + "args": { + "External id": 713119,"Record function id": 0, "Ev Idx": 17379 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.11)", "pid": 2338707, "tid": 2338707, + "ts": 6305207602142.086, "dur": 31253.591, + "args": { + "External id": 713120,"Record function id": 0, "Ev Idx": 17380 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.11)", "pid": 2338707, "tid": 2338707, + "ts": 6305207602150.628, "dur": 950.792, + "args": { + "External id": 713121,"Record function id": 0, "Ev Idx": 17381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6305207602236.781, "dur": 10.967, + "args": { + "External id": 713122,"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": 6305207602261.406, "dur": 39.105, + "args": { + "External id": 713123,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305207602268.219, "dur": 2.298, + "args": { + "External id": 713124,"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": 6305207602274.926, "dur": 0.422, + "args": { + "External id": 713125,"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": 6305207602277.110, "dur": 0.499, + "args": { + "External id": 713126,"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": 6305207602278.741, "dur": 0.364, + "args": { + "External id": 713127,"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": 6305207602283.152, "dur": 0.455, + "args": { + "External id": 713128,"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": 6305207602285.064, "dur": 0.287, + "args": { + "External id": 713129,"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": 6305207602286.874, "dur": 2.838, + "args": { + "External id": 713130,"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": 6305207602290.817, "dur": 0.662, + "args": { + "External id": 713131,"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": 6305207602293.091, "dur": 0.305, + "args": { + "External id": 713132,"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": 6305207602312.259, "dur": 59.412, + "args": { + "External id": 713133,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305207602404.472, "dur": 145.248, + "args": { + "External id": 713134,"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": 6305207602416.105, "dur": 4.074, + "args": { + "External id": 713135,"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": 6305207602425.756, "dur": 12.590, + "args": { + "External id": 713136,"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": 6305207602432.632, "dur": 5.323, + "args": { + "External id": 713137,"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": 6305207602436.188, "dur": 0.469, + "args": { + "External id": 713138,"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": 6305207602445.226, "dur": 31.811, + "args": { + "External id": 713139,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305207602447.015, "dur": 2.878, + "args": { + "External id": 713140,"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": 6305207602451.336, "dur": 0.311, + "args": { + "External id": 713141,"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": 6305207602453.406, "dur": 0.300, + "args": { + "External id": 713142,"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": 6305207602456.878, "dur": 2.442, + "args": { + "External id": 713143,"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": 6305207602461.053, "dur": 0.288, + "args": { + "External id": 713144,"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": 6305207602462.709, "dur": 0.281, + "args": { + "External id": 713145,"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": 6305207602467.125, "dur": 0.323, + "args": { + "External id": 713146,"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": 6305207602468.739, "dur": 0.413, + "args": { + "External id": 713147,"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": 6305207602470.720, "dur": 2.273, + "args": { + "External id": 713148,"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": 6305207602489.271, "dur": 51.084, + "args": { + "External id": 713149,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305207602605.653, "dur": 366.578, + "args": { + "External id": 713150,"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": 6305207602638.065, "dur": 329.055, + "args": { + "External id": 713151,"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": 6305207602648.447, "dur": 313.060, + "args": { + "External id": 713152,"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": 6305207602994.782, "dur": 2.618, + "args": { + "External id": 713153,"Record function id": 0, "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": 6305207603125.895, "dur": 30080.318, + "args": { + "External id": 713154,"Record function id": 0, "Ev Idx": 17414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6305207603223.953, "dur": 6.735, + "args": { + "External id": 713155,"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": 6305207603234.424, "dur": 0.880, + "args": { + "External id": 713156,"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": 6305207603237.284, "dur": 3.298, + "args": { + "External id": 713157,"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": 6305207603242.211, "dur": 0.707, + "args": { + "External id": 713158,"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": 6305207603244.329, "dur": 0.688, + "args": { + "External id": 713159,"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": 6305207603246.474, "dur": 0.659, + "args": { + "External id": 713160,"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": 6305207603250.560, "dur": 0.747, + "args": { + "External id": 713161,"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": 6305207603253.247, "dur": 2.283, + "args": { + "External id": 713162,"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": 6305207603256.834, "dur": 0.828, + "args": { + "External id": 713163,"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": 6305207603259.409, "dur": 0.835, + "args": { + "External id": 713164,"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": 6305207603279.854, "dur": 29882.637, + "args": { + "External id": 713165,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305207603294.974, "dur": 29858.586, + "args": { + "External id": 713166,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305207603309.689, "dur": 16.546, + "args": { + "External id": 713167,"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": 6305207603329.949, "dur": 29784.795, + "args": { + "External id": 713168,"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": 6305207603332.540, "dur": 29781.630, + "args": { + "External id": 713169,"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": 6305207603339.878, "dur": 5.336, + "args": { + "External id": 713170,"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": 6305207603346.716, "dur": 29764.025, + "args": { + "External id": 713171,"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": 6305207633340.200, "dur": 31.926, + "args": { + "External id": 713172,"Sequence number": 7674642, "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": 6305207633340.200, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6305207633358.117, "dur": 9.239, + "args": { + "External id": 713173,"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": 6305207633362.300, "dur": 4.838, + "args": { + "External id": 713174,"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": 6305207633434.565, "dur": 96.974, + "args": { + "External id": 713175,"Record function id": 0, "Ev Idx": 17435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6305207633534.968, "dur": 1142.756, + "args": { + "External id": 713176,"Record function id": 0, "Ev Idx": 17436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305207633578.222, "dur": 1085.406, + "args": { + "External id": 713177,"Sequence number": 7674643, "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": 6305207633578.222, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6305207633647.767, "dur": 52.992, + "args": { + "External id": 713178,"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": 6305207633713.508, "dur": 105.423, + "args": { + "External id": 713179,"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": 6305207633831.947, "dur": 41.063, + "args": { + "External id": 713180,"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": 6305207633882.065, "dur": 29.470, + "args": { + "External id": 713181,"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": 6305207633940.773, "dur": 27.884, + "args": { + "External id": 713182,"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": 6305207633987.257, "dur": 18.328, + "args": { + "External id": 713183,"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": 6305207634027.082, "dur": 178.260, + "args": { + "External id": 713184,"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": 6305207634119.577, "dur": 12.841, + "args": { + "External id": 713185,"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": 6305207634125.177, "dur": 6.199, + "args": { + "External id": 713186,"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": 6305207634135.473, "dur": 3.766, + "args": { + "External id": 713187,"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": 6305207634141.213, "dur": 1.040, + "args": { + "External id": 713188,"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": 6305207634144.869, "dur": 7.520, + "args": { + "External id": 713189,"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": 6305207634217.262, "dur": 55.418, + "args": { + "External id": 713190,"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": 6305207634307.155, "dur": 32.051, + "args": { + "External id": 713191,"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": 6305207634351.027, "dur": 42.853, + "args": { + "External id": 713192,"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": 6305207634400.578, "dur": 34.162, + "args": { + "External id": 713193,"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": 6305207634456.994, "dur": 26.786, + "args": { + "External id": 713194,"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": 6305207634494.583, "dur": 54.068, + "args": { + "External id": 713195,"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": 6305207634571.377, "dur": 22.999, + "args": { + "External id": 713196,"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": 6305207634744.247, "dur": 78.408, + "args": { + "External id": 713197,"Record function id": 0, "Ev Idx": 17457 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6305207634899.299, "dur": 48.208, + "args": { + "External id": 713198,"Record function id": 0, "Ev Idx": 17458 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.12)", "pid": 2338707, "tid": 2338707, + "ts": 6305207634956.073, "dur": 33953.737, + "args": { + "External id": 713199,"Record function id": 0, "Ev Idx": 17459 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.12)", "pid": 2338707, "tid": 2338707, + "ts": 6305207634964.485, "dur": 909.013, + "args": { + "External id": 713200,"Record function id": 0, "Ev Idx": 17460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6305207635047.639, "dur": 48.981, + "args": { + "External id": 713201,"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": 6305207635113.722, "dur": 42.527, + "args": { + "External id": 713202,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305207635119.998, "dur": 2.490, + "args": { + "External id": 713203,"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": 6305207635127.766, "dur": 0.366, + "args": { + "External id": 713204,"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": 6305207635129.533, "dur": 0.329, + "args": { + "External id": 713205,"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": 6305207635131.549, "dur": 0.333, + "args": { + "External id": 713206,"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": 6305207635136.036, "dur": 0.523, + "args": { + "External id": 713207,"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": 6305207635138.421, "dur": 0.420, + "args": { + "External id": 713208,"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": 6305207635140.343, "dur": 4.761, + "args": { + "External id": 713209,"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": 6305207635146.820, "dur": 0.478, + "args": { + "External id": 713210,"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": 6305207635149.235, "dur": 0.427, + "args": { + "External id": 713211,"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": 6305207635167.926, "dur": 55.856, + "args": { + "External id": 713212,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305207635258.627, "dur": 137.946, + "args": { + "External id": 713213,"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": 6305207635270.327, "dur": 4.465, + "args": { + "External id": 713214,"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": 6305207635280.260, "dur": 25.562, + "args": { + "External id": 713215,"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": 6305207635287.502, "dur": 17.898, + "args": { + "External id": 713216,"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": 6305207635303.485, "dur": 0.480, + "args": { + "External id": 713217,"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": 6305207635312.892, "dur": 31.021, + "args": { + "External id": 713218,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305207635315.030, "dur": 2.601, + "args": { + "External id": 713219,"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": 6305207635319.182, "dur": 0.241, + "args": { + "External id": 713220,"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": 6305207635320.732, "dur": 0.297, + "args": { + "External id": 713221,"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": 6305207635324.802, "dur": 2.623, + "args": { + "External id": 713222,"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": 6305207635328.176, "dur": 0.243, + "args": { + "External id": 713223,"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": 6305207635330.130, "dur": 0.439, + "args": { + "External id": 713224,"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": 6305207635333.236, "dur": 0.318, + "args": { + "External id": 713225,"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": 6305207635335.613, "dur": 0.362, + "args": { + "External id": 713226,"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": 6305207635337.046, "dur": 1.914, + "args": { + "External id": 713227,"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": 6305207635355.180, "dur": 33.202, + "args": { + "External id": 713228,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305207635453.209, "dur": 322.019, + "args": { + "External id": 713229,"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": 6305207635485.145, "dur": 284.475, + "args": { + "External id": 713230,"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": 6305207635495.652, "dur": 268.004, + "args": { + "External id": 713231,"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": 6305207635800.401, "dur": 2.438, + "args": { + "External id": 713232,"Record function id": 0, "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": 6305207635893.512, "dur": 32829.682, + "args": { + "External id": 713233,"Record function id": 0, "Ev Idx": 17493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6305207635991.756, "dur": 6.429, + "args": { + "External id": 713234,"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": 6305207636001.900, "dur": 1.216, + "args": { + "External id": 713235,"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": 6305207636004.838, "dur": 3.390, + "args": { + "External id": 713236,"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": 6305207636009.904, "dur": 0.866, + "args": { + "External id": 713237,"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": 6305207636012.120, "dur": 0.858, + "args": { + "External id": 713238,"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": 6305207636014.248, "dur": 0.809, + "args": { + "External id": 713239,"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": 6305207636018.608, "dur": 0.721, + "args": { + "External id": 713240,"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": 6305207636021.327, "dur": 2.111, + "args": { + "External id": 713241,"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": 6305207636024.649, "dur": 0.733, + "args": { + "External id": 713242,"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": 6305207636026.745, "dur": 0.649, + "args": { + "External id": 713243,"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": 6305207636048.102, "dur": 32632.093, + "args": { + "External id": 713244,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305207636101.867, "dur": 32571.016, + "args": { + "External id": 713245,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305207636121.050, "dur": 16.364, + "args": { + "External id": 713246,"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": 6305207636141.056, "dur": 32498.217, + "args": { + "External id": 713247,"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": 6305207636143.885, "dur": 32494.821, + "args": { + "External id": 713248,"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": 6305207636149.754, "dur": 5.696, + "args": { + "External id": 713249,"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": 6305207636156.880, "dur": 32479.043, + "args": { + "External id": 713250,"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": 6305207668855.298, "dur": 29.215, + "args": { + "External id": 713251,"Sequence number": 7674644, "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": 6305207668855.298, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6305207668871.396, "dur": 8.215, + "args": { + "External id": 713252,"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": 6305207668874.875, "dur": 4.499, + "args": { + "External id": 713253,"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": 6305207668950.049, "dur": 74.003, + "args": { + "External id": 713254,"Record function id": 0, "Ev Idx": 17514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6305207669025.442, "dur": 1157.833, + "args": { + "External id": 713255,"Record function id": 0, "Ev Idx": 17515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305207669110.526, "dur": 1058.819, + "args": { + "External id": 713256,"Sequence number": 7674645, "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": 6305207669110.526, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6305207669183.190, "dur": 52.049, + "args": { + "External id": 713257,"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": 6305207669249.125, "dur": 106.077, + "args": { + "External id": 713258,"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": 6305207669368.890, "dur": 37.741, + "args": { + "External id": 713259,"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": 6305207669415.866, "dur": 28.712, + "args": { + "External id": 713260,"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": 6305207669470.237, "dur": 27.774, + "args": { + "External id": 713261,"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": 6305207669532.382, "dur": 21.738, + "args": { + "External id": 713262,"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": 6305207669578.692, "dur": 134.345, + "args": { + "External id": 713263,"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": 6305207669631.712, "dur": 11.783, + "args": { + "External id": 713264,"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": 6305207669637.118, "dur": 5.589, + "args": { + "External id": 713265,"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": 6305207669646.188, "dur": 4.087, + "args": { + "External id": 713266,"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": 6305207669651.329, "dur": 0.822, + "args": { + "External id": 713267,"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": 6305207669655.312, "dur": 6.465, + "args": { + "External id": 713268,"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": 6305207669723.368, "dur": 53.068, + "args": { + "External id": 713269,"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": 6305207669808.523, "dur": 29.878, + "args": { + "External id": 713270,"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": 6305207669848.056, "dur": 41.748, + "args": { + "External id": 713271,"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": 6305207669898.726, "dur": 34.599, + "args": { + "External id": 713272,"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": 6305207669957.026, "dur": 27.349, + "args": { + "External id": 713273,"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": 6305207669992.845, "dur": 34.819, + "args": { + "External id": 713274,"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": 6305207670044.928, "dur": 52.211, + "args": { + "External id": 713275,"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": 6305207670254.319, "dur": 81.501, + "args": { + "External id": 713276,"Record function id": 0, "Ev Idx": 17536 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6305207670409.867, "dur": 46.652, + "args": { + "External id": 713277,"Record function id": 0, "Ev Idx": 17537 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.13)", "pid": 2338707, "tid": 2338707, + "ts": 6305207670464.681, "dur": 33477.494, + "args": { + "External id": 713278,"Record function id": 0, "Ev Idx": 17538 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.13)", "pid": 2338707, "tid": 2338707, + "ts": 6305207670472.888, "dur": 962.498, + "args": { + "External id": 713279,"Record function id": 0, "Ev Idx": 17539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6305207670573.615, "dur": 9.542, + "args": { + "External id": 713280,"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": 6305207670596.871, "dur": 41.353, + "args": { + "External id": 713281,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305207670603.256, "dur": 2.527, + "args": { + "External id": 713282,"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": 6305207670610.624, "dur": 0.432, + "args": { + "External id": 713283,"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": 6305207670612.464, "dur": 0.576, + "args": { + "External id": 713284,"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": 6305207670613.987, "dur": 0.467, + "args": { + "External id": 713285,"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": 6305207670618.617, "dur": 0.347, + "args": { + "External id": 713286,"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": 6305207670620.165, "dur": 0.610, + "args": { + "External id": 713287,"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": 6305207670622.347, "dur": 4.774, + "args": { + "External id": 713288,"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": 6305207670628.480, "dur": 0.259, + "args": { + "External id": 713289,"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": 6305207670630.394, "dur": 0.405, + "args": { + "External id": 713290,"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": 6305207670649.639, "dur": 52.758, + "args": { + "External id": 713291,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305207670745.849, "dur": 121.502, + "args": { + "External id": 713292,"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": 6305207670757.171, "dur": 5.361, + "args": { + "External id": 713293,"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": 6305207670767.910, "dur": 10.865, + "args": { + "External id": 713294,"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": 6305207670772.475, "dur": 5.909, + "args": { + "External id": 713295,"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": 6305207670776.215, "dur": 0.826, + "args": { + "External id": 713296,"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": 6305207670785.112, "dur": 30.772, + "args": { + "External id": 713297,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305207670786.870, "dur": 0.598, + "args": { + "External id": 713298,"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": 6305207670789.393, "dur": 2.834, + "args": { + "External id": 713299,"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": 6305207670793.101, "dur": 0.491, + "args": { + "External id": 713300,"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": 6305207670794.920, "dur": 2.921, + "args": { + "External id": 713301,"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": 6305207670801.144, "dur": 0.356, + "args": { + "External id": 713302,"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": 6305207670803.253, "dur": 0.372, + "args": { + "External id": 713303,"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": 6305207670804.621, "dur": 0.461, + "args": { + "External id": 713304,"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": 6305207670808.944, "dur": 0.376, + "args": { + "External id": 713305,"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": 6305207670810.322, "dur": 0.364, + "args": { + "External id": 713306,"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": 6305207670828.966, "dur": 30.060, + "args": { + "External id": 713307,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305207670920.332, "dur": 409.988, + "args": { + "External id": 713308,"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": 6305207670952.173, "dur": 372.370, + "args": { + "External id": 713309,"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": 6305207670962.820, "dur": 354.824, + "args": { + "External id": 713310,"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": 6305207671356.923, "dur": 2.404, + "args": { + "External id": 713311,"Record function id": 0, "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": 6305207671456.161, "dur": 32282.123, + "args": { + "External id": 713312,"Record function id": 0, "Ev Idx": 17572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6305207671579.793, "dur": 6.791, + "args": { + "External id": 713313,"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": 6305207671590.708, "dur": 1.323, + "args": { + "External id": 713314,"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": 6305207671593.701, "dur": 2.665, + "args": { + "External id": 713315,"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": 6305207671597.916, "dur": 0.811, + "args": { + "External id": 713316,"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": 6305207671600.015, "dur": 0.960, + "args": { + "External id": 713317,"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": 6305207671604.237, "dur": 0.919, + "args": { + "External id": 713318,"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": 6305207671606.776, "dur": 0.837, + "args": { + "External id": 713319,"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": 6305207671608.807, "dur": 2.320, + "args": { + "External id": 713320,"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": 6305207671612.669, "dur": 0.501, + "args": { + "External id": 713321,"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": 6305207671617.104, "dur": 0.580, + "args": { + "External id": 713322,"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": 6305207671635.855, "dur": 32057.353, + "args": { + "External id": 713323,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305207671652.223, "dur": 32032.007, + "args": { + "External id": 713324,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305207671670.877, "dur": 17.389, + "args": { + "External id": 713325,"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": 6305207671691.663, "dur": 31957.558, + "args": { + "External id": 713326,"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": 6305207671694.425, "dur": 31954.226, + "args": { + "External id": 713327,"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": 6305207671700.711, "dur": 5.837, + "args": { + "External id": 713328,"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": 6305207671708.109, "dur": 31937.406, + "args": { + "External id": 713329,"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": 6305207703881.311, "dur": 31.590, + "args": { + "External id": 713330,"Sequence number": 7674646, "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": 6305207703881.311, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6305207703898.883, "dur": 9.038, + "args": { + "External id": 713331,"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": 6305207703902.869, "dur": 4.845, + "args": { + "External id": 713332,"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": 6305207703984.266, "dur": 106.191, + "args": { + "External id": 713333,"Record function id": 0, "Ev Idx": 17593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6305207704093.453, "dur": 1134.016, + "args": { + "External id": 713334,"Record function id": 0, "Ev Idx": 17594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305207704139.330, "dur": 1074.621, + "args": { + "External id": 713335,"Sequence number": 7674647, "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": 6305207704139.330, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6305207704210.876, "dur": 51.258, + "args": { + "External id": 713336,"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": 6305207704274.790, "dur": 109.134, + "args": { + "External id": 713337,"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": 6305207704397.616, "dur": 37.711, + "args": { + "External id": 713338,"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": 6305207704444.641, "dur": 29.370, + "args": { + "External id": 713339,"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": 6305207704503.097, "dur": 45.984, + "args": { + "External id": 713340,"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": 6305207704570.658, "dur": 18.447, + "args": { + "External id": 713341,"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": 6305207704613.002, "dur": 134.736, + "args": { + "External id": 713342,"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": 6305207704663.978, "dur": 11.414, + "args": { + "External id": 713343,"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": 6305207704669.487, "dur": 4.945, + "args": { + "External id": 713344,"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": 6305207704678.070, "dur": 3.979, + "args": { + "External id": 713345,"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": 6305207704683.320, "dur": 0.944, + "args": { + "External id": 713346,"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": 6305207704689.349, "dur": 6.977, + "args": { + "External id": 713347,"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": 6305207704758.813, "dur": 54.724, + "args": { + "External id": 713348,"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": 6305207704843.516, "dur": 31.720, + "args": { + "External id": 713349,"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": 6305207704886.430, "dur": 42.731, + "args": { + "External id": 713350,"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": 6305207704935.908, "dur": 34.109, + "args": { + "External id": 713351,"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": 6305207704994.459, "dur": 28.973, + "args": { + "External id": 713352,"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": 6305207705028.663, "dur": 68.571, + "args": { + "External id": 713353,"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": 6305207705121.137, "dur": 19.819, + "args": { + "External id": 713354,"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": 6305207705295.054, "dur": 79.689, + "args": { + "External id": 713355,"Record function id": 0, "Ev Idx": 17615 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6305207705451.161, "dur": 47.656, + "args": { + "External id": 713356,"Record function id": 0, "Ev Idx": 17616 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.14)", "pid": 2338707, "tid": 2338707, + "ts": 6305207705525.400, "dur": 30861.319, + "args": { + "External id": 713357,"Record function id": 0, "Ev Idx": 17617 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.14)", "pid": 2338707, "tid": 2338707, + "ts": 6305207705534.488, "dur": 814.948, + "args": { + "External id": 713358,"Record function id": 0, "Ev Idx": 17618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6305207705617.944, "dur": 9.944, + "args": { + "External id": 713359,"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": 6305207705641.746, "dur": 38.429, + "args": { + "External id": 713360,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305207705647.741, "dur": 2.286, + "args": { + "External id": 713361,"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": 6305207705654.366, "dur": 0.419, + "args": { + "External id": 713362,"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": 6305207705657.943, "dur": 0.600, + "args": { + "External id": 713363,"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": 6305207705659.564, "dur": 0.497, + "args": { + "External id": 713364,"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": 6305207705663.273, "dur": 0.482, + "args": { + "External id": 713365,"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": 6305207705664.757, "dur": 0.347, + "args": { + "External id": 713366,"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": 6305207705666.550, "dur": 4.334, + "args": { + "External id": 713367,"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": 6305207705672.070, "dur": 0.395, + "args": { + "External id": 713368,"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": 6305207705673.799, "dur": 0.409, + "args": { + "External id": 713369,"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": 6305207705692.161, "dur": 54.316, + "args": { + "External id": 713370,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305207705780.208, "dur": 119.959, + "args": { + "External id": 713371,"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": 6305207705790.998, "dur": 3.911, + "args": { + "External id": 713372,"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": 6305207705802.275, "dur": 10.722, + "args": { + "External id": 713373,"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": 6305207705806.886, "dur": 5.704, + "args": { + "External id": 713374,"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": 6305207705810.578, "dur": 0.686, + "args": { + "External id": 713375,"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": 6305207705819.719, "dur": 31.262, + "args": { + "External id": 713376,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305207705821.777, "dur": 2.301, + "args": { + "External id": 713377,"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": 6305207705825.738, "dur": 0.521, + "args": { + "External id": 713378,"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": 6305207705827.110, "dur": 0.358, + "args": { + "External id": 713379,"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": 6305207705831.855, "dur": 2.388, + "args": { + "External id": 713380,"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": 6305207705835.323, "dur": 0.465, + "args": { + "External id": 713381,"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": 6305207705837.717, "dur": 0.351, + "args": { + "External id": 713382,"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": 6305207705840.837, "dur": 0.381, + "args": { + "External id": 713383,"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": 6305207705842.418, "dur": 0.297, + "args": { + "External id": 713384,"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": 6305207705843.809, "dur": 2.193, + "args": { + "External id": 713385,"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": 6305207705862.570, "dur": 29.019, + "args": { + "External id": 713386,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305207705950.723, "dur": 301.727, + "args": { + "External id": 713387,"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": 6305207705980.234, "dur": 266.944, + "args": { + "External id": 713388,"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": 6305207705990.108, "dur": 250.989, + "args": { + "External id": 713389,"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": 6305207706276.154, "dur": 2.376, + "args": { + "External id": 713390,"Record function id": 0, "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": 6305207706369.341, "dur": 29824.402, + "args": { + "External id": 713391,"Record function id": 0, "Ev Idx": 17651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6305207706463.524, "dur": 5.871, + "args": { + "External id": 713392,"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": 6305207706472.454, "dur": 1.263, + "args": { + "External id": 713393,"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": 6305207706475.385, "dur": 2.993, + "args": { + "External id": 713394,"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": 6305207706479.922, "dur": 0.970, + "args": { + "External id": 713395,"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": 6305207706482.132, "dur": 1.000, + "args": { + "External id": 713396,"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": 6305207706484.446, "dur": 0.853, + "args": { + "External id": 713397,"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": 6305207706488.779, "dur": 0.766, + "args": { + "External id": 713398,"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": 6305207706491.182, "dur": 1.771, + "args": { + "External id": 713399,"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": 6305207706494.366, "dur": 0.718, + "args": { + "External id": 713400,"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": 6305207706496.773, "dur": 0.731, + "args": { + "External id": 713401,"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": 6305207706532.102, "dur": 29619.954, + "args": { + "External id": 713402,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305207706547.897, "dur": 29595.792, + "args": { + "External id": 713403,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305207706565.257, "dur": 16.307, + "args": { + "External id": 713404,"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": 6305207706585.247, "dur": 29523.972, + "args": { + "External id": 713405,"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": 6305207706587.819, "dur": 29520.833, + "args": { + "External id": 713406,"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": 6305207706594.018, "dur": 5.573, + "args": { + "External id": 713407,"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": 6305207706601.071, "dur": 29504.421, + "args": { + "External id": 713408,"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": 6305207736328.951, "dur": 34.117, + "args": { + "External id": 713409,"Sequence number": 7674648, "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": 6305207736328.951, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6305207736349.777, "dur": 8.553, + "args": { + "External id": 713410,"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": 6305207736353.332, "dur": 4.837, + "args": { + "External id": 713411,"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": 6305207736427.498, "dur": 72.558, + "args": { + "External id": 713412,"Record function id": 0, "Ev Idx": 17672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6305207736501.478, "dur": 1154.270, + "args": { + "External id": 713413,"Record function id": 0, "Ev Idx": 17673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305207736558.225, "dur": 1083.903, + "args": { + "External id": 713414,"Sequence number": 7674649, "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": 6305207736558.225, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6305207736625.557, "dur": 49.844, + "args": { + "External id": 713415,"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": 6305207736689.597, "dur": 105.759, + "args": { + "External id": 713416,"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": 6305207736808.025, "dur": 37.347, + "args": { + "External id": 713417,"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": 6305207736856.001, "dur": 29.255, + "args": { + "External id": 713418,"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": 6305207736910.075, "dur": 29.761, + "args": { + "External id": 713419,"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": 6305207736960.156, "dur": 23.674, + "args": { + "External id": 713420,"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": 6305207737006.750, "dur": 177.767, + "args": { + "External id": 713421,"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": 6305207737097.977, "dur": 12.264, + "args": { + "External id": 713422,"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": 6305207737103.368, "dur": 5.958, + "args": { + "External id": 713423,"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": 6305207737113.013, "dur": 3.844, + "args": { + "External id": 713424,"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": 6305207737118.632, "dur": 1.198, + "args": { + "External id": 713425,"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": 6305207737122.190, "dur": 5.862, + "args": { + "External id": 713426,"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": 6305207737196.021, "dur": 56.650, + "args": { + "External id": 713427,"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": 6305207737285.976, "dur": 30.749, + "args": { + "External id": 713428,"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": 6305207737327.834, "dur": 43.634, + "args": { + "External id": 713429,"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": 6305207737380.836, "dur": 34.489, + "args": { + "External id": 713430,"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": 6305207737438.173, "dur": 30.286, + "args": { + "External id": 713431,"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": 6305207737476.232, "dur": 51.627, + "args": { + "External id": 713432,"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": 6305207737550.323, "dur": 20.334, + "args": { + "External id": 713433,"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": 6305207737719.934, "dur": 75.801, + "args": { + "External id": 713434,"Record function id": 0, "Ev Idx": 17694 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6305207737870.693, "dur": 46.858, + "args": { + "External id": 713435,"Record function id": 0, "Ev Idx": 17695 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.15)", "pid": 2338707, "tid": 2338707, + "ts": 6305207737925.698, "dur": 32257.632, + "args": { + "External id": 713436,"Record function id": 0, "Ev Idx": 17696 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.15)", "pid": 2338707, "tid": 2338707, + "ts": 6305207737934.173, "dur": 1015.724, + "args": { + "External id": 713437,"Record function id": 0, "Ev Idx": 17697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6305207738016.391, "dur": 8.830, + "args": { + "External id": 713438,"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": 6305207738038.711, "dur": 83.887, + "args": { + "External id": 713439,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305207738044.700, "dur": 2.395, + "args": { + "External id": 713440,"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": 6305207738050.970, "dur": 0.340, + "args": { + "External id": 713441,"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": 6305207738095.531, "dur": 0.704, + "args": { + "External id": 713442,"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": 6305207738097.856, "dur": 0.484, + "args": { + "External id": 713443,"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": 6305207738102.489, "dur": 0.519, + "args": { + "External id": 713444,"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": 6305207738104.706, "dur": 0.604, + "args": { + "External id": 713445,"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": 6305207738106.764, "dur": 5.144, + "args": { + "External id": 713446,"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": 6305207738112.860, "dur": 0.615, + "args": { + "External id": 713447,"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": 6305207738115.448, "dur": 0.406, + "args": { + "External id": 713448,"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": 6305207738135.376, "dur": 55.812, + "args": { + "External id": 713449,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305207738230.718, "dur": 125.545, + "args": { + "External id": 713450,"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": 6305207738242.680, "dur": 5.101, + "args": { + "External id": 713451,"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": 6305207738253.276, "dur": 10.801, + "args": { + "External id": 713452,"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": 6305207738257.789, "dur": 5.892, + "args": { + "External id": 713453,"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": 6305207738261.731, "dur": 0.708, + "args": { + "External id": 713454,"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": 6305207738271.389, "dur": 32.344, + "args": { + "External id": 713455,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305207738273.231, "dur": 2.903, + "args": { + "External id": 713456,"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": 6305207738277.703, "dur": 0.314, + "args": { + "External id": 713457,"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": 6305207738279.554, "dur": 0.333, + "args": { + "External id": 713458,"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": 6305207738284.434, "dur": 2.123, + "args": { + "External id": 713459,"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": 6305207738287.755, "dur": 0.257, + "args": { + "External id": 713460,"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": 6305207738290.059, "dur": 0.339, + "args": { + "External id": 713461,"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": 6305207738293.407, "dur": 0.394, + "args": { + "External id": 713462,"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": 6305207738295.285, "dur": 0.413, + "args": { + "External id": 713463,"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": 6305207738296.926, "dur": 2.133, + "args": { + "External id": 713464,"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": 6305207738317.148, "dur": 30.904, + "args": { + "External id": 713465,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305207738411.170, "dur": 433.259, + "args": { + "External id": 713466,"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": 6305207738441.669, "dur": 396.735, + "args": { + "External id": 713467,"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": 6305207738452.090, "dur": 377.176, + "args": { + "External id": 713468,"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": 6305207738872.065, "dur": 2.445, + "args": { + "External id": 713469,"Record function id": 0, "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": 6305207738971.151, "dur": 30991.259, + "args": { + "External id": 713470,"Record function id": 0, "Ev Idx": 17730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6305207739111.318, "dur": 7.627, + "args": { + "External id": 713471,"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": 6305207739122.703, "dur": 0.886, + "args": { + "External id": 713472,"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": 6305207739125.153, "dur": 3.013, + "args": { + "External id": 713473,"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": 6305207739129.921, "dur": 0.705, + "args": { + "External id": 713474,"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": 6305207739131.871, "dur": 1.013, + "args": { + "External id": 713475,"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": 6305207739133.941, "dur": 1.083, + "args": { + "External id": 713476,"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": 6305207739138.683, "dur": 0.754, + "args": { + "External id": 713477,"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": 6305207739141.584, "dur": 1.929, + "args": { + "External id": 713478,"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": 6305207739144.724, "dur": 0.522, + "args": { + "External id": 713479,"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": 6305207739146.982, "dur": 0.710, + "args": { + "External id": 713480,"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": 6305207739169.374, "dur": 30750.705, + "args": { + "External id": 713481,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305207739185.873, "dur": 30725.866, + "args": { + "External id": 713482,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305207739200.527, "dur": 17.490, + "args": { + "External id": 713483,"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": 6305207739221.608, "dur": 30656.401, + "args": { + "External id": 713484,"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": 6305207739224.284, "dur": 30653.245, + "args": { + "External id": 713485,"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": 6305207739231.049, "dur": 5.682, + "args": { + "External id": 713486,"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": 6305207739238.284, "dur": 30636.277, + "args": { + "External id": 713487,"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": 6305207770125.013, "dur": 33.259, + "args": { + "External id": 713488,"Sequence number": 7674650, "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": 6305207770125.013, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6305207770144.030, "dur": 9.113, + "args": { + "External id": 713489,"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": 6305207770147.914, "dur": 4.634, + "args": { + "External id": 713490,"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": 6305207770222.841, "dur": 74.277, + "args": { + "External id": 713491,"Record function id": 0, "Ev Idx": 17751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6305207770298.569, "dur": 1128.602, + "args": { + "External id": 713492,"Record function id": 0, "Ev Idx": 17752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305207770335.707, "dur": 1078.041, + "args": { + "External id": 713493,"Sequence number": 7674651, "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": 6305207770335.707, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6305207770400.263, "dur": 52.552, + "args": { + "External id": 713494,"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": 6305207770465.033, "dur": 122.792, + "args": { + "External id": 713495,"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": 6305207770606.054, "dur": 39.827, + "args": { + "External id": 713496,"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": 6305207770655.006, "dur": 28.947, + "args": { + "External id": 713497,"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": 6305207770718.144, "dur": 27.499, + "args": { + "External id": 713498,"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": 6305207770766.645, "dur": 17.192, + "args": { + "External id": 713499,"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": 6305207770807.673, "dur": 134.330, + "args": { + "External id": 713500,"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": 6305207770860.139, "dur": 11.283, + "args": { + "External id": 713501,"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": 6305207770865.617, "dur": 4.881, + "args": { + "External id": 713502,"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": 6305207770873.922, "dur": 4.345, + "args": { + "External id": 713503,"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": 6305207770879.588, "dur": 0.879, + "args": { + "External id": 713504,"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": 6305207770885.336, "dur": 5.018, + "args": { + "External id": 713505,"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": 6305207770952.177, "dur": 49.514, + "args": { + "External id": 713506,"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": 6305207771033.517, "dur": 69.779, + "args": { + "External id": 713507,"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": 6305207771117.772, "dur": 49.383, + "args": { + "External id": 713508,"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": 6305207771175.300, "dur": 35.501, + "args": { + "External id": 713509,"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": 6305207771235.534, "dur": 32.284, + "args": { + "External id": 713510,"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": 6305207771273.489, "dur": 34.644, + "args": { + "External id": 713511,"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": 6305207771325.814, "dur": 17.529, + "args": { + "External id": 713512,"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": 6305207771492.039, "dur": 95.505, + "args": { + "External id": 713513,"Record function id": 0, "Ev Idx": 17773 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6305207771666.625, "dur": 50.961, + "args": { + "External id": 713514,"Record function id": 0, "Ev Idx": 17774 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.16)", "pid": 2338707, "tid": 2338707, + "ts": 6305207771726.586, "dur": 30931.858, + "args": { + "External id": 713515,"Record function id": 0, "Ev Idx": 17775 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.16)", "pid": 2338707, "tid": 2338707, + "ts": 6305207771734.838, "dur": 974.979, + "args": { + "External id": 713516,"Record function id": 0, "Ev Idx": 17776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6305207771819.794, "dur": 9.363, + "args": { + "External id": 713517,"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": 6305207771842.825, "dur": 47.564, + "args": { + "External id": 713518,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305207771848.788, "dur": 2.613, + "args": { + "External id": 713519,"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": 6305207771855.347, "dur": 0.524, + "args": { + "External id": 713520,"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": 6305207771857.460, "dur": 0.325, + "args": { + "External id": 713521,"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": 6305207771858.946, "dur": 0.484, + "args": { + "External id": 713522,"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": 6305207771863.755, "dur": 0.358, + "args": { + "External id": 713523,"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": 6305207771870.640, "dur": 0.711, + "args": { + "External id": 713524,"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": 6305207771872.826, "dur": 5.292, + "args": { + "External id": 713525,"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": 6305207771879.017, "dur": 0.482, + "args": { + "External id": 713526,"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": 6305207771883.545, "dur": 0.536, + "args": { + "External id": 713527,"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": 6305207771902.043, "dur": 53.074, + "args": { + "External id": 713528,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305207771988.318, "dur": 166.931, + "args": { + "External id": 713529,"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": 6305207771999.138, "dur": 4.038, + "args": { + "External id": 713530,"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": 6305207772011.576, "dur": 12.742, + "args": { + "External id": 713531,"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": 6305207772016.140, "dur": 7.724, + "args": { + "External id": 713532,"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": 6305207772019.755, "dur": 2.726, + "args": { + "External id": 713533,"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": 6305207772031.130, "dur": 64.495, + "args": { + "External id": 713534,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305207772032.823, "dur": 0.508, + "args": { + "External id": 713535,"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": 6305207772034.646, "dur": 0.509, + "args": { + "External id": 713536,"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": 6305207772036.258, "dur": 0.425, + "args": { + "External id": 713537,"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": 6305207772040.907, "dur": 2.651, + "args": { + "External id": 713538,"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": 6305207772044.560, "dur": 0.473, + "args": { + "External id": 713539,"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": 6305207772046.778, "dur": 0.838, + "args": { + "External id": 713540,"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": 6305207772048.470, "dur": 0.481, + "args": { + "External id": 713541,"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": 6305207772050.278, "dur": 0.487, + "args": { + "External id": 713542,"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": 6305207772089.494, "dur": 0.854, + "args": { + "External id": 713543,"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": 6305207772109.977, "dur": 37.343, + "args": { + "External id": 713544,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305207772209.703, "dur": 397.560, + "args": { + "External id": 713545,"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": 6305207772242.104, "dur": 359.292, + "args": { + "External id": 713546,"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": 6305207772252.706, "dur": 342.461, + "args": { + "External id": 713547,"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": 6305207772632.762, "dur": 2.612, + "args": { + "External id": 713548,"Record function id": 0, "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": 6305207772730.494, "dur": 29712.789, + "args": { + "External id": 713549,"Record function id": 0, "Ev Idx": 17809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6305207772831.403, "dur": 6.664, + "args": { + "External id": 713550,"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": 6305207772841.297, "dur": 1.296, + "args": { + "External id": 713551,"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": 6305207772844.386, "dur": 3.228, + "args": { + "External id": 713552,"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": 6305207772849.393, "dur": 0.733, + "args": { + "External id": 713553,"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": 6305207772851.583, "dur": 0.976, + "args": { + "External id": 713554,"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": 6305207772853.790, "dur": 0.873, + "args": { + "External id": 713555,"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": 6305207772858.314, "dur": 0.738, + "args": { + "External id": 713556,"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": 6305207772860.609, "dur": 1.881, + "args": { + "External id": 713557,"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": 6305207772863.726, "dur": 0.820, + "args": { + "External id": 713558,"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": 6305207772866.305, "dur": 0.653, + "args": { + "External id": 713559,"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": 6305207772885.896, "dur": 29509.813, + "args": { + "External id": 713560,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305207772902.290, "dur": 29484.392, + "args": { + "External id": 713561,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305207772917.221, "dur": 15.886, + "args": { + "External id": 713562,"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": 6305207772936.816, "dur": 29414.458, + "args": { + "External id": 713563,"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": 6305207772939.360, "dur": 29411.267, + "args": { + "External id": 713564,"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": 6305207772945.434, "dur": 5.671, + "args": { + "External id": 713565,"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": 6305207772952.763, "dur": 29394.674, + "args": { + "External id": 713566,"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": 6305207802599.144, "dur": 32.759, + "args": { + "External id": 713567,"Sequence number": 7674652, "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": 6305207802599.144, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6305207802617.458, "dur": 9.719, + "args": { + "External id": 713568,"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": 6305207802621.445, "dur": 5.370, + "args": { + "External id": 713569,"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": 6305207802700.414, "dur": 71.908, + "args": { + "External id": 713570,"Record function id": 0, "Ev Idx": 17830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6305207802773.683, "dur": 1129.287, + "args": { + "External id": 713571,"Record function id": 0, "Ev Idx": 17831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305207802813.576, "dur": 1075.858, + "args": { + "External id": 713572,"Sequence number": 7674653, "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": 6305207802813.576, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6305207802882.246, "dur": 49.084, + "args": { + "External id": 713573,"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": 6305207802943.933, "dur": 106.243, + "args": { + "External id": 713574,"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": 6305207803100.280, "dur": 44.052, + "args": { + "External id": 713575,"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": 6305207803156.946, "dur": 28.984, + "args": { + "External id": 713576,"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": 6305207803215.689, "dur": 26.224, + "args": { + "External id": 713577,"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": 6305207803262.520, "dur": 16.969, + "args": { + "External id": 713578,"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": 6305207803302.843, "dur": 133.571, + "args": { + "External id": 713579,"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": 6305207803354.666, "dur": 11.303, + "args": { + "External id": 713580,"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": 6305207803360.085, "dur": 5.092, + "args": { + "External id": 713581,"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": 6305207803368.446, "dur": 4.064, + "args": { + "External id": 713582,"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": 6305207803373.812, "dur": 1.334, + "args": { + "External id": 713583,"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": 6305207803377.923, "dur": 6.270, + "args": { + "External id": 713584,"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": 6305207803447.178, "dur": 49.655, + "args": { + "External id": 713585,"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": 6305207803547.080, "dur": 35.514, + "args": { + "External id": 713586,"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": 6305207803595.093, "dur": 47.699, + "args": { + "External id": 713587,"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": 6305207803652.135, "dur": 34.128, + "args": { + "External id": 713588,"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": 6305207803709.732, "dur": 29.157, + "args": { + "External id": 713589,"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": 6305207803746.589, "dur": 35.407, + "args": { + "External id": 713590,"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": 6305207803800.083, "dur": 18.903, + "args": { + "External id": 713591,"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": 6305207803967.671, "dur": 75.484, + "args": { + "External id": 713592,"Record function id": 0, "Ev Idx": 17852 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6305207804163.956, "dur": 49.476, + "args": { + "External id": 713593,"Record function id": 0, "Ev Idx": 17853 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.17)", "pid": 2338707, "tid": 2338707, + "ts": 6305207804222.591, "dur": 32036.130, + "args": { + "External id": 713594,"Record function id": 0, "Ev Idx": 17854 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.17)", "pid": 2338707, "tid": 2338707, + "ts": 6305207804230.974, "dur": 963.431, + "args": { + "External id": 713595,"Record function id": 0, "Ev Idx": 17855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6305207804315.033, "dur": 9.843, + "args": { + "External id": 713596,"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": 6305207804338.321, "dur": 39.859, + "args": { + "External id": 713597,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305207804344.609, "dur": 2.380, + "args": { + "External id": 713598,"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": 6305207804351.991, "dur": 0.450, + "args": { + "External id": 713599,"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": 6305207804354.061, "dur": 0.551, + "args": { + "External id": 713600,"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": 6305207804355.866, "dur": 0.383, + "args": { + "External id": 713601,"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": 6305207804359.957, "dur": 0.469, + "args": { + "External id": 713602,"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": 6305207804361.556, "dur": 0.405, + "args": { + "External id": 713603,"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": 6305207804363.479, "dur": 4.500, + "args": { + "External id": 713604,"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": 6305207804369.191, "dur": 0.416, + "args": { + "External id": 713605,"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": 6305207804371.404, "dur": 0.312, + "args": { + "External id": 713606,"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": 6305207804389.436, "dur": 54.217, + "args": { + "External id": 713607,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305207804476.805, "dur": 146.056, + "args": { + "External id": 713608,"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": 6305207804488.149, "dur": 3.602, + "args": { + "External id": 713609,"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": 6305207804497.198, "dur": 26.203, + "args": { + "External id": 713610,"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": 6305207804501.819, "dur": 21.142, + "args": { + "External id": 713611,"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": 6305207804519.828, "dur": 1.044, + "args": { + "External id": 713612,"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": 6305207804532.357, "dur": 31.963, + "args": { + "External id": 713613,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305207804534.789, "dur": 2.327, + "args": { + "External id": 713614,"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": 6305207804538.597, "dur": 0.342, + "args": { + "External id": 713615,"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": 6305207804540.048, "dur": 0.325, + "args": { + "External id": 713616,"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": 6305207804543.597, "dur": 2.455, + "args": { + "External id": 713617,"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": 6305207804547.201, "dur": 0.544, + "args": { + "External id": 713618,"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": 6305207804549.006, "dur": 0.450, + "args": { + "External id": 713619,"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": 6305207804553.558, "dur": 0.378, + "args": { + "External id": 713620,"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": 6305207804555.035, "dur": 0.415, + "args": { + "External id": 713621,"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": 6305207804556.876, "dur": 3.069, + "args": { + "External id": 713622,"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": 6305207804579.413, "dur": 35.816, + "args": { + "External id": 713623,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305207804678.557, "dur": 371.987, + "args": { + "External id": 713624,"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": 6305207804709.844, "dur": 335.704, + "args": { + "External id": 713625,"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": 6305207804720.073, "dur": 320.312, + "args": { + "External id": 713626,"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": 6305207805110.284, "dur": 3.364, + "args": { + "External id": 713627,"Record function id": 0, "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": 6305207805217.318, "dur": 30816.033, + "args": { + "External id": 713628,"Record function id": 0, "Ev Idx": 17888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6305207805324.405, "dur": 6.566, + "args": { + "External id": 713629,"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": 6305207805334.094, "dur": 1.331, + "args": { + "External id": 713630,"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": 6305207805337.130, "dur": 3.186, + "args": { + "External id": 713631,"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": 6305207805341.873, "dur": 0.974, + "args": { + "External id": 713632,"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": 6305207805343.951, "dur": 0.993, + "args": { + "External id": 713633,"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": 6305207805346.047, "dur": 1.073, + "args": { + "External id": 713634,"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": 6305207805351.338, "dur": 0.646, + "args": { + "External id": 713635,"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": 6305207805353.764, "dur": 2.102, + "args": { + "External id": 713636,"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": 6305207805357.130, "dur": 0.940, + "args": { + "External id": 713637,"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": 6305207805359.577, "dur": 0.882, + "args": { + "External id": 713638,"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": 6305207805387.801, "dur": 30601.834, + "args": { + "External id": 713639,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305207805404.172, "dur": 30577.325, + "args": { + "External id": 713640,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305207805417.659, "dur": 17.506, + "args": { + "External id": 713641,"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": 6305207805438.590, "dur": 30506.849, + "args": { + "External id": 713642,"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": 6305207805441.374, "dur": 30503.564, + "args": { + "External id": 713643,"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": 6305207805447.892, "dur": 5.921, + "args": { + "External id": 713644,"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": 6305207805455.465, "dur": 30486.332, + "args": { + "External id": 713645,"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": 6305207836198.826, "dur": 33.423, + "args": { + "External id": 713646,"Sequence number": 7674654, "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": 6305207836198.826, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6305207836217.687, "dur": 9.445, + "args": { + "External id": 713647,"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": 6305207836221.483, "dur": 5.206, + "args": { + "External id": 713648,"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": 6305207836301.059, "dur": 77.444, + "args": { + "External id": 713649,"Record function id": 0, "Ev Idx": 17909 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6305207836379.841, "dur": 1143.972, + "args": { + "External id": 713650,"Record function id": 0, "Ev Idx": 17910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305207836420.927, "dur": 1074.691, + "args": { + "External id": 713651,"Sequence number": 7674655, "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": 6305207836420.927, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6305207836486.490, "dur": 62.550, + "args": { + "External id": 713652,"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": 6305207836565.534, "dur": 108.720, + "args": { + "External id": 713653,"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": 6305207836686.507, "dur": 38.107, + "args": { + "External id": 713654,"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": 6305207836734.107, "dur": 29.734, + "args": { + "External id": 713655,"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": 6305207836792.354, "dur": 26.621, + "args": { + "External id": 713656,"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": 6305207836839.848, "dur": 17.815, + "args": { + "External id": 713657,"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": 6305207836881.098, "dur": 130.336, + "args": { + "External id": 713658,"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": 6305207836931.566, "dur": 11.222, + "args": { + "External id": 713659,"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": 6305207836937.015, "dur": 5.042, + "args": { + "External id": 713660,"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": 6305207836945.745, "dur": 3.817, + "args": { + "External id": 713661,"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": 6305207836951.143, "dur": 1.044, + "args": { + "External id": 713662,"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": 6305207836954.738, "dur": 5.392, + "args": { + "External id": 713663,"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": 6305207837026.101, "dur": 89.454, + "args": { + "External id": 713664,"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": 6305207837153.102, "dur": 29.766, + "args": { + "External id": 713665,"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": 6305207837193.596, "dur": 47.088, + "args": { + "External id": 713666,"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": 6305207837251.862, "dur": 34.987, + "args": { + "External id": 713667,"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": 6305207837311.007, "dur": 29.780, + "args": { + "External id": 713668,"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": 6305207837349.038, "dur": 36.090, + "args": { + "External id": 713669,"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": 6305207837404.468, "dur": 20.963, + "args": { + "External id": 713670,"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": 6305207837593.046, "dur": 80.511, + "args": { + "External id": 713671,"Record function id": 0, "Ev Idx": 17931 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6305207837752.371, "dur": 47.941, + "args": { + "External id": 713672,"Record function id": 0, "Ev Idx": 17932 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.18)", "pid": 2338707, "tid": 2338707, + "ts": 6305207837809.579, "dur": 30501.220, + "args": { + "External id": 713673,"Record function id": 0, "Ev Idx": 17933 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.18)", "pid": 2338707, "tid": 2338707, + "ts": 6305207837817.453, "dur": 986.213, + "args": { + "External id": 713674,"Record function id": 0, "Ev Idx": 17934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6305207837903.524, "dur": 8.985, + "args": { + "External id": 713675,"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": 6305207837925.957, "dur": 40.738, + "args": { + "External id": 713676,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305207837932.387, "dur": 2.272, + "args": { + "External id": 713677,"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": 6305207837939.703, "dur": 0.611, + "args": { + "External id": 713678,"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": 6305207837941.751, "dur": 0.342, + "args": { + "External id": 713679,"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": 6305207837943.543, "dur": 0.450, + "args": { + "External id": 713680,"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": 6305207837947.699, "dur": 0.525, + "args": { + "External id": 713681,"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": 6305207837949.459, "dur": 0.432, + "args": { + "External id": 713682,"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": 6305207837951.519, "dur": 5.072, + "args": { + "External id": 713683,"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": 6305207837958.074, "dur": 0.388, + "args": { + "External id": 713684,"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": 6305207837960.338, "dur": 0.257, + "args": { + "External id": 713685,"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": 6305207837979.045, "dur": 56.577, + "args": { + "External id": 713686,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305207838108.352, "dur": 135.585, + "args": { + "External id": 713687,"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": 6305207838121.280, "dur": 7.133, + "args": { + "External id": 713688,"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": 6305207838134.369, "dur": 12.163, + "args": { + "External id": 713689,"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": 6305207838138.971, "dur": 7.181, + "args": { + "External id": 713690,"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": 6305207838143.395, "dur": 0.932, + "args": { + "External id": 713691,"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": 6305207838154.137, "dur": 30.661, + "args": { + "External id": 713692,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305207838156.624, "dur": 0.777, + "args": { + "External id": 713693,"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": 6305207838159.225, "dur": 2.647, + "args": { + "External id": 713694,"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": 6305207838162.782, "dur": 0.282, + "args": { + "External id": 713695,"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": 6305207838164.586, "dur": 2.746, + "args": { + "External id": 713696,"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": 6305207838170.655, "dur": 0.359, + "args": { + "External id": 713697,"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": 6305207838172.751, "dur": 0.475, + "args": { + "External id": 713698,"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": 6305207838174.168, "dur": 0.444, + "args": { + "External id": 713699,"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": 6305207838178.461, "dur": 0.410, + "args": { + "External id": 713700,"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": 6305207838179.944, "dur": 0.468, + "args": { + "External id": 713701,"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": 6305207838197.206, "dur": 38.229, + "args": { + "External id": 713702,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305207838300.004, "dur": 395.752, + "args": { + "External id": 713703,"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": 6305207838330.946, "dur": 358.754, + "args": { + "External id": 713704,"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": 6305207838341.304, "dur": 342.476, + "args": { + "External id": 713705,"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": 6305207838723.839, "dur": 2.375, + "args": { + "External id": 713706,"Record function id": 0, "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": 6305207838824.537, "dur": 29289.049, + "args": { + "External id": 713707,"Record function id": 0, "Ev Idx": 17967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6305207838928.208, "dur": 6.470, + "args": { + "External id": 713708,"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": 6305207838937.779, "dur": 1.071, + "args": { + "External id": 713709,"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": 6305207838940.694, "dur": 3.796, + "args": { + "External id": 713710,"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": 6305207838946.148, "dur": 1.100, + "args": { + "External id": 713711,"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": 6305207838948.766, "dur": 0.741, + "args": { + "External id": 713712,"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": 6305207838950.839, "dur": 0.908, + "args": { + "External id": 713713,"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": 6305207838953.683, "dur": 0.883, + "args": { + "External id": 713714,"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": 6305207838955.971, "dur": 1.911, + "args": { + "External id": 713715,"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": 6305207838959.411, "dur": 0.893, + "args": { + "External id": 713716,"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": 6305207838963.939, "dur": 0.695, + "args": { + "External id": 713717,"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": 6305207838982.164, "dur": 29056.465, + "args": { + "External id": 713718,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305207838998.050, "dur": 29032.280, + "args": { + "External id": 713719,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305207839012.378, "dur": 16.382, + "args": { + "External id": 713720,"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": 6305207839032.235, "dur": 28960.181, + "args": { + "External id": 713721,"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": 6305207839034.764, "dur": 28956.976, + "args": { + "External id": 713722,"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": 6305207839041.428, "dur": 6.036, + "args": { + "External id": 713723,"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": 6305207839049.221, "dur": 28939.384, + "args": { + "External id": 713724,"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": 6305207868253.517, "dur": 32.952, + "args": { + "External id": 713725,"Sequence number": 7674656, "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": 6305207868253.517, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6305207868272.888, "dur": 8.758, + "args": { + "External id": 713726,"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": 6305207868276.595, "dur": 4.809, + "args": { + "External id": 713727,"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": 6305207868350.030, "dur": 76.234, + "args": { + "External id": 713728,"Record function id": 0, "Ev Idx": 17988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6305207868467.388, "dur": 1155.910, + "args": { + "External id": 713729,"Record function id": 0, "Ev Idx": 17989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305207868505.029, "dur": 1102.912, + "args": { + "External id": 713730,"Sequence number": 7674657, "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": 6305207868505.029, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6305207868593.009, "dur": 54.030, + "args": { + "External id": 713731,"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": 6305207868660.038, "dur": 104.391, + "args": { + "External id": 713732,"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": 6305207868777.441, "dur": 37.992, + "args": { + "External id": 713733,"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": 6305207868822.204, "dur": 28.542, + "args": { + "External id": 713734,"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": 6305207868879.816, "dur": 28.545, + "args": { + "External id": 713735,"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": 6305207868929.266, "dur": 20.510, + "args": { + "External id": 713736,"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": 6305207868973.414, "dur": 179.036, + "args": { + "External id": 713737,"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": 6305207869026.572, "dur": 11.083, + "args": { + "External id": 713738,"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": 6305207869031.814, "dur": 5.065, + "args": { + "External id": 713739,"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": 6305207869040.407, "dur": 4.123, + "args": { + "External id": 713740,"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": 6305207869046.348, "dur": 0.956, + "args": { + "External id": 713741,"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": 6305207869087.290, "dur": 7.333, + "args": { + "External id": 713742,"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": 6305207869165.363, "dur": 59.303, + "args": { + "External id": 713743,"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": 6305207869258.059, "dur": 32.961, + "args": { + "External id": 713744,"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": 6305207869302.093, "dur": 44.287, + "args": { + "External id": 713745,"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": 6305207869356.306, "dur": 34.284, + "args": { + "External id": 713746,"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": 6305207869412.039, "dur": 30.582, + "args": { + "External id": 713747,"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": 6305207869448.172, "dur": 34.721, + "args": { + "External id": 713748,"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": 6305207869502.901, "dur": 33.380, + "args": { + "External id": 713749,"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": 6305207869690.328, "dur": 80.631, + "args": { + "External id": 713750,"Record function id": 0, "Ev Idx": 18010 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6305207869848.061, "dur": 49.247, + "args": { + "External id": 713751,"Record function id": 0, "Ev Idx": 18011 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.19)", "pid": 2338707, "tid": 2338707, + "ts": 6305207869906.035, "dur": 31657.679, + "args": { + "External id": 713752,"Record function id": 0, "Ev Idx": 18012 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.19)", "pid": 2338707, "tid": 2338707, + "ts": 6305207869915.245, "dur": 977.664, + "args": { + "External id": 713753,"Record function id": 0, "Ev Idx": 18013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6305207869997.474, "dur": 8.222, + "args": { + "External id": 713754,"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": 6305207870018.364, "dur": 78.687, + "args": { + "External id": 713755,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305207870024.476, "dur": 2.111, + "args": { + "External id": 713756,"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": 6305207870032.023, "dur": 0.399, + "args": { + "External id": 713757,"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": 6305207870034.350, "dur": 0.597, + "args": { + "External id": 713758,"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": 6305207870036.240, "dur": 0.546, + "args": { + "External id": 713759,"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": 6305207870041.049, "dur": 0.567, + "args": { + "External id": 713760,"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": 6305207870042.884, "dur": 0.483, + "args": { + "External id": 713761,"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": 6305207870044.708, "dur": 4.749, + "args": { + "External id": 713762,"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": 6305207870051.107, "dur": 0.322, + "args": { + "External id": 713763,"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": 6305207870089.665, "dur": 0.558, + "args": { + "External id": 713764,"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": 6305207870110.914, "dur": 62.710, + "args": { + "External id": 713765,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305207870213.408, "dur": 135.606, + "args": { + "External id": 713766,"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": 6305207870225.387, "dur": 4.886, + "args": { + "External id": 713767,"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": 6305207870242.550, "dur": 10.766, + "args": { + "External id": 713768,"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": 6305207870247.138, "dur": 5.759, + "args": { + "External id": 713769,"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": 6305207870251.079, "dur": 0.452, + "args": { + "External id": 713770,"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": 6305207870260.391, "dur": 30.711, + "args": { + "External id": 713771,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305207870262.396, "dur": 2.399, + "args": { + "External id": 713772,"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": 6305207870266.649, "dur": 0.467, + "args": { + "External id": 713773,"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": 6305207870267.980, "dur": 0.525, + "args": { + "External id": 713774,"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": 6305207870272.201, "dur": 2.843, + "args": { + "External id": 713775,"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": 6305207870276.574, "dur": 0.488, + "args": { + "External id": 713776,"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": 6305207870278.379, "dur": 0.324, + "args": { + "External id": 713777,"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": 6305207870281.508, "dur": 0.394, + "args": { + "External id": 713778,"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": 6305207870283.727, "dur": 0.346, + "args": { + "External id": 713779,"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": 6305207870284.824, "dur": 2.013, + "args": { + "External id": 713780,"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": 6305207870308.932, "dur": 32.377, + "args": { + "External id": 713781,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305207870405.999, "dur": 386.732, + "args": { + "External id": 713782,"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": 6305207870437.492, "dur": 350.170, + "args": { + "External id": 713783,"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": 6305207870448.696, "dur": 332.374, + "args": { + "External id": 713784,"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": 6305207870819.984, "dur": 2.183, + "args": { + "External id": 713785,"Record function id": 0, "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": 6305207870914.222, "dur": 30432.290, + "args": { + "External id": 713786,"Record function id": 0, "Ev Idx": 18046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6305207871011.521, "dur": 6.344, + "args": { + "External id": 713787,"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": 6305207871021.115, "dur": 1.115, + "args": { + "External id": 713788,"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": 6305207871024.240, "dur": 2.962, + "args": { + "External id": 713789,"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": 6305207871028.718, "dur": 0.918, + "args": { + "External id": 713790,"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": 6305207871030.989, "dur": 0.715, + "args": { + "External id": 713791,"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": 6305207871033.592, "dur": 1.033, + "args": { + "External id": 713792,"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": 6305207871036.286, "dur": 0.714, + "args": { + "External id": 713793,"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": 6305207871038.848, "dur": 1.859, + "args": { + "External id": 713794,"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": 6305207871041.949, "dur": 0.708, + "args": { + "External id": 713795,"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": 6305207871046.378, "dur": 0.575, + "args": { + "External id": 713796,"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": 6305207871102.214, "dur": 30199.610, + "args": { + "External id": 713797,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305207871119.338, "dur": 30174.666, + "args": { + "External id": 713798,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305207871139.173, "dur": 16.871, + "args": { + "External id": 713799,"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": 6305207871159.617, "dur": 30101.784, + "args": { + "External id": 713800,"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": 6305207871162.588, "dur": 30098.172, + "args": { + "External id": 713801,"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": 6305207871168.170, "dur": 5.325, + "args": { + "External id": 713802,"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": 6305207871175.480, "dur": 30082.347, + "args": { + "External id": 713803,"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": 6305207901487.955, "dur": 46.136, + "args": { + "External id": 713804,"Sequence number": 7674658, "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": 6305207901487.955, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6305207901504.982, "dur": 23.525, + "args": { + "External id": 713805,"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": 6305207901522.661, "dur": 5.517, + "args": { + "External id": 713806,"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": 6305207901606.464, "dur": 72.047, + "args": { + "External id": 713807,"Record function id": 0, "Ev Idx": 18067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6305207901680.229, "dur": 1146.177, + "args": { + "External id": 713808,"Record function id": 0, "Ev Idx": 18068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305207901718.479, "dur": 1094.405, + "args": { + "External id": 713809,"Sequence number": 7674659, "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": 6305207901718.479, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6305207901784.899, "dur": 49.318, + "args": { + "External id": 713810,"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": 6305207901847.484, "dur": 107.456, + "args": { + "External id": 713811,"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": 6305207901966.310, "dur": 38.456, + "args": { + "External id": 713812,"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": 6305207902015.270, "dur": 29.386, + "args": { + "External id": 713813,"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": 6305207902122.819, "dur": 33.392, + "args": { + "External id": 713814,"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": 6305207902179.440, "dur": 18.722, + "args": { + "External id": 713815,"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": 6305207902222.878, "dur": 133.401, + "args": { + "External id": 713816,"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": 6305207902274.882, "dur": 11.076, + "args": { + "External id": 713817,"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": 6305207902279.851, "dur": 5.287, + "args": { + "External id": 713818,"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": 6305207902289.240, "dur": 4.307, + "args": { + "External id": 713819,"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": 6305207902294.751, "dur": 1.013, + "args": { + "External id": 713820,"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": 6305207902298.523, "dur": 5.880, + "args": { + "External id": 713821,"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": 6305207902366.630, "dur": 58.463, + "args": { + "External id": 713822,"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": 6305207902455.787, "dur": 30.025, + "args": { + "External id": 713823,"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": 6305207902495.884, "dur": 60.969, + "args": { + "External id": 713824,"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": 6305207902570.394, "dur": 37.147, + "args": { + "External id": 713825,"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": 6305207902631.898, "dur": 29.806, + "args": { + "External id": 713826,"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": 6305207902669.830, "dur": 36.361, + "args": { + "External id": 713827,"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": 6305207902723.765, "dur": 19.819, + "args": { + "External id": 713828,"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": 6305207902892.561, "dur": 75.557, + "args": { + "External id": 713829,"Record function id": 0, "Ev Idx": 18089 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6305207903043.416, "dur": 87.498, + "args": { + "External id": 713830,"Record function id": 0, "Ev Idx": 18090 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.20)", "pid": 2338707, "tid": 2338707, + "ts": 6305207903142.338, "dur": 32290.366, + "args": { + "External id": 713831,"Record function id": 0, "Ev Idx": 18091 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.20)", "pid": 2338707, "tid": 2338707, + "ts": 6305207903152.730, "dur": 995.871, + "args": { + "External id": 713832,"Record function id": 0, "Ev Idx": 18092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6305207903237.301, "dur": 9.513, + "args": { + "External id": 713833,"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": 6305207903260.971, "dur": 38.357, + "args": { + "External id": 713834,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305207903267.368, "dur": 2.146, + "args": { + "External id": 713835,"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": 6305207903274.296, "dur": 0.421, + "args": { + "External id": 713836,"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": 6305207903276.361, "dur": 0.682, + "args": { + "External id": 713837,"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": 6305207903278.323, "dur": 0.554, + "args": { + "External id": 713838,"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": 6305207903282.590, "dur": 0.533, + "args": { + "External id": 713839,"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": 6305207903284.261, "dur": 0.510, + "args": { + "External id": 713840,"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": 6305207903286.267, "dur": 2.837, + "args": { + "External id": 713841,"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": 6305207903290.885, "dur": 0.165, + "args": { + "External id": 713842,"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": 6305207903292.624, "dur": 0.373, + "args": { + "External id": 713843,"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": 6305207903311.553, "dur": 54.699, + "args": { + "External id": 713844,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305207903400.604, "dur": 141.947, + "args": { + "External id": 713845,"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": 6305207903412.090, "dur": 3.565, + "args": { + "External id": 713846,"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": 6305207903421.643, "dur": 12.281, + "args": { + "External id": 713847,"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": 6305207903426.226, "dur": 7.265, + "args": { + "External id": 713848,"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": 6305207903431.421, "dur": 0.715, + "args": { + "External id": 713849,"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": 6305207903440.916, "dur": 31.044, + "args": { + "External id": 713850,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305207903442.891, "dur": 2.347, + "args": { + "External id": 713851,"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": 6305207903447.321, "dur": 0.453, + "args": { + "External id": 713852,"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": 6305207903449.038, "dur": 0.306, + "args": { + "External id": 713853,"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": 6305207903452.577, "dur": 2.430, + "args": { + "External id": 713854,"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": 6305207903456.578, "dur": 0.309, + "args": { + "External id": 713855,"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": 6305207903458.712, "dur": 0.411, + "args": { + "External id": 713856,"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": 6305207903462.046, "dur": 0.430, + "args": { + "External id": 713857,"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": 6305207903463.974, "dur": 0.416, + "args": { + "External id": 713858,"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": 6305207903465.794, "dur": 1.887, + "args": { + "External id": 713859,"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": 6305207903483.716, "dur": 48.930, + "args": { + "External id": 713860,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305207903598.743, "dur": 409.122, + "args": { + "External id": 713861,"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": 6305207903630.566, "dur": 371.899, + "args": { + "External id": 713862,"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": 6305207903641.223, "dur": 355.432, + "args": { + "External id": 713863,"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": 6305207904033.219, "dur": 2.511, + "args": { + "External id": 713864,"Record function id": 0, "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": 6305207904172.053, "dur": 31068.555, + "args": { + "External id": 713865,"Record function id": 0, "Ev Idx": 18125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6305207904275.377, "dur": 6.830, + "args": { + "External id": 713866,"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": 6305207904285.914, "dur": 1.020, + "args": { + "External id": 713867,"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": 6305207904288.854, "dur": 3.045, + "args": { + "External id": 713868,"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": 6305207904293.685, "dur": 0.763, + "args": { + "External id": 713869,"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": 6305207904296.083, "dur": 0.702, + "args": { + "External id": 713870,"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": 6305207904298.243, "dur": 0.904, + "args": { + "External id": 713871,"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": 6305207904300.874, "dur": 0.636, + "args": { + "External id": 713872,"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": 6305207904303.206, "dur": 1.984, + "args": { + "External id": 713873,"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": 6305207904306.917, "dur": 0.632, + "args": { + "External id": 713874,"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": 6305207904311.214, "dur": 0.513, + "args": { + "External id": 713875,"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": 6305207904329.396, "dur": 30868.104, + "args": { + "External id": 713876,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305207904345.326, "dur": 30843.948, + "args": { + "External id": 713877,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305207904363.298, "dur": 17.436, + "args": { + "External id": 713878,"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": 6305207904384.265, "dur": 30768.880, + "args": { + "External id": 713879,"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": 6305207904387.235, "dur": 30765.283, + "args": { + "External id": 713880,"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": 6305207904393.870, "dur": 6.151, + "args": { + "External id": 713881,"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": 6305207904401.628, "dur": 30747.824, + "args": { + "External id": 713882,"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": 6305207935375.996, "dur": 30.759, + "args": { + "External id": 713883,"Sequence number": 7674660, "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": 6305207935375.996, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6305207935393.348, "dur": 8.753, + "args": { + "External id": 713884,"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": 6305207935397.205, "dur": 4.676, + "args": { + "External id": 713885,"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": 6305207935473.684, "dur": 89.562, + "args": { + "External id": 713886,"Record function id": 0, "Ev Idx": 18146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6305207935565.943, "dur": 1142.978, + "args": { + "External id": 713887,"Record function id": 0, "Ev Idx": 18147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305207935605.413, "dur": 1089.506, + "args": { + "External id": 713888,"Sequence number": 7674661, "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": 6305207935605.413, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6305207935677.147, "dur": 51.938, + "args": { + "External id": 713889,"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": 6305207935742.357, "dur": 107.386, + "args": { + "External id": 713890,"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": 6305207935862.363, "dur": 40.113, + "args": { + "External id": 713891,"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": 6305207935912.879, "dur": 29.993, + "args": { + "External id": 713892,"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": 6305207935971.901, "dur": 27.516, + "args": { + "External id": 713893,"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": 6305207936019.812, "dur": 18.980, + "args": { + "External id": 713894,"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": 6305207936099.165, "dur": 139.125, + "args": { + "External id": 713895,"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": 6305207936152.423, "dur": 12.515, + "args": { + "External id": 713896,"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": 6305207936158.112, "dur": 5.943, + "args": { + "External id": 713897,"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": 6305207936167.824, "dur": 3.953, + "args": { + "External id": 713898,"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": 6305207936173.404, "dur": 1.105, + "args": { + "External id": 713899,"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": 6305207936176.946, "dur": 5.789, + "args": { + "External id": 713900,"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": 6305207936249.824, "dur": 57.191, + "args": { + "External id": 713901,"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": 6305207936339.396, "dur": 31.334, + "args": { + "External id": 713902,"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": 6305207936380.437, "dur": 42.423, + "args": { + "External id": 713903,"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": 6305207936432.836, "dur": 34.908, + "args": { + "External id": 713904,"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": 6305207936489.545, "dur": 43.265, + "args": { + "External id": 713905,"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": 6305207936543.115, "dur": 39.979, + "args": { + "External id": 713906,"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": 6305207936605.314, "dur": 20.950, + "args": { + "External id": 713907,"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": 6305207936773.383, "dur": 80.117, + "args": { + "External id": 713908,"Record function id": 0, "Ev Idx": 18168 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6305207936927.687, "dur": 48.906, + "args": { + "External id": 713909,"Record function id": 0, "Ev Idx": 18169 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.21)", "pid": 2338707, "tid": 2338707, + "ts": 6305207936985.183, "dur": 30882.540, + "args": { + "External id": 713910,"Record function id": 0, "Ev Idx": 18170 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.21)", "pid": 2338707, "tid": 2338707, + "ts": 6305207936993.557, "dur": 971.145, + "args": { + "External id": 713911,"Record function id": 0, "Ev Idx": 18171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6305207937120.850, "dur": 10.571, + "args": { + "External id": 713912,"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": 6305207937145.415, "dur": 40.152, + "args": { + "External id": 713913,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305207937151.638, "dur": 2.335, + "args": { + "External id": 713914,"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": 6305207937158.937, "dur": 0.680, + "args": { + "External id": 713915,"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": 6305207937160.965, "dur": 0.408, + "args": { + "External id": 713916,"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": 6305207937162.632, "dur": 0.512, + "args": { + "External id": 713917,"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": 6305207937167.175, "dur": 0.498, + "args": { + "External id": 713918,"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": 6305207937169.275, "dur": 0.579, + "args": { + "External id": 713919,"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": 6305207937171.646, "dur": 4.291, + "args": { + "External id": 713920,"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": 6305207937177.451, "dur": 0.270, + "args": { + "External id": 713921,"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": 6305207937179.173, "dur": 0.333, + "args": { + "External id": 713922,"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": 6305207937197.977, "dur": 59.819, + "args": { + "External id": 713923,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305207937291.948, "dur": 127.613, + "args": { + "External id": 713924,"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": 6305207937302.886, "dur": 4.354, + "args": { + "External id": 713925,"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": 6305207937314.829, "dur": 10.821, + "args": { + "External id": 713926,"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": 6305207937319.521, "dur": 5.740, + "args": { + "External id": 713927,"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": 6305207937323.481, "dur": 0.540, + "args": { + "External id": 713928,"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": 6305207937331.944, "dur": 32.253, + "args": { + "External id": 713929,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305207937333.864, "dur": 2.506, + "args": { + "External id": 713930,"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": 6305207937338.561, "dur": 0.367, + "args": { + "External id": 713931,"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": 6305207937340.408, "dur": 0.357, + "args": { + "External id": 713932,"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": 6305207937344.363, "dur": 2.699, + "args": { + "External id": 713933,"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": 6305207937348.146, "dur": 0.499, + "args": { + "External id": 713934,"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": 6305207937350.281, "dur": 0.391, + "args": { + "External id": 713935,"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": 6305207937354.137, "dur": 0.306, + "args": { + "External id": 713936,"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": 6305207937355.740, "dur": 0.307, + "args": { + "External id": 713937,"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": 6305207937357.450, "dur": 2.105, + "args": { + "External id": 713938,"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": 6305207937377.868, "dur": 33.673, + "args": { + "External id": 713939,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305207937475.581, "dur": 390.910, + "args": { + "External id": 713940,"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": 6305207937522.504, "dur": 338.761, + "args": { + "External id": 713941,"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": 6305207937534.568, "dur": 321.592, + "args": { + "External id": 713942,"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": 6305207937891.097, "dur": 2.450, + "args": { + "External id": 713943,"Record function id": 0, "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": 6305207937985.941, "dur": 29692.691, + "args": { + "External id": 713944,"Record function id": 0, "Ev Idx": 18204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6305207938127.069, "dur": 6.807, + "args": { + "External id": 713945,"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": 6305207938137.749, "dur": 0.946, + "args": { + "External id": 713946,"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": 6305207938140.207, "dur": 3.229, + "args": { + "External id": 713947,"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": 6305207938145.397, "dur": 0.713, + "args": { + "External id": 713948,"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": 6305207938147.690, "dur": 1.018, + "args": { + "External id": 713949,"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": 6305207938149.976, "dur": 0.821, + "args": { + "External id": 713950,"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": 6305207938152.504, "dur": 0.841, + "args": { + "External id": 713951,"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": 6305207938155.157, "dur": 2.087, + "args": { + "External id": 713952,"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": 6305207938158.663, "dur": 0.656, + "args": { + "External id": 713953,"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": 6305207938162.614, "dur": 0.510, + "args": { + "External id": 713954,"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": 6305207938182.393, "dur": 29454.239, + "args": { + "External id": 713955,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305207938199.113, "dur": 29430.066, + "args": { + "External id": 713956,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305207938221.354, "dur": 16.290, + "args": { + "External id": 713957,"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": 6305207938241.091, "dur": 29350.695, + "args": { + "External id": 713958,"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": 6305207938243.755, "dur": 29347.496, + "args": { + "External id": 713959,"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": 6305207938249.536, "dur": 5.856, + "args": { + "External id": 713960,"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": 6305207938257.371, "dur": 29330.980, + "args": { + "External id": 713961,"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": 6305207967813.880, "dur": 29.253, + "args": { + "External id": 713962,"Sequence number": 7674662, "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": 6305207967813.880, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6305207967830.306, "dur": 7.740, + "args": { + "External id": 713963,"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": 6305207967833.653, "dur": 4.177, + "args": { + "External id": 713964,"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": 6305207967907.557, "dur": 72.716, + "args": { + "External id": 713965,"Record function id": 0, "Ev Idx": 18225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6305207967981.566, "dur": 1157.076, + "args": { + "External id": 713966,"Record function id": 0, "Ev Idx": 18226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305207968020.564, "dur": 1103.190, + "args": { + "External id": 713967,"Sequence number": 7674663, "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": 6305207968020.564, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6305207968130.961, "dur": 53.447, + "args": { + "External id": 713968,"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": 6305207968198.365, "dur": 106.441, + "args": { + "External id": 713969,"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": 6305207968316.370, "dur": 40.957, + "args": { + "External id": 713970,"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": 6305207968366.454, "dur": 29.657, + "args": { + "External id": 713971,"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": 6305207968422.475, "dur": 26.440, + "args": { + "External id": 713972,"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": 6305207968470.509, "dur": 17.366, + "args": { + "External id": 713973,"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": 6305207968526.488, "dur": 136.542, + "args": { + "External id": 713974,"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": 6305207968582.089, "dur": 11.967, + "args": { + "External id": 713975,"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": 6305207968587.036, "dur": 6.001, + "args": { + "External id": 713976,"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": 6305207968596.882, "dur": 4.009, + "args": { + "External id": 713977,"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": 6305207968601.979, "dur": 0.981, + "args": { + "External id": 713978,"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": 6305207968605.766, "dur": 5.222, + "args": { + "External id": 713979,"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": 6305207968675.106, "dur": 54.503, + "args": { + "External id": 713980,"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": 6305207968762.786, "dur": 30.529, + "args": { + "External id": 713981,"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": 6305207968803.033, "dur": 42.019, + "args": { + "External id": 713982,"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": 6305207968855.259, "dur": 34.588, + "args": { + "External id": 713983,"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": 6305207968912.922, "dur": 24.888, + "args": { + "External id": 713984,"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": 6305207968945.334, "dur": 36.058, + "args": { + "External id": 713985,"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": 6305207969001.333, "dur": 17.569, + "args": { + "External id": 713986,"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": 6305207969207.246, "dur": 77.949, + "args": { + "External id": 713987,"Record function id": 0, "Ev Idx": 18247 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6305207969362.271, "dur": 49.360, + "args": { + "External id": 713988,"Record function id": 0, "Ev Idx": 18248 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.22)", "pid": 2338707, "tid": 2338707, + "ts": 6305207969421.225, "dur": 31806.457, + "args": { + "External id": 713989,"Record function id": 0, "Ev Idx": 18249 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.22)", "pid": 2338707, "tid": 2338707, + "ts": 6305207969429.871, "dur": 950.031, + "args": { + "External id": 713990,"Record function id": 0, "Ev Idx": 18250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6305207969529.633, "dur": 9.211, + "args": { + "External id": 713991,"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": 6305207969553.497, "dur": 36.447, + "args": { + "External id": 713992,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305207969559.388, "dur": 2.101, + "args": { + "External id": 713993,"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": 6305207969565.754, "dur": 0.378, + "args": { + "External id": 713994,"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": 6305207969567.725, "dur": 0.352, + "args": { + "External id": 713995,"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": 6305207969569.489, "dur": 0.499, + "args": { + "External id": 713996,"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": 6305207969573.518, "dur": 0.468, + "args": { + "External id": 713997,"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": 6305207969575.149, "dur": 0.611, + "args": { + "External id": 713998,"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": 6305207969577.077, "dur": 2.718, + "args": { + "External id": 713999,"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": 6305207969581.129, "dur": 0.394, + "args": { + "External id": 714000,"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": 6305207969583.386, "dur": 0.381, + "args": { + "External id": 714001,"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": 6305207969602.066, "dur": 54.813, + "args": { + "External id": 714002,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305207969691.573, "dur": 115.905, + "args": { + "External id": 714003,"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": 6305207969702.538, "dur": 4.357, + "args": { + "External id": 714004,"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": 6305207969712.362, "dur": 10.065, + "args": { + "External id": 714005,"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": 6305207969717.001, "dur": 5.041, + "args": { + "External id": 714006,"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": 6305207969720.548, "dur": 0.379, + "args": { + "External id": 714007,"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": 6305207969729.062, "dur": 30.552, + "args": { + "External id": 714008,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305207969730.747, "dur": 2.128, + "args": { + "External id": 714009,"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": 6305207969734.221, "dur": 0.444, + "args": { + "External id": 714010,"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": 6305207969736.193, "dur": 0.416, + "args": { + "External id": 714011,"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": 6305207969739.388, "dur": 2.269, + "args": { + "External id": 714012,"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": 6305207969745.446, "dur": 0.478, + "args": { + "External id": 714013,"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": 6305207969746.933, "dur": 0.343, + "args": { + "External id": 714014,"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": 6305207969750.292, "dur": 0.266, + "args": { + "External id": 714015,"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": 6305207969751.875, "dur": 0.579, + "args": { + "External id": 714016,"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": 6305207969753.784, "dur": 1.732, + "args": { + "External id": 714017,"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": 6305207969770.964, "dur": 28.428, + "args": { + "External id": 714018,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305207969863.051, "dur": 410.413, + "args": { + "External id": 714019,"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": 6305207969894.138, "dur": 373.365, + "args": { + "External id": 714020,"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": 6305207969904.285, "dur": 357.136, + "args": { + "External id": 714021,"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": 6305207970300.828, "dur": 2.517, + "args": { + "External id": 714022,"Record function id": 0, "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": 6305207970401.012, "dur": 30596.363, + "args": { + "External id": 714023,"Record function id": 0, "Ev Idx": 18283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6305207970500.682, "dur": 21.416, + "args": { + "External id": 714024,"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": 6305207970528.018, "dur": 1.318, + "args": { + "External id": 714025,"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": 6305207970530.976, "dur": 3.413, + "args": { + "External id": 714026,"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": 6305207970536.042, "dur": 0.702, + "args": { + "External id": 714027,"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": 6305207970538.262, "dur": 0.944, + "args": { + "External id": 714028,"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": 6305207970540.458, "dur": 0.580, + "args": { + "External id": 714029,"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": 6305207970542.809, "dur": 0.890, + "args": { + "External id": 714030,"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": 6305207970545.068, "dur": 1.778, + "args": { + "External id": 714031,"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": 6305207970548.281, "dur": 0.830, + "args": { + "External id": 714032,"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": 6305207970552.851, "dur": 0.496, + "args": { + "External id": 714033,"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": 6305207970571.884, "dur": 30380.203, + "args": { + "External id": 714034,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305207970587.869, "dur": 30356.388, + "args": { + "External id": 714035,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305207970603.933, "dur": 15.130, + "args": { + "External id": 714036,"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": 6305207970622.785, "dur": 30284.545, + "args": { + "External id": 714037,"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": 6305207970625.359, "dur": 30281.248, + "args": { + "External id": 714038,"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": 6305207970631.503, "dur": 6.520, + "args": { + "External id": 714039,"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": 6305207970640.022, "dur": 30263.760, + "args": { + "External id": 714040,"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": 6305208001167.724, "dur": 33.551, + "args": { + "External id": 714041,"Sequence number": 7674664, "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": 6305208001167.724, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6305208001187.131, "dur": 9.152, + "args": { + "External id": 714042,"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": 6305208001190.774, "dur": 5.096, + "args": { + "External id": 714043,"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": 6305208001269.256, "dur": 71.616, + "args": { + "External id": 714044,"Record function id": 0, "Ev Idx": 18304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6305208001342.159, "dur": 1125.840, + "args": { + "External id": 714045,"Record function id": 0, "Ev Idx": 18305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305208001379.602, "dur": 1073.781, + "args": { + "External id": 714046,"Sequence number": 7674665, "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": 6305208001379.602, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6305208001445.243, "dur": 51.225, + "args": { + "External id": 714047,"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": 6305208001524.237, "dur": 108.554, + "args": { + "External id": 714048,"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": 6305208001646.503, "dur": 37.644, + "args": { + "External id": 714049,"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": 6305208001693.004, "dur": 28.771, + "args": { + "External id": 714050,"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": 6305208001748.737, "dur": 28.529, + "args": { + "External id": 714051,"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": 6305208001797.989, "dur": 17.590, + "args": { + "External id": 714052,"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": 6305208001837.936, "dur": 130.004, + "args": { + "External id": 714053,"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": 6305208001888.934, "dur": 11.539, + "args": { + "External id": 714054,"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": 6305208001894.289, "dur": 5.467, + "args": { + "External id": 714055,"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": 6305208001903.396, "dur": 4.084, + "args": { + "External id": 714056,"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": 6305208001908.844, "dur": 0.944, + "args": { + "External id": 714057,"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": 6305208001912.138, "dur": 5.181, + "args": { + "External id": 714058,"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": 6305208001978.418, "dur": 46.445, + "args": { + "External id": 714059,"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": 6305208002102.310, "dur": 37.175, + "args": { + "External id": 714060,"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": 6305208002154.089, "dur": 51.267, + "args": { + "External id": 714061,"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": 6305208002215.565, "dur": 35.649, + "args": { + "External id": 714062,"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": 6305208002274.833, "dur": 27.810, + "args": { + "External id": 714063,"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": 6305208002310.574, "dur": 36.519, + "args": { + "External id": 714064,"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": 6305208002367.202, "dur": 17.883, + "args": { + "External id": 714065,"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": 6305208002549.295, "dur": 76.463, + "args": { + "External id": 714066,"Record function id": 0, "Ev Idx": 18326 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6305208002701.552, "dur": 50.551, + "args": { + "External id": 714067,"Record function id": 0, "Ev Idx": 18327 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.23)", "pid": 2338707, "tid": 2338707, + "ts": 6305208002761.620, "dur": 31989.445, + "args": { + "External id": 714068,"Record function id": 0, "Ev Idx": 18328 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.23)", "pid": 2338707, "tid": 2338707, + "ts": 6305208002770.094, "dur": 955.423, + "args": { + "External id": 714069,"Record function id": 0, "Ev Idx": 18329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6305208002854.817, "dur": 9.296, + "args": { + "External id": 714070,"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": 6305208002878.268, "dur": 40.511, + "args": { + "External id": 714071,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305208002884.510, "dur": 2.285, + "args": { + "External id": 714072,"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": 6305208002891.816, "dur": 0.380, + "args": { + "External id": 714073,"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": 6305208002893.658, "dur": 0.383, + "args": { + "External id": 714074,"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": 6305208002895.250, "dur": 0.337, + "args": { + "External id": 714075,"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": 6305208002899.214, "dur": 0.585, + "args": { + "External id": 714076,"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": 6305208002901.452, "dur": 0.355, + "args": { + "External id": 714077,"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": 6305208002905.223, "dur": 4.299, + "args": { + "External id": 714078,"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": 6305208002910.983, "dur": 0.315, + "args": { + "External id": 714079,"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": 6305208002912.773, "dur": 0.270, + "args": { + "External id": 714080,"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": 6305208002930.036, "dur": 58.213, + "args": { + "External id": 714081,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305208003020.533, "dur": 165.935, + "args": { + "External id": 714082,"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": 6305208003031.191, "dur": 3.386, + "args": { + "External id": 714083,"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": 6305208003039.856, "dur": 10.639, + "args": { + "External id": 714084,"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": 6305208003044.632, "dur": 5.462, + "args": { + "External id": 714085,"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": 6305208003048.361, "dur": 0.562, + "args": { + "External id": 714086,"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": 6305208003094.671, "dur": 31.573, + "args": { + "External id": 714087,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305208003097.293, "dur": 2.664, + "args": { + "External id": 714088,"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": 6305208003101.740, "dur": 0.435, + "args": { + "External id": 714089,"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": 6305208003103.593, "dur": 0.291, + "args": { + "External id": 714090,"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": 6305208003107.334, "dur": 2.726, + "args": { + "External id": 714091,"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": 6305208003111.679, "dur": 0.485, + "args": { + "External id": 714092,"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": 6305208003113.404, "dur": 0.296, + "args": { + "External id": 714093,"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": 6305208003116.468, "dur": 0.367, + "args": { + "External id": 714094,"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": 6305208003118.136, "dur": 0.391, + "args": { + "External id": 714095,"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": 6305208003119.302, "dur": 2.409, + "args": { + "External id": 714096,"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": 6305208003140.520, "dur": 37.503, + "args": { + "External id": 714097,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305208003242.767, "dur": 382.622, + "args": { + "External id": 714098,"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": 6305208003273.743, "dur": 345.960, + "args": { + "External id": 714099,"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": 6305208003284.458, "dur": 326.512, + "args": { + "External id": 714100,"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": 6305208003652.828, "dur": 2.317, + "args": { + "External id": 714101,"Record function id": 0, "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": 6305208003746.542, "dur": 30810.523, + "args": { + "External id": 714102,"Record function id": 0, "Ev Idx": 18362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6305208003851.050, "dur": 6.642, + "args": { + "External id": 714103,"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": 6305208003861.152, "dur": 0.850, + "args": { + "External id": 714104,"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": 6305208003864.117, "dur": 3.820, + "args": { + "External id": 714105,"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": 6305208003869.384, "dur": 0.908, + "args": { + "External id": 714106,"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": 6305208003871.888, "dur": 0.902, + "args": { + "External id": 714107,"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": 6305208003874.127, "dur": 0.852, + "args": { + "External id": 714108,"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": 6305208003876.592, "dur": 0.902, + "args": { + "External id": 714109,"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": 6305208003878.986, "dur": 2.385, + "args": { + "External id": 714110,"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": 6305208003882.824, "dur": 0.620, + "args": { + "External id": 714111,"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": 6305208003887.444, "dur": 0.967, + "args": { + "External id": 714112,"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": 6305208003906.164, "dur": 30608.993, + "args": { + "External id": 714113,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305208003921.375, "dur": 30576.159, + "args": { + "External id": 714114,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305208003936.732, "dur": 15.726, + "args": { + "External id": 714115,"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": 6305208003956.098, "dur": 30507.213, + "args": { + "External id": 714116,"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": 6305208003958.944, "dur": 30503.706, + "args": { + "External id": 714117,"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": 6305208003965.012, "dur": 5.939, + "args": { + "External id": 714118,"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": 6305208003972.875, "dur": 30486.445, + "args": { + "External id": 714119,"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": 6305208034695.800, "dur": 31.148, + "args": { + "External id": 714120,"Sequence number": 7674666, "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": 6305208034695.800, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6305208034713.690, "dur": 8.587, + "args": { + "External id": 714121,"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": 6305208034717.176, "dur": 4.906, + "args": { + "External id": 714122,"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": 6305208034792.690, "dur": 74.261, + "args": { + "External id": 714123,"Record function id": 0, "Ev Idx": 18383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6305208034868.458, "dur": 1122.684, + "args": { + "External id": 714124,"Record function id": 0, "Ev Idx": 18384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305208034905.011, "dur": 1072.038, + "args": { + "External id": 714125,"Sequence number": 7674667, "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": 6305208034905.011, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6305208034971.235, "dur": 50.452, + "args": { + "External id": 714126,"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": 6305208035033.877, "dur": 142.889, + "args": { + "External id": 714127,"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": 6305208035194.406, "dur": 40.404, + "args": { + "External id": 714128,"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": 6305208035244.286, "dur": 29.886, + "args": { + "External id": 714129,"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": 6305208035305.010, "dur": 30.081, + "args": { + "External id": 714130,"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": 6305208035355.241, "dur": 17.571, + "args": { + "External id": 714131,"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": 6305208035395.936, "dur": 148.611, + "args": { + "External id": 714132,"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": 6305208035448.647, "dur": 11.344, + "args": { + "External id": 714133,"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": 6305208035453.927, "dur": 5.273, + "args": { + "External id": 714134,"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": 6305208035462.807, "dur": 4.742, + "args": { + "External id": 714135,"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": 6305208035468.888, "dur": 0.837, + "args": { + "External id": 714136,"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": 6305208035472.368, "dur": 5.498, + "args": { + "External id": 714137,"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": 6305208035557.000, "dur": 57.200, + "args": { + "External id": 714138,"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": 6305208035646.952, "dur": 29.971, + "args": { + "External id": 714139,"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": 6305208035686.457, "dur": 43.011, + "args": { + "External id": 714140,"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": 6305208035740.432, "dur": 34.631, + "args": { + "External id": 714141,"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": 6305208035797.341, "dur": 26.605, + "args": { + "External id": 714142,"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": 6305208035831.608, "dur": 36.537, + "args": { + "External id": 714143,"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": 6305208035888.670, "dur": 19.280, + "args": { + "External id": 714144,"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": 6305208036091.837, "dur": 86.779, + "args": { + "External id": 714145,"Record function id": 0, "Ev Idx": 18405 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6305208036259.968, "dur": 48.461, + "args": { + "External id": 714146,"Record function id": 0, "Ev Idx": 18406 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.24)", "pid": 2338707, "tid": 2338707, + "ts": 6305208036317.774, "dur": 33652.804, + "args": { + "External id": 714147,"Record function id": 0, "Ev Idx": 18407 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.24)", "pid": 2338707, "tid": 2338707, + "ts": 6305208036326.130, "dur": 953.243, + "args": { + "External id": 714148,"Record function id": 0, "Ev Idx": 18408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6305208036411.993, "dur": 8.918, + "args": { + "External id": 714149,"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": 6305208036434.560, "dur": 38.415, + "args": { + "External id": 714150,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305208036440.557, "dur": 2.326, + "args": { + "External id": 714151,"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": 6305208036447.400, "dur": 0.471, + "args": { + "External id": 714152,"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": 6305208036449.183, "dur": 0.479, + "args": { + "External id": 714153,"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": 6305208036451.166, "dur": 0.464, + "args": { + "External id": 714154,"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": 6305208036455.235, "dur": 0.387, + "args": { + "External id": 714155,"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": 6305208036456.523, "dur": 0.440, + "args": { + "External id": 714156,"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": 6305208036458.477, "dur": 4.668, + "args": { + "External id": 714157,"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": 6305208036464.474, "dur": 0.383, + "args": { + "External id": 714158,"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": 6305208036466.418, "dur": 0.345, + "args": { + "External id": 714159,"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": 6305208036484.597, "dur": 69.280, + "args": { + "External id": 714160,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305208036589.915, "dur": 126.396, + "args": { + "External id": 714161,"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": 6305208036602.505, "dur": 5.120, + "args": { + "External id": 714162,"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": 6305208036613.197, "dur": 11.397, + "args": { + "External id": 714163,"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": 6305208036618.026, "dur": 6.155, + "args": { + "External id": 714164,"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": 6305208036621.958, "dur": 0.568, + "args": { + "External id": 714165,"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": 6305208036631.483, "dur": 32.168, + "args": { + "External id": 714166,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305208036633.737, "dur": 2.324, + "args": { + "External id": 714167,"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": 6305208036637.513, "dur": 0.524, + "args": { + "External id": 714168,"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": 6305208036639.532, "dur": 0.364, + "args": { + "External id": 714169,"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": 6305208036643.248, "dur": 2.743, + "args": { + "External id": 714170,"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": 6305208036647.699, "dur": 0.265, + "args": { + "External id": 714171,"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": 6305208036649.137, "dur": 0.283, + "args": { + "External id": 714172,"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": 6305208036653.296, "dur": 0.399, + "args": { + "External id": 714173,"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": 6305208036655.043, "dur": 0.428, + "args": { + "External id": 714174,"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": 6305208036657.001, "dur": 2.458, + "args": { + "External id": 714175,"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": 6305208036678.429, "dur": 30.065, + "args": { + "External id": 714176,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305208036772.001, "dur": 407.020, + "args": { + "External id": 714177,"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": 6305208036803.038, "dur": 370.616, + "args": { + "External id": 714178,"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": 6305208036814.292, "dur": 352.488, + "args": { + "External id": 714179,"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": 6305208037206.306, "dur": 2.317, + "args": { + "External id": 714180,"Record function id": 0, "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": 6305208037299.908, "dur": 32476.111, + "args": { + "External id": 714181,"Record function id": 0, "Ev Idx": 18441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6305208037403.098, "dur": 6.899, + "args": { + "External id": 714182,"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": 6305208037413.533, "dur": 1.263, + "args": { + "External id": 714183,"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": 6305208037416.686, "dur": 3.412, + "args": { + "External id": 714184,"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": 6305208037422.015, "dur": 1.023, + "args": { + "External id": 714185,"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": 6305208037424.434, "dur": 1.123, + "args": { + "External id": 714186,"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": 6305208037426.921, "dur": 0.712, + "args": { + "External id": 714187,"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": 6305208037429.273, "dur": 0.717, + "args": { + "External id": 714188,"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": 6305208037431.649, "dur": 2.600, + "args": { + "External id": 714189,"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": 6305208037435.605, "dur": 0.808, + "args": { + "External id": 714190,"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": 6305208037440.194, "dur": 0.559, + "args": { + "External id": 714191,"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": 6305208037457.825, "dur": 32274.312, + "args": { + "External id": 714192,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305208037473.344, "dur": 32250.757, + "args": { + "External id": 714193,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305208037487.865, "dur": 16.728, + "args": { + "External id": 714194,"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": 6305208037524.620, "dur": 32161.482, + "args": { + "External id": 714195,"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": 6305208037527.490, "dur": 32158.057, + "args": { + "External id": 714196,"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": 6305208037534.508, "dur": 6.565, + "args": { + "External id": 714197,"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": 6305208037543.000, "dur": 32139.704, + "args": { + "External id": 714198,"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": 6305208069915.156, "dur": 30.724, + "args": { + "External id": 714199,"Sequence number": 7674668, "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": 6305208069915.156, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6305208069932.016, "dur": 8.945, + "args": { + "External id": 714200,"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": 6305208069935.993, "dur": 4.767, + "args": { + "External id": 714201,"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": 6305208070011.153, "dur": 105.085, + "args": { + "External id": 714202,"Record function id": 0, "Ev Idx": 18462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6305208070118.910, "dur": 1125.935, + "args": { + "External id": 714203,"Record function id": 0, "Ev Idx": 18463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305208070160.952, "dur": 1069.744, + "args": { + "External id": 714204,"Sequence number": 7674669, "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": 6305208070160.952, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6305208070232.903, "dur": 50.905, + "args": { + "External id": 714205,"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": 6305208070296.137, "dur": 105.143, + "args": { + "External id": 714206,"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": 6305208070412.985, "dur": 38.174, + "args": { + "External id": 714207,"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": 6305208070460.407, "dur": 30.084, + "args": { + "External id": 714208,"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": 6305208070530.391, "dur": 30.431, + "args": { + "External id": 714209,"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": 6305208070584.609, "dur": 16.250, + "args": { + "External id": 714210,"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": 6305208070625.707, "dur": 132.249, + "args": { + "External id": 714211,"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": 6305208070677.512, "dur": 11.544, + "args": { + "External id": 714212,"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": 6305208070683.194, "dur": 5.038, + "args": { + "External id": 714213,"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": 6305208070691.574, "dur": 4.084, + "args": { + "External id": 714214,"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": 6305208070697.529, "dur": 0.919, + "args": { + "External id": 714215,"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": 6305208070701.248, "dur": 5.638, + "args": { + "External id": 714216,"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": 6305208070768.692, "dur": 51.766, + "args": { + "External id": 714217,"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": 6305208070851.610, "dur": 29.685, + "args": { + "External id": 714218,"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": 6305208070890.902, "dur": 42.413, + "args": { + "External id": 714219,"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": 6305208070948.281, "dur": 35.694, + "args": { + "External id": 714220,"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": 6305208071009.214, "dur": 28.564, + "args": { + "External id": 714221,"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": 6305208071045.931, "dur": 72.898, + "args": { + "External id": 714222,"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": 6305208071142.263, "dur": 19.339, + "args": { + "External id": 714223,"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": 6305208071309.100, "dur": 85.451, + "args": { + "External id": 714224,"Record function id": 0, "Ev Idx": 18484 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 2338707, "tid": 2338707, + "ts": 6305208071469.578, "dur": 65.986, + "args": { + "External id": 714225,"Record function id": 0, "Ev Idx": 18485 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.25)", "pid": 2338707, "tid": 2338707, + "ts": 6305208071546.558, "dur": 34852.021, + "args": { + "External id": 714226,"Record function id": 0, "Ev Idx": 18486 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.25)", "pid": 2338707, "tid": 2338707, + "ts": 6305208071555.671, "dur": 1019.752, + "args": { + "External id": 714227,"Record function id": 0, "Ev Idx": 18487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6305208071646.278, "dur": 9.543, + "args": { + "External id": 714228,"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": 6305208071669.678, "dur": 38.900, + "args": { + "External id": 714229,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305208071675.188, "dur": 2.495, + "args": { + "External id": 714230,"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": 6305208071682.347, "dur": 0.467, + "args": { + "External id": 714231,"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": 6305208071684.080, "dur": 0.563, + "args": { + "External id": 714232,"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": 6305208071686.077, "dur": 0.341, + "args": { + "External id": 714233,"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": 6305208071690.343, "dur": 0.381, + "args": { + "External id": 714234,"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": 6305208071692.110, "dur": 0.688, + "args": { + "External id": 714235,"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": 6305208071694.422, "dur": 3.988, + "args": { + "External id": 714236,"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": 6305208071699.945, "dur": 0.566, + "args": { + "External id": 714237,"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": 6305208071701.860, "dur": 0.762, + "args": { + "External id": 714238,"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": 6305208071721.580, "dur": 51.295, + "args": { + "External id": 714239,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305208071805.702, "dur": 141.573, + "args": { + "External id": 714240,"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": 6305208071834.105, "dur": 5.275, + "args": { + "External id": 714241,"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": 6305208071845.060, "dur": 10.344, + "args": { + "External id": 714242,"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": 6305208071849.481, "dur": 5.542, + "args": { + "External id": 714243,"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": 6305208071853.057, "dur": 0.560, + "args": { + "External id": 714244,"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": 6305208071862.278, "dur": 34.834, + "args": { + "External id": 714245,"Record function id": 0, "Concrete Inputs": ["", "[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": 6305208071871.008, "dur": 0.328, + "args": { + "External id": 714246,"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": 6305208071874.977, "dur": 0.424, + "args": { + "External id": 714247,"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": 6305208071876.712, "dur": 0.333, + "args": { + "External id": 714248,"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": 6305208071878.611, "dur": 4.334, + "args": { + "External id": 714249,"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": 6305208071884.073, "dur": 0.139, + "args": { + "External id": 714250,"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": 6305208071885.439, "dur": 0.239, + "args": { + "External id": 714251,"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": 6305208071889.103, "dur": 0.358, + "args": { + "External id": 714252,"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": 6305208071890.956, "dur": 0.319, + "args": { + "External id": 714253,"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": 6305208071892.517, "dur": 0.336, + "args": { + "External id": 714254,"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": 6305208071910.787, "dur": 29.012, + "args": { + "External id": 714255,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 6305208071999.985, "dur": 450.845, + "args": { + "External id": 714256,"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": 6305208072030.932, "dur": 413.527, + "args": { + "External id": 714257,"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": 6305208072041.230, "dur": 396.971, + "args": { + "External id": 714258,"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": 6305208072480.039, "dur": 2.515, + "args": { + "External id": 714259,"Record function id": 0, "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": 6305208072598.387, "dur": 33604.233, + "args": { + "External id": 714260,"Record function id": 0, "Ev Idx": 18520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6305208072703.563, "dur": 7.065, + "args": { + "External id": 714261,"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": 6305208072713.942, "dur": 1.232, + "args": { + "External id": 714262,"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": 6305208072716.908, "dur": 3.340, + "args": { + "External id": 714263,"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": 6305208072722.097, "dur": 0.848, + "args": { + "External id": 714264,"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": 6305208072724.328, "dur": 0.786, + "args": { + "External id": 714265,"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": 6305208072726.408, "dur": 1.020, + "args": { + "External id": 714266,"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": 6305208072729.285, "dur": 0.556, + "args": { + "External id": 714267,"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": 6305208072731.752, "dur": 2.229, + "args": { + "External id": 714268,"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": 6305208072735.224, "dur": 1.052, + "args": { + "External id": 714269,"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": 6305208072739.950, "dur": 0.548, + "args": { + "External id": 714270,"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": 6305208072759.378, "dur": 33399.335, + "args": { + "External id": 714271,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305208072775.331, "dur": 33375.151, + "args": { + "External id": 714272,"Record function id": 0, "Concrete Inputs": ["", "[512, 2097152, 524288, 524288, 2097152, 512, 7340032, 7340032, 7340032]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[27264000, 1], [], [], [[512, 1], [2097152, 1], [524288, 1], [524288, 1], [2097152, 1], [512, 1], [7340032, 1], [7340032, 1], [7340032, 1]]], "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": 6305208072796.621, "dur": 16.387, + "args": { + "External id": 714273,"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": 6305208072817.206, "dur": 33295.591, + "args": { + "External id": 714274,"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": 6305208072819.748, "dur": 33292.456, + "args": { + "External id": 714275,"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": 6305208072825.167, "dur": 5.568, + "args": { + "External id": 714276,"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": 6305208072832.667, "dur": 33276.219, + "args": { + "External id": 714277,"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": 6305208106343.520, "dur": 30.740, + "args": { + "External id": 714278,"Sequence number": 7674670, "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": 6305208106343.520, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 2338707, "tid": 2338707, + "ts": 6305208106360.724, "dur": 8.773, + "args": { + "External id": 714279,"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": 6305208106364.510, "dur": 4.768, + "args": { + "External id": 714280,"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": 6305208106438.442, "dur": 88.242, + "args": { + "External id": 714281,"Record function id": 0, "Ev Idx": 18541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 2338707, "tid": 2338707, + "ts": 6305208106529.486, "dur": 1135.646, + "args": { + "External id": 714282,"Record function id": 0, "Ev Idx": 18542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305208106569.722, "dur": 1081.269, + "args": { + "External id": 714283,"Sequence number": 7674671, "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": 6305208106569.722, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6305208106636.942, "dur": 51.783, + "args": { + "External id": 714284,"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": 6305208106701.160, "dur": 95.000, + "args": { + "External id": 714285,"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": 6305208106807.865, "dur": 35.637, + "args": { + "External id": 714286,"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": 6305208106852.369, "dur": 31.056, + "args": { + "External id": 714287,"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": 6305208106906.620, "dur": 27.159, + "args": { + "External id": 714288,"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": 6305208106957.252, "dur": 18.303, + "args": { + "External id": 714289,"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": 6305208106997.591, "dur": 189.069, + "args": { + "External id": 714290,"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": 6305208107049.995, "dur": 62.163, + "args": { + "External id": 714291,"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": 6305208107104.568, "dur": 6.606, + "args": { + "External id": 714292,"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": 6305208107115.362, "dur": 4.494, + "args": { + "External id": 714293,"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": 6305208107121.120, "dur": 1.293, + "args": { + "External id": 714294,"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": 6305208107125.062, "dur": 5.418, + "args": { + "External id": 714295,"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": 6305208107198.645, "dur": 56.371, + "args": { + "External id": 714296,"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": 6305208107289.755, "dur": 30.968, + "args": { + "External id": 714297,"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": 6305208107330.409, "dur": 42.560, + "args": { + "External id": 714298,"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": 6305208107383.468, "dur": 34.031, + "args": { + "External id": 714299,"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": 6305208107439.301, "dur": 28.424, + "args": { + "External id": 714300,"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": 6305208107475.132, "dur": 51.630, + "args": { + "External id": 714301,"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": 6305208107552.174, "dur": 21.871, + "args": { + "External id": 714302,"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": 6305208107732.108, "dur": 33.734, + "args": { + "External id": 714303,"Record function id": 0, "Ev Idx": 18563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305208107903.804, "dur": 354.699, + "args": { + "External id": 714304,"Sequence number": 7674672, "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": 6305208107903.804, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6305208107939.349, "dur": 8.279, + "args": { + "External id": 714305,"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": 6305208107941.502, "dur": 5.854, + "args": { + "External id": 714306,"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": 6305208107958.948, "dur": 12.314, + "args": { + "External id": 714307,"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": 6305208107962.487, "dur": 8.107, + "args": { + "External id": 714308,"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": 6305208107981.021, "dur": 4.431, + "args": { + "External id": 714309,"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": 6305208108235.520, "dur": 7.531, + "args": { + "External id": 714310,"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": 6305208108238.603, "dur": 4.036, + "args": { + "External id": 714311,"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": 6305208108287.844, "dur": 140.727, + "args": { + "External id": 714312,"Sequence number": 7674673, "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": 6305208108290.290, "dur": 15.519, + "args": { + "External id": 714313,"Sequence number": 7674673, "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": 6305208108290.290, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6305208108295.483, "dur": 8.380, + "args": { + "External id": 714314,"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": 6305208108301.436, "dur": 2.073, + "args": { + "External id": 714315,"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": 6305208108308.450, "dur": 119.820, + "args": { + "External id": 714316,"Sequence number": 7674674, "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": 6305208108311.712, "dur": 4.862, + "args": { + "External id": 714317,"Sequence number": 7674674, "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": 6305208108312.615, "dur": 3.779, + "args": { + "External id": 714318,"Sequence number": 7674674, "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": 6305208108312.615, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6305208108321.404, "dur": 95.100, + "args": { + "External id": 714319,"Sequence number": 7674675, "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": 6305208108321.404, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6305208108420.133, "dur": 7.011, + "args": { + "External id": 714320,"Sequence number": 7674676, "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": 6305208108420.133, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338707, "tid": 2338707, + "ts": 6305208108437.815, "dur": 66.345, + "args": { + "External id": 714321,"Sequence number": 7674677, "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": 6305208108438.457, "dur": 8.419, + "args": { + "External id": 714322,"Sequence number": 7674677, "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": 6305208108438.457, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6305208108440.396, "dur": 5.435, + "args": { + "External id": 714323,"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": 6305208108444.908, "dur": 0.777, + "args": { + "External id": 714324,"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": 6305208108447.510, "dur": 56.395, + "args": { + "External id": 714325,"Sequence number": 7674678, "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": 6305208108448.462, "dur": 5.702, + "args": { + "External id": 714326,"Sequence number": 7674678, "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": 6305208108449.538, "dur": 4.476, + "args": { + "External id": 714327,"Sequence number": 7674678, "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": 6305208108449.538, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6305208108454.806, "dur": 42.814, + "args": { + "External id": 714328,"Sequence number": 7674679, "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": 6305208108454.806, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6305208108499.268, "dur": 4.270, + "args": { + "External id": 714329,"Sequence number": 7674680, "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": 6305208108499.268, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338707, "tid": 2338707, + "ts": 6305208108527.757, "dur": 71.508, + "args": { + "External id": 714330,"Sequence number": 7674681, "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": 6305208108528.457, "dur": 7.027, + "args": { + "External id": 714331,"Sequence number": 7674681, "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": 6305208108528.457, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6305208108531.019, "dur": 3.059, + "args": { + "External id": 714332,"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": 6305208108532.845, "dur": 0.947, + "args": { + "External id": 714333,"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": 6305208108538.697, "dur": 60.322, + "args": { + "External id": 714334,"Sequence number": 7674682, "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": 6305208108539.938, "dur": 4.490, + "args": { + "External id": 714335,"Sequence number": 7674682, "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": 6305208108540.586, "dur": 3.708, + "args": { + "External id": 714336,"Sequence number": 7674682, "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": 6305208108540.586, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6305208108545.158, "dur": 45.392, + "args": { + "External id": 714337,"Sequence number": 7674683, "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": 6305208108545.158, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6305208108592.542, "dur": 6.101, + "args": { + "External id": 714338,"Sequence number": 7674684, "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": 6305208108592.542, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6305208108624.699, "dur": 3.911, + "args": { + "External id": 714339,"Sequence number": 7674685, "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": 6305208108625.663, "dur": 2.838, + "args": { + "External id": 714340,"Sequence number": 7674685, "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": 6305208108625.663, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6305208108637.125, "dur": 5.505, + "args": { + "External id": 714341,"Sequence number": 7674686, "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": 6305208108638.613, "dur": 3.892, + "args": { + "External id": 714342,"Sequence number": 7674686, "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": 6305208108638.613, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6305208108649.221, "dur": 4.606, + "args": { + "External id": 714343,"Sequence number": 7674687, "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": 6305208108650.394, "dur": 3.294, + "args": { + "External id": 714344,"Sequence number": 7674687, "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": 6305208108650.394, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305208108691.446, "dur": 191.180, + "args": { + "External id": 714345,"Sequence number": 7674688, "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": 6305208108691.446, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338707, "tid": 2338707, + "ts": 6305208108715.709, "dur": 9.252, + "args": { + "External id": 714346,"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": 6305208108719.172, "dur": 5.346, + "args": { + "External id": 714347,"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": 6305208108896.244, "dur": 115.542, + "args": { + "External id": 714348,"Sequence number": 7674689, "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": 6305208108896.244, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338707, "tid": 2338707, + "ts": 6305208108910.717, "dur": 7.248, + "args": { + "External id": 714349,"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": 6305208108913.150, "dur": 4.429, + "args": { + "External id": 714350,"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": 6305208109040.141, "dur": 251.716, + "args": { + "External id": 714351,"Sequence number": 7674690, "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": 6305208109040.141, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338707, "tid": 2338707, + "ts": 6305208109125.333, "dur": 134.959, + "args": { + "External id": 714352,"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": 6305208109179.708, "dur": 11.333, + "args": { + "External id": 714353,"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": 6305208109182.737, "dur": 7.556, + "args": { + "External id": 714354,"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": 6305208109193.582, "dur": 3.791, + "args": { + "External id": 714355,"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": 6305208109198.413, "dur": 0.926, + "args": { + "External id": 714356,"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": 6305208109201.806, "dur": 3.591, + "args": { + "External id": 714357,"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": 6305208109274.228, "dur": 6.353, + "args": { + "External id": 714358,"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": 6305208109298.508, "dur": 6.613, + "args": { + "External id": 714359,"Sequence number": 7674691, "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": 6305208109300.159, "dur": 4.740, + "args": { + "External id": 714360,"Sequence number": 7674691, "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": 6305208109300.159, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338707, "tid": 2338707, + "ts": 6305208109318.004, "dur": 120.690, + "args": { + "External id": 714361,"Sequence number": 7674692, "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": 6305208109321.624, "dur": 10.005, + "args": { + "External id": 714362,"Sequence number": 7674692, "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": 6305208109321.624, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6305208109325.440, "dur": 5.077, + "args": { + "External id": 714363,"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": 6305208109328.270, "dur": 1.965, + "args": { + "External id": 714364,"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": 6305208109333.384, "dur": 105.015, + "args": { + "External id": 714365,"Sequence number": 7674693, "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": 6305208109335.323, "dur": 4.685, + "args": { + "External id": 714366,"Sequence number": 7674693, "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": 6305208109337.849, "dur": 2.017, + "args": { + "External id": 714367,"Sequence number": 7674693, "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": 6305208109337.849, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6305208109341.156, "dur": 89.850, + "args": { + "External id": 714368,"Sequence number": 7674694, "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": 6305208109341.156, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6305208109433.853, "dur": 3.670, + "args": { + "External id": 714369,"Sequence number": 7674695, "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": 6305208109433.853, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305208109476.185, "dur": 274.938, + "args": { + "External id": 714370,"Sequence number": 7674696, "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": 6305208109476.185, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6305208109502.250, "dur": 21.609, + "args": { + "External id": 714371,"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": 6305208109503.221, "dur": 20.172, + "args": { + "External id": 714372,"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": 6305208109531.374, "dur": 5.918, + "args": { + "External id": 714373,"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": 6305208109532.734, "dur": 4.328, + "args": { + "External id": 714374,"Record 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": 6305208109533.570, "dur": 3.394, + "args": { + "External id": 714375,"Record 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": 6305208109545.507, "dur": 10.075, + "args": { + "External id": 714376,"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": 6305208109550.174, "dur": 5.049, + "args": { + "External id": 714377,"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": 6305208109562.726, "dur": 2.608, + "args": { + "External id": 714378,"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": 6305208109569.141, "dur": 3.507, + "args": { + "External id": 714379,"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": 6305208109726.080, "dur": 3.537, + "args": { + "External id": 714380,"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": 6305208109727.283, "dur": 2.164, + "args": { + "External id": 714381,"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": 6305208109732.319, "dur": 4.329, + "args": { + "External id": 714382,"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": 6305208109735.686, "dur": 0.855, + "args": { + "External id": 714383,"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": 6305208109775.557, "dur": 109.612, + "args": { + "External id": 714384,"Sequence number": 7674697, "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": 6305208109776.755, "dur": 9.348, + "args": { + "External id": 714385,"Sequence number": 7674697, "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": 6305208109776.755, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6305208109780.015, "dur": 4.663, + "args": { + "External id": 714386,"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": 6305208109782.443, "dur": 1.967, + "args": { + "External id": 714387,"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": 6305208109787.019, "dur": 97.809, + "args": { + "External id": 714388,"Sequence number": 7674698, "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": 6305208109791.038, "dur": 3.652, + "args": { + "External id": 714389,"Sequence number": 7674698, "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": 6305208109791.702, "dur": 2.853, + "args": { + "External id": 714390,"Sequence number": 7674698, "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": 6305208109791.702, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6305208109795.459, "dur": 81.394, + "args": { + "External id": 714391,"Sequence number": 7674699, "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": 6305208109795.459, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6305208109879.215, "dur": 5.007, + "args": { + "External id": 714392,"Sequence number": 7674700, "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": 6305208109879.215, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338707, "tid": 2338707, + "ts": 6305208109897.286, "dur": 68.567, + "args": { + "External id": 714393,"Sequence number": 7674701, "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": 6305208109898.179, "dur": 5.956, + "args": { + "External id": 714394,"Sequence number": 7674701, "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": 6305208109898.179, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6305208109900.077, "dur": 2.824, + "args": { + "External id": 714395,"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": 6305208109901.784, "dur": 0.963, + "args": { + "External id": 714396,"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": 6305208109904.836, "dur": 60.739, + "args": { + "External id": 714397,"Sequence number": 7674702, "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": 6305208109908.135, "dur": 4.820, + "args": { + "External id": 714398,"Sequence number": 7674702, "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": 6305208109909.206, "dur": 3.629, + "args": { + "External id": 714399,"Sequence number": 7674702, "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": 6305208109909.206, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6305208109913.408, "dur": 48.473, + "args": { + "External id": 714400,"Sequence number": 7674703, "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": 6305208109913.408, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6305208109963.402, "dur": 1.767, + "args": { + "External id": 714401,"Sequence number": 7674704, "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": 6305208109963.402, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305208109991.550, "dur": 234.427, + "args": { + "External id": 714402,"Sequence number": 7674705, "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": 6305208109991.550, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6305208110038.016, "dur": 3.833, + "args": { + "External id": 714403,"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": 6305208110132.209, "dur": 76.098, + "args": { + "External id": 714404,"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": 6305208110132.883, "dur": 8.846, + "args": { + "External id": 714405,"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": 6305208110136.424, "dur": 4.100, + "args": { + "External id": 714406,"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": 6305208110138.803, "dur": 1.313, + "args": { + "External id": 714407,"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": 6305208110142.636, "dur": 65.259, + "args": { + "External id": 714408,"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": 6305208110146.625, "dur": 3.120, + "args": { + "External id": 714409,"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": 6305208110147.886, "dur": 1.761, + "args": { + "External id": 714410,"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": 6305208110150.576, "dur": 53.756, + "args": { + "External id": 714411,"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": 6305208110206.019, "dur": 1.142, + "args": { + "External id": 714412,"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": 6305208110237.290, "dur": 30.137, + "args": { + "External id": 714413,"Sequence number": 7674706, "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": 6305208110237.290, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305208110306.937, "dur": 195.376, + "args": { + "External id": 714414,"Sequence number": 7674707, "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": 6305208110306.937, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6305208110328.700, "dur": 3.553, + "args": { + "External id": 714415,"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": 6305208110330.310, "dur": 1.807, + "args": { + "External id": 714416,"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": 6305208110340.539, "dur": 7.071, + "args": { + "External id": 714417,"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": 6305208110343.277, "dur": 3.982, + "args": { + "External id": 714418,"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": 6305208110353.903, "dur": 3.466, + "args": { + "External id": 714419,"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": 6305208110487.615, "dur": 3.102, + "args": { + "External id": 714420,"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": 6305208110488.737, "dur": 1.787, + "args": { + "External id": 714421,"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": 6305208110537.770, "dur": 106.032, + "args": { + "External id": 714422,"Sequence number": 7674708, "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": 6305208110541.417, "dur": 9.043, + "args": { + "External id": 714423,"Sequence number": 7674708, "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": 6305208110541.417, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6305208110544.744, "dur": 4.182, + "args": { + "External id": 714424,"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": 6305208110547.073, "dur": 1.524, + "args": { + "External id": 714425,"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": 6305208110551.242, "dur": 92.205, + "args": { + "External id": 714426,"Sequence number": 7674709, "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": 6305208110552.589, "dur": 8.742, + "args": { + "External id": 714427,"Sequence number": 7674709, "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": 6305208110555.150, "dur": 5.984, + "args": { + "External id": 714428,"Sequence number": 7674709, "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": 6305208110555.150, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6305208110562.106, "dur": 70.323, + "args": { + "External id": 714429,"Sequence number": 7674710, "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": 6305208110562.106, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6305208110634.683, "dur": 8.055, + "args": { + "External id": 714430,"Sequence number": 7674711, "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": 6305208110634.683, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338707, "tid": 2338707, + "ts": 6305208110652.518, "dur": 69.036, + "args": { + "External id": 714431,"Sequence number": 7674712, "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": 6305208110653.373, "dur": 9.666, + "args": { + "External id": 714432,"Sequence number": 7674712, "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": 6305208110653.373, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6305208110659.733, "dur": 2.189, + "args": { + "External id": 714433,"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": 6305208110661.171, "dur": 0.621, + "args": { + "External id": 714434,"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": 6305208110663.622, "dur": 57.735, + "args": { + "External id": 714435,"Sequence number": 7674713, "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": 6305208110664.755, "dur": 5.549, + "args": { + "External id": 714436,"Sequence number": 7674713, "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": 6305208110667.546, "dur": 2.592, + "args": { + "External id": 714437,"Sequence number": 7674713, "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": 6305208110667.546, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6305208110670.826, "dur": 45.365, + "args": { + "External id": 714438,"Sequence number": 7674714, "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": 6305208110670.826, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6305208110717.962, "dur": 3.060, + "args": { + "External id": 714439,"Sequence number": 7674715, "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": 6305208110717.962, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338707, "tid": 2338707, + "ts": 6305208110729.439, "dur": 59.850, + "args": { + "External id": 714440,"Sequence number": 7674716, "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": 6305208110730.062, "dur": 7.780, + "args": { + "External id": 714441,"Sequence number": 7674716, "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": 6305208110730.062, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6305208110731.998, "dur": 4.826, + "args": { + "External id": 714442,"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": 6305208110735.944, "dur": 0.772, + "args": { + "External id": 714443,"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": 6305208110738.371, "dur": 50.730, + "args": { + "External id": 714444,"Sequence number": 7674717, "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": 6305208110739.157, "dur": 8.232, + "args": { + "External id": 714445,"Sequence number": 7674717, "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": 6305208110740.186, "dur": 7.052, + "args": { + "External id": 714446,"Sequence number": 7674717, "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": 6305208110740.186, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6305208110750.255, "dur": 35.287, + "args": { + "External id": 714447,"Sequence number": 7674718, "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": 6305208110750.255, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6305208110787.254, "dur": 1.528, + "args": { + "External id": 714448,"Sequence number": 7674719, "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": 6305208110787.254, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6305208110806.904, "dur": 5.105, + "args": { + "External id": 714449,"Sequence number": 7674720, "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": 6305208110807.811, "dur": 4.054, + "args": { + "External id": 714450,"Sequence number": 7674720, "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": 6305208110807.811, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6305208110819.755, "dur": 5.042, + "args": { + "External id": 714451,"Sequence number": 7674721, "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": 6305208110823.008, "dur": 1.667, + "args": { + "External id": 714452,"Sequence number": 7674721, "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": 6305208110823.008, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6305208110829.022, "dur": 3.504, + "args": { + "External id": 714453,"Sequence number": 7674722, "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": 6305208110830.447, "dur": 1.975, + "args": { + "External id": 714454,"Sequence number": 7674722, "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": 6305208110830.447, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305208110862.527, "dur": 156.375, + "args": { + "External id": 714455,"Sequence number": 7674723, "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": 6305208110862.527, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338707, "tid": 2338707, + "ts": 6305208110881.579, "dur": 12.699, + "args": { + "External id": 714456,"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": 6305208110888.991, "dur": 4.961, + "args": { + "External id": 714457,"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": 6305208111032.859, "dur": 161.127, + "args": { + "External id": 714458,"Sequence number": 7674724, "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": 6305208111032.859, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338707, "tid": 2338707, + "ts": 6305208111045.793, "dur": 6.578, + "args": { + "External id": 714459,"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": 6305208111048.347, "dur": 3.683, + "args": { + "External id": 714460,"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": 6305208111223.830, "dur": 180.291, + "args": { + "External id": 714461,"Sequence number": 7674725, "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": 6305208111223.830, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338707, "tid": 2338707, + "ts": 6305208111257.100, "dur": 122.095, + "args": { + "External id": 714462,"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": 6305208111301.910, "dur": 10.226, + "args": { + "External id": 714463,"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": 6305208111306.393, "dur": 5.207, + "args": { + "External id": 714464,"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": 6305208111314.940, "dur": 3.696, + "args": { + "External id": 714465,"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": 6305208111319.669, "dur": 1.282, + "args": { + "External id": 714466,"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": 6305208111323.445, "dur": 4.243, + "args": { + "External id": 714467,"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": 6305208111389.970, "dur": 5.272, + "args": { + "External id": 714468,"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": 6305208111409.322, "dur": 8.859, + "args": { + "External id": 714469,"Sequence number": 7674726, "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": 6305208111411.009, "dur": 7.054, + "args": { + "External id": 714470,"Sequence number": 7674726, "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": 6305208111411.009, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338707, "tid": 2338707, + "ts": 6305208111429.542, "dur": 135.766, + "args": { + "External id": 714471,"Sequence number": 7674727, "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": 6305208111430.887, "dur": 8.606, + "args": { + "External id": 714472,"Sequence number": 7674727, "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": 6305208111430.887, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6305208111433.262, "dur": 4.952, + "args": { + "External id": 714473,"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": 6305208111436.237, "dur": 1.737, + "args": { + "External id": 714474,"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": 6305208111440.534, "dur": 124.472, + "args": { + "External id": 714475,"Sequence number": 7674728, "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": 6305208111444.575, "dur": 3.872, + "args": { + "External id": 714476,"Sequence number": 7674728, "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": 6305208111445.587, "dur": 2.693, + "args": { + "External id": 714477,"Sequence number": 7674728, "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": 6305208111445.587, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6305208111449.236, "dur": 104.821, + "args": { + "External id": 714478,"Sequence number": 7674729, "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": 6305208111449.236, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6305208111557.896, "dur": 5.864, + "args": { + "External id": 714479,"Sequence number": 7674730, "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": 6305208111557.896, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305208111605.511, "dur": 226.979, + "args": { + "External id": 714480,"Sequence number": 7674731, "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": 6305208111605.511, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6305208111625.918, "dur": 5.439, + "args": { + "External id": 714481,"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": 6305208111629.094, "dur": 2.059, + "args": { + "External id": 714482,"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": 6305208111635.426, "dur": 5.405, + "args": { + "External id": 714483,"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": 6305208111636.467, "dur": 4.259, + "args": { + "External id": 714484,"Record 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": 6305208111639.353, "dur": 1.061, + "args": { + "External id": 714485,"Record 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": 6305208111648.655, "dur": 8.836, + "args": { + "External id": 714486,"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": 6305208111651.334, "dur": 5.804, + "args": { + "External id": 714487,"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": 6305208111664.058, "dur": 3.011, + "args": { + "External id": 714488,"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": 6305208111670.790, "dur": 2.820, + "args": { + "External id": 714489,"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": 6305208111810.594, "dur": 4.156, + "args": { + "External id": 714490,"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": 6305208111811.995, "dur": 2.550, + "args": { + "External id": 714491,"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": 6305208111817.301, "dur": 2.066, + "args": { + "External id": 714492,"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": 6305208111818.238, "dur": 1.027, + "args": { + "External id": 714493,"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": 6305208111851.770, "dur": 103.699, + "args": { + "External id": 714494,"Sequence number": 7674732, "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": 6305208111852.766, "dur": 10.543, + "args": { + "External id": 714495,"Sequence number": 7674732, "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": 6305208111852.766, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6305208111855.888, "dur": 5.974, + "args": { + "External id": 714496,"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": 6305208111860.217, "dur": 1.412, + "args": { + "External id": 714497,"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": 6305208111864.268, "dur": 90.867, + "args": { + "External id": 714498,"Sequence number": 7674733, "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": 6305208111865.751, "dur": 3.844, + "args": { + "External id": 714499,"Sequence number": 7674733, "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": 6305208111866.637, "dur": 2.842, + "args": { + "External id": 714500,"Sequence number": 7674733, "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": 6305208111866.637, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6305208111870.292, "dur": 79.023, + "args": { + "External id": 714501,"Sequence number": 7674734, "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": 6305208111870.292, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6305208111951.227, "dur": 3.435, + "args": { + "External id": 714502,"Sequence number": 7674735, "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": 6305208111951.227, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338707, "tid": 2338707, + "ts": 6305208111963.931, "dur": 69.525, + "args": { + "External id": 714503,"Sequence number": 7674736, "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": 6305208111964.671, "dur": 6.155, + "args": { + "External id": 714504,"Sequence number": 7674736, "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": 6305208111964.671, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6305208111966.606, "dur": 2.714, + "args": { + "External id": 714505,"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": 6305208111968.442, "dur": 0.680, + "args": { + "External id": 714506,"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": 6305208111973.622, "dur": 59.572, + "args": { + "External id": 714507,"Sequence number": 7674737, "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": 6305208111974.517, "dur": 7.162, + "args": { + "External id": 714508,"Sequence number": 7674737, "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": 6305208111975.510, "dur": 6.005, + "args": { + "External id": 714509,"Sequence number": 7674737, "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": 6305208111975.510, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6305208111982.464, "dur": 44.206, + "args": { + "External id": 714510,"Sequence number": 7674738, "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": 6305208111982.464, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6305208112028.849, "dur": 4.025, + "args": { + "External id": 714511,"Sequence number": 7674739, "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": 6305208112028.849, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305208112054.622, "dur": 204.908, + "args": { + "External id": 714512,"Sequence number": 7674740, "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": 6305208112054.622, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6305208112133.469, "dur": 6.107, + "args": { + "External id": 714513,"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": 6305208112176.174, "dur": 67.861, + "args": { + "External id": 714514,"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": 6305208112177.374, "dur": 7.874, + "args": { + "External id": 714515,"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": 6305208112179.631, "dur": 4.570, + "args": { + "External id": 714516,"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": 6305208112183.229, "dur": 0.811, + "args": { + "External id": 714517,"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": 6305208112186.049, "dur": 57.642, + "args": { + "External id": 714518,"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": 6305208112187.041, "dur": 2.780, + "args": { + "External id": 714519,"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": 6305208112188.075, "dur": 1.661, + "args": { + "External id": 714520,"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": 6305208112190.364, "dur": 46.844, + "args": { + "External id": 714521,"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": 6305208112239.024, "dur": 3.866, + "args": { + "External id": 714522,"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": 6305208112268.978, "dur": 27.141, + "args": { + "External id": 714523,"Sequence number": 7674741, "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": 6305208112268.978, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305208112337.205, "dur": 204.211, + "args": { + "External id": 714524,"Sequence number": 7674742, "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": 6305208112337.205, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6305208112355.887, "dur": 2.824, + "args": { + "External id": 714525,"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": 6305208112357.008, "dur": 1.533, + "args": { + "External id": 714526,"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": 6305208112366.789, "dur": 7.426, + "args": { + "External id": 714527,"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": 6305208112369.810, "dur": 3.993, + "args": { + "External id": 714528,"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": 6305208112380.125, "dur": 3.303, + "args": { + "External id": 714529,"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": 6305208112523.744, "dur": 3.980, + "args": { + "External id": 714530,"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": 6305208112524.659, "dur": 2.771, + "args": { + "External id": 714531,"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": 6305208112560.950, "dur": 98.639, + "args": { + "External id": 714532,"Sequence number": 7674743, "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": 6305208112561.914, "dur": 7.627, + "args": { + "External id": 714533,"Sequence number": 7674743, "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": 6305208112561.914, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6305208112565.205, "dur": 3.279, + "args": { + "External id": 714534,"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": 6305208112566.998, "dur": 1.303, + "args": { + "External id": 714535,"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": 6305208112570.581, "dur": 88.708, + "args": { + "External id": 714536,"Sequence number": 7674744, "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": 6305208112574.745, "dur": 4.444, + "args": { + "External id": 714537,"Sequence number": 7674744, "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": 6305208112575.547, "dur": 3.510, + "args": { + "External id": 714538,"Sequence number": 7674744, "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": 6305208112575.547, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6305208112579.793, "dur": 68.547, + "args": { + "External id": 714539,"Sequence number": 7674745, "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": 6305208112579.793, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6305208112651.031, "dur": 7.214, + "args": { + "External id": 714540,"Sequence number": 7674746, "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": 6305208112651.031, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338707, "tid": 2338707, + "ts": 6305208112674.444, "dur": 59.119, + "args": { + "External id": 714541,"Sequence number": 7674747, "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": 6305208112675.280, "dur": 5.425, + "args": { + "External id": 714542,"Sequence number": 7674747, "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": 6305208112675.280, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6305208112677.507, "dur": 2.008, + "args": { + "External id": 714543,"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": 6305208112678.670, "dur": 0.707, + "args": { + "External id": 714544,"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": 6305208112681.268, "dur": 51.988, + "args": { + "External id": 714545,"Sequence number": 7674748, "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": 6305208112684.230, "dur": 4.794, + "args": { + "External id": 714546,"Sequence number": 7674748, "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": 6305208112684.858, "dur": 4.025, + "args": { + "External id": 714547,"Sequence number": 7674748, "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": 6305208112684.858, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6305208112689.485, "dur": 39.031, + "args": { + "External id": 714548,"Sequence number": 7674749, "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": 6305208112689.485, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6305208112729.932, "dur": 2.947, + "args": { + "External id": 714549,"Sequence number": 7674750, "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": 6305208112729.932, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338707, "tid": 2338707, + "ts": 6305208112740.213, "dur": 60.050, + "args": { + "External id": 714550,"Sequence number": 7674751, "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": 6305208112740.983, "dur": 8.860, + "args": { + "External id": 714551,"Sequence number": 7674751, "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": 6305208112740.983, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6305208112744.226, "dur": 4.362, + "args": { + "External id": 714552,"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": 6305208112747.885, "dur": 0.580, + "args": { + "External id": 714553,"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": 6305208112750.378, "dur": 49.629, + "args": { + "External id": 714554,"Sequence number": 7674752, "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": 6305208112751.195, "dur": 6.817, + "args": { + "External id": 714555,"Sequence number": 7674752, "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": 6305208112754.469, "dur": 3.421, + "args": { + "External id": 714556,"Sequence number": 7674752, "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": 6305208112754.469, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6305208112758.456, "dur": 35.164, + "args": { + "External id": 714557,"Sequence number": 7674753, "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": 6305208112758.456, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6305208112795.391, "dur": 4.240, + "args": { + "External id": 714558,"Sequence number": 7674754, "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": 6305208112795.391, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6305208112816.191, "dur": 5.727, + "args": { + "External id": 714559,"Sequence number": 7674755, "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": 6305208112817.129, "dur": 4.686, + "args": { + "External id": 714560,"Sequence number": 7674755, "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": 6305208112817.129, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6305208112829.015, "dur": 5.470, + "args": { + "External id": 714561,"Sequence number": 7674756, "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": 6305208112830.027, "dur": 4.354, + "args": { + "External id": 714562,"Sequence number": 7674756, "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": 6305208112830.027, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6305208112838.878, "dur": 3.266, + "args": { + "External id": 714563,"Sequence number": 7674757, "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": 6305208112839.671, "dur": 2.363, + "args": { + "External id": 714564,"Sequence number": 7674757, "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": 6305208112839.671, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305208112872.843, "dur": 154.202, + "args": { + "External id": 714565,"Sequence number": 7674758, "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": 6305208112872.843, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338707, "tid": 2338707, + "ts": 6305208112891.941, "dur": 9.096, + "args": { + "External id": 714566,"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": 6305208112894.711, "dur": 5.746, + "args": { + "External id": 714567,"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": 6305208113038.926, "dur": 149.670, + "args": { + "External id": 714568,"Sequence number": 7674759, "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": 6305208113038.926, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338707, "tid": 2338707, + "ts": 6305208113051.258, "dur": 42.345, + "args": { + "External id": 714569,"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": 6305208113053.166, "dur": 39.659, + "args": { + "External id": 714570,"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": 6305208113220.394, "dur": 177.529, + "args": { + "External id": 714571,"Sequence number": 7674760, "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": 6305208113220.394, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338707, "tid": 2338707, + "ts": 6305208113246.740, "dur": 126.733, + "args": { + "External id": 714572,"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": 6305208113293.096, "dur": 7.704, + "args": { + "External id": 714573,"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": 6305208113295.886, "dur": 4.561, + "args": { + "External id": 714574,"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": 6305208113303.350, "dur": 3.870, + "args": { + "External id": 714575,"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": 6305208113308.738, "dur": 3.680, + "args": { + "External id": 714576,"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": 6305208113314.746, "dur": 5.173, + "args": { + "External id": 714577,"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": 6305208113384.132, "dur": 4.935, + "args": { + "External id": 714578,"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": 6305208113403.010, "dur": 6.046, + "args": { + "External id": 714579,"Sequence number": 7674761, "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": 6305208113404.591, "dur": 4.305, + "args": { + "External id": 714580,"Sequence number": 7674761, "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": 6305208113404.591, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338707, "tid": 2338707, + "ts": 6305208113420.743, "dur": 130.160, + "args": { + "External id": 714581,"Sequence number": 7674762, "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": 6305208113422.095, "dur": 12.050, + "args": { + "External id": 714582,"Sequence number": 7674762, "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": 6305208113422.095, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6305208113426.769, "dur": 6.438, + "args": { + "External id": 714583,"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": 6305208113431.223, "dur": 1.767, + "args": { + "External id": 714584,"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": 6305208113435.292, "dur": 115.287, + "args": { + "External id": 714585,"Sequence number": 7674763, "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": 6305208113437.461, "dur": 3.691, + "args": { + "External id": 714586,"Sequence number": 7674763, "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": 6305208113438.157, "dur": 2.867, + "args": { + "External id": 714587,"Sequence number": 7674763, "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": 6305208113438.157, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6305208113442.085, "dur": 100.189, + "args": { + "External id": 714588,"Sequence number": 7674764, "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": 6305208113442.085, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6305208113545.564, "dur": 4.273, + "args": { + "External id": 714589,"Sequence number": 7674765, "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": 6305208113545.564, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305208113587.690, "dur": 213.060, + "args": { + "External id": 714590,"Sequence number": 7674766, "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": 6305208113587.690, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6305208113606.159, "dur": 3.188, + "args": { + "External id": 714591,"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": 6305208113607.382, "dur": 1.834, + "args": { + "External id": 714592,"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": 6305208113613.396, "dur": 8.315, + "args": { + "External id": 714593,"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": 6305208113619.204, "dur": 2.397, + "args": { + "External id": 714594,"Record 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": 6305208113620.310, "dur": 1.197, + "args": { + "External id": 714595,"Record 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": 6305208113629.334, "dur": 8.285, + "args": { + "External id": 714596,"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": 6305208113631.676, "dur": 5.678, + "args": { + "External id": 714597,"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": 6305208113643.839, "dur": 5.113, + "args": { + "External id": 714598,"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": 6305208113654.463, "dur": 4.491, + "args": { + "External id": 714599,"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": 6305208113781.639, "dur": 3.540, + "args": { + "External id": 714600,"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": 6305208113783.547, "dur": 1.474, + "args": { + "External id": 714601,"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": 6305208113787.765, "dur": 2.340, + "args": { + "External id": 714602,"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": 6305208113789.015, "dur": 0.991, + "args": { + "External id": 714603,"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": 6305208113818.536, "dur": 99.895, + "args": { + "External id": 714604,"Sequence number": 7674767, "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": 6305208113819.892, "dur": 12.055, + "args": { + "External id": 714605,"Sequence number": 7674767, "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": 6305208113819.892, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6305208113824.802, "dur": 6.001, + "args": { + "External id": 714606,"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": 6305208113827.328, "dur": 3.224, + "args": { + "External id": 714607,"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": 6305208113832.901, "dur": 85.276, + "args": { + "External id": 714608,"Sequence number": 7674768, "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": 6305208113834.464, "dur": 5.197, + "args": { + "External id": 714609,"Sequence number": 7674768, "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": 6305208113835.200, "dur": 4.165, + "args": { + "External id": 714610,"Sequence number": 7674768, "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": 6305208113835.200, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6305208113840.562, "dur": 70.780, + "args": { + "External id": 714611,"Sequence number": 7674769, "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": 6305208113840.562, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6305208113913.415, "dur": 4.295, + "args": { + "External id": 714612,"Sequence number": 7674770, "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": 6305208113913.415, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338707, "tid": 2338707, + "ts": 6305208113927.305, "dur": 73.084, + "args": { + "External id": 714613,"Sequence number": 7674771, "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": 6305208113928.247, "dur": 8.183, + "args": { + "External id": 714614,"Sequence number": 7674771, "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": 6305208113928.247, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6305208113930.132, "dur": 5.033, + "args": { + "External id": 714615,"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": 6305208113934.312, "dur": 0.723, + "args": { + "External id": 714616,"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": 6305208113937.399, "dur": 62.624, + "args": { + "External id": 714617,"Sequence number": 7674772, "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": 6305208113938.606, "dur": 5.135, + "args": { + "External id": 714618,"Sequence number": 7674772, "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": 6305208113939.745, "dur": 3.867, + "args": { + "External id": 714619,"Sequence number": 7674772, "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": 6305208113939.745, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6305208113946.930, "dur": 45.613, + "args": { + "External id": 714620,"Sequence number": 7674773, "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": 6305208113946.930, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6305208113994.521, "dur": 4.864, + "args": { + "External id": 714621,"Sequence number": 7674774, "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": 6305208113994.521, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305208114020.377, "dur": 205.045, + "args": { + "External id": 714622,"Sequence number": 7674775, "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": 6305208114020.377, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6305208114093.612, "dur": 6.367, + "args": { + "External id": 714623,"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": 6305208114140.142, "dur": 71.895, + "args": { + "External id": 714624,"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": 6305208114141.371, "dur": 8.850, + "args": { + "External id": 714625,"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": 6305208114143.503, "dur": 5.521, + "args": { + "External id": 714626,"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": 6305208114145.779, "dur": 3.030, + "args": { + "External id": 714627,"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": 6305208114151.265, "dur": 60.440, + "args": { + "External id": 714628,"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": 6305208114152.914, "dur": 2.701, + "args": { + "External id": 714629,"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": 6305208114154.128, "dur": 1.142, + "args": { + "External id": 714630,"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": 6305208114158.636, "dur": 49.050, + "args": { + "External id": 714631,"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": 6305208114209.845, "dur": 1.133, + "args": { + "External id": 714632,"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": 6305208114234.283, "dur": 25.839, + "args": { + "External id": 714633,"Sequence number": 7674776, "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": 6305208114234.283, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305208114296.958, "dur": 178.374, + "args": { + "External id": 714634,"Sequence number": 7674777, "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": 6305208114296.958, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6305208114314.382, "dur": 4.783, + "args": { + "External id": 714635,"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": 6305208114315.785, "dur": 3.228, + "args": { + "External id": 714636,"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": 6305208114327.106, "dur": 9.218, + "args": { + "External id": 714637,"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": 6305208114332.050, "dur": 3.920, + "args": { + "External id": 714638,"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": 6305208114342.264, "dur": 4.211, + "args": { + "External id": 714639,"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": 6305208114460.981, "dur": 5.117, + "args": { + "External id": 714640,"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": 6305208114462.374, "dur": 3.545, + "args": { + "External id": 714641,"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": 6305208114492.463, "dur": 114.472, + "args": { + "External id": 714642,"Sequence number": 7674778, "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": 6305208114493.570, "dur": 10.265, + "args": { + "External id": 714643,"Sequence number": 7674778, "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": 6305208114493.570, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6305208114496.276, "dur": 6.100, + "args": { + "External id": 714644,"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": 6305208114500.861, "dur": 1.343, + "args": { + "External id": 714645,"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": 6305208114504.888, "dur": 101.700, + "args": { + "External id": 714646,"Sequence number": 7674779, "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": 6305208114524.994, "dur": 6.908, + "args": { + "External id": 714647,"Sequence number": 7674779, "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": 6305208114526.010, "dur": 5.598, + "args": { + "External id": 714648,"Sequence number": 7674779, "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": 6305208114526.010, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6305208114532.937, "dur": 67.383, + "args": { + "External id": 714649,"Sequence number": 7674780, "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": 6305208114532.937, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6305208114602.619, "dur": 3.353, + "args": { + "External id": 714650,"Sequence number": 7674781, "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": 6305208114602.619, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338707, "tid": 2338707, + "ts": 6305208114617.111, "dur": 62.385, + "args": { + "External id": 714651,"Sequence number": 7674782, "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": 6305208114618.022, "dur": 8.321, + "args": { + "External id": 714652,"Sequence number": 7674782, "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": 6305208114618.022, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6305208114620.064, "dur": 5.204, + "args": { + "External id": 714653,"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": 6305208114623.949, "dur": 1.169, + "args": { + "External id": 714654,"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": 6305208114629.091, "dur": 50.088, + "args": { + "External id": 714655,"Sequence number": 7674783, "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": 6305208114630.659, "dur": 3.312, + "args": { + "External id": 714656,"Sequence number": 7674783, "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": 6305208114631.622, "dur": 2.229, + "args": { + "External id": 714657,"Sequence number": 7674783, "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": 6305208114631.622, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6305208114634.664, "dur": 38.113, + "args": { + "External id": 714658,"Sequence number": 7674784, "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": 6305208114634.664, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6305208114674.348, "dur": 4.534, + "args": { + "External id": 714659,"Sequence number": 7674785, "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": 6305208114674.348, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338707, "tid": 2338707, + "ts": 6305208114689.277, "dur": 57.924, + "args": { + "External id": 714660,"Sequence number": 7674786, "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": 6305208114689.776, "dur": 5.328, + "args": { + "External id": 714661,"Sequence number": 7674786, "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": 6305208114689.776, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6305208114691.701, "dur": 2.377, + "args": { + "External id": 714662,"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": 6305208114693.323, "dur": 0.628, + "args": { + "External id": 714663,"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": 6305208114695.903, "dur": 51.015, + "args": { + "External id": 714664,"Sequence number": 7674787, "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": 6305208114698.592, "dur": 6.630, + "args": { + "External id": 714665,"Sequence number": 7674787, "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": 6305208114699.592, "dur": 5.499, + "args": { + "External id": 714666,"Sequence number": 7674787, "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": 6305208114699.592, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6305208114705.776, "dur": 36.641, + "args": { + "External id": 714667,"Sequence number": 7674788, "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": 6305208114705.776, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6305208114743.820, "dur": 2.785, + "args": { + "External id": 714668,"Sequence number": 7674789, "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": 6305208114743.820, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6305208114765.075, "dur": 4.294, + "args": { + "External id": 714669,"Sequence number": 7674790, "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": 6305208114766.381, "dur": 2.876, + "args": { + "External id": 714670,"Sequence number": 7674790, "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": 6305208114766.381, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6305208114776.068, "dur": 4.996, + "args": { + "External id": 714671,"Sequence number": 7674791, "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": 6305208114777.259, "dur": 3.678, + "args": { + "External id": 714672,"Sequence number": 7674791, "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": 6305208114777.259, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6305208114785.423, "dur": 4.760, + "args": { + "External id": 714673,"Sequence number": 7674792, "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": 6305208114786.517, "dur": 3.538, + "args": { + "External id": 714674,"Sequence number": 7674792, "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": 6305208114786.517, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305208114819.199, "dur": 153.975, + "args": { + "External id": 714675,"Sequence number": 7674793, "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": 6305208114819.199, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338707, "tid": 2338707, + "ts": 6305208114838.424, "dur": 8.951, + "args": { + "External id": 714676,"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": 6305208114841.585, "dur": 5.395, + "args": { + "External id": 714677,"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": 6305208114985.197, "dur": 141.548, + "args": { + "External id": 714678,"Sequence number": 7674794, "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": 6305208114985.197, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 2338707, "tid": 2338707, + "ts": 6305208114998.299, "dur": 6.662, + "args": { + "External id": 714679,"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": 6305208115000.681, "dur": 3.934, + "args": { + "External id": 714680,"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": 6305208115159.125, "dur": 183.788, + "args": { + "External id": 714681,"Sequence number": 7674795, "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": 6305208115159.125, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 2338707, "tid": 2338707, + "ts": 6305208115185.354, "dur": 129.526, + "args": { + "External id": 714682,"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": 6305208115234.222, "dur": 8.449, + "args": { + "External id": 714683,"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": 6305208115237.019, "dur": 5.159, + "args": { + "External id": 714684,"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": 6305208115245.162, "dur": 4.145, + "args": { + "External id": 714685,"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": 6305208115254.073, "dur": 1.108, + "args": { + "External id": 714686,"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": 6305208115257.789, "dur": 3.330, + "args": { + "External id": 714687,"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": 6305208115325.786, "dur": 5.130, + "args": { + "External id": 714688,"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": 6305208115348.817, "dur": 7.182, + "args": { + "External id": 714689,"Sequence number": 7674796, "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": 6305208115350.990, "dur": 4.848, + "args": { + "External id": 714690,"Sequence number": 7674796, "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": 6305208115350.990, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338707, "tid": 2338707, + "ts": 6305208115368.920, "dur": 116.706, + "args": { + "External id": 714691,"Sequence number": 7674797, "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": 6305208115370.168, "dur": 10.755, + "args": { + "External id": 714692,"Sequence number": 7674797, "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": 6305208115370.168, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6305208115373.064, "dur": 6.720, + "args": { + "External id": 714693,"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": 6305208115377.949, "dur": 1.519, + "args": { + "External id": 714694,"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": 6305208115382.206, "dur": 103.110, + "args": { + "External id": 714695,"Sequence number": 7674798, "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": 6305208115384.155, "dur": 3.463, + "args": { + "External id": 714696,"Sequence number": 7674798, "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": 6305208115384.764, "dur": 2.702, + "args": { + "External id": 714697,"Sequence number": 7674798, "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": 6305208115384.764, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6305208115390.865, "dur": 86.296, + "args": { + "External id": 714698,"Sequence number": 7674799, "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": 6305208115390.865, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6305208115479.901, "dur": 4.761, + "args": { + "External id": 714699,"Sequence number": 7674800, "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": 6305208115479.901, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305208115545.180, "dur": 221.381, + "args": { + "External id": 714700,"Sequence number": 7674801, "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": 6305208115545.180, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 2338707, "tid": 2338707, + "ts": 6305208115565.206, "dur": 5.333, + "args": { + "External id": 714701,"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": 6305208115568.280, "dur": 1.974, + "args": { + "External id": 714702,"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": 6305208115574.464, "dur": 3.224, + "args": { + "External id": 714703,"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": 6305208115575.711, "dur": 1.872, + "args": { + "External id": 714704,"Record 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": 6305208115576.445, "dur": 1.050, + "args": { + "External id": 714705,"Record 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": 6305208115585.471, "dur": 8.021, + "args": { + "External id": 714706,"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": 6305208115587.962, "dur": 5.174, + "args": { + "External id": 714707,"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": 6305208115601.921, "dur": 4.677, + "args": { + "External id": 714708,"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": 6305208115611.812, "dur": 3.336, + "args": { + "External id": 714709,"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": 6305208115744.636, "dur": 3.359, + "args": { + "External id": 714710,"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": 6305208115746.026, "dur": 1.690, + "args": { + "External id": 714711,"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": 6305208115750.927, "dur": 2.044, + "args": { + "External id": 714712,"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": 6305208115752.076, "dur": 0.793, + "args": { + "External id": 714713,"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": 6305208115785.316, "dur": 105.105, + "args": { + "External id": 714714,"Sequence number": 7674802, "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": 6305208115786.513, "dur": 9.850, + "args": { + "External id": 714715,"Sequence number": 7674802, "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": 6305208115786.513, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6305208115791.251, "dur": 4.070, + "args": { + "External id": 714716,"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": 6305208115793.528, "dur": 1.558, + "args": { + "External id": 714717,"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": 6305208115797.286, "dur": 92.841, + "args": { + "External id": 714718,"Sequence number": 7674803, "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": 6305208115798.981, "dur": 6.750, + "args": { + "External id": 714719,"Sequence number": 7674803, "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": 6305208115801.995, "dur": 3.606, + "args": { + "External id": 714720,"Sequence number": 7674803, "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": 6305208115801.995, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6305208115806.536, "dur": 74.979, + "args": { + "External id": 714721,"Sequence number": 7674804, "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": 6305208115806.536, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6305208115884.408, "dur": 5.091, + "args": { + "External id": 714722,"Sequence number": 7674805, "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": 6305208115884.408, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 2338707, "tid": 2338707, + "ts": 6305208115898.608, "dur": 82.298, + "args": { + "External id": 714723,"Sequence number": 7674806, "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": 6305208115899.255, "dur": 10.771, + "args": { + "External id": 714724,"Sequence number": 7674806, "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": 6305208115899.255, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 2338707, "tid": 2338707, + "ts": 6305208115906.141, "dur": 2.847, + "args": { + "External id": 714725,"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": 6305208115907.868, "dur": 0.916, + "args": { + "External id": 714726,"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": 6305208115910.771, "dur": 69.851, + "args": { + "External id": 714727,"Sequence number": 7674807, "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": 6305208115911.576, "dur": 6.451, + "args": { + "External id": 714728,"Sequence number": 7674807, "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": 6305208115912.721, "dur": 5.167, + "args": { + "External id": 714729,"Sequence number": 7674807, "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": 6305208115912.721, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 2338707, "tid": 2338707, + "ts": 6305208115918.725, "dur": 53.979, + "args": { + "External id": 714730,"Sequence number": 7674808, "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": 6305208115918.725, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 2338707, "tid": 2338707, + "ts": 6305208115974.371, "dur": 5.299, + "args": { + "External id": 714731,"Sequence number": 7674809, "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": 6305208115974.371, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305208116002.143, "dur": 211.148, + "args": { + "External id": 714732,"Sequence number": 7674810, "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": 6305208116002.143, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 2338707, "tid": 2338707, + "ts": 6305208116042.950, "dur": 4.556, + "args": { + "External id": 714733,"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": 6305208116123.723, "dur": 74.453, + "args": { + "External id": 714734,"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": 6305208116125.028, "dur": 8.589, + "args": { + "External id": 714735,"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": 6305208116127.095, "dur": 4.994, + "args": { + "External id": 714736,"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": 6305208116130.731, "dur": 1.047, + "args": { + "External id": 714737,"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": 6305208116134.713, "dur": 62.909, + "args": { + "External id": 714738,"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": 6305208116136.992, "dur": 4.768, + "args": { + "External id": 714739,"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": 6305208116139.949, "dur": 1.701, + "args": { + "External id": 714740,"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": 6305208116142.470, "dur": 50.474, + "args": { + "External id": 714741,"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": 6305208116195.440, "dur": 1.471, + "args": { + "External id": 714742,"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": 6305208116222.884, "dur": 24.981, + "args": { + "External id": 714743,"Sequence number": 7674811, "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": 6305208116222.884, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::stack", "pid": 2338707, "tid": 2338707, + "ts": 6305208116267.571, "dur": 42.738, + "args": { + "External id": 714744,"Sequence number": 7674812, "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": 6305208116267.571, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::cat", "pid": 2338707, "tid": 2338707, + "ts": 6305208116276.202, "dur": 29.946, + "args": { + "External id": 714745,"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": 6305208116307.502, "dur": 1.294, + "args": { + "External id": 714746,"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": 6305208116347.396, "dur": 51.398, + "args": { + "External id": 714747,"Record function id": 0, "Ev Idx": 19007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 2/0", "pid": 2338707, "tid": 2338707, + "ts": 6305208116400.343, "dur": 226.387, + "args": { + "External id": 714748,"Record function id": 0, "Ev Idx": 19008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 2338707, "tid": 2338707, + "ts": 6305208116441.245, "dur": 176.245, + "args": { + "External id": 714749,"Sequence number": 7674813, "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": 6305208116441.245, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 2338707, "tid": 2338707, + "ts": 6305208116532.227, "dur": 42.302, + "args": { + "External id": 714750,"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": 6305208116718.817, "dur": 66.208, + "args": { + "External id": 714751,"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": 6305208116721.978, "dur": 5.594, + "args": { + "External id": 714752,"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": 6305208116748.832, "dur": 35.871, + "args": { + "External id": 714753,"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": 6305208116752.458, "dur": 31.751, + "args": { + "External id": 714754,"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": 6305208116789.819, "dur": 17.379, + "args": { + "External id": 714755,"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": 6305208116790.564, "dur": 1.940, + "args": { + "External id": 714756,"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": 6305208116793.028, "dur": 13.866, + "args": { + "External id": 714757,"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": 6305208116795.525, "dur": 11.001, + "args": { + "External id": 714758,"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": 6305208116810.538, "dur": 18.246, + "args": { + "External id": 714759,"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": 6305208116811.200, "dur": 2.651, + "args": { + "External id": 714760,"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": 6305208116814.439, "dur": 14.097, + "args": { + "External id": 714761,"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": 6305208116815.159, "dur": 13.078, + "args": { + "External id": 714762,"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": 6305208116838.835, "dur": 0.705, + "args": { + "External id": 714763,"Sequence number": 7674814, "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": 6305208116849.466, "dur": 11.709, + "args": { + "External id": 714764,"Sequence number": 7674814, "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": 6305208116857.119, "dur": 2.106, + "args": { + "External id": 714765,"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": 6305208116867.475, "dur": 6.786, + "args": { + "External id": 714766,"Sequence number": 7674814, "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": 6305208116871.720, "dur": 0.760, + "args": { + "External id": 714767,"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": 6305208116875.366, "dur": 2.826, + "args": { + "External id": 714768,"Sequence number": 7674814, "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": 6305208116877.076, "dur": 0.338, + "args": { + "External id": 714769,"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": 6305208116879.442, "dur": 2.926, + "args": { + "External id": 714770,"Sequence number": 7674814, "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": 6305208116881.377, "dur": 0.452, + "args": { + "External id": 714771,"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": 6305208116885.231, "dur": 5.175, + "args": { + "External id": 714772,"Sequence number": 7674814, "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": 6305208116887.065, "dur": 2.795, + "args": { + "External id": 714773,"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": 6305208116891.505, "dur": 2.887, + "args": { + "External id": 714774,"Sequence number": 7674814, "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": 6305208116893.198, "dur": 0.532, + "args": { + "External id": 714775,"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": 6305208116895.360, "dur": 2.706, + "args": { + "External id": 714776,"Sequence number": 7674814, "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": 6305208116897.068, "dur": 0.480, + "args": { + "External id": 714777,"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": 6305208116902.330, "dur": 4.928, + "args": { + "External id": 714778,"Sequence number": 7674814, "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": 6305208116906.035, "dur": 0.400, + "args": { + "External id": 714779,"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": 6305208116911.622, "dur": 2.978, + "args": { + "External id": 714780,"Sequence number": 7674814, "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": 6305208116913.433, "dur": 0.603, + "args": { + "External id": 714781,"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": 6305208116917.805, "dur": 9.206, + "args": { + "External id": 714782,"Sequence number": 7674814, "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": 6305208116925.464, "dur": 0.394, + "args": { + "External id": 714783,"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": 6305208116927.966, "dur": 2.208, + "args": { + "External id": 714784,"Sequence number": 7674814, "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": 6305208116929.239, "dur": 0.382, + "args": { + "External id": 714785,"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": 6305208116932.535, "dur": 5.332, + "args": { + "External id": 714786,"Sequence number": 7674814, "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": 6305208116932.535, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2338707, + "ts": 6305208116935.966, "dur": 0.503, + "args": { + "External id": 714787,"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": 6305208116940.948, "dur": 6.841, + "args": { + "External id": 714788,"Sequence number": 7674815, "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": 6305208116940.948, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2338707, + "ts": 6305208116944.390, "dur": 2.629, + "args": { + "External id": 714789,"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": 6305208116948.755, "dur": 4.891, + "args": { + "External id": 714790,"Sequence number": 7674816, "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": 6305208116948.755, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2338707, + "ts": 6305208116952.458, "dur": 0.334, + "args": { + "External id": 714791,"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": 6305208116954.645, "dur": 5.880, + "args": { + "External id": 714792,"Sequence number": 7674817, "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": 6305208116954.645, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2338707, + "ts": 6305208116959.432, "dur": 0.330, + "args": { + "External id": 714793,"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": 6305208116964.559, "dur": 39.253, + "args": { + "External id": 714794,"Sequence number": 7674818, "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": 6305208116968.897, "dur": 34.676, + "args": { + "External id": 714795,"Sequence number": 7674818, "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": 6305208116971.610, "dur": 6.262, + "args": { + "External id": 714796,"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": 6305208116973.544, "dur": 3.682, + "args": { + "External id": 714797,"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": 6305208116979.358, "dur": 23.686, + "args": { + "External id": 714798,"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": 6305208117029.318, "dur": 4.188, + "args": { + "External id": 714799,"Sequence number": 7674818, "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": 6305208117029.318, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6305208117035.574, "dur": 0.927, + "args": { + "External id": 714800,"Sequence number": 7674819, "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": 6305208117103.273, "dur": 143120.749, + "args": { + "External id": 714801,"Sequence number": 7674819, "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": 6305208117103.273, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338707, "tid": 2338707, + "ts": 6305208117119.633, "dur": 36.247, + "args": { + "External id": 714802,"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": 6305208117120.412, "dur": 35.254, + "args": { + "External id": 714803,"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": 6305208117122.685, "dur": 7.971, + "args": { + "External id": 714804,"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": 6305208117125.659, "dur": 4.383, + "args": { + "External id": 714805,"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": 6305208117131.383, "dur": 23.783, + "args": { + "External id": 714806,"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": 6305208117175.785, "dur": 24.877, + "args": { + "External id": 714807,"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": 6305208117177.152, "dur": 6.101, + "args": { + "External id": 714808,"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": 6305208117179.500, "dur": 3.504, + "args": { + "External id": 714809,"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": 6305208117184.108, "dur": 16.358, + "args": { + "External id": 714810,"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": 6305208117185.208, "dur": 14.858, + "args": { + "External id": 714811,"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": 6305208117204.337, "dur": 22.912, + "args": { + "External id": 714812,"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": 6305208117205.125, "dur": 10.089, + "args": { + "External id": 714813,"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": 6305208117208.515, "dur": 6.483, + "args": { + "External id": 714814,"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": 6305208117216.113, "dur": 10.953, + "args": { + "External id": 714815,"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": 6305208117216.518, "dur": 10.234, + "args": { + "External id": 714816,"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": 6305208117232.726, "dur": 15.016, + "args": { + "External id": 714817,"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": 6305208117233.898, "dur": 3.018, + "args": { + "External id": 714818,"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": 6305208117237.432, "dur": 10.048, + "args": { + "External id": 714819,"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": 6305208117238.124, "dur": 9.074, + "args": { + "External id": 714820,"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": 6305208117257.476, "dur": 29.431, + "args": { + "External id": 714821,"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": 6305208117291.531, "dur": 64.485, + "args": { + "External id": 714822,"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": 6305208117295.060, "dur": 60.514, + "args": { + "External id": 714823,"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": 6305208117303.166, "dur": 0.836, + "args": { + "External id": 714824,"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": 6305208117308.117, "dur": 25.023, + "args": { + "External id": 714825,"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": 6305208117310.060, "dur": 22.879, + "args": { + "External id": 714826,"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": 6305208117312.749, "dur": 2.698, + "args": { + "External id": 714827,"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": 6305208117316.191, "dur": 16.211, + "args": { + "External id": 714828,"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": 6305208117363.490, "dur": 136902.484, + "args": { + "External id": 714829,"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": 6305208117365.660, "dur": 136898.474, + "args": { + "External id": 714830,"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": 6305208254281.118, "dur": 9.053, + "args": { + "External id": 714831,"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": 6305208254286.485, "dur": 1.498, + "args": { + "External id": 714832,"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": 6305208254296.093, "dur": 115.973, + "args": { + "External id": 714833,"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": 6305208254297.855, "dur": 6.590, + "args": { + "External id": 714834,"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": 6305208254300.185, "dur": 3.168, + "args": { + "External id": 714835,"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": 6305208254302.305, "dur": 0.787, + "args": { + "External id": 714836,"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": 6305208254308.340, "dur": 102.984, + "args": { + "External id": 714837,"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": 6305208254310.043, "dur": 100.489, + "args": { + "External id": 714838,"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": 6305208254416.399, "dur": 4.698, + "args": { + "External id": 714839,"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": 6305208254418.913, "dur": 0.669, + "args": { + "External id": 714840,"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": 6305208254430.832, "dur": 4.138, + "args": { + "External id": 714841,"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": 6305208254447.202, "dur": 12.929, + "args": { + "External id": 714842,"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": 6305208254452.809, "dur": 6.980, + "args": { + "External id": 714843,"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": 6305208254632.486, "dur": 245.152, + "args": { + "External id": 714844,"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": 6305208254637.688, "dur": 2.642, + "args": { + "External id": 714845,"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": 6305208254643.205, "dur": 233.908, + "args": { + "External id": 714846,"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": 6305208254646.838, "dur": 0.765, + "args": { + "External id": 714847,"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": 6305208254650.715, "dur": 30.071, + "args": { + "External id": 714848,"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": 6305208254683.076, "dur": 5.788, + "args": { + "External id": 714849,"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": 6305208254687.429, "dur": 0.942, + "args": { + "External id": 714850,"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": 6305208254691.343, "dur": 33.894, + "args": { + "External id": 714851,"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": 6305208254694.972, "dur": 1.060, + "args": { + "External id": 714852,"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": 6305208254699.134, "dur": 25.821, + "args": { + "External id": 714853,"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": 6305208254704.989, "dur": 4.261, + "args": { + "External id": 714854,"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": 6305208254727.668, "dur": 25.693, + "args": { + "External id": 714855,"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": 6305208254755.905, "dur": 20.184, + "args": { + "External id": 714856,"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": 6305208254780.505, "dur": 17.706, + "args": { + "External id": 714857,"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": 6305208254800.779, "dur": 16.615, + "args": { + "External id": 714858,"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": 6305208254819.858, "dur": 24.583, + "args": { + "External id": 714859,"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": 6305208254822.086, "dur": 1.327, + "args": { + "External id": 714860,"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": 6305208254827.850, "dur": 0.720, + "args": { + "External id": 714861,"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": 6305208254846.628, "dur": 15.405, + "args": { + "External id": 714862,"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": 6305208254864.370, "dur": 11.745, + "args": { + "External id": 714863,"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": 6305208254885.402, "dur": 2.764, + "args": { + "External id": 714864,"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": 6305208254896.501, "dur": 4.395, + "args": { + "External id": 714865,"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": 6305208254899.364, "dur": 0.442, + "args": { + "External id": 714866,"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": 6305208254988.745, "dur": 115.305, + "args": { + "External id": 714867,"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": 6305208255115.381, "dur": 9.147, + "args": { + "External id": 714868,"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": 6305208255119.567, "dur": 3.039, + "args": { + "External id": 714869,"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": 6305208255126.441, "dur": 35.613, + "args": { + "External id": 714870,"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": 6305208255170.063, "dur": 7.528, + "args": { + "External id": 714871,"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": 6305208255172.458, "dur": 4.411, + "args": { + "External id": 714872,"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": 6305208255175.058, "dur": 1.536, + "args": { + "External id": 714873,"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": 6305208255185.539, "dur": 61.651, + "args": { + "External id": 714874,"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": 6305208255187.003, "dur": 59.475, + "args": { + "External id": 714875,"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": 6305208255254.158, "dur": 19.675, + "args": { + "External id": 714876,"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": 6305208255282.014, "dur": 3.749, + "args": { + "External id": 714877,"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": 6305208255284.534, "dur": 0.380, + "args": { + "External id": 714878,"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": 6305208255290.670, "dur": 48.307, + "args": { + "External id": 714879,"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": 6305208255291.721, "dur": 5.607, + "args": { + "External id": 714880,"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": 6305208255294.654, "dur": 2.069, + "args": { + "External id": 714881,"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": 6305208255295.934, "dur": 0.647, + "args": { + "External id": 714882,"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": 6305208255298.154, "dur": 40.358, + "args": { + "External id": 714883,"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": 6305208255298.619, "dur": 39.447, + "args": { + "External id": 714884,"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": 6305208255343.170, "dur": 3.674, + "args": { + "External id": 714885,"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": 6305208255345.232, "dur": 0.451, + "args": { + "External id": 714886,"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": 6305208255354.095, "dur": 1.906, + "args": { + "External id": 714887,"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": 6305208255367.117, "dur": 9.589, + "args": { + "External id": 714888,"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": 6305208255369.795, "dur": 6.535, + "args": { + "External id": 714889,"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": 6305208255480.970, "dur": 210.071, + "args": { + "External id": 714890,"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": 6305208255483.791, "dur": 2.055, + "args": { + "External id": 714891,"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": 6305208255487.851, "dur": 202.597, + "args": { + "External id": 714892,"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": 6305208255489.927, "dur": 0.512, + "args": { + "External id": 714893,"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": 6305208255494.343, "dur": 40.224, + "args": { + "External id": 714894,"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": 6305208255537.588, "dur": 6.296, + "args": { + "External id": 714895,"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": 6305208255540.263, "dur": 3.356, + "args": { + "External id": 714896,"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": 6305208255545.227, "dur": 25.527, + "args": { + "External id": 714897,"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": 6305208255546.476, "dur": 1.859, + "args": { + "External id": 714898,"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": 6305208255549.948, "dur": 20.514, + "args": { + "External id": 714899,"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": 6305208255555.635, "dur": 2.360, + "args": { + "External id": 714900,"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": 6305208255572.570, "dur": 21.495, + "args": { + "External id": 714901,"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": 6305208255595.987, "dur": 12.779, + "args": { + "External id": 714902,"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": 6305208255611.654, "dur": 12.550, + "args": { + "External id": 714903,"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": 6305208255625.896, "dur": 12.192, + "args": { + "External id": 714904,"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": 6305208255643.021, "dur": 21.276, + "args": { + "External id": 714905,"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": 6305208255645.321, "dur": 2.366, + "args": { + "External id": 714906,"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": 6305208255650.162, "dur": 0.794, + "args": { + "External id": 714907,"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": 6305208255665.810, "dur": 11.615, + "args": { + "External id": 714908,"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": 6305208255678.644, "dur": 10.599, + "args": { + "External id": 714909,"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": 6305208255699.745, "dur": 2.643, + "args": { + "External id": 714910,"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": 6305208255712.948, "dur": 4.161, + "args": { + "External id": 714911,"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": 6305208255715.614, "dur": 0.607, + "args": { + "External id": 714912,"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": 6305208255793.279, "dur": 59.636, + "args": { + "External id": 714913,"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": 6305208255858.845, "dur": 5.120, + "args": { + "External id": 714914,"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": 6305208255861.883, "dur": 0.940, + "args": { + "External id": 714915,"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": 6305208255865.538, "dur": 24.582, + "args": { + "External id": 714916,"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": 6305208255894.904, "dur": 8.432, + "args": { + "External id": 714917,"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": 6305208255896.803, "dur": 5.873, + "args": { + "External id": 714918,"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": 6305208255901.211, "dur": 1.265, + "args": { + "External id": 714919,"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": 6305208255906.475, "dur": 41.802, + "args": { + "External id": 714920,"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": 6305208255907.849, "dur": 39.794, + "args": { + "External id": 714921,"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": 6305208255952.385, "dur": 14.132, + "args": { + "External id": 714922,"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": 6305208255972.637, "dur": 6.593, + "args": { + "External id": 714923,"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": 6305208255977.703, "dur": 0.624, + "args": { + "External id": 714924,"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": 6305208255984.095, "dur": 49.338, + "args": { + "External id": 714925,"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": 6305208255987.150, "dur": 6.200, + "args": { + "External id": 714926,"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": 6305208255988.537, "dur": 4.140, + "args": { + "External id": 714927,"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": 6305208255990.159, "dur": 2.254, + "args": { + "External id": 714928,"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": 6305208255993.877, "dur": 39.107, + "args": { + "External id": 714929,"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": 6305208255994.903, "dur": 37.413, + "args": { + "External id": 714930,"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": 6305208256037.391, "dur": 5.769, + "args": { + "External id": 714931,"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": 6305208256039.408, "dur": 2.529, + "args": { + "External id": 714932,"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": 6305208256050.989, "dur": 35.741, + "args": { + "External id": 714933,"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": 6305208256098.384, "dur": 7.428, + "args": { + "External id": 714934,"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": 6305208256100.964, "dur": 4.603, + "args": { + "External id": 714935,"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": 6305208256204.375, "dur": 206.625, + "args": { + "External id": 714936,"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": 6305208256207.264, "dur": 1.861, + "args": { + "External id": 714937,"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": 6305208256211.077, "dur": 199.282, + "args": { + "External id": 714938,"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": 6305208256215.024, "dur": 0.361, + "args": { + "External id": 714939,"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": 6305208256218.455, "dur": 23.959, + "args": { + "External id": 714940,"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": 6305208256244.352, "dur": 3.800, + "args": { + "External id": 714941,"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": 6305208256247.122, "dur": 0.722, + "args": { + "External id": 714942,"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": 6305208256249.105, "dur": 24.059, + "args": { + "External id": 714943,"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": 6305208256250.076, "dur": 2.922, + "args": { + "External id": 714944,"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": 6305208256254.792, "dur": 18.136, + "args": { + "External id": 714945,"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": 6305208256257.851, "dur": 2.754, + "args": { + "External id": 714946,"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": 6305208256274.840, "dur": 25.511, + "args": { + "External id": 714947,"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": 6305208256302.048, "dur": 14.030, + "args": { + "External id": 714948,"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": 6305208256322.303, "dur": 18.409, + "args": { + "External id": 714949,"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": 6305208256342.082, "dur": 13.487, + "args": { + "External id": 714950,"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": 6305208256357.604, "dur": 22.721, + "args": { + "External id": 714951,"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": 6305208256360.232, "dur": 1.894, + "args": { + "External id": 714952,"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": 6305208256364.588, "dur": 0.644, + "args": { + "External id": 714953,"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": 6305208256381.574, "dur": 13.188, + "args": { + "External id": 714954,"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": 6305208256397.657, "dur": 11.450, + "args": { + "External id": 714955,"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": 6305208256417.665, "dur": 1.900, + "args": { + "External id": 714956,"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": 6305208256429.183, "dur": 4.172, + "args": { + "External id": 714957,"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": 6305208256432.020, "dur": 0.573, + "args": { + "External id": 714958,"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": 6305208256500.595, "dur": 106.734, + "args": { + "External id": 714959,"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": 6305208256615.479, "dur": 6.513, + "args": { + "External id": 714960,"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": 6305208256619.507, "dur": 0.989, + "args": { + "External id": 714961,"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": 6305208256623.864, "dur": 29.500, + "args": { + "External id": 714962,"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": 6305208256661.052, "dur": 7.667, + "args": { + "External id": 714963,"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": 6305208256662.885, "dur": 5.201, + "args": { + "External id": 714964,"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": 6305208256665.179, "dur": 2.628, + "args": { + "External id": 714965,"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": 6305208256672.147, "dur": 45.161, + "args": { + "External id": 714966,"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": 6305208256673.310, "dur": 43.154, + "args": { + "External id": 714967,"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": 6305208256721.671, "dur": 14.488, + "args": { + "External id": 714968,"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": 6305208256742.141, "dur": 6.142, + "args": { + "External id": 714969,"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": 6305208256746.863, "dur": 0.493, + "args": { + "External id": 714970,"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": 6305208256753.055, "dur": 46.304, + "args": { + "External id": 714971,"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": 6305208256753.933, "dur": 3.521, + "args": { + "External id": 714972,"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": 6305208256754.690, "dur": 2.183, + "args": { + "External id": 714973,"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": 6305208256756.077, "dur": 0.651, + "args": { + "External id": 714974,"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": 6305208256757.965, "dur": 41.014, + "args": { + "External id": 714975,"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": 6305208256760.553, "dur": 37.747, + "args": { + "External id": 714976,"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": 6305208256802.992, "dur": 3.654, + "args": { + "External id": 714977,"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": 6305208256805.004, "dur": 0.473, + "args": { + "External id": 714978,"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": 6305208256812.708, "dur": 1.611, + "args": { + "External id": 714979,"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": 6305208256822.185, "dur": 5.977, + "args": { + "External id": 714980,"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": 6305208256824.378, "dur": 3.462, + "args": { + "External id": 714981,"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": 6305208256918.004, "dur": 215.856, + "args": { + "External id": 714982,"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": 6305208256920.261, "dur": 3.861, + "args": { + "External id": 714983,"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": 6305208256926.969, "dur": 206.340, + "args": { + "External id": 714984,"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": 6305208256928.791, "dur": 0.414, + "args": { + "External id": 714985,"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": 6305208256930.457, "dur": 19.696, + "args": { + "External id": 714986,"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": 6305208256951.801, "dur": 4.605, + "args": { + "External id": 714987,"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": 6305208256954.132, "dur": 1.983, + "args": { + "External id": 714988,"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": 6305208256957.475, "dur": 23.445, + "args": { + "External id": 714989,"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": 6305208256958.689, "dur": 1.225, + "args": { + "External id": 714990,"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": 6305208256963.657, "dur": 17.018, + "args": { + "External id": 714991,"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": 6305208256966.783, "dur": 2.286, + "args": { + "External id": 714992,"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": 6305208256982.659, "dur": 17.844, + "args": { + "External id": 714993,"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": 6305208257001.959, "dur": 13.198, + "args": { + "External id": 714994,"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": 6305208257017.677, "dur": 12.218, + "args": { + "External id": 714995,"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": 6305208257031.420, "dur": 10.975, + "args": { + "External id": 714996,"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": 6305208257044.226, "dur": 59.422, + "args": { + "External id": 714997,"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": 6305208257046.738, "dur": 1.364, + "args": { + "External id": 714998,"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": 6305208257050.252, "dur": 36.089, + "args": { + "External id": 714999,"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": 6305208257108.399, "dur": 11.715, + "args": { + "External id": 715000,"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": 6305208257121.181, "dur": 10.808, + "args": { + "External id": 715001,"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": 6305208257142.960, "dur": 2.478, + "args": { + "External id": 715002,"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": 6305208257155.566, "dur": 4.222, + "args": { + "External id": 715003,"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": 6305208257158.157, "dur": 0.704, + "args": { + "External id": 715004,"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": 6305208257229.774, "dur": 58.547, + "args": { + "External id": 715005,"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": 6305208257293.692, "dur": 4.684, + "args": { + "External id": 715006,"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": 6305208257296.635, "dur": 0.779, + "args": { + "External id": 715007,"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": 6305208257301.920, "dur": 23.998, + "args": { + "External id": 715008,"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": 6305208257330.784, "dur": 6.416, + "args": { + "External id": 715009,"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": 6305208257332.600, "dur": 3.624, + "args": { + "External id": 715010,"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": 6305208257334.704, "dur": 1.327, + "args": { + "External id": 715011,"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": 6305208257340.214, "dur": 41.112, + "args": { + "External id": 715012,"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": 6305208257341.256, "dur": 39.585, + "args": { + "External id": 715013,"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": 6305208257385.365, "dur": 13.859, + "args": { + "External id": 715014,"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": 6305208257407.021, "dur": 3.365, + "args": { + "External id": 715015,"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": 6305208257409.001, "dur": 0.580, + "args": { + "External id": 715016,"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": 6305208257414.169, "dur": 49.329, + "args": { + "External id": 715017,"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": 6305208257414.967, "dur": 4.184, + "args": { + "External id": 715018,"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": 6305208257416.112, "dur": 2.459, + "args": { + "External id": 715019,"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": 6305208257417.671, "dur": 0.777, + "args": { + "External id": 715020,"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": 6305208257422.169, "dur": 40.802, + "args": { + "External id": 715021,"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": 6305208257423.055, "dur": 39.376, + "args": { + "External id": 715022,"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": 6305208257467.931, "dur": 3.615, + "args": { + "External id": 715023,"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": 6305208257470.046, "dur": 0.409, + "args": { + "External id": 715024,"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": 6305208257477.344, "dur": 1.293, + "args": { + "External id": 715025,"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": 6305208257486.682, "dur": 9.466, + "args": { + "External id": 715026,"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": 6305208257491.335, "dur": 4.512, + "args": { + "External id": 715027,"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": 6305208257601.111, "dur": 185.428, + "args": { + "External id": 715028,"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": 6305208257607.129, "dur": 2.578, + "args": { + "External id": 715029,"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": 6305208257611.222, "dur": 174.851, + "args": { + "External id": 715030,"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": 6305208257612.972, "dur": 0.280, + "args": { + "External id": 715031,"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": 6305208257614.784, "dur": 21.721, + "args": { + "External id": 715032,"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": 6305208257638.347, "dur": 5.970, + "args": { + "External id": 715033,"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": 6305208257643.064, "dur": 0.960, + "args": { + "External id": 715034,"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": 6305208257645.569, "dur": 22.726, + "args": { + "External id": 715035,"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": 6305208257648.641, "dur": 1.177, + "args": { + "External id": 715036,"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": 6305208257651.435, "dur": 16.571, + "args": { + "External id": 715037,"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": 6305208257654.455, "dur": 3.102, + "args": { + "External id": 715038,"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": 6305208257669.730, "dur": 21.792, + "args": { + "External id": 715039,"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": 6305208257692.978, "dur": 11.888, + "args": { + "External id": 715040,"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": 6305208257708.185, "dur": 12.771, + "args": { + "External id": 715041,"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": 6305208257722.366, "dur": 11.363, + "args": { + "External id": 715042,"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": 6305208257735.602, "dur": 24.555, + "args": { + "External id": 715043,"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": 6305208257740.060, "dur": 1.804, + "args": { + "External id": 715044,"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": 6305208257746.502, "dur": 0.734, + "args": { + "External id": 715045,"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": 6305208257761.563, "dur": 11.532, + "args": { + "External id": 715046,"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": 6305208257774.191, "dur": 10.800, + "args": { + "External id": 715047,"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": 6305208257793.406, "dur": 2.181, + "args": { + "External id": 715048,"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": 6305208257805.496, "dur": 4.315, + "args": { + "External id": 715049,"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": 6305208257808.216, "dur": 0.647, + "args": { + "External id": 715050,"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": 6305208257874.313, "dur": 58.122, + "args": { + "External id": 715051,"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": 6305208257946.065, "dur": 5.759, + "args": { + "External id": 715052,"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": 6305208257950.028, "dur": 0.718, + "args": { + "External id": 715053,"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": 6305208257953.377, "dur": 23.197, + "args": { + "External id": 715054,"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": 6305208257980.646, "dur": 6.648, + "args": { + "External id": 715055,"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": 6305208257982.130, "dur": 4.271, + "args": { + "External id": 715056,"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": 6305208257983.852, "dur": 2.370, + "args": { + "External id": 715057,"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": 6305208257992.451, "dur": 42.959, + "args": { + "External id": 715058,"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": 6305208257993.463, "dur": 41.186, + "args": { + "External id": 715059,"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": 6305208258039.474, "dur": 48.982, + "args": { + "External id": 715060,"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": 6305208258098.289, "dur": 4.841, + "args": { + "External id": 715061,"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": 6305208258101.293, "dur": 0.676, + "args": { + "External id": 715062,"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": 6305208258107.732, "dur": 58.684, + "args": { + "External id": 715063,"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": 6305208258108.691, "dur": 7.288, + "args": { + "External id": 715064,"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": 6305208258112.771, "dur": 2.473, + "args": { + "External id": 715065,"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": 6305208258114.120, "dur": 0.920, + "args": { + "External id": 715066,"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": 6305208258116.951, "dur": 49.001, + "args": { + "External id": 715067,"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": 6305208258119.998, "dur": 45.367, + "args": { + "External id": 715068,"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": 6305208258170.886, "dur": 3.883, + "args": { + "External id": 715069,"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": 6305208258172.812, "dur": 0.697, + "args": { + "External id": 715070,"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": 6305208258181.597, "dur": 1.837, + "args": { + "External id": 715071,"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": 6305208258194.525, "dur": 9.859, + "args": { + "External id": 715072,"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": 6305208258196.601, "dur": 7.470, + "args": { + "External id": 715073,"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": 6305208258301.002, "dur": 175.300, + "args": { + "External id": 715074,"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": 6305208258302.983, "dur": 1.813, + "args": { + "External id": 715075,"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": 6305208258306.436, "dur": 169.414, + "args": { + "External id": 715076,"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": 6305208258308.005, "dur": 0.401, + "args": { + "External id": 715077,"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": 6305208258311.686, "dur": 23.597, + "args": { + "External id": 715078,"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": 6305208258336.943, "dur": 2.825, + "args": { + "External id": 715079,"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": 6305208258338.746, "dur": 0.634, + "args": { + "External id": 715080,"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": 6305208258340.915, "dur": 21.625, + "args": { + "External id": 715081,"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": 6305208258341.911, "dur": 1.091, + "args": { + "External id": 715082,"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": 6305208258344.242, "dur": 18.015, + "args": { + "External id": 715083,"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": 6305208258349.251, "dur": 2.257, + "args": { + "External id": 715084,"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": 6305208258364.151, "dur": 19.103, + "args": { + "External id": 715085,"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": 6305208258385.089, "dur": 12.776, + "args": { + "External id": 715086,"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": 6305208258400.042, "dur": 12.703, + "args": { + "External id": 715087,"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": 6305208258414.098, "dur": 11.515, + "args": { + "External id": 715088,"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": 6305208258429.991, "dur": 18.841, + "args": { + "External id": 715089,"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": 6305208258432.120, "dur": 1.498, + "args": { + "External id": 715090,"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": 6305208258435.806, "dur": 0.465, + "args": { + "External id": 715091,"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": 6305208258450.100, "dur": 11.710, + "args": { + "External id": 715092,"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": 6305208258462.951, "dur": 11.687, + "args": { + "External id": 715093,"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": 6305208258482.665, "dur": 1.511, + "args": { + "External id": 715094,"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": 6305208258493.165, "dur": 3.560, + "args": { + "External id": 715095,"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": 6305208258495.401, "dur": 0.505, + "args": { + "External id": 715096,"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": 6305208258585.104, "dur": 58.177, + "args": { + "External id": 715097,"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": 6305208258649.483, "dur": 6.030, + "args": { + "External id": 715098,"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": 6305208258653.135, "dur": 1.040, + "args": { + "External id": 715099,"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": 6305208258656.782, "dur": 24.675, + "args": { + "External id": 715100,"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": 6305208258686.132, "dur": 13.984, + "args": { + "External id": 715101,"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": 6305208258687.906, "dur": 11.436, + "args": { + "External id": 715102,"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": 6305208258698.265, "dur": 0.864, + "args": { + "External id": 715103,"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": 6305208258703.112, "dur": 42.877, + "args": { + "External id": 715104,"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": 6305208258704.265, "dur": 41.207, + "args": { + "External id": 715105,"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": 6305208258750.636, "dur": 14.367, + "args": { + "External id": 715106,"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": 6305208258771.098, "dur": 3.795, + "args": { + "External id": 715107,"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": 6305208258773.542, "dur": 0.551, + "args": { + "External id": 715108,"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": 6305208258779.046, "dur": 51.889, + "args": { + "External id": 715109,"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": 6305208258782.139, "dur": 6.105, + "args": { + "External id": 715110,"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": 6305208258783.266, "dur": 4.369, + "args": { + "External id": 715111,"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": 6305208258785.162, "dur": 2.331, + "args": { + "External id": 715112,"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": 6305208258789.044, "dur": 41.371, + "args": { + "External id": 715113,"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": 6305208258789.689, "dur": 40.216, + "args": { + "External id": 715114,"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": 6305208258835.178, "dur": 3.790, + "args": { + "External id": 715115,"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": 6305208258837.513, "dur": 0.346, + "args": { + "External id": 715116,"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": 6305208258847.185, "dur": 1.601, + "args": { + "External id": 715117,"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": 6305208258857.005, "dur": 5.873, + "args": { + "External id": 715118,"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": 6305208258858.996, "dur": 3.610, + "args": { + "External id": 715119,"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": 6305208258944.376, "dur": 233.800, + "args": { + "External id": 715120,"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": 6305208258946.691, "dur": 1.805, + "args": { + "External id": 715121,"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": 6305208258950.189, "dur": 227.406, + "args": { + "External id": 715122,"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": 6305208258954.732, "dur": 0.342, + "args": { + "External id": 715123,"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": 6305208258957.865, "dur": 22.109, + "args": { + "External id": 715124,"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": 6305208258981.707, "dur": 3.573, + "args": { + "External id": 715125,"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": 6305208258984.292, "dur": 0.721, + "args": { + "External id": 715126,"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": 6305208258986.552, "dur": 23.489, + "args": { + "External id": 715127,"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": 6305208258987.809, "dur": 2.724, + "args": { + "External id": 715128,"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": 6305208258992.246, "dur": 17.527, + "args": { + "External id": 715129,"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": 6305208258994.758, "dur": 2.567, + "args": { + "External id": 715130,"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": 6305208259011.285, "dur": 22.674, + "args": { + "External id": 715131,"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": 6305208259035.579, "dur": 14.804, + "args": { + "External id": 715132,"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": 6305208259091.213, "dur": 17.601, + "args": { + "External id": 715133,"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": 6305208259110.661, "dur": 13.879, + "args": { + "External id": 715134,"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": 6305208259126.869, "dur": 21.336, + "args": { + "External id": 715135,"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": 6305208259128.984, "dur": 1.983, + "args": { + "External id": 715136,"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": 6305208259132.778, "dur": 0.655, + "args": { + "External id": 715137,"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": 6305208259149.583, "dur": 13.174, + "args": { + "External id": 715138,"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": 6305208259166.051, "dur": 10.526, + "args": { + "External id": 715139,"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": 6305208259186.531, "dur": 2.187, + "args": { + "External id": 715140,"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": 6305208259198.845, "dur": 3.697, + "args": { + "External id": 715141,"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": 6305208259201.192, "dur": 0.502, + "args": { + "External id": 715142,"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": 6305208259272.084, "dur": 56.189, + "args": { + "External id": 715143,"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": 6305208259333.648, "dur": 4.831, + "args": { + "External id": 715144,"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": 6305208259336.626, "dur": 0.832, + "args": { + "External id": 715145,"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": 6305208259339.892, "dur": 21.609, + "args": { + "External id": 715146,"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": 6305208259368.321, "dur": 7.061, + "args": { + "External id": 715147,"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": 6305208259369.954, "dur": 4.544, + "args": { + "External id": 715148,"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": 6305208259371.734, "dur": 2.524, + "args": { + "External id": 715149,"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": 6305208259378.488, "dur": 41.631, + "args": { + "External id": 715150,"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": 6305208259379.827, "dur": 39.730, + "args": { + "External id": 715151,"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": 6305208259424.241, "dur": 13.580, + "args": { + "External id": 715152,"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": 6305208259443.425, "dur": 6.287, + "args": { + "External id": 715153,"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": 6305208259448.278, "dur": 0.552, + "args": { + "External id": 715154,"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": 6305208259454.102, "dur": 45.807, + "args": { + "External id": 715155,"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": 6305208259455.035, "dur": 3.879, + "args": { + "External id": 715156,"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": 6305208259456.053, "dur": 2.289, + "args": { + "External id": 715157,"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": 6305208259457.514, "dur": 0.705, + "args": { + "External id": 715158,"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": 6305208259459.664, "dur": 39.759, + "args": { + "External id": 715159,"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": 6305208259462.525, "dur": 36.356, + "args": { + "External id": 715160,"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": 6305208259504.074, "dur": 19.957, + "args": { + "External id": 715161,"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": 6305208259521.278, "dur": 0.784, + "args": { + "External id": 715162,"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": 6305208259530.961, "dur": 1.877, + "args": { + "External id": 715163,"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": 6305208259540.803, "dur": 7.095, + "args": { + "External id": 715164,"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": 6305208259543.025, "dur": 4.570, + "args": { + "External id": 715165,"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": 6305208259633.189, "dur": 179.575, + "args": { + "External id": 715166,"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": 6305208259635.187, "dur": 3.851, + "args": { + "External id": 715167,"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": 6305208259642.584, "dur": 169.776, + "args": { + "External id": 715168,"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": 6305208259643.947, "dur": 0.571, + "args": { + "External id": 715169,"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": 6305208259645.745, "dur": 19.915, + "args": { + "External id": 715170,"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": 6305208259667.509, "dur": 8.304, + "args": { + "External id": 715171,"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": 6305208259673.569, "dur": 1.947, + "args": { + "External id": 715172,"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": 6305208259677.076, "dur": 21.963, + "args": { + "External id": 715173,"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": 6305208259680.772, "dur": 1.197, + "args": { + "External id": 715174,"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": 6305208259683.167, "dur": 15.625, + "args": { + "External id": 715175,"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": 6305208259685.802, "dur": 2.453, + "args": { + "External id": 715176,"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": 6305208259700.460, "dur": 18.341, + "args": { + "External id": 715177,"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": 6305208259720.142, "dur": 12.695, + "args": { + "External id": 715178,"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": 6305208259735.131, "dur": 12.231, + "args": { + "External id": 715179,"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": 6305208259748.576, "dur": 11.520, + "args": { + "External id": 715180,"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": 6305208259761.766, "dur": 23.619, + "args": { + "External id": 715181,"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": 6305208259763.907, "dur": 1.701, + "args": { + "External id": 715182,"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": 6305208259769.634, "dur": 3.023, + "args": { + "External id": 715183,"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": 6305208259786.782, "dur": 12.238, + "args": { + "External id": 715184,"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": 6305208259800.009, "dur": 11.220, + "args": { + "External id": 715185,"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": 6305208259819.067, "dur": 1.698, + "args": { + "External id": 715186,"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": 6305208259829.254, "dur": 3.384, + "args": { + "External id": 715187,"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": 6305208259831.429, "dur": 0.394, + "args": { + "External id": 715188,"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": 6305208259892.968, "dur": 54.938, + "args": { + "External id": 715189,"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": 6305208259953.074, "dur": 7.500, + "args": { + "External id": 715190,"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": 6305208259958.796, "dur": 0.614, + "args": { + "External id": 715191,"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": 6305208259962.180, "dur": 27.583, + "args": { + "External id": 715192,"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": 6305208259994.326, "dur": 6.137, + "args": { + "External id": 715193,"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": 6305208259996.038, "dur": 3.622, + "args": { + "External id": 715194,"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": 6305208259998.289, "dur": 1.215, + "args": { + "External id": 715195,"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": 6305208260003.278, "dur": 40.777, + "args": { + "External id": 715196,"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": 6305208260004.410, "dur": 39.060, + "args": { + "External id": 715197,"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": 6305208260050.103, "dur": 50.262, + "args": { + "External id": 715198,"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": 6305208260107.630, "dur": 28.027, + "args": { + "External id": 715199,"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": 6305208260110.615, "dur": 24.682, + "args": { + "External id": 715200,"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": 6305208260116.352, "dur": 0.909, + "args": { + "External id": 715201,"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": 6305208260141.822, "dur": 30.165, + "args": { + "External id": 715202,"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": 6305208260143.574, "dur": 28.209, + "args": { + "External id": 715203,"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": 6305208260148.610, "dur": 4.534, + "args": { + "External id": 715204,"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": 6305208260154.888, "dur": 16.470, + "args": { + "External id": 715205,"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": 6305208260189.872, "dur": 6.248, + "args": { + "External id": 715206,"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": 6305208260192.005, "dur": 3.837, + "args": { + "External id": 715207,"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": 6305208260197.290, "dur": 1.508, + "args": { + "External id": 715208,"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": 6305208260198.039, "dur": 0.688, + "args": { + "External id": 715209,"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": 6305208260243.907, "dur": 25.176, + "args": { + "External id": 715210,"Sequence number": 7674820, "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": 6305208260243.907, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338707, "tid": 2338707, + "ts": 6305208260275.824, "dur": 6.491, + "args": { + "External id": 715211,"Sequence number": 7674821, "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": 6305208260279.807, "dur": 0.994, + "args": { + "External id": 715212,"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": 6305208260287.639, "dur": 6.725, + "args": { + "External id": 715213,"Sequence number": 7674821, "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": 6305208260292.451, "dur": 0.574, + "args": { + "External id": 715214,"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": 6305208260295.746, "dur": 2.932, + "args": { + "External id": 715215,"Sequence number": 7674821, "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": 6305208260297.583, "dur": 0.464, + "args": { + "External id": 715216,"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": 6305208260302.859, "dur": 7.526, + "args": { + "External id": 715217,"Sequence number": 7674821, "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": 6305208260302.859, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2338707, + "ts": 6305208260308.242, "dur": 0.801, + "args": { + "External id": 715218,"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": 6305208260311.402, "dur": 4.790, + "args": { + "External id": 715219,"Sequence number": 7674822, "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": 6305208260311.402, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2338707, + "ts": 6305208260315.007, "dur": 0.465, + "args": { + "External id": 715220,"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": 6305208260317.467, "dur": 7.807, + "args": { + "External id": 715221,"Sequence number": 7674823, "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": 6305208260317.467, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2338707, + "ts": 6305208260323.898, "dur": 0.543, + "args": { + "External id": 715222,"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": 6305208260326.428, "dur": 7.237, + "args": { + "External id": 715223,"Sequence number": 7674824, "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": 6305208260326.428, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2338707, + "ts": 6305208260330.157, "dur": 2.774, + "args": { + "External id": 715224,"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": 6305208260337.955, "dur": 30.571, + "args": { + "External id": 715225,"Sequence number": 7674825, "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": 6305208260339.653, "dur": 28.674, + "args": { + "External id": 715226,"Sequence number": 7674825, "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": 6305208260342.720, "dur": 6.155, + "args": { + "External id": 715227,"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": 6305208260344.738, "dur": 3.616, + "args": { + "External id": 715228,"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": 6305208260349.751, "dur": 18.068, + "args": { + "External id": 715229,"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": 6305208260396.472, "dur": 5.966, + "args": { + "External id": 715230,"Sequence number": 7674825, "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": 6305208260396.472, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6305208260407.337, "dur": 1.203, + "args": { + "External id": 715231,"Sequence number": 7674826, "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": 6305208260439.752, "dur": 48877.518, + "args": { + "External id": 715232,"Sequence number": 7674826, "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": 6305208260439.752, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338707, "tid": 2338707, + "ts": 6305208260456.712, "dur": 26.555, + "args": { + "External id": 715233,"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": 6305208260457.681, "dur": 25.357, + "args": { + "External id": 715234,"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": 6305208260459.102, "dur": 5.063, + "args": { + "External id": 715235,"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": 6305208260460.661, "dur": 3.186, + "args": { + "External id": 715236,"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": 6305208260465.069, "dur": 17.500, + "args": { + "External id": 715237,"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": 6305208260499.146, "dur": 48.881, + "args": { + "External id": 715238,"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": 6305208260500.464, "dur": 20.166, + "args": { + "External id": 715239,"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": 6305208260502.487, "dur": 2.437, + "args": { + "External id": 715240,"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": 6305208260523.020, "dur": 24.792, + "args": { + "External id": 715241,"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": 6305208260527.894, "dur": 19.511, + "args": { + "External id": 715242,"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": 6305208260553.209, "dur": 21.358, + "args": { + "External id": 715243,"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": 6305208260554.045, "dur": 5.900, + "args": { + "External id": 715244,"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": 6305208260555.477, "dur": 4.247, + "args": { + "External id": 715245,"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": 6305208260560.399, "dur": 13.977, + "args": { + "External id": 715246,"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": 6305208260561.063, "dur": 13.002, + "args": { + "External id": 715247,"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": 6305208260582.187, "dur": 21.885, + "args": { + "External id": 715248,"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": 6305208260585.725, "dur": 2.746, + "args": { + "External id": 715249,"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": 6305208260589.046, "dur": 14.705, + "args": { + "External id": 715250,"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": 6305208260591.769, "dur": 11.709, + "args": { + "External id": 715251,"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": 6305208260609.034, "dur": 23.560, + "args": { + "External id": 715252,"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": 6305208260635.254, "dur": 50.059, + "args": { + "External id": 715253,"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": 6305208260637.495, "dur": 47.411, + "args": { + "External id": 715254,"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": 6305208260641.511, "dur": 0.846, + "args": { + "External id": 715255,"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": 6305208260643.587, "dur": 24.745, + "args": { + "External id": 715256,"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": 6305208260645.222, "dur": 22.916, + "args": { + "External id": 715257,"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": 6305208260649.750, "dur": 2.481, + "args": { + "External id": 715258,"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": 6305208260653.219, "dur": 14.473, + "args": { + "External id": 715259,"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": 6305208260689.730, "dur": 42844.803, + "args": { + "External id": 715260,"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": 6305208260691.775, "dur": 42841.223, + "args": { + "External id": 715261,"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": 6305208303549.041, "dur": 7.450, + "args": { + "External id": 715262,"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": 6305208303553.480, "dur": 1.239, + "args": { + "External id": 715263,"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": 6305208303562.175, "dur": 132.992, + "args": { + "External id": 715264,"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": 6305208303581.657, "dur": 6.657, + "args": { + "External id": 715265,"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": 6305208303584.422, "dur": 2.943, + "args": { + "External id": 715266,"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": 6305208303586.386, "dur": 0.714, + "args": { + "External id": 715267,"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": 6305208303591.817, "dur": 102.587, + "args": { + "External id": 715268,"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": 6305208303593.572, "dur": 100.224, + "args": { + "External id": 715269,"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": 6305208303699.678, "dur": 5.024, + "args": { + "External id": 715270,"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": 6305208303701.972, "dur": 0.586, + "args": { + "External id": 715271,"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": 6305208303712.681, "dur": 2.136, + "args": { + "External id": 715272,"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": 6305208303726.168, "dur": 8.373, + "args": { + "External id": 715273,"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": 6305208303730.144, "dur": 4.091, + "args": { + "External id": 715274,"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": 6305208303876.592, "dur": 243.534, + "args": { + "External id": 715275,"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": 6305208303881.524, "dur": 1.604, + "args": { + "External id": 715276,"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": 6305208303884.831, "dur": 234.646, + "args": { + "External id": 715277,"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": 6305208303886.339, "dur": 0.487, + "args": { + "External id": 715278,"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": 6305208303888.246, "dur": 29.100, + "args": { + "External id": 715279,"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": 6305208303919.073, "dur": 4.996, + "args": { + "External id": 715280,"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": 6305208303923.072, "dur": 0.726, + "args": { + "External id": 715281,"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": 6305208303925.151, "dur": 28.863, + "args": { + "External id": 715282,"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": 6305208303928.706, "dur": 0.920, + "args": { + "External id": 715283,"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": 6305208303931.097, "dur": 22.652, + "args": { + "External id": 715284,"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": 6305208303935.245, "dur": 3.392, + "args": { + "External id": 715285,"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": 6305208303955.847, "dur": 23.859, + "args": { + "External id": 715286,"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": 6305208303981.693, "dur": 18.852, + "args": { + "External id": 715287,"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": 6305208304003.579, "dur": 14.398, + "args": { + "External id": 715288,"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": 6305208304019.726, "dur": 12.457, + "args": { + "External id": 715289,"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": 6305208304033.833, "dur": 55.124, + "args": { + "External id": 715290,"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": 6305208304036.284, "dur": 1.669, + "args": { + "External id": 715291,"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": 6305208304042.501, "dur": 0.452, + "args": { + "External id": 715292,"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": 6305208304092.043, "dur": 13.755, + "args": { + "External id": 715293,"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": 6305208304107.356, "dur": 11.018, + "args": { + "External id": 715294,"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": 6305208304129.320, "dur": 2.574, + "args": { + "External id": 715295,"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": 6305208304139.524, "dur": 4.242, + "args": { + "External id": 715296,"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": 6305208304142.253, "dur": 0.571, + "args": { + "External id": 715297,"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": 6305208304226.760, "dur": 73.221, + "args": { + "External id": 715298,"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": 6305208304308.060, "dur": 6.850, + "args": { + "External id": 715299,"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": 6305208304311.208, "dur": 0.867, + "args": { + "External id": 715300,"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": 6305208304316.707, "dur": 26.893, + "args": { + "External id": 715301,"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": 6305208304352.791, "dur": 7.383, + "args": { + "External id": 715302,"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": 6305208304354.571, "dur": 4.929, + "args": { + "External id": 715303,"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": 6305208304356.599, "dur": 2.608, + "args": { + "External id": 715304,"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": 6305208304366.113, "dur": 48.511, + "args": { + "External id": 715305,"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": 6305208304367.617, "dur": 46.237, + "args": { + "External id": 715306,"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": 6305208304419.404, "dur": 14.942, + "args": { + "External id": 715307,"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": 6305208304441.065, "dur": 4.095, + "args": { + "External id": 715308,"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": 6305208304443.666, "dur": 0.598, + "args": { + "External id": 715309,"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": 6305208304449.651, "dur": 46.950, + "args": { + "External id": 715310,"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": 6305208304450.668, "dur": 5.993, + "args": { + "External id": 715311,"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": 6305208304453.610, "dur": 2.420, + "args": { + "External id": 715312,"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": 6305208304455.187, "dur": 0.674, + "args": { + "External id": 715313,"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": 6305208304457.354, "dur": 38.780, + "args": { + "External id": 715314,"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": 6305208304458.020, "dur": 37.560, + "args": { + "External id": 715315,"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": 6305208304501.271, "dur": 18.576, + "args": { + "External id": 715316,"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": 6305208304503.374, "dur": 0.310, + "args": { + "External id": 715317,"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": 6305208304528.504, "dur": 2.257, + "args": { + "External id": 715318,"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": 6305208304541.721, "dur": 7.579, + "args": { + "External id": 715319,"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": 6305208304544.194, "dur": 4.834, + "args": { + "External id": 715320,"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": 6305208304652.882, "dur": 188.286, + "args": { + "External id": 715321,"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": 6305208304655.086, "dur": 1.824, + "args": { + "External id": 715322,"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": 6305208304660.162, "dur": 180.381, + "args": { + "External id": 715323,"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": 6305208304661.478, "dur": 0.524, + "args": { + "External id": 715324,"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": 6305208304665.713, "dur": 21.864, + "args": { + "External id": 715325,"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": 6305208304689.206, "dur": 5.262, + "args": { + "External id": 715326,"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": 6305208304691.898, "dur": 2.277, + "args": { + "External id": 715327,"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": 6305208304695.498, "dur": 23.676, + "args": { + "External id": 715328,"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": 6305208304696.664, "dur": 3.238, + "args": { + "External id": 715329,"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": 6305208304701.373, "dur": 17.529, + "args": { + "External id": 715330,"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": 6305208304704.727, "dur": 2.510, + "args": { + "External id": 715331,"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": 6305208304721.008, "dur": 21.929, + "args": { + "External id": 715332,"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": 6305208304744.528, "dur": 12.704, + "args": { + "External id": 715333,"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": 6305208304760.266, "dur": 13.514, + "args": { + "External id": 715334,"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": 6305208304775.711, "dur": 12.415, + "args": { + "External id": 715335,"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": 6305208304792.906, "dur": 21.941, + "args": { + "External id": 715336,"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": 6305208304795.011, "dur": 2.169, + "args": { + "External id": 715337,"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": 6305208304799.407, "dur": 2.329, + "args": { + "External id": 715338,"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": 6305208304816.464, "dur": 11.078, + "args": { + "External id": 715339,"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": 6305208304828.555, "dur": 10.639, + "args": { + "External id": 715340,"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": 6305208304848.375, "dur": 1.850, + "args": { + "External id": 715341,"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": 6305208304860.204, "dur": 4.238, + "args": { + "External id": 715342,"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": 6305208304862.991, "dur": 0.595, + "args": { + "External id": 715343,"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": 6305208304933.460, "dur": 58.136, + "args": { + "External id": 715344,"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": 6305208304996.510, "dur": 5.241, + "args": { + "External id": 715345,"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": 6305208304999.913, "dur": 0.611, + "args": { + "External id": 715346,"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": 6305208305003.308, "dur": 24.425, + "args": { + "External id": 715347,"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": 6305208305032.312, "dur": 8.059, + "args": { + "External id": 715348,"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": 6305208305033.909, "dur": 5.742, + "args": { + "External id": 715349,"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": 6305208305038.171, "dur": 1.280, + "args": { + "External id": 715350,"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": 6305208305043.209, "dur": 82.197, + "args": { + "External id": 715351,"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": 6305208305044.369, "dur": 79.734, + "args": { + "External id": 715352,"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": 6305208305131.177, "dur": 16.014, + "args": { + "External id": 715353,"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": 6305208305154.053, "dur": 5.209, + "args": { + "External id": 715354,"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": 6305208305157.148, "dur": 0.818, + "args": { + "External id": 715355,"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": 6305208305163.640, "dur": 50.671, + "args": { + "External id": 715356,"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": 6305208305166.854, "dur": 4.448, + "args": { + "External id": 715357,"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": 6305208305167.913, "dur": 2.743, + "args": { + "External id": 715358,"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": 6305208305169.928, "dur": 0.563, + "args": { + "External id": 715359,"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": 6305208305171.841, "dur": 41.981, + "args": { + "External id": 715360,"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": 6305208305172.688, "dur": 40.641, + "args": { + "External id": 715361,"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": 6305208305218.658, "dur": 3.795, + "args": { + "External id": 715362,"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": 6305208305220.441, "dur": 0.649, + "args": { + "External id": 715363,"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": 6305208305230.775, "dur": 1.515, + "args": { + "External id": 715364,"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": 6305208305240.876, "dur": 8.544, + "args": { + "External id": 715365,"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": 6305208305242.717, "dur": 6.460, + "args": { + "External id": 715366,"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": 6305208305340.151, "dur": 209.603, + "args": { + "External id": 715367,"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": 6305208305344.816, "dur": 1.774, + "args": { + "External id": 715368,"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": 6305208305347.772, "dur": 201.608, + "args": { + "External id": 715369,"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": 6305208305351.392, "dur": 0.495, + "args": { + "External id": 715370,"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": 6305208305353.180, "dur": 21.237, + "args": { + "External id": 715371,"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": 6305208305376.246, "dur": 4.836, + "args": { + "External id": 715372,"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": 6305208305380.157, "dur": 0.715, + "args": { + "External id": 715373,"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": 6305208305382.331, "dur": 23.430, + "args": { + "External id": 715374,"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": 6305208305383.487, "dur": 1.148, + "args": { + "External id": 715375,"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": 6305208305386.006, "dur": 19.505, + "args": { + "External id": 715376,"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": 6305208305389.189, "dur": 3.139, + "args": { + "External id": 715377,"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": 6305208305407.497, "dur": 18.541, + "args": { + "External id": 715378,"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": 6305208305427.586, "dur": 17.283, + "args": { + "External id": 715379,"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": 6305208305450.239, "dur": 13.477, + "args": { + "External id": 715380,"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": 6305208305465.356, "dur": 13.070, + "args": { + "External id": 715381,"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": 6305208305480.187, "dur": 21.471, + "args": { + "External id": 715382,"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": 6305208305482.427, "dur": 1.692, + "args": { + "External id": 715383,"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": 6305208305486.573, "dur": 0.507, + "args": { + "External id": 715384,"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": 6305208305503.066, "dur": 29.204, + "args": { + "External id": 715385,"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": 6305208305536.644, "dur": 11.218, + "args": { + "External id": 715386,"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": 6305208305557.576, "dur": 2.118, + "args": { + "External id": 715387,"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": 6305208305570.189, "dur": 4.084, + "args": { + "External id": 715388,"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": 6305208305572.791, "dur": 0.629, + "args": { + "External id": 715389,"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": 6305208305647.814, "dur": 58.608, + "args": { + "External id": 715390,"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": 6305208305711.178, "dur": 4.836, + "args": { + "External id": 715391,"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": 6305208305714.236, "dur": 0.691, + "args": { + "External id": 715392,"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": 6305208305717.898, "dur": 30.341, + "args": { + "External id": 715393,"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": 6305208305755.313, "dur": 6.025, + "args": { + "External id": 715394,"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": 6305208305757.183, "dur": 3.519, + "args": { + "External id": 715395,"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": 6305208305759.371, "dur": 1.169, + "args": { + "External id": 715396,"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": 6305208305763.976, "dur": 72.742, + "args": { + "External id": 715397,"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": 6305208305765.000, "dur": 71.088, + "args": { + "External id": 715398,"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": 6305208305840.257, "dur": 27.853, + "args": { + "External id": 715399,"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": 6305208305874.231, "dur": 5.617, + "args": { + "External id": 715400,"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": 6305208305878.382, "dur": 0.600, + "args": { + "External id": 715401,"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": 6305208305883.854, "dur": 47.818, + "args": { + "External id": 715402,"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": 6305208305884.620, "dur": 3.666, + "args": { + "External id": 715403,"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": 6305208305885.378, "dur": 2.353, + "args": { + "External id": 715404,"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": 6305208305886.811, "dur": 0.555, + "args": { + "External id": 715405,"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": 6305208305888.911, "dur": 42.270, + "args": { + "External id": 715406,"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": 6305208305891.823, "dur": 38.830, + "args": { + "External id": 715407,"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": 6305208305935.939, "dur": 3.786, + "args": { + "External id": 715408,"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": 6305208305937.746, "dur": 0.567, + "args": { + "External id": 715409,"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": 6305208305944.936, "dur": 1.296, + "args": { + "External id": 715410,"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": 6305208305954.007, "dur": 9.932, + "args": { + "External id": 715411,"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": 6305208305956.251, "dur": 7.372, + "args": { + "External id": 715412,"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": 6305208306049.098, "dur": 232.764, + "args": { + "External id": 715413,"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": 6305208306051.420, "dur": 40.040, + "args": { + "External id": 715414,"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": 6305208306094.399, "dur": 187.030, + "args": { + "External id": 715415,"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": 6305208306096.039, "dur": 0.535, + "args": { + "External id": 715416,"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": 6305208306097.747, "dur": 29.087, + "args": { + "External id": 715417,"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": 6305208306128.351, "dur": 3.234, + "args": { + "External id": 715418,"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": 6305208306130.564, "dur": 0.735, + "args": { + "External id": 715419,"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": 6305208306132.670, "dur": 26.269, + "args": { + "External id": 715420,"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": 6305208306133.696, "dur": 1.189, + "args": { + "External id": 715421,"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": 6305208306138.170, "dur": 20.434, + "args": { + "External id": 715422,"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": 6305208306142.952, "dur": 2.314, + "args": { + "External id": 715423,"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": 6305208306160.508, "dur": 22.592, + "args": { + "External id": 715424,"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": 6305208306184.601, "dur": 13.430, + "args": { + "External id": 715425,"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": 6305208306200.565, "dur": 15.135, + "args": { + "External id": 715426,"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": 6305208306220.732, "dur": 12.319, + "args": { + "External id": 715427,"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": 6305208306234.690, "dur": 19.403, + "args": { + "External id": 715428,"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": 6305208306236.825, "dur": 1.555, + "args": { + "External id": 715429,"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": 6305208306240.656, "dur": 0.555, + "args": { + "External id": 715430,"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": 6305208306257.587, "dur": 11.099, + "args": { + "External id": 715431,"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": 6305208306269.767, "dur": 10.671, + "args": { + "External id": 715432,"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": 6305208306290.438, "dur": 2.647, + "args": { + "External id": 715433,"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": 6305208306302.974, "dur": 3.893, + "args": { + "External id": 715434,"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": 6305208306305.552, "dur": 0.455, + "args": { + "External id": 715435,"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": 6305208306374.115, "dur": 57.166, + "args": { + "External id": 715436,"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": 6305208306437.060, "dur": 6.336, + "args": { + "External id": 715437,"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": 6305208306440.016, "dur": 2.185, + "args": { + "External id": 715438,"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": 6305208306447.318, "dur": 22.833, + "args": { + "External id": 715439,"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": 6305208306474.966, "dur": 5.558, + "args": { + "External id": 715440,"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": 6305208306476.706, "dur": 3.131, + "args": { + "External id": 715441,"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": 6305208306478.894, "dur": 0.753, + "args": { + "External id": 715442,"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": 6305208306483.055, "dur": 58.730, + "args": { + "External id": 715443,"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": 6305208306484.024, "dur": 56.732, + "args": { + "External id": 715444,"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": 6305208306547.326, "dur": 15.053, + "args": { + "External id": 715445,"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": 6305208306571.634, "dur": 4.194, + "args": { + "External id": 715446,"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": 6305208306574.089, "dur": 0.654, + "args": { + "External id": 715447,"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": 6305208306580.022, "dur": 49.267, + "args": { + "External id": 715448,"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": 6305208306580.862, "dur": 4.135, + "args": { + "External id": 715449,"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": 6305208306581.625, "dur": 2.786, + "args": { + "External id": 715450,"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": 6305208306583.654, "dur": 0.634, + "args": { + "External id": 715451,"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": 6305208306587.612, "dur": 41.215, + "args": { + "External id": 715452,"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": 6305208306588.267, "dur": 40.022, + "args": { + "External id": 715453,"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": 6305208306634.007, "dur": 3.574, + "args": { + "External id": 715454,"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": 6305208306635.826, "dur": 0.364, + "args": { + "External id": 715455,"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": 6305208306643.567, "dur": 1.488, + "args": { + "External id": 715456,"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": 6305208306653.574, "dur": 11.480, + "args": { + "External id": 715457,"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": 6305208306658.052, "dur": 6.750, + "args": { + "External id": 715458,"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": 6305208306752.831, "dur": 178.358, + "args": { + "External id": 715459,"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": 6305208306754.974, "dur": 4.015, + "args": { + "External id": 715460,"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": 6305208306760.427, "dur": 170.364, + "args": { + "External id": 715461,"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": 6305208306761.472, "dur": 0.384, + "args": { + "External id": 715462,"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": 6305208306762.809, "dur": 19.422, + "args": { + "External id": 715463,"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": 6305208306783.815, "dur": 5.281, + "args": { + "External id": 715464,"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": 6305208306788.165, "dur": 0.690, + "args": { + "External id": 715465,"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": 6305208306790.094, "dur": 22.106, + "args": { + "External id": 715466,"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": 6305208306793.237, "dur": 1.035, + "args": { + "External id": 715467,"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": 6305208306795.538, "dur": 16.274, + "args": { + "External id": 715468,"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": 6305208306798.062, "dur": 2.996, + "args": { + "External id": 715469,"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": 6305208306813.649, "dur": 17.550, + "args": { + "External id": 715470,"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": 6305208306832.638, "dur": 12.979, + "args": { + "External id": 715471,"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": 6305208306848.295, "dur": 12.381, + "args": { + "External id": 715472,"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": 6305208306862.098, "dur": 13.956, + "args": { + "External id": 715473,"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": 6305208306877.949, "dur": 24.413, + "args": { + "External id": 715474,"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": 6305208306881.875, "dur": 1.410, + "args": { + "External id": 715475,"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": 6305208306887.370, "dur": 0.792, + "args": { + "External id": 715476,"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": 6305208306903.638, "dur": 13.732, + "args": { + "External id": 715477,"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": 6305208306918.262, "dur": 11.419, + "args": { + "External id": 715478,"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": 6305208306938.047, "dur": 1.654, + "args": { + "External id": 715479,"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": 6305208306948.516, "dur": 4.434, + "args": { + "External id": 715480,"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": 6305208306951.357, "dur": 0.619, + "args": { + "External id": 715481,"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": 6305208307017.629, "dur": 95.351, + "args": { + "External id": 715482,"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": 6305208307122.629, "dur": 6.903, + "args": { + "External id": 715483,"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": 6305208307126.267, "dur": 1.309, + "args": { + "External id": 715484,"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": 6305208307131.108, "dur": 28.464, + "args": { + "External id": 715485,"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": 6305208307165.236, "dur": 6.577, + "args": { + "External id": 715486,"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": 6305208307167.108, "dur": 3.863, + "args": { + "External id": 715487,"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": 6305208307169.074, "dur": 1.647, + "args": { + "External id": 715488,"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": 6305208307177.492, "dur": 49.506, + "args": { + "External id": 715489,"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": 6305208307178.646, "dur": 47.777, + "args": { + "External id": 715490,"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": 6305208307231.196, "dur": 14.081, + "args": { + "External id": 715491,"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": 6305208307251.818, "dur": 3.713, + "args": { + "External id": 715492,"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": 6305208307254.067, "dur": 0.687, + "args": { + "External id": 715493,"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": 6305208307259.603, "dur": 50.532, + "args": { + "External id": 715494,"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": 6305208307260.603, "dur": 8.660, + "args": { + "External id": 715495,"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": 6305208307263.543, "dur": 5.107, + "args": { + "External id": 715496,"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": 6305208307265.510, "dur": 3.004, + "args": { + "External id": 715497,"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": 6305208307269.789, "dur": 39.888, + "args": { + "External id": 715498,"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": 6305208307270.497, "dur": 38.436, + "args": { + "External id": 715499,"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": 6305208307314.797, "dur": 3.768, + "args": { + "External id": 715500,"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": 6305208307316.721, "dur": 0.489, + "args": { + "External id": 715501,"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": 6305208307324.892, "dur": 1.787, + "args": { + "External id": 715502,"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": 6305208307337.405, "dur": 7.245, + "args": { + "External id": 715503,"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": 6305208307339.730, "dur": 4.668, + "args": { + "External id": 715504,"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": 6305208307432.439, "dur": 203.338, + "args": { + "External id": 715505,"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": 6305208307436.158, "dur": 1.927, + "args": { + "External id": 715506,"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": 6305208307439.507, "dur": 195.869, + "args": { + "External id": 715507,"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": 6305208307440.632, "dur": 0.485, + "args": { + "External id": 715508,"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": 6305208307445.133, "dur": 22.146, + "args": { + "External id": 715509,"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": 6305208307468.834, "dur": 4.787, + "args": { + "External id": 715510,"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": 6305208307472.912, "dur": 0.509, + "args": { + "External id": 715511,"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": 6305208307474.517, "dur": 21.058, + "args": { + "External id": 715512,"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": 6305208307475.614, "dur": 1.167, + "args": { + "External id": 715513,"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": 6305208307477.949, "dur": 17.325, + "args": { + "External id": 715514,"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": 6305208307480.781, "dur": 2.160, + "args": { + "External id": 715515,"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": 6305208307497.045, "dur": 40.200, + "args": { + "External id": 715516,"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": 6305208307539.778, "dur": 15.119, + "args": { + "External id": 715517,"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": 6305208307557.985, "dur": 13.893, + "args": { + "External id": 715518,"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": 6305208307573.529, "dur": 11.129, + "args": { + "External id": 715519,"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": 6305208307589.061, "dur": 20.544, + "args": { + "External id": 715520,"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": 6305208307591.601, "dur": 2.037, + "args": { + "External id": 715521,"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": 6305208307595.600, "dur": 0.966, + "args": { + "External id": 715522,"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": 6305208307611.029, "dur": 10.992, + "args": { + "External id": 715523,"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": 6305208307623.013, "dur": 10.919, + "args": { + "External id": 715524,"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": 6305208307643.882, "dur": 2.423, + "args": { + "External id": 715525,"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": 6305208307655.537, "dur": 3.918, + "args": { + "External id": 715526,"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": 6305208307658.013, "dur": 0.419, + "args": { + "External id": 715527,"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": 6305208307728.418, "dur": 57.387, + "args": { + "External id": 715528,"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": 6305208307790.743, "dur": 4.969, + "args": { + "External id": 715529,"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": 6305208307794.053, "dur": 0.561, + "args": { + "External id": 715530,"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": 6305208307796.998, "dur": 24.501, + "args": { + "External id": 715531,"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": 6305208307826.014, "dur": 7.846, + "args": { + "External id": 715532,"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": 6305208307827.798, "dur": 5.325, + "args": { + "External id": 715533,"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": 6305208307831.694, "dur": 1.258, + "args": { + "External id": 715534,"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": 6305208307836.354, "dur": 42.005, + "args": { + "External id": 715535,"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": 6305208307837.590, "dur": 40.129, + "args": { + "External id": 715536,"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": 6305208307882.312, "dur": 15.709, + "args": { + "External id": 715537,"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": 6305208307904.037, "dur": 3.857, + "args": { + "External id": 715538,"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": 6305208307906.538, "dur": 0.510, + "args": { + "External id": 715539,"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": 6305208307911.563, "dur": 46.273, + "args": { + "External id": 715540,"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": 6305208307914.639, "dur": 3.844, + "args": { + "External id": 715541,"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": 6305208307915.408, "dur": 2.438, + "args": { + "External id": 715542,"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": 6305208307916.991, "dur": 0.727, + "args": { + "External id": 715543,"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": 6305208307918.999, "dur": 38.531, + "args": { + "External id": 715544,"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": 6305208307919.639, "dur": 37.291, + "args": { + "External id": 715545,"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": 6305208307961.775, "dur": 6.771, + "args": { + "External id": 715546,"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": 6305208307966.781, "dur": 0.533, + "args": { + "External id": 715547,"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": 6305208307976.066, "dur": 1.413, + "args": { + "External id": 715548,"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": 6305208307985.566, "dur": 10.000, + "args": { + "External id": 715549,"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": 6305208307987.407, "dur": 7.812, + "args": { + "External id": 715550,"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": 6305208308116.388, "dur": 178.679, + "args": { + "External id": 715551,"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": 6305208308118.725, "dur": 2.990, + "args": { + "External id": 715552,"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": 6305208308123.943, "dur": 170.794, + "args": { + "External id": 715553,"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": 6305208308127.854, "dur": 0.524, + "args": { + "External id": 715554,"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": 6305208308129.534, "dur": 24.392, + "args": { + "External id": 715555,"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": 6305208308155.605, "dur": 3.179, + "args": { + "External id": 715556,"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": 6305208308157.732, "dur": 0.779, + "args": { + "External id": 715557,"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": 6305208308159.754, "dur": 23.729, + "args": { + "External id": 715558,"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": 6305208308161.056, "dur": 1.447, + "args": { + "External id": 715559,"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": 6305208308163.922, "dur": 19.235, + "args": { + "External id": 715560,"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": 6305208308168.947, "dur": 3.016, + "args": { + "External id": 715561,"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": 6305208308185.220, "dur": 20.282, + "args": { + "External id": 715562,"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": 6305208308206.993, "dur": 11.927, + "args": { + "External id": 715563,"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": 6305208308224.260, "dur": 12.129, + "args": { + "External id": 715564,"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": 6305208308238.107, "dur": 11.117, + "args": { + "External id": 715565,"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": 6305208308250.857, "dur": 18.214, + "args": { + "External id": 715566,"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": 6305208308252.562, "dur": 1.432, + "args": { + "External id": 715567,"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": 6305208308256.521, "dur": 0.659, + "args": { + "External id": 715568,"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": 6305208308270.371, "dur": 11.070, + "args": { + "External id": 715569,"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": 6305208308284.300, "dur": 9.263, + "args": { + "External id": 715570,"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": 6305208308302.153, "dur": 2.205, + "args": { + "External id": 715571,"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": 6305208308313.447, "dur": 4.414, + "args": { + "External id": 715572,"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": 6305208308316.591, "dur": 0.298, + "args": { + "External id": 715573,"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": 6305208308384.324, "dur": 56.048, + "args": { + "External id": 715574,"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": 6305208308445.821, "dur": 5.153, + "args": { + "External id": 715575,"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": 6305208308449.209, "dur": 0.801, + "args": { + "External id": 715576,"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": 6305208308452.283, "dur": 22.806, + "args": { + "External id": 715577,"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": 6305208308481.973, "dur": 5.088, + "args": { + "External id": 715578,"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": 6305208308483.409, "dur": 3.058, + "args": { + "External id": 715579,"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": 6305208308485.298, "dur": 0.982, + "args": { + "External id": 715580,"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": 6305208308489.677, "dur": 57.622, + "args": { + "External id": 715581,"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": 6305208308490.694, "dur": 55.327, + "args": { + "External id": 715582,"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": 6305208308552.838, "dur": 15.180, + "args": { + "External id": 715583,"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": 6305208308574.785, "dur": 7.023, + "args": { + "External id": 715584,"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": 6305208308580.172, "dur": 0.545, + "args": { + "External id": 715585,"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": 6305208308586.124, "dur": 49.779, + "args": { + "External id": 715586,"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": 6305208308587.083, "dur": 3.934, + "args": { + "External id": 715587,"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": 6305208308588.091, "dur": 2.308, + "args": { + "External id": 715588,"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": 6305208308589.726, "dur": 0.549, + "args": { + "External id": 715589,"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": 6305208308591.570, "dur": 43.892, + "args": { + "External id": 715590,"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": 6305208308594.648, "dur": 40.214, + "args": { + "External id": 715591,"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": 6305208308640.341, "dur": 5.700, + "args": { + "External id": 715592,"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": 6305208308642.283, "dur": 2.588, + "args": { + "External id": 715593,"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": 6305208308651.732, "dur": 1.658, + "args": { + "External id": 715594,"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": 6305208308660.811, "dur": 7.756, + "args": { + "External id": 715595,"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": 6305208308662.853, "dur": 5.342, + "args": { + "External id": 715596,"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": 6305208308753.259, "dur": 166.987, + "args": { + "External id": 715597,"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": 6305208308754.988, "dur": 1.814, + "args": { + "External id": 715598,"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": 6305208308758.777, "dur": 161.005, + "args": { + "External id": 715599,"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": 6305208308759.990, "dur": 0.473, + "args": { + "External id": 715600,"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": 6305208308762.019, "dur": 21.240, + "args": { + "External id": 715601,"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": 6305208308784.826, "dur": 3.271, + "args": { + "External id": 715602,"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": 6305208308787.186, "dur": 0.740, + "args": { + "External id": 715603,"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": 6305208308789.026, "dur": 23.570, + "args": { + "External id": 715604,"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": 6305208308789.982, "dur": 1.135, + "args": { + "External id": 715605,"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": 6305208308794.808, "dur": 17.455, + "args": { + "External id": 715606,"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": 6305208308799.178, "dur": 2.310, + "args": { + "External id": 715607,"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": 6305208308813.827, "dur": 18.369, + "args": { + "External id": 715608,"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": 6305208308833.434, "dur": 12.190, + "args": { + "External id": 715609,"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": 6305208308847.872, "dur": 11.830, + "args": { + "External id": 715610,"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": 6305208308861.322, "dur": 10.884, + "args": { + "External id": 715611,"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": 6305208308873.924, "dur": 18.257, + "args": { + "External id": 715612,"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": 6305208308875.948, "dur": 1.451, + "args": { + "External id": 715613,"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": 6305208308879.463, "dur": 0.451, + "args": { + "External id": 715614,"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": 6305208308895.359, "dur": 11.386, + "args": { + "External id": 715615,"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": 6305208308907.615, "dur": 11.254, + "args": { + "External id": 715616,"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": 6305208308926.275, "dur": 1.703, + "args": { + "External id": 715617,"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": 6305208308935.106, "dur": 3.768, + "args": { + "External id": 715618,"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": 6305208308937.683, "dur": 0.292, + "args": { + "External id": 715619,"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": 6305208308997.929, "dur": 48.217, + "args": { + "External id": 715620,"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": 6305208309051.348, "dur": 37.947, + "args": { + "External id": 715621,"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": 6305208309054.306, "dur": 0.662, + "args": { + "External id": 715622,"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": 6305208309093.616, "dur": 28.033, + "args": { + "External id": 715623,"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": 6305208309127.410, "dur": 6.362, + "args": { + "External id": 715624,"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": 6305208309129.080, "dur": 3.955, + "args": { + "External id": 715625,"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": 6305208309131.277, "dur": 1.529, + "args": { + "External id": 715626,"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": 6305208309136.911, "dur": 47.832, + "args": { + "External id": 715627,"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": 6305208309137.923, "dur": 46.216, + "args": { + "External id": 715628,"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": 6305208309188.781, "dur": 16.334, + "args": { + "External id": 715629,"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": 6305208309212.388, "dur": 26.116, + "args": { + "External id": 715630,"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": 6305208309214.715, "dur": 23.367, + "args": { + "External id": 715631,"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": 6305208309221.424, "dur": 0.702, + "args": { + "External id": 715632,"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": 6305208309244.028, "dur": 27.228, + "args": { + "External id": 715633,"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": 6305208309245.847, "dur": 25.208, + "args": { + "External id": 715634,"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": 6305208309250.482, "dur": 3.999, + "args": { + "External id": 715635,"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": 6305208309255.737, "dur": 14.833, + "args": { + "External id": 715636,"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": 6305208309284.282, "dur": 6.901, + "args": { + "External id": 715637,"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": 6305208309288.219, "dur": 2.695, + "args": { + "External id": 715638,"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": 6305208309292.382, "dur": 1.329, + "args": { + "External id": 715639,"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": 6305208309293.037, "dur": 0.560, + "args": { + "External id": 715640,"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": 6305208309335.190, "dur": 23.884, + "args": { + "External id": 715641,"Sequence number": 7674827, "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": 6305208309360.779, "dur": 13.295, + "args": { + "External id": 715642,"Sequence number": 7674828, "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": 6305208309360.779, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338707, "tid": 2338707, + "ts": 6305208309380.051, "dur": 6.656, + "args": { + "External id": 715643,"Sequence number": 7674829, "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": 6305208309384.009, "dur": 1.012, + "args": { + "External id": 715644,"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": 6305208309389.322, "dur": 9.016, + "args": { + "External id": 715645,"Sequence number": 7674829, "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": 6305208309396.470, "dur": 0.443, + "args": { + "External id": 715646,"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": 6305208309399.722, "dur": 2.542, + "args": { + "External id": 715647,"Sequence number": 7674829, "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": 6305208309401.292, "dur": 0.405, + "args": { + "External id": 715648,"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": 6305208309406.234, "dur": 5.743, + "args": { + "External id": 715649,"Sequence number": 7674829, "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": 6305208309406.234, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2338707, + "ts": 6305208309409.890, "dur": 0.802, + "args": { + "External id": 715650,"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": 6305208309415.090, "dur": 4.727, + "args": { + "External id": 715651,"Sequence number": 7674830, "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": 6305208309415.090, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2338707, + "ts": 6305208309418.618, "dur": 0.424, + "args": { + "External id": 715652,"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": 6305208309420.917, "dur": 5.193, + "args": { + "External id": 715653,"Sequence number": 7674831, "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": 6305208309420.917, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2338707, + "ts": 6305208309424.698, "dur": 0.537, + "args": { + "External id": 715654,"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": 6305208309427.182, "dur": 6.862, + "args": { + "External id": 715655,"Sequence number": 7674832, "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": 6305208309427.182, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2338707, + "ts": 6305208309430.216, "dur": 3.048, + "args": { + "External id": 715656,"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": 6305208309437.806, "dur": 32.991, + "args": { + "External id": 715657,"Sequence number": 7674833, "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": 6305208309441.494, "dur": 29.078, + "args": { + "External id": 715658,"Sequence number": 7674833, "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": 6305208309444.739, "dur": 6.018, + "args": { + "External id": 715659,"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": 6305208309446.914, "dur": 3.308, + "args": { + "External id": 715660,"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": 6305208309451.527, "dur": 18.548, + "args": { + "External id": 715661,"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": 6305208309498.165, "dur": 3.994, + "args": { + "External id": 715662,"Sequence number": 7674833, "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": 6305208309498.165, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6305208309504.542, "dur": 17.035, + "args": { + "External id": 715663,"Sequence number": 7674834, "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": 6305208309558.259, "dur": 48822.368, + "args": { + "External id": 715664,"Sequence number": 7674834, "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": 6305208309558.259, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338707, "tid": 2338707, + "ts": 6305208309575.139, "dur": 37.814, + "args": { + "External id": 715665,"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": 6305208309580.728, "dur": 32.014, + "args": { + "External id": 715666,"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": 6305208309582.659, "dur": 7.863, + "args": { + "External id": 715667,"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": 6305208309586.435, "dur": 3.641, + "args": { + "External id": 715668,"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": 6305208309591.429, "dur": 20.937, + "args": { + "External id": 715669,"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": 6305208309629.509, "dur": 27.655, + "args": { + "External id": 715670,"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": 6305208309630.831, "dur": 5.781, + "args": { + "External id": 715671,"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": 6305208309632.845, "dur": 3.476, + "args": { + "External id": 715672,"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": 6305208309638.098, "dur": 18.846, + "args": { + "External id": 715673,"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": 6305208309641.844, "dur": 14.729, + "args": { + "External id": 715674,"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": 6305208309661.151, "dur": 18.513, + "args": { + "External id": 715675,"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": 6305208309661.783, "dur": 4.619, + "args": { + "External id": 715676,"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": 6305208309663.524, "dur": 2.672, + "args": { + "External id": 715677,"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": 6305208309667.058, "dur": 12.412, + "args": { + "External id": 715678,"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": 6305208309667.684, "dur": 11.478, + "args": { + "External id": 715679,"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": 6305208309685.890, "dur": 18.522, + "args": { + "External id": 715680,"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": 6305208309687.782, "dur": 3.656, + "args": { + "External id": 715681,"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": 6305208309691.971, "dur": 12.127, + "args": { + "External id": 715682,"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": 6305208309694.506, "dur": 9.316, + "args": { + "External id": 715683,"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": 6305208309710.127, "dur": 27.938, + "args": { + "External id": 715684,"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": 6305208309740.694, "dur": 49.284, + "args": { + "External id": 715685,"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": 6305208309742.571, "dur": 46.916, + "args": { + "External id": 715686,"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": 6305208309748.635, "dur": 0.733, + "args": { + "External id": 715687,"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": 6305208309750.585, "dur": 23.421, + "args": { + "External id": 715688,"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": 6305208309752.258, "dur": 21.523, + "args": { + "External id": 715689,"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": 6305208309754.975, "dur": 2.737, + "args": { + "External id": 715690,"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": 6305208309758.529, "dur": 14.908, + "args": { + "External id": 715691,"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": 6305208309795.926, "dur": 42785.985, + "args": { + "External id": 715692,"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": 6305208309797.418, "dur": 42783.898, + "args": { + "External id": 715693,"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": 6305208352593.392, "dur": 7.508, + "args": { + "External id": 715694,"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": 6305208352597.977, "dur": 1.060, + "args": { + "External id": 715695,"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": 6305208352606.097, "dur": 105.441, + "args": { + "External id": 715696,"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": 6305208352607.670, "dur": 6.026, + "args": { + "External id": 715697,"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": 6305208352609.991, "dur": 2.815, + "args": { + "External id": 715698,"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": 6305208352611.884, "dur": 0.640, + "args": { + "External id": 715699,"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": 6305208352617.354, "dur": 93.482, + "args": { + "External id": 715700,"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": 6305208352619.214, "dur": 90.956, + "args": { + "External id": 715701,"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": 6305208352715.349, "dur": 4.434, + "args": { + "External id": 715702,"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": 6305208352717.768, "dur": 0.565, + "args": { + "External id": 715703,"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": 6305208352726.947, "dur": 2.432, + "args": { + "External id": 715704,"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": 6305208352739.783, "dur": 8.741, + "args": { + "External id": 715705,"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": 6305208352744.262, "dur": 3.929, + "args": { + "External id": 715706,"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": 6305208352885.306, "dur": 237.860, + "args": { + "External id": 715707,"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": 6305208352888.745, "dur": 1.833, + "args": { + "External id": 715708,"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": 6305208352892.470, "dur": 230.182, + "args": { + "External id": 715709,"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": 6305208352893.954, "dur": 0.545, + "args": { + "External id": 715710,"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": 6305208352895.866, "dur": 29.583, + "args": { + "External id": 715711,"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": 6305208352927.265, "dur": 3.524, + "args": { + "External id": 715712,"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": 6305208352929.758, "dur": 0.761, + "args": { + "External id": 715713,"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": 6305208352931.921, "dur": 33.124, + "args": { + "External id": 715714,"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": 6305208352941.103, "dur": 2.858, + "args": { + "External id": 715715,"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": 6305208352945.525, "dur": 19.260, + "args": { + "External id": 715716,"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": 6305208352949.506, "dur": 3.159, + "args": { + "External id": 715717,"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": 6305208352966.781, "dur": 22.014, + "args": { + "External id": 715718,"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": 6305208352991.116, "dur": 13.844, + "args": { + "External id": 715719,"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": 6305208353008.145, "dur": 14.291, + "args": { + "External id": 715720,"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": 6305208353024.295, "dur": 12.913, + "args": { + "External id": 715721,"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": 6305208353038.866, "dur": 54.139, + "args": { + "External id": 715722,"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": 6305208353041.371, "dur": 1.581, + "args": { + "External id": 715723,"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": 6305208353047.077, "dur": 0.532, + "args": { + "External id": 715724,"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": 6305208353095.855, "dur": 13.312, + "args": { + "External id": 715725,"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": 6305208353110.488, "dur": 11.023, + "args": { + "External id": 715726,"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": 6305208353133.113, "dur": 2.608, + "args": { + "External id": 715727,"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": 6305208353143.683, "dur": 3.950, + "args": { + "External id": 715728,"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": 6305208353146.144, "dur": 0.614, + "args": { + "External id": 715729,"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": 6305208353229.652, "dur": 75.690, + "args": { + "External id": 715730,"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": 6305208353313.628, "dur": 6.813, + "args": { + "External id": 715731,"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": 6305208353316.798, "dur": 0.943, + "args": { + "External id": 715732,"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": 6305208353322.117, "dur": 34.663, + "args": { + "External id": 715733,"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": 6305208353362.915, "dur": 8.531, + "args": { + "External id": 715734,"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": 6305208353364.866, "dur": 5.626, + "args": { + "External id": 715735,"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": 6305208353367.375, "dur": 2.794, + "args": { + "External id": 715736,"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": 6305208353377.319, "dur": 48.603, + "args": { + "External id": 715737,"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": 6305208353378.592, "dur": 46.749, + "args": { + "External id": 715738,"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": 6305208353430.638, "dur": 16.286, + "args": { + "External id": 715739,"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": 6305208353453.436, "dur": 3.753, + "args": { + "External id": 715740,"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": 6305208353455.765, "dur": 0.607, + "args": { + "External id": 715741,"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": 6305208353461.827, "dur": 66.144, + "args": { + "External id": 715742,"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": 6305208353462.821, "dur": 5.955, + "args": { + "External id": 715743,"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": 6305208353465.898, "dur": 2.252, + "args": { + "External id": 715744,"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": 6305208353467.261, "dur": 0.730, + "args": { + "External id": 715745,"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": 6305208353469.358, "dur": 58.031, + "args": { + "External id": 715746,"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": 6305208353470.002, "dur": 56.345, + "args": { + "External id": 715747,"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": 6305208353534.492, "dur": 5.064, + "args": { + "External id": 715748,"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": 6305208353537.489, "dur": 0.769, + "args": { + "External id": 715749,"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": 6305208353548.827, "dur": 1.937, + "args": { + "External id": 715750,"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": 6305208353560.195, "dur": 6.847, + "args": { + "External id": 715751,"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": 6305208353561.827, "dur": 4.949, + "args": { + "External id": 715752,"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": 6305208353669.430, "dur": 191.983, + "args": { + "External id": 715753,"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": 6305208353671.384, "dur": 1.991, + "args": { + "External id": 715754,"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": 6305208353677.341, "dur": 183.541, + "args": { + "External id": 715755,"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": 6305208353681.036, "dur": 0.340, + "args": { + "External id": 715756,"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": 6305208353682.863, "dur": 23.351, + "args": { + "External id": 715757,"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": 6305208353707.898, "dur": 7.130, + "args": { + "External id": 715758,"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": 6305208353710.171, "dur": 4.610, + "args": { + "External id": 715759,"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": 6305208353716.003, "dur": 23.378, + "args": { + "External id": 715760,"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": 6305208353717.715, "dur": 1.094, + "args": { + "External id": 715761,"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": 6305208353720.388, "dur": 18.728, + "args": { + "External id": 715762,"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": 6305208353723.417, "dur": 2.312, + "args": { + "External id": 715763,"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": 6305208353740.947, "dur": 21.095, + "args": { + "External id": 715764,"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": 6305208353764.107, "dur": 14.960, + "args": { + "External id": 715765,"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": 6305208353784.051, "dur": 14.528, + "args": { + "External id": 715766,"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": 6305208353800.003, "dur": 13.578, + "args": { + "External id": 715767,"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": 6305208353815.467, "dur": 19.469, + "args": { + "External id": 715768,"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": 6305208353817.807, "dur": 1.547, + "args": { + "External id": 715769,"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": 6305208353821.275, "dur": 0.515, + "args": { + "External id": 715770,"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": 6305208353836.236, "dur": 11.802, + "args": { + "External id": 715771,"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": 6305208353849.066, "dur": 10.731, + "args": { + "External id": 715772,"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": 6305208353870.717, "dur": 1.632, + "args": { + "External id": 715773,"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": 6305208353881.661, "dur": 3.667, + "args": { + "External id": 715774,"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": 6305208353884.063, "dur": 0.472, + "args": { + "External id": 715775,"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": 6305208353952.802, "dur": 57.232, + "args": { + "External id": 715776,"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": 6305208354032.247, "dur": 6.474, + "args": { + "External id": 715777,"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": 6305208354035.368, "dur": 2.106, + "args": { + "External id": 715778,"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": 6305208354040.033, "dur": 62.881, + "args": { + "External id": 715779,"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": 6305208354113.440, "dur": 8.302, + "args": { + "External id": 715780,"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": 6305208354115.227, "dur": 5.602, + "args": { + "External id": 715781,"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": 6305208354119.588, "dur": 0.968, + "args": { + "External id": 715782,"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": 6305208354125.349, "dur": 49.456, + "args": { + "External id": 715783,"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": 6305208354126.661, "dur": 47.602, + "args": { + "External id": 715784,"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": 6305208354179.441, "dur": 17.132, + "args": { + "External id": 715785,"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": 6305208354203.658, "dur": 6.805, + "args": { + "External id": 715786,"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": 6305208354208.816, "dur": 0.648, + "args": { + "External id": 715787,"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": 6305208354215.076, "dur": 46.138, + "args": { + "External id": 715788,"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": 6305208354215.735, "dur": 3.092, + "args": { + "External id": 715789,"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": 6305208354216.349, "dur": 1.872, + "args": { + "External id": 715790,"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": 6305208354217.523, "dur": 0.561, + "args": { + "External id": 715791,"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": 6305208354219.355, "dur": 41.392, + "args": { + "External id": 715792,"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": 6305208354222.013, "dur": 38.131, + "args": { + "External id": 715793,"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": 6305208354265.984, "dur": 5.645, + "args": { + "External id": 715794,"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": 6305208354268.165, "dur": 2.371, + "args": { + "External id": 715795,"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": 6305208354278.560, "dur": 1.528, + "args": { + "External id": 715796,"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": 6305208354288.696, "dur": 7.486, + "args": { + "External id": 715797,"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": 6305208354290.403, "dur": 5.507, + "args": { + "External id": 715798,"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": 6305208354395.434, "dur": 199.483, + "args": { + "External id": 715799,"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": 6305208354397.546, "dur": 1.813, + "args": { + "External id": 715800,"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": 6305208354401.221, "dur": 193.117, + "args": { + "External id": 715801,"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": 6305208354402.490, "dur": 0.276, + "args": { + "External id": 715802,"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": 6305208354404.027, "dur": 22.454, + "args": { + "External id": 715803,"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": 6305208354428.410, "dur": 3.225, + "args": { + "External id": 715804,"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": 6305208354430.898, "dur": 0.529, + "args": { + "External id": 715805,"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": 6305208354432.763, "dur": 24.287, + "args": { + "External id": 715806,"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": 6305208354434.201, "dur": 1.000, + "args": { + "External id": 715807,"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": 6305208354436.561, "dur": 20.207, + "args": { + "External id": 715808,"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": 6305208354443.532, "dur": 2.811, + "args": { + "External id": 715809,"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": 6305208354458.550, "dur": 21.601, + "args": { + "External id": 715810,"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": 6305208354481.920, "dur": 12.679, + "args": { + "External id": 715811,"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": 6305208354497.549, "dur": 29.314, + "args": { + "External id": 715812,"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": 6305208354529.274, "dur": 12.839, + "args": { + "External id": 715813,"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": 6305208354543.845, "dur": 19.543, + "args": { + "External id": 715814,"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": 6305208354546.125, "dur": 1.940, + "args": { + "External id": 715815,"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": 6305208354549.933, "dur": 0.728, + "args": { + "External id": 715816,"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": 6305208354567.332, "dur": 12.280, + "args": { + "External id": 715817,"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": 6305208354580.545, "dur": 12.726, + "args": { + "External id": 715818,"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": 6305208354603.197, "dur": 2.411, + "args": { + "External id": 715819,"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": 6305208354615.314, "dur": 3.567, + "args": { + "External id": 715820,"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": 6305208354617.695, "dur": 0.395, + "args": { + "External id": 715821,"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": 6305208354690.251, "dur": 57.717, + "args": { + "External id": 715822,"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": 6305208354753.747, "dur": 8.004, + "args": { + "External id": 715823,"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": 6305208354759.517, "dur": 1.026, + "args": { + "External id": 715824,"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": 6305208354763.024, "dur": 27.489, + "args": { + "External id": 715825,"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": 6305208354795.187, "dur": 4.880, + "args": { + "External id": 715826,"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": 6305208354796.790, "dur": 2.657, + "args": { + "External id": 715827,"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": 6305208354798.611, "dur": 0.630, + "args": { + "External id": 715828,"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": 6305208354802.696, "dur": 68.945, + "args": { + "External id": 715829,"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": 6305208354803.621, "dur": 67.428, + "args": { + "External id": 715830,"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": 6305208354877.921, "dur": 29.462, + "args": { + "External id": 715831,"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": 6305208354913.149, "dur": 3.785, + "args": { + "External id": 715832,"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": 6305208354915.392, "dur": 0.546, + "args": { + "External id": 715833,"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": 6305208354920.843, "dur": 49.602, + "args": { + "External id": 715834,"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": 6305208354921.832, "dur": 7.972, + "args": { + "External id": 715835,"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": 6305208354922.547, "dur": 6.636, + "args": { + "External id": 715836,"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": 6305208354925.978, "dur": 2.921, + "args": { + "External id": 715837,"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": 6305208354930.542, "dur": 39.522, + "args": { + "External id": 715838,"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": 6305208354931.210, "dur": 38.263, + "args": { + "External id": 715839,"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": 6305208354974.500, "dur": 3.717, + "args": { + "External id": 715840,"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": 6305208354976.698, "dur": 0.407, + "args": { + "External id": 715841,"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": 6305208354983.361, "dur": 1.364, + "args": { + "External id": 715842,"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": 6305208354994.794, "dur": 5.870, + "args": { + "External id": 715843,"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": 6305208354996.659, "dur": 3.711, + "args": { + "External id": 715844,"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": 6305208355123.932, "dur": 186.636, + "args": { + "External id": 715845,"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": 6305208355126.646, "dur": 5.200, + "args": { + "External id": 715846,"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": 6305208355134.015, "dur": 176.137, + "args": { + "External id": 715847,"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": 6305208355135.332, "dur": 0.247, + "args": { + "External id": 715848,"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": 6305208355139.093, "dur": 22.328, + "args": { + "External id": 715849,"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": 6305208355165.403, "dur": 3.195, + "args": { + "External id": 715850,"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": 6305208355167.619, "dur": 0.751, + "args": { + "External id": 715851,"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": 6305208355169.559, "dur": 23.379, + "args": { + "External id": 715852,"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": 6305208355171.284, "dur": 3.021, + "args": { + "External id": 715853,"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": 6305208355175.834, "dur": 16.838, + "args": { + "External id": 715854,"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": 6305208355178.623, "dur": 2.464, + "args": { + "External id": 715855,"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": 6305208355194.523, "dur": 18.441, + "args": { + "External id": 715856,"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": 6305208355214.716, "dur": 14.110, + "args": { + "External id": 715857,"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": 6305208355231.230, "dur": 13.287, + "args": { + "External id": 715858,"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": 6305208355245.919, "dur": 13.371, + "args": { + "External id": 715859,"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": 6305208355260.790, "dur": 21.804, + "args": { + "External id": 715860,"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": 6305208355264.651, "dur": 1.493, + "args": { + "External id": 715861,"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": 6305208355267.799, "dur": 0.531, + "args": { + "External id": 715862,"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": 6305208355283.665, "dur": 13.173, + "args": { + "External id": 715863,"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": 6305208355297.833, "dur": 11.450, + "args": { + "External id": 715864,"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": 6305208355317.977, "dur": 2.049, + "args": { + "External id": 715865,"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": 6305208355329.193, "dur": 4.049, + "args": { + "External id": 715866,"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": 6305208355331.807, "dur": 0.426, + "args": { + "External id": 715867,"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": 6305208355404.480, "dur": 56.453, + "args": { + "External id": 715868,"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": 6305208355465.941, "dur": 4.821, + "args": { + "External id": 715869,"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": 6305208355468.773, "dur": 0.730, + "args": { + "External id": 715870,"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": 6305208355472.239, "dur": 24.094, + "args": { + "External id": 715871,"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": 6305208355500.770, "dur": 24.761, + "args": { + "External id": 715872,"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": 6305208355502.458, "dur": 22.141, + "args": { + "External id": 715873,"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": 6305208355521.416, "dur": 2.761, + "args": { + "External id": 715874,"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": 6305208355528.785, "dur": 46.938, + "args": { + "External id": 715875,"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": 6305208355530.138, "dur": 44.968, + "args": { + "External id": 715876,"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": 6305208355580.330, "dur": 14.606, + "args": { + "External id": 715877,"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": 6305208355601.590, "dur": 4.097, + "args": { + "External id": 715878,"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": 6305208355604.250, "dur": 0.544, + "args": { + "External id": 715879,"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": 6305208355609.765, "dur": 47.482, + "args": { + "External id": 715880,"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": 6305208355612.873, "dur": 3.808, + "args": { + "External id": 715881,"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": 6305208355613.779, "dur": 2.288, + "args": { + "External id": 715882,"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": 6305208355615.197, "dur": 0.710, + "args": { + "External id": 715883,"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": 6305208355617.166, "dur": 39.671, + "args": { + "External id": 715884,"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": 6305208355617.795, "dur": 38.438, + "args": { + "External id": 715885,"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": 6305208355661.833, "dur": 3.801, + "args": { + "External id": 715886,"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": 6305208355664.080, "dur": 0.474, + "args": { + "External id": 715887,"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": 6305208355671.827, "dur": 1.487, + "args": { + "External id": 715888,"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": 6305208355683.526, "dur": 5.661, + "args": { + "External id": 715889,"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": 6305208355685.476, "dur": 3.418, + "args": { + "External id": 715890,"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": 6305208355773.566, "dur": 186.876, + "args": { + "External id": 715891,"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": 6305208355775.341, "dur": 1.733, + "args": { + "External id": 715892,"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": 6305208355781.374, "dur": 178.592, + "args": { + "External id": 715893,"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": 6305208355782.619, "dur": 0.411, + "args": { + "External id": 715894,"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": 6305208355786.574, "dur": 25.075, + "args": { + "External id": 715895,"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": 6305208355813.505, "dur": 4.429, + "args": { + "External id": 715896,"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": 6305208355815.431, "dur": 2.266, + "args": { + "External id": 715897,"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": 6305208355818.760, "dur": 20.995, + "args": { + "External id": 715898,"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": 6305208355820.195, "dur": 1.181, + "args": { + "External id": 715899,"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": 6305208355822.611, "dur": 16.817, + "args": { + "External id": 715900,"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": 6305208355825.534, "dur": 3.327, + "args": { + "External id": 715901,"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": 6305208355841.023, "dur": 20.663, + "args": { + "External id": 715902,"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": 6305208355863.226, "dur": 12.221, + "args": { + "External id": 715903,"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": 6305208355884.175, "dur": 13.226, + "args": { + "External id": 715904,"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": 6305208355901.164, "dur": 10.985, + "args": { + "External id": 715905,"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": 6305208355913.712, "dur": 20.985, + "args": { + "External id": 715906,"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": 6305208355916.017, "dur": 1.561, + "args": { + "External id": 715907,"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": 6305208355919.517, "dur": 2.180, + "args": { + "External id": 715908,"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": 6305208355936.108, "dur": 11.010, + "args": { + "External id": 715909,"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": 6305208355948.409, "dur": 10.499, + "args": { + "External id": 715910,"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": 6305208355968.768, "dur": 1.718, + "args": { + "External id": 715911,"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": 6305208355979.530, "dur": 3.620, + "args": { + "External id": 715912,"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": 6305208355981.949, "dur": 0.401, + "args": { + "External id": 715913,"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": 6305208356048.887, "dur": 102.036, + "args": { + "External id": 715914,"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": 6305208356158.493, "dur": 6.940, + "args": { + "External id": 715915,"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": 6305208356162.701, "dur": 1.117, + "args": { + "External id": 715916,"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": 6305208356166.822, "dur": 29.982, + "args": { + "External id": 715917,"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": 6305208356202.233, "dur": 8.429, + "args": { + "External id": 715918,"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": 6305208356206.379, "dur": 3.548, + "args": { + "External id": 715919,"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": 6305208356208.119, "dur": 1.564, + "args": { + "External id": 715920,"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": 6305208356214.314, "dur": 43.495, + "args": { + "External id": 715921,"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": 6305208356215.515, "dur": 41.650, + "args": { + "External id": 715922,"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": 6305208356261.873, "dur": 16.550, + "args": { + "External id": 715923,"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": 6305208356284.600, "dur": 6.311, + "args": { + "External id": 715924,"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": 6305208356289.466, "dur": 0.633, + "args": { + "External id": 715925,"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": 6305208356299.023, "dur": 45.493, + "args": { + "External id": 715926,"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": 6305208356299.901, "dur": 3.711, + "args": { + "External id": 715927,"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": 6305208356300.808, "dur": 2.206, + "args": { + "External id": 715928,"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": 6305208356302.332, "dur": 0.559, + "args": { + "External id": 715929,"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": 6305208356304.249, "dur": 39.838, + "args": { + "External id": 715930,"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": 6305208356304.685, "dur": 38.638, + "args": { + "External id": 715931,"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": 6305208356350.432, "dur": 4.303, + "args": { + "External id": 715932,"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": 6305208356352.993, "dur": 0.685, + "args": { + "External id": 715933,"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": 6305208356360.787, "dur": 1.604, + "args": { + "External id": 715934,"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": 6305208356370.993, "dur": 10.087, + "args": { + "External id": 715935,"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": 6305208356372.906, "dur": 7.846, + "args": { + "External id": 715936,"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": 6305208356472.462, "dur": 197.233, + "args": { + "External id": 715937,"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": 6305208356474.497, "dur": 1.706, + "args": { + "External id": 715938,"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": 6305208356477.797, "dur": 191.275, + "args": { + "External id": 715939,"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": 6305208356479.268, "dur": 0.440, + "args": { + "External id": 715940,"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": 6305208356480.664, "dur": 21.814, + "args": { + "External id": 715941,"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": 6305208356504.438, "dur": 18.734, + "args": { + "External id": 715942,"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": 6305208356521.862, "dur": 0.818, + "args": { + "External id": 715943,"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": 6305208356524.182, "dur": 31.786, + "args": { + "External id": 715944,"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": 6305208356525.509, "dur": 2.188, + "args": { + "External id": 715945,"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": 6305208356531.526, "dur": 24.129, + "args": { + "External id": 715946,"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": 6305208356537.423, "dur": 2.677, + "args": { + "External id": 715947,"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": 6305208356557.199, "dur": 20.663, + "args": { + "External id": 715948,"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": 6305208356579.306, "dur": 12.616, + "args": { + "External id": 715949,"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": 6305208356594.581, "dur": 12.600, + "args": { + "External id": 715950,"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": 6305208356608.504, "dur": 11.301, + "args": { + "External id": 715951,"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": 6305208356621.773, "dur": 18.787, + "args": { + "External id": 715952,"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": 6305208356623.808, "dur": 1.607, + "args": { + "External id": 715953,"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": 6305208356627.830, "dur": 0.581, + "args": { + "External id": 715954,"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": 6305208356644.040, "dur": 11.733, + "args": { + "External id": 715955,"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": 6305208356656.716, "dur": 10.978, + "args": { + "External id": 715956,"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": 6305208356677.712, "dur": 1.986, + "args": { + "External id": 715957,"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": 6305208356689.071, "dur": 3.855, + "args": { + "External id": 715958,"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": 6305208356691.706, "dur": 0.296, + "args": { + "External id": 715959,"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": 6305208356759.333, "dur": 56.791, + "args": { + "External id": 715960,"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": 6305208356821.347, "dur": 4.823, + "args": { + "External id": 715961,"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": 6305208356824.386, "dur": 0.751, + "args": { + "External id": 715962,"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": 6305208356829.578, "dur": 24.837, + "args": { + "External id": 715963,"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": 6305208356858.638, "dur": 5.660, + "args": { + "External id": 715964,"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": 6305208356860.217, "dur": 3.254, + "args": { + "External id": 715965,"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": 6305208356862.308, "dur": 0.963, + "args": { + "External id": 715966,"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": 6305208356867.042, "dur": 47.702, + "args": { + "External id": 715967,"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": 6305208356868.111, "dur": 45.939, + "args": { + "External id": 715968,"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": 6305208356918.461, "dur": 12.889, + "args": { + "External id": 715969,"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": 6305208356938.904, "dur": 3.215, + "args": { + "External id": 715970,"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": 6305208356940.794, "dur": 0.440, + "args": { + "External id": 715971,"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": 6305208356946.155, "dur": 47.051, + "args": { + "External id": 715972,"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": 6305208356946.879, "dur": 3.283, + "args": { + "External id": 715973,"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": 6305208356947.522, "dur": 2.060, + "args": { + "External id": 715974,"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": 6305208356949.035, "dur": 0.431, + "args": { + "External id": 715975,"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": 6305208356953.138, "dur": 39.728, + "args": { + "External id": 715976,"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": 6305208356953.838, "dur": 38.468, + "args": { + "External id": 715977,"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": 6305208356997.613, "dur": 5.779, + "args": { + "External id": 715978,"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": 6305208356999.491, "dur": 2.787, + "args": { + "External id": 715979,"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": 6305208357008.455, "dur": 1.358, + "args": { + "External id": 715980,"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": 6305208357017.291, "dur": 5.450, + "args": { + "External id": 715981,"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": 6305208357019.392, "dur": 3.094, + "args": { + "External id": 715982,"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": 6305208357147.821, "dur": 179.958, + "args": { + "External id": 715983,"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": 6305208357150.511, "dur": 2.495, + "args": { + "External id": 715984,"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": 6305208357154.832, "dur": 172.405, + "args": { + "External id": 715985,"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": 6305208357156.146, "dur": 0.333, + "args": { + "External id": 715986,"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": 6305208357158.012, "dur": 23.500, + "args": { + "External id": 715987,"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": 6305208357183.030, "dur": 3.398, + "args": { + "External id": 715988,"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": 6305208357185.457, "dur": 0.753, + "args": { + "External id": 715989,"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": 6305208357187.338, "dur": 25.928, + "args": { + "External id": 715990,"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": 6305208357188.392, "dur": 1.530, + "args": { + "External id": 715991,"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": 6305208357193.598, "dur": 19.396, + "args": { + "External id": 715992,"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": 6305208357199.166, "dur": 2.885, + "args": { + "External id": 715993,"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": 6305208357214.659, "dur": 21.032, + "args": { + "External id": 715994,"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": 6305208357237.168, "dur": 12.101, + "args": { + "External id": 715995,"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": 6305208357252.079, "dur": 13.736, + "args": { + "External id": 715996,"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": 6305208357267.358, "dur": 11.245, + "args": { + "External id": 715997,"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": 6305208357280.346, "dur": 21.595, + "args": { + "External id": 715998,"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": 6305208357282.406, "dur": 1.430, + "args": { + "External id": 715999,"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": 6305208357288.038, "dur": 0.428, + "args": { + "External id": 716000,"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": 6305208357303.341, "dur": 11.150, + "args": { + "External id": 716001,"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": 6305208357315.369, "dur": 10.804, + "args": { + "External id": 716002,"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": 6305208357335.022, "dur": 2.119, + "args": { + "External id": 716003,"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": 6305208357346.782, "dur": 3.811, + "args": { + "External id": 716004,"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": 6305208357349.418, "dur": 0.339, + "args": { + "External id": 716005,"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": 6305208357412.231, "dur": 56.836, + "args": { + "External id": 716006,"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": 6305208357473.960, "dur": 7.241, + "args": { + "External id": 716007,"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": 6305208357479.000, "dur": 0.872, + "args": { + "External id": 716008,"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": 6305208357482.542, "dur": 22.380, + "args": { + "External id": 716009,"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": 6305208357524.927, "dur": 6.157, + "args": { + "External id": 716010,"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": 6305208357526.744, "dur": 3.354, + "args": { + "External id": 716011,"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": 6305208357528.862, "dur": 0.946, + "args": { + "External id": 716012,"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": 6305208357534.000, "dur": 47.729, + "args": { + "External id": 716013,"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": 6305208357537.840, "dur": 43.284, + "args": { + "External id": 716014,"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": 6305208357585.447, "dur": 16.787, + "args": { + "External id": 716015,"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": 6305208357608.031, "dur": 3.869, + "args": { + "External id": 716016,"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": 6305208357610.391, "dur": 0.663, + "args": { + "External id": 716017,"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": 6305208357615.756, "dur": 49.701, + "args": { + "External id": 716018,"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": 6305208357616.677, "dur": 7.913, + "args": { + "External id": 716019,"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": 6305208357617.481, "dur": 6.478, + "args": { + "External id": 716020,"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": 6305208357623.294, "dur": 0.554, + "args": { + "External id": 716021,"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": 6305208357625.427, "dur": 39.607, + "args": { + "External id": 716022,"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": 6305208357626.374, "dur": 38.107, + "args": { + "External id": 716023,"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": 6305208357669.277, "dur": 3.916, + "args": { + "External id": 716024,"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": 6305208357671.434, "dur": 0.680, + "args": { + "External id": 716025,"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": 6305208357682.871, "dur": 1.596, + "args": { + "External id": 716026,"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": 6305208357694.255, "dur": 7.043, + "args": { + "External id": 716027,"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": 6305208357696.209, "dur": 4.829, + "args": { + "External id": 716028,"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": 6305208357784.048, "dur": 186.439, + "args": { + "External id": 716029,"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": 6305208357788.248, "dur": 1.486, + "args": { + "External id": 716030,"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": 6305208357791.267, "dur": 178.777, + "args": { + "External id": 716031,"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": 6305208357792.408, "dur": 0.447, + "args": { + "External id": 716032,"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": 6305208357796.266, "dur": 22.215, + "args": { + "External id": 716033,"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": 6305208357819.967, "dur": 5.097, + "args": { + "External id": 716034,"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": 6305208357824.260, "dur": 0.599, + "args": { + "External id": 716035,"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": 6305208357825.876, "dur": 20.608, + "args": { + "External id": 716036,"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": 6305208357826.611, "dur": 1.133, + "args": { + "External id": 716037,"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": 6305208357828.871, "dur": 17.339, + "args": { + "External id": 716038,"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": 6305208357831.588, "dur": 2.369, + "args": { + "External id": 716039,"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": 6305208357847.734, "dur": 20.521, + "args": { + "External id": 716040,"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": 6305208357869.474, "dur": 13.810, + "args": { + "External id": 716041,"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": 6305208357885.615, "dur": 13.653, + "args": { + "External id": 716042,"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": 6305208357900.804, "dur": 14.191, + "args": { + "External id": 716043,"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": 6305208357918.675, "dur": 23.585, + "args": { + "External id": 716044,"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": 6305208357923.617, "dur": 1.565, + "args": { + "External id": 716045,"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": 6305208357927.147, "dur": 0.615, + "args": { + "External id": 716046,"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": 6305208357943.366, "dur": 13.568, + "args": { + "External id": 716047,"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": 6305208357957.713, "dur": 11.389, + "args": { + "External id": 716048,"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": 6305208357976.437, "dur": 1.785, + "args": { + "External id": 716049,"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": 6305208357986.132, "dur": 3.622, + "args": { + "External id": 716050,"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": 6305208357988.518, "dur": 0.336, + "args": { + "External id": 716051,"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": 6305208358052.726, "dur": 93.760, + "args": { + "External id": 716052,"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": 6305208358154.115, "dur": 6.161, + "args": { + "External id": 716053,"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": 6305208358157.962, "dur": 0.681, + "args": { + "External id": 716054,"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": 6305208358161.635, "dur": 27.771, + "args": { + "External id": 716055,"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": 6305208358194.328, "dur": 8.201, + "args": { + "External id": 716056,"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": 6305208358196.376, "dur": 5.388, + "args": { + "External id": 716057,"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": 6305208358200.344, "dur": 1.176, + "args": { + "External id": 716058,"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": 6305208358205.580, "dur": 41.189, + "args": { + "External id": 716059,"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": 6305208358206.567, "dur": 39.500, + "args": { + "External id": 716060,"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": 6305208358250.648, "dur": 18.310, + "args": { + "External id": 716061,"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": 6305208358273.645, "dur": 24.909, + "args": { + "External id": 716062,"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": 6305208358276.136, "dur": 21.986, + "args": { + "External id": 716063,"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": 6305208358281.144, "dur": 0.525, + "args": { + "External id": 716064,"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": 6305208358303.762, "dur": 31.135, + "args": { + "External id": 716065,"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": 6305208358305.917, "dur": 28.750, + "args": { + "External id": 716066,"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": 6305208358312.891, "dur": 3.302, + "args": { + "External id": 716067,"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": 6305208358317.559, "dur": 16.450, + "args": { + "External id": 716068,"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": 6305208358345.485, "dur": 4.531, + "args": { + "External id": 716069,"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": 6305208358347.267, "dur": 2.481, + "args": { + "External id": 716070,"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": 6305208358351.242, "dur": 1.273, + "args": { + "External id": 716071,"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": 6305208358351.836, "dur": 0.503, + "args": { + "External id": 716072,"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": 6305208358398.683, "dur": 23.533, + "args": { + "External id": 716073,"Sequence number": 7674835, "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": 6305208358424.183, "dur": 15.013, + "args": { + "External id": 716074,"Sequence number": 7674836, "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": 6305208358424.183, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 2338707, "tid": 2338707, + "ts": 6305208358445.194, "dur": 5.978, + "args": { + "External id": 716075,"Sequence number": 7674837, "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": 6305208358448.675, "dur": 0.930, + "args": { + "External id": 716076,"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": 6305208358453.817, "dur": 6.546, + "args": { + "External id": 716077,"Sequence number": 7674837, "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": 6305208358458.710, "dur": 0.357, + "args": { + "External id": 716078,"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": 6305208358463.725, "dur": 2.242, + "args": { + "External id": 716079,"Sequence number": 7674837, "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": 6305208358465.147, "dur": 0.269, + "args": { + "External id": 716080,"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": 6305208358469.677, "dur": 5.590, + "args": { + "External id": 716081,"Sequence number": 7674837, "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": 6305208358469.677, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2338707, + "ts": 6305208358473.305, "dur": 0.759, + "args": { + "External id": 716082,"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": 6305208358476.396, "dur": 6.307, + "args": { + "External id": 716083,"Sequence number": 7674838, "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": 6305208358476.396, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2338707, + "ts": 6305208358481.611, "dur": 0.335, + "args": { + "External id": 716084,"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": 6305208358483.939, "dur": 6.088, + "args": { + "External id": 716085,"Sequence number": 7674839, "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": 6305208358483.939, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2338707, + "ts": 6305208358487.045, "dur": 2.165, + "args": { + "External id": 716086,"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": 6305208358491.090, "dur": 4.122, + "args": { + "External id": 716087,"Sequence number": 7674840, "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": 6305208358491.090, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 2338707, "tid": 2338707, + "ts": 6305208358493.974, "dur": 0.523, + "args": { + "External id": 716088,"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": 6305208358498.916, "dur": 55.319, + "args": { + "External id": 716089,"Sequence number": 7674841, "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": 6305208358500.632, "dur": 53.328, + "args": { + "External id": 716090,"Sequence number": 7674841, "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": 6305208358503.413, "dur": 28.174, + "args": { + "External id": 716091,"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": 6305208358523.954, "dur": 6.793, + "args": { + "External id": 716092,"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": 6305208358532.703, "dur": 20.673, + "args": { + "External id": 716093,"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": 6305208358584.221, "dur": 5.652, + "args": { + "External id": 716094,"Sequence number": 7674841, "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": 6305208358584.221, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 2338707, "tid": 2338707, + "ts": 6305208358592.421, "dur": 1.096, + "args": { + "External id": 716095,"Sequence number": 7674842, "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": 6305208358626.411, "dur": 47785.103, + "args": { + "External id": 716096,"Sequence number": 7674842, "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": 6305208358626.411, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 2338707, "tid": 2338707, + "ts": 6305208358642.866, "dur": 28.814, + "args": { + "External id": 716097,"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": 6305208358645.809, "dur": 25.658, + "args": { + "External id": 716098,"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": 6305208358647.705, "dur": 5.252, + "args": { + "External id": 716099,"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": 6305208358649.300, "dur": 3.336, + "args": { + "External id": 716100,"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": 6305208358653.844, "dur": 17.138, + "args": { + "External id": 716101,"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": 6305208358688.252, "dur": 25.713, + "args": { + "External id": 716102,"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": 6305208358689.543, "dur": 5.919, + "args": { + "External id": 716103,"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": 6305208358691.614, "dur": 3.530, + "args": { + "External id": 716104,"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": 6305208358697.193, "dur": 16.550, + "args": { + "External id": 716105,"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": 6305208358698.940, "dur": 14.447, + "args": { + "External id": 716106,"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": 6305208358717.520, "dur": 22.823, + "args": { + "External id": 716107,"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": 6305208358718.317, "dur": 6.711, + "args": { + "External id": 716108,"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": 6305208358721.913, "dur": 2.853, + "args": { + "External id": 716109,"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": 6305208358725.754, "dur": 14.389, + "args": { + "External id": 716110,"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": 6305208358726.437, "dur": 13.402, + "args": { + "External id": 716111,"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": 6305208358746.557, "dur": 17.359, + "args": { + "External id": 716112,"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": 6305208358748.175, "dur": 3.711, + "args": { + "External id": 716113,"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": 6305208358752.371, "dur": 11.203, + "args": { + "External id": 716114,"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": 6305208358753.140, "dur": 10.150, + "args": { + "External id": 716115,"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": 6305208358768.629, "dur": 20.580, + "args": { + "External id": 716116,"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": 6305208358794.702, "dur": 48.978, + "args": { + "External id": 716117,"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": 6305208358796.624, "dur": 46.656, + "args": { + "External id": 716118,"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": 6305208358800.758, "dur": 0.687, + "args": { + "External id": 716119,"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": 6305208358802.740, "dur": 25.611, + "args": { + "External id": 716120,"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": 6305208358804.267, "dur": 23.884, + "args": { + "External id": 716121,"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": 6305208358808.789, "dur": 2.824, + "args": { + "External id": 716122,"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": 6305208358812.549, "dur": 15.163, + "args": { + "External id": 716123,"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": 6305208358847.488, "dur": 41562.157, + "args": { + "External id": 716124,"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": 6305208358848.918, "dur": 41559.650, + "args": { + "External id": 716125,"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": 6305208400421.262, "dur": 10.278, + "args": { + "External id": 716126,"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": 6305208400428.445, "dur": 1.119, + "args": { + "External id": 716127,"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": 6305208400437.271, "dur": 116.545, + "args": { + "External id": 716128,"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": 6305208400439.109, "dur": 5.950, + "args": { + "External id": 716129,"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": 6305208400441.186, "dur": 2.943, + "args": { + "External id": 716130,"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": 6305208400443.185, "dur": 0.695, + "args": { + "External id": 716131,"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": 6305208400446.381, "dur": 106.558, + "args": { + "External id": 716132,"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": 6305208400448.032, "dur": 103.419, + "args": { + "External id": 716133,"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": 6305208400561.485, "dur": 6.202, + "args": { + "External id": 716134,"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": 6305208400564.933, "dur": 0.741, + "args": { + "External id": 716135,"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": 6305208400576.056, "dur": 2.416, + "args": { + "External id": 716136,"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": 6305208400589.071, "dur": 6.462, + "args": { + "External id": 716137,"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": 6305208400590.967, "dur": 4.289, + "args": { + "External id": 716138,"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": 6305208400735.197, "dur": 197.524, + "args": { + "External id": 716139,"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": 6305208400737.928, "dur": 3.574, + "args": { + "External id": 716140,"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": 6305208400745.498, "dur": 186.631, + "args": { + "External id": 716141,"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": 6305208400747.059, "dur": 0.442, + "args": { + "External id": 716142,"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": 6305208400749.227, "dur": 25.246, + "args": { + "External id": 716143,"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": 6305208400776.708, "dur": 5.459, + "args": { + "External id": 716144,"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": 6305208400779.398, "dur": 2.454, + "args": { + "External id": 716145,"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": 6305208400783.172, "dur": 25.086, + "args": { + "External id": 716146,"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": 6305208400784.471, "dur": 1.196, + "args": { + "External id": 716147,"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": 6305208400787.381, "dur": 20.546, + "args": { + "External id": 716148,"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": 6305208400793.213, "dur": 2.779, + "args": { + "External id": 716149,"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": 6305208400810.071, "dur": 21.750, + "args": { + "External id": 716150,"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": 6305208400834.107, "dur": 14.527, + "args": { + "External id": 716151,"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": 6305208400851.794, "dur": 14.327, + "args": { + "External id": 716152,"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": 6305208400868.186, "dur": 12.475, + "args": { + "External id": 716153,"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": 6305208400882.589, "dur": 21.245, + "args": { + "External id": 716154,"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": 6305208400884.938, "dur": 1.232, + "args": { + "External id": 716155,"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": 6305208400888.136, "dur": 2.889, + "args": { + "External id": 716156,"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": 6305208400908.143, "dur": 11.309, + "args": { + "External id": 716157,"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": 6305208400921.115, "dur": 10.133, + "args": { + "External id": 716158,"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": 6305208400940.221, "dur": 1.555, + "args": { + "External id": 716159,"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": 6305208400948.352, "dur": 4.119, + "args": { + "External id": 716160,"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": 6305208400950.657, "dur": 0.583, + "args": { + "External id": 716161,"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": 6305208401029.381, "dur": 109.181, + "args": { + "External id": 716162,"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": 6305208401146.302, "dur": 10.623, + "args": { + "External id": 716163,"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": 6305208401152.196, "dur": 1.138, + "args": { + "External id": 716164,"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": 6305208401158.678, "dur": 28.971, + "args": { + "External id": 716165,"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": 6305208401194.145, "dur": 6.529, + "args": { + "External id": 716166,"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": 6305208401196.276, "dur": 3.613, + "args": { + "External id": 716167,"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": 6305208401198.278, "dur": 1.365, + "args": { + "External id": 716168,"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": 6305208401204.731, "dur": 48.006, + "args": { + "External id": 716169,"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": 6305208401206.015, "dur": 46.125, + "args": { + "External id": 716170,"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": 6305208401259.445, "dur": 16.136, + "args": { + "External id": 716171,"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": 6305208401283.020, "dur": 4.107, + "args": { + "External id": 716172,"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": 6305208401285.369, "dur": 0.567, + "args": { + "External id": 716173,"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": 6305208401291.845, "dur": 54.639, + "args": { + "External id": 716174,"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": 6305208401292.829, "dur": 9.014, + "args": { + "External id": 716175,"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": 6305208401293.938, "dur": 7.298, + "args": { + "External id": 716176,"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": 6305208401298.661, "dur": 2.459, + "args": { + "External id": 716177,"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": 6305208401305.792, "dur": 40.342, + "args": { + "External id": 716178,"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": 6305208401306.345, "dur": 39.191, + "args": { + "External id": 716179,"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": 6305208401350.738, "dur": 3.717, + "args": { + "External id": 716180,"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": 6305208401352.610, "dur": 0.352, + "args": { + "External id": 716181,"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": 6305208401361.344, "dur": 1.526, + "args": { + "External id": 716182,"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": 6305208401374.123, "dur": 8.632, + "args": { + "External id": 716183,"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": 6305208401376.412, "dur": 6.016, + "args": { + "External id": 716184,"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": 6305208401482.219, "dur": 212.609, + "args": { + "External id": 716185,"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": 6305208401484.092, "dur": 1.502, + "args": { + "External id": 716186,"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": 6305208401487.094, "dur": 207.101, + "args": { + "External id": 716187,"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": 6305208401488.740, "dur": 0.376, + "args": { + "External id": 716188,"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": 6305208401490.398, "dur": 39.846, + "args": { + "External id": 716189,"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": 6305208401534.970, "dur": 3.903, + "args": { + "External id": 716190,"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": 6305208401537.876, "dur": 0.727, + "args": { + "External id": 716191,"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": 6305208401539.889, "dur": 25.570, + "args": { + "External id": 716192,"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": 6305208401540.932, "dur": 1.790, + "args": { + "External id": 716193,"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": 6305208401543.961, "dur": 21.213, + "args": { + "External id": 716194,"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": 6305208401549.727, "dur": 2.560, + "args": { + "External id": 716195,"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": 6305208401566.972, "dur": 21.856, + "args": { + "External id": 716196,"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": 6305208401590.581, "dur": 14.138, + "args": { + "External id": 716197,"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": 6305208401607.590, "dur": 14.857, + "args": { + "External id": 716198,"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": 6305208401624.117, "dur": 14.075, + "args": { + "External id": 716199,"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": 6305208401640.018, "dur": 24.984, + "args": { + "External id": 716200,"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": 6305208401644.650, "dur": 2.184, + "args": { + "External id": 716201,"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": 6305208401649.230, "dur": 0.541, + "args": { + "External id": 716202,"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": 6305208401666.547, "dur": 12.947, + "args": { + "External id": 716203,"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": 6305208401680.666, "dur": 12.599, + "args": { + "External id": 716204,"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": 6305208401703.005, "dur": 2.283, + "args": { + "External id": 716205,"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": 6305208401715.235, "dur": 4.280, + "args": { + "External id": 716206,"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": 6305208401718.221, "dur": 0.389, + "args": { + "External id": 716207,"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": 6305208401792.562, "dur": 60.547, + "args": { + "External id": 716208,"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": 6305208401860.583, "dur": 4.977, + "args": { + "External id": 716209,"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": 6305208401863.247, "dur": 0.913, + "args": { + "External id": 716210,"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": 6305208401867.073, "dur": 28.991, + "args": { + "External id": 716211,"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": 6305208401900.423, "dur": 5.373, + "args": { + "External id": 716212,"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": 6305208401901.878, "dur": 3.110, + "args": { + "External id": 716213,"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": 6305208401903.990, "dur": 0.820, + "args": { + "External id": 716214,"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": 6305208401910.733, "dur": 40.763, + "args": { + "External id": 716215,"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": 6305208401911.749, "dur": 39.342, + "args": { + "External id": 716216,"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": 6305208401955.328, "dur": 13.575, + "args": { + "External id": 716217,"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": 6305208401974.924, "dur": 3.514, + "args": { + "External id": 716218,"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": 6305208401977.151, "dur": 0.389, + "args": { + "External id": 716219,"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": 6305208401982.672, "dur": 46.933, + "args": { + "External id": 716220,"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": 6305208401983.517, "dur": 7.321, + "args": { + "External id": 716221,"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": 6305208401986.483, "dur": 3.778, + "args": { + "External id": 716222,"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": 6305208401987.918, "dur": 2.160, + "args": { + "External id": 716223,"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": 6305208401991.530, "dur": 37.518, + "args": { + "External id": 716224,"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": 6305208401992.349, "dur": 36.103, + "args": { + "External id": 716225,"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": 6305208402033.518, "dur": 3.596, + "args": { + "External id": 716226,"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": 6305208402035.472, "dur": 0.434, + "args": { + "External id": 716227,"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": 6305208402042.357, "dur": 1.324, + "args": { + "External id": 716228,"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": 6305208402101.773, "dur": 10.496, + "args": { + "External id": 716229,"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": 6305208402104.940, "dur": 6.805, + "args": { + "External id": 716230,"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": 6305208402207.936, "dur": 187.777, + "args": { + "External id": 716231,"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": 6305208402210.481, "dur": 1.833, + "args": { + "External id": 716232,"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": 6305208402213.612, "dur": 181.656, + "args": { + "External id": 716233,"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": 6305208402214.981, "dur": 0.393, + "args": { + "External id": 716234,"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": 6305208402218.639, "dur": 21.373, + "args": { + "External id": 716235,"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": 6305208402243.598, "dur": 3.286, + "args": { + "External id": 716236,"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": 6305208402245.775, "dur": 0.860, + "args": { + "External id": 716237,"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": 6305208402247.819, "dur": 22.634, + "args": { + "External id": 716238,"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": 6305208402248.593, "dur": 2.768, + "args": { + "External id": 716239,"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": 6305208402252.741, "dur": 17.369, + "args": { + "External id": 716240,"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": 6305208402255.448, "dur": 2.879, + "args": { + "External id": 716241,"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": 6305208402271.859, "dur": 18.453, + "args": { + "External id": 716242,"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": 6305208402291.693, "dur": 13.766, + "args": { + "External id": 716243,"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": 6305208402308.279, "dur": 14.373, + "args": { + "External id": 716244,"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": 6305208402324.123, "dur": 18.461, + "args": { + "External id": 716245,"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": 6305208402346.369, "dur": 20.677, + "args": { + "External id": 716246,"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": 6305208402348.387, "dur": 1.417, + "args": { + "External id": 716247,"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": 6305208402351.868, "dur": 0.539, + "args": { + "External id": 716248,"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": 6305208402368.496, "dur": 13.179, + "args": { + "External id": 716249,"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": 6305208402382.719, "dur": 11.254, + "args": { + "External id": 716250,"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": 6305208402402.973, "dur": 2.180, + "args": { + "External id": 716251,"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": 6305208402417.648, "dur": 3.984, + "args": { + "External id": 716252,"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": 6305208402420.367, "dur": 0.440, + "args": { + "External id": 716253,"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": 6305208402492.439, "dur": 102.318, + "args": { + "External id": 716254,"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": 6305208402601.460, "dur": 5.790, + "args": { + "External id": 716255,"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": 6305208402604.811, "dur": 0.910, + "args": { + "External id": 716256,"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": 6305208402608.543, "dur": 30.584, + "args": { + "External id": 716257,"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": 6305208402644.453, "dur": 9.577, + "args": { + "External id": 716258,"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": 6305208402646.061, "dur": 7.283, + "args": { + "External id": 716259,"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": 6305208402650.441, "dur": 2.691, + "args": { + "External id": 716260,"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": 6305208402660.211, "dur": 44.636, + "args": { + "External id": 716261,"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": 6305208402661.233, "dur": 42.987, + "args": { + "External id": 716262,"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": 6305208402708.774, "dur": 14.512, + "args": { + "External id": 716263,"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": 6305208402729.981, "dur": 3.385, + "args": { + "External id": 716264,"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": 6305208402731.911, "dur": 0.428, + "args": { + "External id": 716265,"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": 6305208402739.703, "dur": 42.368, + "args": { + "External id": 716266,"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": 6305208402740.707, "dur": 3.207, + "args": { + "External id": 716267,"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": 6305208402741.220, "dur": 2.091, + "args": { + "External id": 716268,"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": 6305208402742.752, "dur": 0.444, + "args": { + "External id": 716269,"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": 6305208402744.349, "dur": 37.291, + "args": { + "External id": 716270,"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": 6305208402744.789, "dur": 36.220, + "args": { + "External id": 716271,"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": 6305208402788.109, "dur": 3.419, + "args": { + "External id": 716272,"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": 6305208402789.821, "dur": 0.541, + "args": { + "External id": 716273,"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": 6305208402797.346, "dur": 1.703, + "args": { + "External id": 716274,"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": 6305208402807.036, "dur": 8.617, + "args": { + "External id": 716275,"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": 6305208402808.746, "dur": 6.595, + "args": { + "External id": 716276,"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": 6305208402905.808, "dur": 298.762, + "args": { + "External id": 716277,"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": 6305208402907.414, "dur": 1.843, + "args": { + "External id": 716278,"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": 6305208402910.613, "dur": 293.143, + "args": { + "External id": 716279,"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": 6305208402911.914, "dur": 0.425, + "args": { + "External id": 716280,"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": 6305208402913.634, "dur": 23.974, + "args": { + "External id": 716281,"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": 6305208402938.922, "dur": 3.395, + "args": { + "External id": 716282,"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": 6305208402941.478, "dur": 0.644, + "args": { + "External id": 716283,"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": 6305208402943.247, "dur": 26.450, + "args": { + "External id": 716284,"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": 6305208402944.205, "dur": 0.943, + "args": { + "External id": 716285,"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": 6305208402946.343, "dur": 23.038, + "args": { + "External id": 716286,"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": 6305208402953.630, "dur": 2.358, + "args": { + "External id": 716287,"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": 6305208402970.803, "dur": 22.621, + "args": { + "External id": 716288,"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": 6305208403024.215, "dur": 14.271, + "args": { + "External id": 716289,"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": 6305208403041.570, "dur": 82.912, + "args": { + "External id": 716290,"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": 6305208403127.688, "dur": 16.260, + "args": { + "External id": 716291,"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": 6305208403146.357, "dur": 25.146, + "args": { + "External id": 716292,"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": 6305208403149.175, "dur": 2.683, + "args": { + "External id": 716293,"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": 6305208403154.145, "dur": 0.868, + "args": { + "External id": 716294,"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": 6305208403175.654, "dur": 12.883, + "args": { + "External id": 716295,"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": 6305208403189.852, "dur": 12.205, + "args": { + "External id": 716296,"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": 6305208403215.670, "dur": 2.800, + "args": { + "External id": 716297,"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": 6305208403229.328, "dur": 3.987, + "args": { + "External id": 716298,"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": 6305208403231.940, "dur": 0.623, + "args": { + "External id": 716299,"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": 6305208403314.290, "dur": 71.974, + "args": { + "External id": 716300,"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": 6305208403391.939, "dur": 5.731, + "args": { + "External id": 716301,"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": 6305208403395.109, "dur": 1.133, + "args": { + "External id": 716302,"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": 6305208403401.588, "dur": 28.255, + "args": { + "External id": 716303,"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": 6305208403434.753, "dur": 7.463, + "args": { + "External id": 716304,"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": 6305208403436.412, "dur": 4.791, + "args": { + "External id": 716305,"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": 6305208403438.250, "dur": 2.663, + "args": { + "External id": 716306,"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": 6305208403445.397, "dur": 44.468, + "args": { + "External id": 716307,"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": 6305208403446.492, "dur": 42.729, + "args": { + "External id": 716308,"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": 6305208403494.238, "dur": 31.935, + "args": { + "External id": 716309,"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": 6305208403537.166, "dur": 4.898, + "args": { + "External id": 716310,"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": 6305208403539.843, "dur": 0.774, + "args": { + "External id": 716311,"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": 6305208403547.003, "dur": 54.008, + "args": { + "External id": 716312,"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": 6305208403547.764, "dur": 3.819, + "args": { + "External id": 716313,"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": 6305208403548.821, "dur": 2.077, + "args": { + "External id": 716314,"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": 6305208403550.207, "dur": 0.521, + "args": { + "External id": 716315,"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": 6305208403554.372, "dur": 46.086, + "args": { + "External id": 716316,"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": 6305208403555.202, "dur": 44.526, + "args": { + "External id": 716317,"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": 6305208403605.632, "dur": 4.198, + "args": { + "External id": 716318,"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": 6305208403608.139, "dur": 0.365, + "args": { + "External id": 716319,"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": 6305208403616.433, "dur": 1.624, + "args": { + "External id": 716320,"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": 6305208403626.605, "dur": 7.429, + "args": { + "External id": 716321,"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": 6305208403629.117, "dur": 4.649, + "args": { + "External id": 716322,"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": 6305208403729.828, "dur": 193.271, + "args": { + "External id": 716323,"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": 6305208403731.928, "dur": 1.858, + "args": { + "External id": 716324,"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": 6305208403737.728, "dur": 184.887, + "args": { + "External id": 716325,"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": 6305208403738.908, "dur": 0.476, + "args": { + "External id": 716326,"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": 6305208403740.590, "dur": 22.980, + "args": { + "External id": 716327,"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": 6305208403765.233, "dur": 4.802, + "args": { + "External id": 716328,"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": 6305208403767.194, "dur": 2.563, + "args": { + "External id": 716329,"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": 6305208403771.064, "dur": 25.915, + "args": { + "External id": 716330,"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": 6305208403772.270, "dur": 0.995, + "args": { + "External id": 716331,"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": 6305208403776.899, "dur": 19.787, + "args": { + "External id": 716332,"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": 6305208403779.760, "dur": 3.071, + "args": { + "External id": 716333,"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": 6305208403798.253, "dur": 22.005, + "args": { + "External id": 716334,"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": 6305208403821.697, "dur": 15.078, + "args": { + "External id": 716335,"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": 6305208403839.513, "dur": 14.196, + "args": { + "External id": 716336,"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": 6305208403855.150, "dur": 13.700, + "args": { + "External id": 716337,"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": 6305208403870.435, "dur": 24.069, + "args": { + "External id": 716338,"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": 6305208403872.534, "dur": 1.317, + "args": { + "External id": 716339,"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": 6305208403877.613, "dur": 2.327, + "args": { + "External id": 716340,"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": 6305208403895.737, "dur": 13.511, + "args": { + "External id": 716341,"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": 6305208403910.188, "dur": 11.355, + "args": { + "External id": 716342,"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": 6305208403929.515, "dur": 1.571, + "args": { + "External id": 716343,"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": 6305208403939.577, "dur": 3.664, + "args": { + "External id": 716344,"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": 6305208403942.098, "dur": 0.310, + "args": { + "External id": 716345,"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": 6305208404007.348, "dur": 105.566, + "args": { + "External id": 716346,"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": 6305208404120.624, "dur": 9.960, + "args": { + "External id": 716347,"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": 6305208404127.856, "dur": 1.004, + "args": { + "External id": 716348,"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": 6305208404132.385, "dur": 32.252, + "args": { + "External id": 716349,"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": 6305208404170.706, "dur": 13.604, + "args": { + "External id": 716350,"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": 6305208404177.971, "dur": 5.529, + "args": { + "External id": 716351,"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": 6305208404180.182, "dur": 3.041, + "args": { + "External id": 716352,"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": 6305208404187.850, "dur": 50.769, + "args": { + "External id": 716353,"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": 6305208404191.580, "dur": 46.465, + "args": { + "External id": 716354,"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": 6305208404242.695, "dur": 17.411, + "args": { + "External id": 716355,"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": 6305208404266.664, "dur": 3.601, + "args": { + "External id": 716356,"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": 6305208404268.768, "dur": 0.574, + "args": { + "External id": 716357,"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": 6305208404274.500, "dur": 47.623, + "args": { + "External id": 716358,"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": 6305208404275.466, "dur": 6.616, + "args": { + "External id": 716359,"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": 6305208404276.276, "dur": 5.170, + "args": { + "External id": 716360,"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": 6305208404280.581, "dur": 0.670, + "args": { + "External id": 716361,"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": 6305208404282.599, "dur": 39.098, + "args": { + "External id": 716362,"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": 6305208404283.372, "dur": 37.660, + "args": { + "External id": 716363,"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": 6305208404326.074, "dur": 4.157, + "args": { + "External id": 716364,"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": 6305208404328.312, "dur": 0.698, + "args": { + "External id": 716365,"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": 6305208404336.547, "dur": 1.643, + "args": { + "External id": 716366,"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": 6305208404348.677, "dur": 8.487, + "args": { + "External id": 716367,"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": 6305208404350.793, "dur": 6.106, + "args": { + "External id": 716368,"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": 6305208404446.307, "dur": 212.161, + "args": { + "External id": 716369,"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": 6305208404448.590, "dur": 1.683, + "args": { + "External id": 716370,"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": 6305208404453.536, "dur": 204.495, + "args": { + "External id": 716371,"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": 6305208404454.716, "dur": 0.427, + "args": { + "External id": 716372,"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": 6305208404458.413, "dur": 22.227, + "args": { + "External id": 716373,"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": 6305208404482.159, "dur": 5.554, + "args": { + "External id": 716374,"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": 6305208404484.424, "dur": 2.882, + "args": { + "External id": 716375,"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": 6305208404488.718, "dur": 39.351, + "args": { + "External id": 716376,"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": 6305208404489.414, "dur": 1.024, + "args": { + "External id": 716377,"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": 6305208404491.872, "dur": 35.487, + "args": { + "External id": 716378,"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": 6305208404494.911, "dur": 2.515, + "args": { + "External id": 716379,"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": 6305208404530.171, "dur": 24.773, + "args": { + "External id": 716380,"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": 6305208404556.469, "dur": 13.505, + "args": { + "External id": 716381,"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": 6305208404572.489, "dur": 15.176, + "args": { + "External id": 716382,"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": 6305208404589.020, "dur": 13.361, + "args": { + "External id": 716383,"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": 6305208404606.400, "dur": 23.767, + "args": { + "External id": 716384,"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": 6305208404608.470, "dur": 1.976, + "args": { + "External id": 716385,"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": 6305208404612.513, "dur": 2.747, + "args": { + "External id": 716386,"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": 6305208404631.422, "dur": 13.163, + "args": { + "External id": 716387,"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": 6305208404645.439, "dur": 11.525, + "args": { + "External id": 716388,"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": 6305208404666.153, "dur": 2.442, + "args": { + "External id": 716389,"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": 6305208404677.535, "dur": 4.260, + "args": { + "External id": 716390,"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": 6305208404680.464, "dur": 0.527, + "args": { + "External id": 716391,"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": 6305208404750.610, "dur": 56.677, + "args": { + "External id": 716392,"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": 6305208404812.163, "dur": 4.308, + "args": { + "External id": 716393,"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": 6305208404814.787, "dur": 0.634, + "args": { + "External id": 716394,"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": 6305208404818.048, "dur": 25.133, + "args": { + "External id": 716395,"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": 6305208404847.778, "dur": 8.654, + "args": { + "External id": 716396,"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": 6305208404849.442, "dur": 6.313, + "args": { + "External id": 716397,"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": 6305208404854.038, "dur": 1.503, + "args": { + "External id": 716398,"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": 6305208404858.954, "dur": 41.453, + "args": { + "External id": 716399,"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": 6305208404860.267, "dur": 39.518, + "args": { + "External id": 716400,"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": 6305208404903.898, "dur": 15.419, + "args": { + "External id": 716401,"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": 6305208404924.639, "dur": 3.251, + "args": { + "External id": 716402,"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": 6305208404926.639, "dur": 0.375, + "args": { + "External id": 716403,"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": 6305208404932.291, "dur": 45.118, + "args": { + "External id": 716404,"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": 6305208404935.175, "dur": 3.650, + "args": { + "External id": 716405,"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": 6305208404935.875, "dur": 2.373, + "args": { + "External id": 716406,"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": 6305208404937.468, "dur": 0.654, + "args": { + "External id": 716407,"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": 6305208404939.384, "dur": 37.680, + "args": { + "External id": 716408,"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": 6305208404940.004, "dur": 36.611, + "args": { + "External id": 716409,"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": 6305208404981.366, "dur": 5.108, + "args": { + "External id": 716410,"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": 6305208404983.363, "dur": 1.765, + "args": { + "External id": 716411,"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": 6305208404992.111, "dur": 1.455, + "args": { + "External id": 716412,"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": 6305208405002.670, "dur": 5.712, + "args": { + "External id": 716413,"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": 6305208405004.644, "dur": 3.444, + "args": { + "External id": 716414,"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": 6305208405142.970, "dur": 196.654, + "args": { + "External id": 716415,"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": 6305208405148.042, "dur": 2.938, + "args": { + "External id": 716416,"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": 6305208405152.479, "dur": 186.619, + "args": { + "External id": 716417,"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": 6305208405154.080, "dur": 0.504, + "args": { + "External id": 716418,"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": 6305208405157.919, "dur": 23.507, + "args": { + "External id": 716419,"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": 6305208405183.335, "dur": 6.176, + "args": { + "External id": 716420,"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": 6305208405188.175, "dur": 0.867, + "args": { + "External id": 716421,"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": 6305208405190.320, "dur": 23.181, + "args": { + "External id": 716422,"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": 6305208405191.567, "dur": 1.308, + "args": { + "External id": 716423,"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": 6305208405193.995, "dur": 19.232, + "args": { + "External id": 716424,"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": 6305208405196.854, "dur": 3.124, + "args": { + "External id": 716425,"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": 6305208405214.802, "dur": 19.598, + "args": { + "External id": 716426,"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": 6305208405235.822, "dur": 14.604, + "args": { + "External id": 716427,"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": 6305208405253.075, "dur": 13.871, + "args": { + "External id": 716428,"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": 6305208405273.482, "dur": 13.845, + "args": { + "External id": 716429,"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": 6305208405288.942, "dur": 23.187, + "args": { + "External id": 716430,"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": 6305208405293.022, "dur": 1.504, + "args": { + "External id": 716431,"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": 6305208405296.897, "dur": 0.605, + "args": { + "External id": 716432,"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": 6305208405313.195, "dur": 13.503, + "args": { + "External id": 716433,"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": 6305208405327.586, "dur": 10.550, + "args": { + "External id": 716434,"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": 6305208405348.772, "dur": 1.871, + "args": { + "External id": 716435,"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": 6305208405359.363, "dur": 3.946, + "args": { + "External id": 716436,"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": 6305208405362.005, "dur": 0.477, + "args": { + "External id": 716437,"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": 6305208405429.761, "dur": 56.402, + "args": { + "External id": 716438,"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": 6305208405490.931, "dur": 4.778, + "args": { + "External id": 716439,"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": 6305208405494.121, "dur": 0.532, + "args": { + "External id": 716440,"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": 6305208405497.420, "dur": 44.864, + "args": { + "External id": 716441,"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": 6305208405548.715, "dur": 9.115, + "args": { + "External id": 716442,"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": 6305208405552.903, "dur": 4.120, + "args": { + "External id": 716443,"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": 6305208405555.512, "dur": 1.268, + "args": { + "External id": 716444,"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": 6305208405560.864, "dur": 45.792, + "args": { + "External id": 716445,"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": 6305208405561.797, "dur": 44.254, + "args": { + "External id": 716446,"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": 6305208405610.603, "dur": 16.633, + "args": { + "External id": 716447,"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": 6305208405633.423, "dur": 6.740, + "args": { + "External id": 716448,"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": 6305208405638.526, "dur": 0.768, + "args": { + "External id": 716449,"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": 6305208405644.364, "dur": 44.826, + "args": { + "External id": 716450,"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": 6305208405645.424, "dur": 3.463, + "args": { + "External id": 716451,"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": 6305208405646.232, "dur": 2.096, + "args": { + "External id": 716452,"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": 6305208405647.692, "dur": 0.514, + "args": { + "External id": 716453,"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": 6305208405649.627, "dur": 39.190, + "args": { + "External id": 716454,"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": 6305208405650.277, "dur": 38.033, + "args": { + "External id": 716455,"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": 6305208405695.958, "dur": 4.101, + "args": { + "External id": 716456,"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": 6305208405697.992, "dur": 0.804, + "args": { + "External id": 716457,"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": 6305208405706.070, "dur": 1.605, + "args": { + "External id": 716458,"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": 6305208405715.469, "dur": 6.671, + "args": { + "External id": 716459,"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": 6305208405717.417, "dur": 4.437, + "args": { + "External id": 716460,"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": 6305208405810.130, "dur": 183.028, + "args": { + "External id": 716461,"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": 6305208405814.510, "dur": 2.042, + "args": { + "External id": 716462,"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": 6305208405817.743, "dur": 174.906, + "args": { + "External id": 716463,"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": 6305208405819.005, "dur": 0.373, + "args": { + "External id": 716464,"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": 6305208405820.838, "dur": 22.318, + "args": { + "External id": 716465,"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": 6305208405844.614, "dur": 5.855, + "args": { + "External id": 716466,"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": 6305208405849.104, "dur": 1.167, + "args": { + "External id": 716467,"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": 6305208405851.418, "dur": 24.586, + "args": { + "External id": 716468,"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": 6305208405852.458, "dur": 1.166, + "args": { + "External id": 716469,"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": 6305208405857.257, "dur": 18.501, + "args": { + "External id": 716470,"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": 6305208405860.078, "dur": 2.143, + "args": { + "External id": 716471,"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": 6305208405877.135, "dur": 22.881, + "args": { + "External id": 716472,"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": 6305208405901.437, "dur": 13.193, + "args": { + "External id": 716473,"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": 6305208405916.983, "dur": 13.742, + "args": { + "External id": 716474,"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": 6305208405932.040, "dur": 10.654, + "args": { + "External id": 716475,"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": 6305208405944.567, "dur": 19.204, + "args": { + "External id": 716476,"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": 6305208405946.735, "dur": 1.979, + "args": { + "External id": 716477,"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": 6305208405950.923, "dur": 0.934, + "args": { + "External id": 716478,"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": 6305208405967.364, "dur": 11.123, + "args": { + "External id": 716479,"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": 6305208405979.443, "dur": 12.128, + "args": { + "External id": 716480,"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": 6305208405999.940, "dur": 1.649, + "args": { + "External id": 716481,"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": 6305208406009.840, "dur": 3.511, + "args": { + "External id": 716482,"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": 6305208406012.264, "dur": 0.258, + "args": { + "External id": 716483,"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": 6305208406116.795, "dur": 62.481, + "args": { + "External id": 716484,"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": 6305208406185.232, "dur": 6.728, + "args": { + "External id": 716485,"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": 6305208406188.911, "dur": 1.414, + "args": { + "External id": 716486,"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": 6305208406196.105, "dur": 27.097, + "args": { + "External id": 716487,"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": 6305208406228.070, "dur": 6.295, + "args": { + "External id": 716488,"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": 6305208406229.746, "dur": 3.798, + "args": { + "External id": 716489,"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": 6305208406231.758, "dur": 1.549, + "args": { + "External id": 716490,"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": 6305208406237.081, "dur": 49.053, + "args": { + "External id": 716491,"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": 6305208406238.138, "dur": 47.485, + "args": { + "External id": 716492,"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": 6305208406290.279, "dur": 14.546, + "args": { + "External id": 716493,"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": 6305208406311.559, "dur": 25.080, + "args": { + "External id": 716494,"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": 6305208406313.912, "dur": 22.287, + "args": { + "External id": 716495,"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": 6305208406321.474, "dur": 0.926, + "args": { + "External id": 716496,"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": 6305208406341.627, "dur": 25.554, + "args": { + "External id": 716497,"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": 6305208406343.289, "dur": 23.582, + "args": { + "External id": 716498,"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": 6305208406347.960, "dur": 4.273, + "args": { + "External id": 716499,"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": 6305208406353.452, "dur": 12.983, + "args": { + "External id": 716500,"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": 6305208406378.630, "dur": 6.704, + "args": { + "External id": 716501,"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": 6305208406382.419, "dur": 2.630, + "args": { + "External id": 716502,"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": 6305208406386.406, "dur": 1.188, + "args": { + "External id": 716503,"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": 6305208406387.080, "dur": 0.424, + "args": { + "External id": 716504,"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": 6305208406433.967, "dur": 21.213, + "args": { + "External id": 716505,"Sequence number": 7674843, "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": 6305208406457.052, "dur": 12.677, + "args": { + "External id": 716506,"Sequence number": 7674844, "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": 6305208406457.052, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward", "pid": 2338707, "tid": 2338707, + "ts": 6305208406605.963, "dur": 43.624, + "args": { + "External id": 716507,"Record function id": 0, "Ev Idx": 20767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::div", "pid": 2338707, "tid": 2338707, + "ts": 6305208406756.091, "dur": 36.905, + "args": { + "External id": 716508,"Sequence number": 7674845, "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": 6305208406756.091, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ones_like", "pid": 2338707, "tid": 2338707, + "ts": 6305208406826.992, "dur": 26.787, + "args": { + "External id": 716509,"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": 6305208406828.986, "dur": 8.986, + "args": { + "External id": 716510,"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": 6305208406833.461, "dur": 3.872, + "args": { + "External id": 716511,"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": 6305208406839.708, "dur": 13.797, + "args": { + "External id": 716512,"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": 6305210476393.096, "dur": 56.955, + "args": { + "External id": 716513,"Sequence number": 7674846, "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": 6305210476457.722, "dur": 20.699, + "args": { + "External id": 716514,"Sequence number": 7674847, "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": 6305210476491.055, "dur": 43.907, + "args": { + "External id": 716515,"Sequence number": 7674848, "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": 6305210476539.732, "dur": 110.290, + "args": { + "External id": 716516,"Sequence number": 7674849, "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": 6305210477699.469, "dur": 47.141, + "args": { + "External id": 716517,"Sequence number": 7674850, "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": 6305210477750.609, "dur": 14.908, + "args": { + "External id": 716518,"Sequence number": 7674851, "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": 6305210477774.283, "dur": 15.165, + "args": { + "External id": 716519,"Sequence number": 7674852, "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": 6305210477791.391, "dur": 12.567, + "args": { + "External id": 716520,"Sequence number": 7674853, "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": 6305210479958.111, "dur": 3457.764, + "args": { + "External id": 716521,"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": 6305210480621.913, "dur": 1308.646, + "args": { + "External id": 716522,"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": 6305210480644.870, "dur": 77.454, + "args": { + "External id": 716523,"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": 6305210480648.602, "dur": 16.749, + "args": { + "External id": 716524,"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": 6305210480670.874, "dur": 51.107, + "args": { + "External id": 716525,"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": 6305210480675.628, "dur": 45.813, + "args": { + "External id": 716526,"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": 6305210483451.127, "dur": 4.769, + "args": { + "External id": 716527,"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": 6305210483457.983, "dur": 0.565, + "args": { + "External id": 716528,"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": 6305210483460.046, "dur": 0.606, + "args": { + "External id": 716529,"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": 6305210483461.815, "dur": 0.449, + "args": { + "External id": 716530,"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": 6305210483463.356, "dur": 0.216, + "args": { + "External id": 716531,"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": 6305210483464.855, "dur": 0.423, + "args": { + "External id": 716532,"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": 6305210483466.280, "dur": 0.446, + "args": { + "External id": 716533,"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": 6305210483469.823, "dur": 0.403, + "args": { + "External id": 716534,"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": 6305210483471.426, "dur": 0.490, + "args": { + "External id": 716535,"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": 6305210483473.091, "dur": 0.425, + "args": { + "External id": 716536,"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": 6305210483474.439, "dur": 0.426, + "args": { + "External id": 716537,"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": 6305210483475.899, "dur": 0.444, + "args": { + "External id": 716538,"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": 6305210483477.284, "dur": 0.211, + "args": { + "External id": 716539,"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": 6305210483478.416, "dur": 0.253, + "args": { + "External id": 716540,"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": 6305210483479.623, "dur": 0.202, + "args": { + "External id": 716541,"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": 6305210483482.850, "dur": 0.483, + "args": { + "External id": 716542,"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": 6305210483484.312, "dur": 0.243, + "args": { + "External id": 716543,"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": 6305210483485.748, "dur": 0.169, + "args": { + "External id": 716544,"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": 6305210483487.015, "dur": 0.245, + "args": { + "External id": 716545,"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": 6305210483488.048, "dur": 0.214, + "args": { + "External id": 716546,"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": 6305210483489.172, "dur": 0.240, + "args": { + "External id": 716547,"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": 6305210483490.181, "dur": 0.201, + "args": { + "External id": 716548,"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": 6305210483491.276, "dur": 0.214, + "args": { + "External id": 716549,"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": 6305210483494.329, "dur": 0.223, + "args": { + "External id": 716550,"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": 6305210483495.346, "dur": 0.210, + "args": { + "External id": 716551,"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": 6305210483496.659, "dur": 0.217, + "args": { + "External id": 716552,"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": 6305210483497.652, "dur": 0.203, + "args": { + "External id": 716553,"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": 6305210483498.617, "dur": 0.211, + "args": { + "External id": 716554,"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": 6305210483499.596, "dur": 0.221, + "args": { + "External id": 716555,"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": 6305210483504.240, "dur": 0.239, + "args": { + "External id": 716556,"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": 6305210483516.003, "dur": 0.538, + "args": { + "External id": 716557,"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": 6305210483520.697, "dur": 0.340, + "args": { + "External id": 716558,"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": 6305210483521.987, "dur": 0.252, + "args": { + "External id": 716559,"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": 6305210483523.418, "dur": 0.448, + "args": { + "External id": 716560,"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": 6305210483524.810, "dur": 0.220, + "args": { + "External id": 716561,"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": 6305210483525.915, "dur": 0.243, + "args": { + "External id": 716562,"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": 6305210483527.057, "dur": 0.420, + "args": { + "External id": 716563,"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": 6305210483528.234, "dur": 0.413, + "args": { + "External id": 716564,"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": 6305210483529.769, "dur": 0.236, + "args": { + "External id": 716565,"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": 6305210483533.117, "dur": 0.286, + "args": { + "External id": 716566,"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": 6305210483534.333, "dur": 0.235, + "args": { + "External id": 716567,"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": 6305210483535.905, "dur": 0.283, + "args": { + "External id": 716568,"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": 6305210483538.209, "dur": 0.254, + "args": { + "External id": 716569,"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": 6305210483539.248, "dur": 0.215, + "args": { + "External id": 716570,"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": 6305210483540.290, "dur": 0.403, + "args": { + "External id": 716571,"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": 6305210483541.603, "dur": 0.240, + "args": { + "External id": 716572,"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": 6305210483542.852, "dur": 0.171, + "args": { + "External id": 716573,"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": 6305210483546.057, "dur": 0.457, + "args": { + "External id": 716574,"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": 6305210483547.296, "dur": 0.209, + "args": { + "External id": 716575,"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": 6305210483548.228, "dur": 0.204, + "args": { + "External id": 716576,"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": 6305210483549.330, "dur": 0.210, + "args": { + "External id": 716577,"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": 6305210483550.458, "dur": 0.205, + "args": { + "External id": 716578,"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": 6305210483551.377, "dur": 0.209, + "args": { + "External id": 716579,"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": 6305210483552.705, "dur": 0.207, + "args": { + "External id": 716580,"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": 6305210483553.677, "dur": 0.224, + "args": { + "External id": 716581,"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": 6305210483556.939, "dur": 0.227, + "args": { + "External id": 716582,"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": 6305210483557.946, "dur": 0.217, + "args": { + "External id": 716583,"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": 6305210483558.958, "dur": 0.227, + "args": { + "External id": 716584,"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": 6305210483560.050, "dur": 0.205, + "args": { + "External id": 716585,"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": 6305210483561.017, "dur": 0.218, + "args": { + "External id": 716586,"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": 6305210483562.118, "dur": 0.205, + "args": { + "External id": 716587,"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": 6305210483563.083, "dur": 0.211, + "args": { + "External id": 716588,"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": 6305210483564.036, "dur": 0.209, + "args": { + "External id": 716589,"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": 6305210483567.014, "dur": 0.204, + "args": { + "External id": 716590,"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": 6305210483567.976, "dur": 0.211, + "args": { + "External id": 716591,"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": 6305210483569.063, "dur": 0.434, + "args": { + "External id": 716592,"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": 6305210483570.283, "dur": 0.207, + "args": { + "External id": 716593,"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": 6305210483571.256, "dur": 0.389, + "args": { + "External id": 716594,"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": 6305210483572.376, "dur": 0.405, + "args": { + "External id": 716595,"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": 6305210483573.512, "dur": 0.405, + "args": { + "External id": 716596,"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": 6305210483574.655, "dur": 0.246, + "args": { + "External id": 716597,"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": 6305210483577.641, "dur": 0.455, + "args": { + "External id": 716598,"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": 6305210483578.910, "dur": 0.503, + "args": { + "External id": 716599,"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": 6305210483580.329, "dur": 0.398, + "args": { + "External id": 716600,"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": 6305210483581.515, "dur": 0.214, + "args": { + "External id": 716601,"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": 6305210483582.472, "dur": 0.447, + "args": { + "External id": 716602,"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": 6305210483583.726, "dur": 0.215, + "args": { + "External id": 716603,"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": 6305210483585.721, "dur": 0.216, + "args": { + "External id": 716604,"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": 6305210483586.695, "dur": 0.205, + "args": { + "External id": 716605,"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": 6305210483589.330, "dur": 0.211, + "args": { + "External id": 716606,"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": 6305210483590.507, "dur": 0.203, + "args": { + "External id": 716607,"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": 6305210483591.591, "dur": 0.213, + "args": { + "External id": 716608,"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": 6305210483592.820, "dur": 0.237, + "args": { + "External id": 716609,"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": 6305210483593.768, "dur": 0.216, + "args": { + "External id": 716610,"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": 6305210483594.869, "dur": 0.214, + "args": { + "External id": 716611,"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": 6305210483596.003, "dur": 0.209, + "args": { + "External id": 716612,"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": 6305210483597.039, "dur": 0.490, + "args": { + "External id": 716613,"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": 6305210483600.196, "dur": 0.453, + "args": { + "External id": 716614,"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": 6305210483601.558, "dur": 0.229, + "args": { + "External id": 716615,"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": 6305210483602.530, "dur": 0.480, + "args": { + "External id": 716616,"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": 6305210483603.824, "dur": 0.399, + "args": { + "External id": 716617,"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": 6305210483605.015, "dur": 0.410, + "args": { + "External id": 716618,"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": 6305210483606.159, "dur": 0.208, + "args": { + "External id": 716619,"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": 6305210483608.433, "dur": 0.219, + "args": { + "External id": 716620,"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": 6305210483609.392, "dur": 0.209, + "args": { + "External id": 716621,"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": 6305210483612.993, "dur": 0.424, + "args": { + "External id": 716622,"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": 6305210483614.128, "dur": 0.211, + "args": { + "External id": 716623,"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": 6305210483615.207, "dur": 0.440, + "args": { + "External id": 716624,"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": 6305210483616.563, "dur": 0.245, + "args": { + "External id": 716625,"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": 6305210483617.540, "dur": 0.210, + "args": { + "External id": 716626,"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": 6305210483618.817, "dur": 0.407, + "args": { + "External id": 716627,"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": 6305210483620.131, "dur": 0.218, + "args": { + "External id": 716628,"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": 6305210483621.060, "dur": 0.205, + "args": { + "External id": 716629,"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": 6305210483624.044, "dur": 0.360, + "args": { + "External id": 716630,"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": 6305210483625.236, "dur": 0.229, + "args": { + "External id": 716631,"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": 6305210483626.364, "dur": 0.469, + "args": { + "External id": 716632,"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": 6305210483627.850, "dur": 0.209, + "args": { + "External id": 716633,"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": 6305210483628.777, "dur": 0.226, + "args": { + "External id": 716634,"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": 6305210483629.844, "dur": 0.217, + "args": { + "External id": 716635,"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": 6305210483631.370, "dur": 0.211, + "args": { + "External id": 716636,"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": 6305210483632.439, "dur": 0.211, + "args": { + "External id": 716637,"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": 6305210483635.250, "dur": 0.216, + "args": { + "External id": 716638,"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": 6305210483636.174, "dur": 0.488, + "args": { + "External id": 716639,"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": 6305210483637.577, "dur": 0.352, + "args": { + "External id": 716640,"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": 6305210483638.668, "dur": 0.205, + "args": { + "External id": 716641,"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": 6305210483639.650, "dur": 0.334, + "args": { + "External id": 716642,"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": 6305210483640.871, "dur": 0.318, + "args": { + "External id": 716643,"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": 6305210483641.950, "dur": 0.327, + "args": { + "External id": 716644,"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": 6305210483642.998, "dur": 0.356, + "args": { + "External id": 716645,"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": 6305210483645.983, "dur": 0.407, + "args": { + "External id": 716646,"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": 6305210483647.120, "dur": 0.350, + "args": { + "External id": 716647,"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": 6305210483648.364, "dur": 0.221, + "args": { + "External id": 716648,"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": 6305210483649.502, "dur": 0.203, + "args": { + "External id": 716649,"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": 6305210483650.417, "dur": 0.207, + "args": { + "External id": 716650,"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": 6305210483651.662, "dur": 0.215, + "args": { + "External id": 716651,"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": 6305210483652.610, "dur": 0.212, + "args": { + "External id": 716652,"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": 6305210483653.613, "dur": 0.208, + "args": { + "External id": 716653,"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": 6305210483656.690, "dur": 0.238, + "args": { + "External id": 716654,"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": 6305210483657.719, "dur": 0.207, + "args": { + "External id": 716655,"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": 6305210483658.984, "dur": 0.202, + "args": { + "External id": 716656,"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": 6305210483659.935, "dur": 0.203, + "args": { + "External id": 716657,"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": 6305210483660.850, "dur": 0.215, + "args": { + "External id": 716658,"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": 6305210483661.999, "dur": 0.207, + "args": { + "External id": 716659,"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": 6305210483662.945, "dur": 0.203, + "args": { + "External id": 716660,"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": 6305210483663.876, "dur": 0.207, + "args": { + "External id": 716661,"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": 6305210483666.963, "dur": 0.208, + "args": { + "External id": 716662,"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": 6305210483667.910, "dur": 0.214, + "args": { + "External id": 716663,"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": 6305210483668.847, "dur": 0.210, + "args": { + "External id": 716664,"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": 6305210483669.817, "dur": 0.208, + "args": { + "External id": 716665,"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": 6305210483670.986, "dur": 0.210, + "args": { + "External id": 716666,"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": 6305210483671.949, "dur": 0.208, + "args": { + "External id": 716667,"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": 6305210483672.909, "dur": 0.211, + "args": { + "External id": 716668,"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": 6305210483673.855, "dur": 0.211, + "args": { + "External id": 716669,"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": 6305210483676.760, "dur": 0.208, + "args": { + "External id": 716670,"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": 6305210483677.935, "dur": 0.230, + "args": { + "External id": 716671,"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": 6305210483678.944, "dur": 0.224, + "args": { + "External id": 716672,"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": 6305210483679.959, "dur": 0.219, + "args": { + "External id": 716673,"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": 6305210483680.892, "dur": 0.204, + "args": { + "External id": 716674,"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": 6305210483681.844, "dur": 0.212, + "args": { + "External id": 716675,"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": 6305210483683.508, "dur": 0.216, + "args": { + "External id": 716676,"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": 6305210483684.501, "dur": 0.203, + "args": { + "External id": 716677,"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": 6305210483687.464, "dur": 0.370, + "args": { + "External id": 716678,"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": 6305210483688.545, "dur": 0.339, + "args": { + "External id": 716679,"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": 6305210483689.979, "dur": 0.342, + "args": { + "External id": 716680,"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": 6305210483691.203, "dur": 0.206, + "args": { + "External id": 716681,"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": 6305210483692.144, "dur": 0.338, + "args": { + "External id": 716682,"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": 6305210483694.657, "dur": 0.235, + "args": { + "External id": 716683,"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": 6305210483695.805, "dur": 0.232, + "args": { + "External id": 716684,"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": 6305210483696.791, "dur": 0.345, + "args": { + "External id": 716685,"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": 6305210483700.140, "dur": 0.224, + "args": { + "External id": 716686,"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": 6305210483701.112, "dur": 0.345, + "args": { + "External id": 716687,"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": 6305210483702.380, "dur": 0.212, + "args": { + "External id": 716688,"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": 6305210483703.344, "dur": 0.506, + "args": { + "External id": 716689,"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": 6305210483704.637, "dur": 0.227, + "args": { + "External id": 716690,"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": 6305210483705.585, "dur": 0.225, + "args": { + "External id": 716691,"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": 6305210483706.526, "dur": 0.438, + "args": { + "External id": 716692,"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": 6305210483707.943, "dur": 0.207, + "args": { + "External id": 716693,"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": 6305210483710.729, "dur": 0.207, + "args": { + "External id": 716694,"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": 6305210483711.908, "dur": 0.224, + "args": { + "External id": 716695,"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": 6305210483712.880, "dur": 0.207, + "args": { + "External id": 716696,"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": 6305210483714.051, "dur": 0.210, + "args": { + "External id": 716697,"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": 6305210483714.983, "dur": 0.205, + "args": { + "External id": 716698,"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": 6305210483715.924, "dur": 0.227, + "args": { + "External id": 716699,"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": 6305210483717.505, "dur": 0.234, + "args": { + "External id": 716700,"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": 6305210483718.542, "dur": 0.206, + "args": { + "External id": 716701,"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": 6305210483721.462, "dur": 0.215, + "args": { + "External id": 716702,"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": 6305210483722.408, "dur": 0.209, + "args": { + "External id": 716703,"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": 6305210483723.500, "dur": 0.211, + "args": { + "External id": 716704,"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": 6305210483724.605, "dur": 0.215, + "args": { + "External id": 716705,"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": 6305210483725.570, "dur": 0.202, + "args": { + "External id": 716706,"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": 6305210483726.675, "dur": 0.210, + "args": { + "External id": 716707,"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": 6305210483727.704, "dur": 0.231, + "args": { + "External id": 716708,"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": 6305210483728.669, "dur": 0.203, + "args": { + "External id": 716709,"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": 6305210483731.852, "dur": 0.237, + "args": { + "External id": 716710,"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": 6305210483732.865, "dur": 0.205, + "args": { + "External id": 716711,"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": 6305210483733.860, "dur": 0.495, + "args": { + "External id": 716712,"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": 6305210483735.073, "dur": 0.204, + "args": { + "External id": 716713,"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": 6305210483736.054, "dur": 0.530, + "args": { + "External id": 716714,"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": 6305210483737.437, "dur": 0.372, + "args": { + "External id": 716715,"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": 6305210483738.666, "dur": 0.285, + "args": { + "External id": 716716,"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": 6305210483744.065, "dur": 0.418, + "args": { + "External id": 716717,"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": 6305210483747.461, "dur": 0.409, + "args": { + "External id": 716718,"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": 6305210483748.620, "dur": 0.429, + "args": { + "External id": 716719,"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": 6305210483749.760, "dur": 0.452, + "args": { + "External id": 716720,"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": 6305210483750.924, "dur": 0.204, + "args": { + "External id": 716721,"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": 6305210483751.845, "dur": 0.204, + "args": { + "External id": 716722,"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": 6305210483752.786, "dur": 0.213, + "args": { + "External id": 716723,"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": 6305210483753.907, "dur": 0.214, + "args": { + "External id": 716724,"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": 6305210483755.124, "dur": 0.204, + "args": { + "External id": 716725,"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": 6305210483758.334, "dur": 0.230, + "args": { + "External id": 716726,"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": 6305210483759.358, "dur": 0.206, + "args": { + "External id": 716727,"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": 6305210483760.810, "dur": 0.216, + "args": { + "External id": 716728,"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": 6305210483761.947, "dur": 0.204, + "args": { + "External id": 716729,"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": 6305210483762.892, "dur": 0.443, + "args": { + "External id": 716730,"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": 6305210483764.250, "dur": 0.210, + "args": { + "External id": 716731,"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": 6305210483765.495, "dur": 0.209, + "args": { + "External id": 716732,"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": 6305210483766.458, "dur": 0.213, + "args": { + "External id": 716733,"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": 6305210483769.283, "dur": 0.207, + "args": { + "External id": 716734,"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": 6305210483770.217, "dur": 0.208, + "args": { + "External id": 716735,"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": 6305210483771.404, "dur": 0.204, + "args": { + "External id": 716736,"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": 6305210483772.335, "dur": 0.210, + "args": { + "External id": 716737,"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": 6305210483773.309, "dur": 0.206, + "args": { + "External id": 716738,"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": 6305210483774.308, "dur": 0.207, + "args": { + "External id": 716739,"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": 6305210483775.250, "dur": 0.208, + "args": { + "External id": 716740,"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": 6305210483776.180, "dur": 0.409, + "args": { + "External id": 716741,"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": 6305210483779.531, "dur": 0.394, + "args": { + "External id": 716742,"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": 6305210483780.683, "dur": 0.212, + "args": { + "External id": 716743,"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": 6305210483781.635, "dur": 0.448, + "args": { + "External id": 716744,"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": 6305210483782.852, "dur": 0.213, + "args": { + "External id": 716745,"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": 6305210483783.792, "dur": 0.205, + "args": { + "External id": 716746,"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": 6305210483784.734, "dur": 0.252, + "args": { + "External id": 716747,"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": 6305210483785.793, "dur": 0.413, + "args": { + "External id": 716748,"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": 6305210483786.931, "dur": 0.450, + "args": { + "External id": 716749,"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": 6305210483789.868, "dur": 0.447, + "args": { + "External id": 716750,"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": 6305210483791.088, "dur": 0.200, + "args": { + "External id": 716751,"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": 6305210483792.115, "dur": 0.219, + "args": { + "External id": 716752,"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": 6305210483793.137, "dur": 0.208, + "args": { + "External id": 716753,"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": 6305210483794.071, "dur": 0.214, + "args": { + "External id": 716754,"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": 6305210483795.205, "dur": 0.213, + "args": { + "External id": 716755,"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": 6305210483796.159, "dur": 0.211, + "args": { + "External id": 716756,"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": 6305210483797.085, "dur": 0.213, + "args": { + "External id": 716757,"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": 6305210483800.141, "dur": 0.204, + "args": { + "External id": 716758,"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": 6305210483801.079, "dur": 0.211, + "args": { + "External id": 716759,"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": 6305210483802.442, "dur": 0.218, + "args": { + "External id": 716760,"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": 6305210483803.411, "dur": 0.206, + "args": { + "External id": 716761,"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": 6305210483804.340, "dur": 0.531, + "args": { + "External id": 716762,"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": 6305210483805.591, "dur": 0.202, + "args": { + "External id": 716763,"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": 6305210483806.523, "dur": 0.429, + "args": { + "External id": 716764,"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": 6305210483807.692, "dur": 0.216, + "args": { + "External id": 716765,"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": 6305210483810.695, "dur": 0.205, + "args": { + "External id": 716766,"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": 6305210483811.637, "dur": 0.209, + "args": { + "External id": 716767,"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": 6305210483812.559, "dur": 0.204, + "args": { + "External id": 716768,"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": 6305210483813.490, "dur": 0.214, + "args": { + "External id": 716769,"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": 6305210483814.522, "dur": 0.442, + "args": { + "External id": 716770,"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": 6305210483815.699, "dur": 0.396, + "args": { + "External id": 716771,"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": 6305210483816.805, "dur": 0.396, + "args": { + "External id": 716772,"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": 6305210483817.915, "dur": 0.422, + "args": { + "External id": 716773,"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": 6305210483820.902, "dur": 0.530, + "args": { + "External id": 716774,"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": 6305210483822.327, "dur": 0.418, + "args": { + "External id": 716775,"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": 6305210483823.493, "dur": 0.397, + "args": { + "External id": 716776,"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": 6305210483824.822, "dur": 0.207, + "args": { + "External id": 716777,"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": 6305210483825.742, "dur": 0.396, + "args": { + "External id": 716778,"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": 6305210483827.001, "dur": 0.414, + "args": { + "External id": 716779,"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": 6305210483828.183, "dur": 0.399, + "args": { + "External id": 716780,"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": 6305210483829.407, "dur": 0.204, + "args": { + "External id": 716781,"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": 6305210483832.235, "dur": 0.215, + "args": { + "External id": 716782,"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": 6305210483833.201, "dur": 0.202, + "args": { + "External id": 716783,"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": 6305210483834.111, "dur": 0.200, + "args": { + "External id": 716784,"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": 6305210483835.019, "dur": 0.203, + "args": { + "External id": 716785,"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": 6305210483835.945, "dur": 0.213, + "args": { + "External id": 716786,"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": 6305210483836.992, "dur": 0.209, + "args": { + "External id": 716787,"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": 6305210483838.030, "dur": 0.207, + "args": { + "External id": 716788,"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": 6305210483839.014, "dur": 0.345, + "args": { + "External id": 716789,"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": 6305210483842.161, "dur": 0.216, + "args": { + "External id": 716790,"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": 6305210483843.124, "dur": 0.226, + "args": { + "External id": 716791,"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": 6305210483844.101, "dur": 0.206, + "args": { + "External id": 716792,"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": 6305210483845.154, "dur": 0.216, + "args": { + "External id": 716793,"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": 6305210483846.108, "dur": 0.210, + "args": { + "External id": 716794,"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": 6305210483847.118, "dur": 0.210, + "args": { + "External id": 716795,"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": 6305210483848.524, "dur": 0.214, + "args": { + "External id": 716796,"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": 6305210483850.600, "dur": 0.222, + "args": { + "External id": 716797,"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": 6305210483854.160, "dur": 0.203, + "args": { + "External id": 716798,"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": 6305210483855.152, "dur": 0.216, + "args": { + "External id": 716799,"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": 6305210483909.398, "dur": 1510.933, + "args": { + "External id": 716800,"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": 6305210484326.077, "dur": 1007.727, + "args": { + "External id": 722945,"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": 6305210484333.932, "dur": 9.941, + "args": { + "External id": 722946,"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": 6305210484340.037, "dur": 3.110, + "args": { + "External id": 722947,"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": 6305210484344.535, "dur": 1.490, + "args": { + "External id": 722948,"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": 6305210484345.448, "dur": 0.490, + "args": { + "External id": 722949,"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": 6305210484346.359, "dur": 4.274, + "args": { + "External id": 722950,"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": 6305210484348.526, "dur": 1.967, + "args": { + "External id": 722951,"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": 6305210484350.914, "dur": 1.044, + "args": { + "External id": 722952,"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": 6305210484351.324, "dur": 0.551, + "args": { + "External id": 722953,"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": 6305210484352.248, "dur": 3.195, + "args": { + "External id": 722954,"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": 6305210484354.416, "dur": 0.959, + "args": { + "External id": 722955,"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": 6305210484355.897, "dur": 2.519, + "args": { + "External id": 722956,"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": 6305210484357.839, "dur": 0.507, + "args": { + "External id": 722957,"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": 6305210484360.567, "dur": 0.950, + "args": { + "External id": 722958,"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": 6305210484360.966, "dur": 0.481, + "args": { + "External id": 722959,"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": 6305210484361.796, "dur": 2.398, + "args": { + "External id": 722960,"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": 6305210484363.604, "dur": 0.522, + "args": { + "External id": 722961,"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": 6305210484364.473, "dur": 2.552, + "args": { + "External id": 722962,"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": 6305210484366.410, "dur": 0.550, + "args": { + "External id": 722963,"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": 6305210484367.250, "dur": 1.331, + "args": { + "External id": 722964,"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": 6305210484367.702, "dur": 0.817, + "args": { + "External id": 722965,"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": 6305210484368.903, "dur": 4.112, + "args": { + "External id": 722966,"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": 6305210484370.623, "dur": 2.078, + "args": { + "External id": 722967,"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": 6305210484373.287, "dur": 1.303, + "args": { + "External id": 722968,"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": 6305210484373.672, "dur": 0.854, + "args": { + "External id": 722969,"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": 6305210484374.812, "dur": 3.096, + "args": { + "External id": 722970,"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": 6305210484376.829, "dur": 1.008, + "args": { + "External id": 722971,"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": 6305210484378.334, "dur": 2.599, + "args": { + "External id": 722972,"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": 6305210484380.273, "dur": 0.598, + "args": { + "External id": 722973,"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": 6305210484383.129, "dur": 1.103, + "args": { + "External id": 722974,"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": 6305210484383.559, "dur": 0.606, + "args": { + "External id": 722975,"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": 6305210484384.464, "dur": 2.997, + "args": { + "External id": 722976,"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": 6305210484386.383, "dur": 0.999, + "args": { + "External id": 722977,"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": 6305210484387.683, "dur": 2.941, + "args": { + "External id": 722978,"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": 6305210484390.053, "dur": 0.502, + "args": { + "External id": 722979,"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": 6305210484391.075, "dur": 0.980, + "args": { + "External id": 722980,"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": 6305210484391.434, "dur": 0.552, + "args": { + "External id": 722981,"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": 6305210484392.289, "dur": 3.826, + "args": { + "External id": 722982,"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": 6305210484393.726, "dur": 2.320, + "args": { + "External id": 722983,"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": 6305210484396.366, "dur": 1.000, + "args": { + "External id": 722984,"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": 6305210484396.721, "dur": 0.578, + "args": { + "External id": 722985,"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": 6305210484397.819, "dur": 2.254, + "args": { + "External id": 722986,"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": 6305210484399.314, "dur": 0.692, + "args": { + "External id": 722987,"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": 6305210484400.401, "dur": 2.996, + "args": { + "External id": 722988,"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": 6305210484402.586, "dur": 0.744, + "args": { + "External id": 722989,"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": 6305210484405.828, "dur": 0.978, + "args": { + "External id": 722990,"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": 6305210484406.197, "dur": 0.542, + "args": { + "External id": 722991,"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": 6305210484407.033, "dur": 2.687, + "args": { + "External id": 722992,"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": 6305210484408.828, "dur": 0.826, + "args": { + "External id": 722993,"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": 6305210484409.943, "dur": 2.632, + "args": { + "External id": 722994,"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": 6305210484412.013, "dur": 0.492, + "args": { + "External id": 722995,"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": 6305210484412.795, "dur": 1.046, + "args": { + "External id": 722996,"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": 6305210484413.146, "dur": 0.631, + "args": { + "External id": 722997,"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": 6305210484414.058, "dur": 3.087, + "args": { + "External id": 722998,"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": 6305210484415.388, "dur": 1.507, + "args": { + "External id": 722999,"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": 6305210484417.373, "dur": 1.410, + "args": { + "External id": 723000,"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": 6305210484417.725, "dur": 0.989, + "args": { + "External id": 723001,"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": 6305210484419.301, "dur": 2.385, + "args": { + "External id": 723002,"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": 6305210484420.897, "dur": 0.723, + "args": { + "External id": 723003,"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": 6305210484421.909, "dur": 3.028, + "args": { + "External id": 723004,"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": 6305210484424.295, "dur": 0.579, + "args": { + "External id": 723005,"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": 6305210484427.189, "dur": 0.970, + "args": { + "External id": 723006,"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": 6305210484427.615, "dur": 0.482, + "args": { + "External id": 723007,"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": 6305210484428.388, "dur": 2.206, + "args": { + "External id": 723008,"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": 6305210484429.940, "dur": 0.588, + "args": { + "External id": 723009,"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": 6305210484430.815, "dur": 2.758, + "args": { + "External id": 723010,"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": 6305210484432.957, "dur": 0.547, + "args": { + "External id": 723011,"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": 6305210484433.809, "dur": 1.108, + "args": { + "External id": 723012,"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": 6305210484434.166, "dur": 0.687, + "args": { + "External id": 723013,"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": 6305210484435.139, "dur": 4.276, + "args": { + "External id": 723014,"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": 6305210484437.292, "dur": 2.049, + "args": { + "External id": 723015,"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": 6305210484439.642, "dur": 0.924, + "args": { + "External id": 723016,"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": 6305210484440.010, "dur": 0.496, + "args": { + "External id": 723017,"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": 6305210484440.793, "dur": 2.477, + "args": { + "External id": 723018,"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": 6305210484442.493, "dur": 0.709, + "args": { + "External id": 723019,"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": 6305210484443.657, "dur": 2.680, + "args": { + "External id": 723020,"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": 6305210484445.634, "dur": 0.634, + "args": { + "External id": 723021,"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": 6305210484448.990, "dur": 1.270, + "args": { + "External id": 723022,"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": 6305210484449.397, "dur": 0.796, + "args": { + "External id": 723023,"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": 6305210484450.520, "dur": 2.298, + "args": { + "External id": 723024,"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": 6305210484451.846, "dur": 0.903, + "args": { + "External id": 723025,"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": 6305210484453.050, "dur": 2.640, + "args": { + "External id": 723026,"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": 6305210484455.060, "dur": 0.569, + "args": { + "External id": 723027,"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": 6305210484455.913, "dur": 0.980, + "args": { + "External id": 723028,"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": 6305210484456.272, "dur": 0.549, + "args": { + "External id": 723029,"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": 6305210484457.120, "dur": 3.791, + "args": { + "External id": 723030,"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": 6305210484458.834, "dur": 2.003, + "args": { + "External id": 723031,"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": 6305210484461.135, "dur": 1.205, + "args": { + "External id": 723032,"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": 6305210484461.542, "dur": 0.731, + "args": { + "External id": 723033,"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": 6305210484462.561, "dur": 2.479, + "args": { + "External id": 723034,"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": 6305210484464.283, "dur": 0.690, + "args": { + "External id": 723035,"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": 6305210484465.261, "dur": 2.379, + "args": { + "External id": 723036,"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": 6305210484467.026, "dur": 0.545, + "args": { + "External id": 723037,"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": 6305210484470.076, "dur": 1.022, + "args": { + "External id": 723038,"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": 6305210484470.443, "dur": 0.584, + "args": { + "External id": 723039,"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": 6305210484471.315, "dur": 2.431, + "args": { + "External id": 723040,"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": 6305210484473.074, "dur": 0.603, + "args": { + "External id": 723041,"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": 6305210484473.966, "dur": 2.754, + "args": { + "External id": 723042,"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": 6305210484475.844, "dur": 0.807, + "args": { + "External id": 723043,"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": 6305210484476.942, "dur": 1.298, + "args": { + "External id": 723044,"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": 6305210484477.326, "dur": 0.847, + "args": { + "External id": 723045,"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": 6305210484478.551, "dur": 4.343, + "args": { + "External id": 723046,"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": 6305210484480.788, "dur": 2.036, + "args": { + "External id": 723047,"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": 6305210484483.132, "dur": 1.283, + "args": { + "External id": 723048,"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": 6305210484483.504, "dur": 0.846, + "args": { + "External id": 723049,"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": 6305210484484.636, "dur": 2.003, + "args": { + "External id": 723050,"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": 6305210484486.079, "dur": 0.488, + "args": { + "External id": 723051,"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": 6305210484486.864, "dur": 2.222, + "args": { + "External id": 723052,"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": 6305210484488.461, "dur": 0.560, + "args": { + "External id": 723053,"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": 6305210484490.837, "dur": 1.003, + "args": { + "External id": 723054,"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": 6305210484491.235, "dur": 0.538, + "args": { + "External id": 723055,"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": 6305210484492.062, "dur": 3.984, + "args": { + "External id": 723056,"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": 6305210484494.317, "dur": 1.653, + "args": { + "External id": 723057,"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": 6305210484496.273, "dur": 0.957, + "args": { + "External id": 723058,"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": 6305210484496.684, "dur": 0.478, + "args": { + "External id": 723059,"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": 6305210484497.537, "dur": 1.098, + "args": { + "External id": 723060,"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": 6305210484497.888, "dur": 0.684, + "args": { + "External id": 723061,"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": 6305210484498.870, "dur": 3.691, + "args": { + "External id": 723062,"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": 6305210484501.868, "dur": 0.625, + "args": { + "External id": 723063,"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": 6305210484502.826, "dur": 1.199, + "args": { + "External id": 723064,"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": 6305210484503.186, "dur": 0.774, + "args": { + "External id": 723065,"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": 6305210484504.417, "dur": 15.266, + "args": { + "External id": 723066,"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": 6305210484518.386, "dur": 0.920, + "args": { + "External id": 723067,"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": 6305210484520.379, "dur": 3.122, + "args": { + "External id": 723068,"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": 6305210484522.776, "dur": 0.662, + "args": { + "External id": 723069,"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": 6305210484526.021, "dur": 0.880, + "args": { + "External id": 723070,"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": 6305210484526.374, "dur": 0.466, + "args": { + "External id": 723071,"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": 6305210484527.146, "dur": 3.954, + "args": { + "External id": 723072,"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": 6305210484528.814, "dur": 2.218, + "args": { + "External id": 723073,"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": 6305210484531.329, "dur": 0.931, + "args": { + "External id": 723074,"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": 6305210484531.688, "dur": 0.505, + "args": { + "External id": 723075,"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": 6305210484532.482, "dur": 0.984, + "args": { + "External id": 723076,"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": 6305210484532.833, "dur": 0.571, + "args": { + "External id": 723077,"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": 6305210484533.727, "dur": 4.260, + "args": { + "External id": 723078,"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": 6305210484537.481, "dur": 0.441, + "args": { + "External id": 723079,"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": 6305210484538.264, "dur": 1.217, + "args": { + "External id": 723080,"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": 6305210484538.818, "dur": 0.601, + "args": { + "External id": 723081,"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": 6305210484539.913, "dur": 2.654, + "args": { + "External id": 723082,"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": 6305210484542.010, "dur": 0.493, + "args": { + "External id": 723083,"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": 6305210484542.802, "dur": 2.559, + "args": { + "External id": 723084,"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": 6305210484544.641, "dur": 0.650, + "args": { + "External id": 723085,"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": 6305210484547.444, "dur": 1.209, + "args": { + "External id": 723086,"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": 6305210484547.960, "dur": 0.629, + "args": { + "External id": 723087,"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": 6305210484548.875, "dur": 3.789, + "args": { + "External id": 723088,"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": 6305210484550.459, "dur": 2.134, + "args": { + "External id": 723089,"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": 6305210484552.894, "dur": 1.095, + "args": { + "External id": 723090,"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": 6305210484553.247, "dur": 0.669, + "args": { + "External id": 723091,"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": 6305210484554.210, "dur": 1.448, + "args": { + "External id": 723092,"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": 6305210484554.565, "dur": 1.030, + "args": { + "External id": 723093,"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": 6305210484555.900, "dur": 3.766, + "args": { + "External id": 723094,"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": 6305210484559.009, "dur": 0.587, + "args": { + "External id": 723095,"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": 6305210484559.933, "dur": 1.010, + "args": { + "External id": 723096,"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": 6305210484560.298, "dur": 0.584, + "args": { + "External id": 723097,"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": 6305210484561.186, "dur": 2.431, + "args": { + "External id": 723098,"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": 6305210484563.033, "dur": 0.520, + "args": { + "External id": 723099,"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": 6305210484563.839, "dur": 2.668, + "args": { + "External id": 723100,"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": 6305210484565.904, "dur": 0.537, + "args": { + "External id": 723101,"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": 6305210484568.830, "dur": 0.821, + "args": { + "External id": 723102,"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": 6305210484569.196, "dur": 0.392, + "args": { + "External id": 723103,"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": 6305210484569.868, "dur": 3.186, + "args": { + "External id": 723104,"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": 6305210484571.293, "dur": 1.687, + "args": { + "External id": 723105,"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": 6305210484573.277, "dur": 1.076, + "args": { + "External id": 723106,"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": 6305210484573.626, "dur": 0.654, + "args": { + "External id": 723107,"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": 6305210484574.652, "dur": 1.048, + "args": { + "External id": 723108,"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": 6305210484575.000, "dur": 0.637, + "args": { + "External id": 723109,"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": 6305210484576.045, "dur": 3.538, + "args": { + "External id": 723110,"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": 6305210484578.980, "dur": 0.540, + "args": { + "External id": 723111,"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": 6305210484579.827, "dur": 1.038, + "args": { + "External id": 723112,"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": 6305210484580.202, "dur": 0.601, + "args": { + "External id": 723113,"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": 6305210484581.103, "dur": 2.423, + "args": { + "External id": 723114,"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": 6305210484582.623, "dur": 0.835, + "args": { + "External id": 723115,"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": 6305210484583.759, "dur": 2.900, + "args": { + "External id": 723116,"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": 6305210484586.060, "dur": 0.533, + "args": { + "External id": 723117,"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": 6305210484589.007, "dur": 1.133, + "args": { + "External id": 723118,"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": 6305210484589.353, "dur": 0.722, + "args": { + "External id": 723119,"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": 6305210484590.371, "dur": 3.210, + "args": { + "External id": 723120,"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": 6305210484591.709, "dur": 1.608, + "args": { + "External id": 723121,"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": 6305210484593.830, "dur": 1.036, + "args": { + "External id": 723122,"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": 6305210484594.201, "dur": 0.600, + "args": { + "External id": 723123,"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": 6305210484595.275, "dur": 1.585, + "args": { + "External id": 723124,"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": 6305210484596.044, "dur": 0.751, + "args": { + "External id": 723125,"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": 6305210484597.099, "dur": 3.474, + "args": { + "External id": 723126,"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": 6305210484599.997, "dur": 0.513, + "args": { + "External id": 723127,"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": 6305210484600.846, "dur": 1.635, + "args": { + "External id": 723128,"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": 6305210484601.877, "dur": 0.540, + "args": { + "External id": 723129,"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": 6305210484602.723, "dur": 1.545, + "args": { + "External id": 723130,"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": 6305210484603.386, "dur": 0.818, + "args": { + "External id": 723131,"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": 6305210484604.623, "dur": 4.063, + "args": { + "External id": 723132,"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": 6305210484608.087, "dur": 0.526, + "args": { + "External id": 723133,"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": 6305210484611.955, "dur": 1.699, + "args": { + "External id": 723134,"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": 6305210484613.082, "dur": 0.506, + "args": { + "External id": 723135,"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": 6305210484613.894, "dur": 3.239, + "args": { + "External id": 723136,"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": 6305210484614.950, "dur": 1.900, + "args": { + "External id": 723137,"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": 6305210484617.421, "dur": 1.783, + "args": { + "External id": 723138,"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": 6305210484618.353, "dur": 0.787, + "args": { + "External id": 723139,"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": 6305210484619.444, "dur": 1.956, + "args": { + "External id": 723140,"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": 6305210484620.626, "dur": 0.714, + "args": { + "External id": 723141,"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": 6305210484621.821, "dur": 2.829, + "args": { + "External id": 723142,"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": 6305210484623.920, "dur": 0.665, + "args": { + "External id": 723143,"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": 6305210484624.975, "dur": 2.128, + "args": { + "External id": 723144,"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": 6305210484626.306, "dur": 0.731, + "args": { + "External id": 723145,"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": 6305210484627.373, "dur": 1.836, + "args": { + "External id": 723146,"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": 6305210484628.510, "dur": 0.636, + "args": { + "External id": 723147,"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": 6305210484629.446, "dur": 3.267, + "args": { + "External id": 723148,"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": 6305210484632.127, "dur": 0.525, + "args": { + "External id": 723149,"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": 6305210484634.930, "dur": 1.261, + "args": { + "External id": 723150,"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": 6305210484635.597, "dur": 0.522, + "args": { + "External id": 723151,"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": 6305210484636.553, "dur": 3.558, + "args": { + "External id": 723152,"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": 6305210484637.921, "dur": 1.902, + "args": { + "External id": 723153,"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": 6305210484640.361, "dur": 1.282, + "args": { + "External id": 723154,"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": 6305210484641.000, "dur": 0.583, + "args": { + "External id": 723155,"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": 6305210484642.000, "dur": 1.793, + "args": { + "External id": 723156,"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": 6305210484643.088, "dur": 0.641, + "args": { + "External id": 723157,"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": 6305210484644.033, "dur": 2.771, + "args": { + "External id": 723158,"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": 6305210484646.086, "dur": 0.651, + "args": { + "External id": 723159,"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": 6305210484647.083, "dur": 1.826, + "args": { + "External id": 723160,"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": 6305210484648.273, "dur": 0.569, + "args": { + "External id": 723161,"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": 6305210484649.147, "dur": 1.840, + "args": { + "External id": 723162,"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": 6305210484650.252, "dur": 0.674, + "args": { + "External id": 723163,"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": 6305210484651.337, "dur": 3.926, + "args": { + "External id": 723164,"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": 6305210484654.422, "dur": 0.773, + "args": { + "External id": 723165,"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": 6305210484657.420, "dur": 1.517, + "args": { + "External id": 723166,"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": 6305210484658.269, "dur": 0.605, + "args": { + "External id": 723167,"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": 6305210484659.174, "dur": 2.445, + "args": { + "External id": 723168,"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": 6305210484660.175, "dur": 1.375, + "args": { + "External id": 723169,"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": 6305210484661.865, "dur": 1.476, + "args": { + "External id": 723170,"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": 6305210484662.654, "dur": 0.620, + "args": { + "External id": 723171,"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": 6305210484663.598, "dur": 1.732, + "args": { + "External id": 723172,"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": 6305210484664.515, "dur": 0.752, + "args": { + "External id": 723173,"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": 6305210484665.581, "dur": 3.079, + "args": { + "External id": 723174,"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": 6305210484668.067, "dur": 0.526, + "args": { + "External id": 723175,"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": 6305210484668.946, "dur": 2.269, + "args": { + "External id": 723176,"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": 6305210484670.536, "dur": 0.604, + "args": { + "External id": 723177,"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": 6305210484671.480, "dur": 1.579, + "args": { + "External id": 723178,"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": 6305210484672.367, "dur": 0.630, + "args": { + "External id": 723179,"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": 6305210484673.293, "dur": 3.766, + "args": { + "External id": 723180,"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": 6305210484676.405, "dur": 0.581, + "args": { + "External id": 723181,"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": 6305210484678.797, "dur": 1.738, + "args": { + "External id": 723182,"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": 6305210484679.784, "dur": 0.686, + "args": { + "External id": 723183,"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": 6305210484680.770, "dur": 3.616, + "args": { + "External id": 723184,"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": 6305210484682.234, "dur": 2.084, + "args": { + "External id": 723185,"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": 6305210484684.628, "dur": 2.180, + "args": { + "External id": 723186,"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": 6305210484685.727, "dur": 1.015, + "args": { + "External id": 723187,"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": 6305210484687.043, "dur": 2.543, + "args": { + "External id": 723188,"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": 6305210484688.462, "dur": 1.062, + "args": { + "External id": 723189,"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": 6305210484689.883, "dur": 2.827, + "args": { + "External id": 723190,"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": 6305210484692.077, "dur": 0.567, + "args": { + "External id": 723191,"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": 6305210484692.988, "dur": 1.586, + "args": { + "External id": 723192,"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": 6305210484693.915, "dur": 0.596, + "args": { + "External id": 723193,"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": 6305210484694.823, "dur": 2.178, + "args": { + "External id": 723194,"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": 6305210484696.060, "dur": 0.876, + "args": { + "External id": 723195,"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": 6305210484697.255, "dur": 3.593, + "args": { + "External id": 723196,"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": 6305210484700.099, "dur": 0.686, + "args": { + "External id": 723197,"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": 6305210484703.548, "dur": 1.613, + "args": { + "External id": 723198,"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": 6305210484704.466, "dur": 0.631, + "args": { + "External id": 723199,"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": 6305210484705.401, "dur": 3.171, + "args": { + "External id": 723200,"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": 6305210484706.457, "dur": 2.050, + "args": { + "External id": 723201,"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": 6305210484708.834, "dur": 1.626, + "args": { + "External id": 723202,"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": 6305210484709.874, "dur": 0.522, + "args": { + "External id": 723203,"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": 6305210484710.726, "dur": 2.500, + "args": { + "External id": 723204,"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": 6305210484712.260, "dur": 0.904, + "args": { + "External id": 723205,"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": 6305210484713.488, "dur": 2.829, + "args": { + "External id": 723206,"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": 6305210484715.537, "dur": 0.710, + "args": { + "External id": 723207,"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": 6305210484716.589, "dur": 2.060, + "args": { + "External id": 723208,"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": 6305210484717.852, "dur": 0.730, + "args": { + "External id": 723209,"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": 6305210484718.932, "dur": 1.798, + "args": { + "External id": 723210,"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": 6305210484719.739, "dur": 0.928, + "args": { + "External id": 723211,"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": 6305210484721.034, "dur": 2.599, + "args": { + "External id": 723212,"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": 6305210484722.994, "dur": 0.576, + "args": { + "External id": 723213,"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": 6305210484725.694, "dur": 1.857, + "args": { + "External id": 723214,"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": 6305210484726.989, "dur": 0.499, + "args": { + "External id": 723215,"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": 6305210484727.919, "dur": 2.631, + "args": { + "External id": 723216,"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": 6305210484728.960, "dur": 1.521, + "args": { + "External id": 723217,"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": 6305210484730.840, "dur": 1.323, + "args": { + "External id": 723218,"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": 6305210484731.523, "dur": 0.581, + "args": { + "External id": 723219,"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": 6305210484732.442, "dur": 1.682, + "args": { + "External id": 723220,"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": 6305210484733.438, "dur": 0.623, + "args": { + "External id": 723221,"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": 6305210484734.418, "dur": 3.275, + "args": { + "External id": 723222,"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": 6305210484737.010, "dur": 0.620, + "args": { + "External id": 723223,"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": 6305210484737.952, "dur": 2.287, + "args": { + "External id": 723224,"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": 6305210484739.200, "dur": 0.973, + "args": { + "External id": 723225,"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": 6305210484740.496, "dur": 1.529, + "args": { + "External id": 723226,"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": 6305210484741.271, "dur": 0.689, + "args": { + "External id": 723227,"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": 6305210484742.284, "dur": 3.729, + "args": { + "External id": 723228,"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": 6305210484745.008, "dur": 0.945, + "args": { + "External id": 723229,"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": 6305210484748.177, "dur": 1.303, + "args": { + "External id": 723230,"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": 6305210484748.884, "dur": 0.536, + "args": { + "External id": 723231,"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": 6305210484749.717, "dur": 3.201, + "args": { + "External id": 723232,"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": 6305210484751.004, "dur": 1.842, + "args": { + "External id": 723233,"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": 6305210484753.168, "dur": 1.511, + "args": { + "External id": 723234,"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": 6305210484753.910, "dur": 0.707, + "args": { + "External id": 723235,"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": 6305210484754.921, "dur": 2.261, + "args": { + "External id": 723236,"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": 6305210484756.329, "dur": 0.792, + "args": { + "External id": 723237,"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": 6305210484757.427, "dur": 2.581, + "args": { + "External id": 723238,"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": 6305210484759.470, "dur": 0.476, + "args": { + "External id": 723239,"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": 6305210484760.264, "dur": 1.692, + "args": { + "External id": 723240,"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": 6305210484761.328, "dur": 0.567, + "args": { + "External id": 723241,"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": 6305210484762.193, "dur": 1.633, + "args": { + "External id": 723242,"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": 6305210484762.888, "dur": 0.872, + "args": { + "External id": 723243,"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": 6305210484764.085, "dur": 3.247, + "args": { + "External id": 723244,"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": 6305210484766.687, "dur": 0.579, + "args": { + "External id": 723245,"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": 6305210484769.384, "dur": 1.542, + "args": { + "External id": 723246,"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": 6305210484770.280, "dur": 0.580, + "args": { + "External id": 723247,"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": 6305210484771.167, "dur": 2.907, + "args": { + "External id": 723248,"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": 6305210484772.418, "dur": 1.583, + "args": { + "External id": 723249,"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": 6305210484774.330, "dur": 1.710, + "args": { + "External id": 723250,"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": 6305210484775.211, "dur": 0.765, + "args": { + "External id": 723251,"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": 6305210484776.305, "dur": 1.879, + "args": { + "External id": 723252,"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": 6305210484777.231, "dur": 0.890, + "args": { + "External id": 723253,"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": 6305210484778.452, "dur": 3.460, + "args": { + "External id": 723254,"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": 6305210484781.097, "dur": 0.746, + "args": { + "External id": 723255,"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": 6305210484782.170, "dur": 1.719, + "args": { + "External id": 723256,"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": 6305210484783.232, "dur": 0.589, + "args": { + "External id": 723257,"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": 6305210484784.135, "dur": 1.491, + "args": { + "External id": 723258,"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": 6305210484784.886, "dur": 0.676, + "args": { + "External id": 723259,"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": 6305210484785.873, "dur": 3.800, + "args": { + "External id": 723260,"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": 6305210484788.753, "dur": 0.852, + "args": { + "External id": 723261,"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": 6305210484791.827, "dur": 1.458, + "args": { + "External id": 723262,"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": 6305210484792.615, "dur": 0.605, + "args": { + "External id": 723263,"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": 6305210484793.623, "dur": 3.132, + "args": { + "External id": 723264,"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": 6305210484794.561, "dur": 1.912, + "args": { + "External id": 723265,"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": 6305210484797.021, "dur": 2.507, + "args": { + "External id": 723266,"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": 6305210484798.415, "dur": 1.047, + "args": { + "External id": 723267,"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": 6305210484799.764, "dur": 1.919, + "args": { + "External id": 723268,"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": 6305210484800.854, "dur": 0.766, + "args": { + "External id": 723269,"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": 6305210484801.950, "dur": 3.231, + "args": { + "External id": 723270,"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": 6305210484804.567, "dur": 0.549, + "args": { + "External id": 723271,"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": 6305210484805.461, "dur": 1.943, + "args": { + "External id": 723272,"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": 6305210484806.764, "dur": 0.575, + "args": { + "External id": 723273,"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": 6305210484807.680, "dur": 1.383, + "args": { + "External id": 723274,"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": 6305210484808.326, "dur": 0.675, + "args": { + "External id": 723275,"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": 6305210484809.478, "dur": 3.477, + "args": { + "External id": 723276,"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": 6305210484812.356, "dur": 0.534, + "args": { + "External id": 723277,"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": 6305210484815.321, "dur": 1.534, + "args": { + "External id": 723278,"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": 6305210484816.150, "dur": 0.641, + "args": { + "External id": 723279,"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": 6305210484817.277, "dur": 3.070, + "args": { + "External id": 723280,"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": 6305210484818.374, "dur": 1.906, + "args": { + "External id": 723281,"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": 6305210484820.666, "dur": 1.548, + "args": { + "External id": 723282,"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": 6305210484821.721, "dur": 0.427, + "args": { + "External id": 723283,"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": 6305210484822.661, "dur": 2.006, + "args": { + "External id": 723284,"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": 6305210484823.966, "dur": 0.635, + "args": { + "External id": 723285,"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": 6305210484824.926, "dur": 3.242, + "args": { + "External id": 723286,"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": 6305210484827.606, "dur": 0.502, + "args": { + "External id": 723287,"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": 6305210484828.630, "dur": 1.898, + "args": { + "External id": 723288,"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": 6305210484829.879, "dur": 0.586, + "args": { + "External id": 723289,"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": 6305210484830.949, "dur": 1.740, + "args": { + "External id": 723290,"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": 6305210484831.810, "dur": 0.816, + "args": { + "External id": 723291,"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": 6305210484832.933, "dur": 3.594, + "args": { + "External id": 723292,"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": 6305210484835.947, "dur": 0.519, + "args": { + "External id": 723293,"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": 6305210484838.897, "dur": 1.256, + "args": { + "External id": 723294,"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": 6305210484839.554, "dur": 0.538, + "args": { + "External id": 723295,"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": 6305210484840.403, "dur": 2.604, + "args": { + "External id": 723296,"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": 6305210484841.294, "dur": 1.646, + "args": { + "External id": 723297,"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": 6305210484843.247, "dur": 1.516, + "args": { + "External id": 723298,"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": 6305210484844.112, "dur": 0.584, + "args": { + "External id": 723299,"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": 6305210484845.045, "dur": 2.068, + "args": { + "External id": 723300,"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": 6305210484846.404, "dur": 0.645, + "args": { + "External id": 723301,"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": 6305210484847.440, "dur": 3.636, + "args": { + "External id": 723302,"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": 6305210484850.208, "dur": 0.805, + "args": { + "External id": 723303,"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": 6305210484851.334, "dur": 2.072, + "args": { + "External id": 723304,"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": 6305210484852.788, "dur": 0.558, + "args": { + "External id": 723305,"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": 6305210484853.673, "dur": 1.695, + "args": { + "External id": 723306,"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": 6305210484854.658, "dur": 0.643, + "args": { + "External id": 723307,"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": 6305210484855.619, "dur": 4.558, + "args": { + "External id": 723308,"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": 6305210484859.064, "dur": 1.046, + "args": { + "External id": 723309,"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": 6305210484862.375, "dur": 1.866, + "args": { + "External id": 723310,"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": 6305210484863.421, "dur": 0.756, + "args": { + "External id": 723311,"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": 6305210484864.495, "dur": 5.490, + "args": { + "External id": 723312,"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": 6305210484867.869, "dur": 2.044, + "args": { + "External id": 723313,"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": 6305210484870.226, "dur": 2.029, + "args": { + "External id": 723314,"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": 6305210484871.112, "dur": 0.869, + "args": { + "External id": 723315,"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": 6305210484872.520, "dur": 1.754, + "args": { + "External id": 723316,"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": 6305210484873.308, "dur": 0.902, + "args": { + "External id": 723317,"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": 6305210484874.541, "dur": 3.136, + "args": { + "External id": 723318,"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": 6305210484877.088, "dur": 0.528, + "args": { + "External id": 723319,"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": 6305210484877.953, "dur": 1.580, + "args": { + "External id": 723320,"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": 6305210484878.897, "dur": 0.574, + "args": { + "External id": 723321,"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": 6305210484879.777, "dur": 1.537, + "args": { + "External id": 723322,"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": 6305210484880.572, "dur": 0.678, + "args": { + "External id": 723323,"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": 6305210484881.553, "dur": 3.115, + "args": { + "External id": 723324,"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": 6305210484884.033, "dur": 0.572, + "args": { + "External id": 723325,"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": 6305210484886.790, "dur": 1.797, + "args": { + "External id": 723326,"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": 6305210484887.741, "dur": 0.780, + "args": { + "External id": 723327,"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": 6305210484888.825, "dur": 2.748, + "args": { + "External id": 723328,"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": 6305210484889.834, "dur": 1.674, + "args": { + "External id": 723329,"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": 6305210484891.818, "dur": 1.168, + "args": { + "External id": 723330,"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": 6305210484892.406, "dur": 0.514, + "args": { + "External id": 723331,"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": 6305210484893.228, "dur": 2.606, + "args": { + "External id": 723332,"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": 6305210484894.701, "dur": 1.072, + "args": { + "External id": 723333,"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": 6305210484896.105, "dur": 3.301, + "args": { + "External id": 723334,"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": 6305210484898.909, "dur": 0.432, + "args": { + "External id": 723335,"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": 6305210484899.675, "dur": 1.758, + "args": { + "External id": 723336,"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": 6305210484900.853, "dur": 0.515, + "args": { + "External id": 723337,"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": 6305210484901.874, "dur": 1.331, + "args": { + "External id": 723338,"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": 6305210484902.491, "dur": 0.650, + "args": { + "External id": 723339,"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": 6305210484903.631, "dur": 3.497, + "args": { + "External id": 723340,"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": 6305210484906.543, "dur": 0.518, + "args": { + "External id": 723341,"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": 6305210484909.474, "dur": 1.107, + "args": { + "External id": 723342,"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": 6305210484910.098, "dur": 0.417, + "args": { + "External id": 723343,"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": 6305210484910.880, "dur": 2.473, + "args": { + "External id": 723344,"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": 6305210484911.766, "dur": 1.426, + "args": { + "External id": 723345,"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": 6305210484913.615, "dur": 1.477, + "args": { + "External id": 723346,"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": 6305210484914.433, "dur": 0.595, + "args": { + "External id": 723347,"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": 6305210484915.560, "dur": 2.190, + "args": { + "External id": 723348,"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": 6305210484916.937, "dur": 0.749, + "args": { + "External id": 723349,"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": 6305210484917.988, "dur": 2.946, + "args": { + "External id": 723350,"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": 6305210484920.305, "dur": 0.563, + "args": { + "External id": 723351,"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": 6305210484921.188, "dur": 1.709, + "args": { + "External id": 723352,"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": 6305210484922.174, "dur": 0.660, + "args": { + "External id": 723353,"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": 6305210484923.150, "dur": 1.751, + "args": { + "External id": 723354,"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": 6305210484924.130, "dur": 0.706, + "args": { + "External id": 723355,"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": 6305210484925.161, "dur": 3.816, + "args": { + "External id": 723356,"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": 6305210484928.331, "dur": 0.579, + "args": { + "External id": 723357,"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": 6305210484931.371, "dur": 1.500, + "args": { + "External id": 723358,"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": 6305210484932.180, "dur": 0.631, + "args": { + "External id": 723359,"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": 6305210484933.142, "dur": 3.339, + "args": { + "External id": 723360,"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": 6305210484934.519, "dur": 1.722, + "args": { + "External id": 723361,"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": 6305210484936.737, "dur": 1.641, + "args": { + "External id": 723362,"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": 6305210484937.788, "dur": 0.523, + "args": { + "External id": 723363,"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": 6305210484938.909, "dur": 2.275, + "args": { + "External id": 723364,"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": 6305210484940.268, "dur": 0.853, + "args": { + "External id": 723365,"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": 6305210484941.454, "dur": 3.307, + "args": { + "External id": 723366,"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": 6305210484943.914, "dur": 0.771, + "args": { + "External id": 723367,"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": 6305210484945.056, "dur": 1.922, + "args": { + "External id": 723368,"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": 6305210484946.381, "dur": 0.534, + "args": { + "External id": 723369,"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": 6305210484947.215, "dur": 1.223, + "args": { + "External id": 723370,"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": 6305210484947.784, "dur": 0.590, + "args": { + "External id": 723371,"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": 6305210484948.681, "dur": 2.683, + "args": { + "External id": 723372,"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": 6305210484950.721, "dur": 0.583, + "args": { + "External id": 723373,"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": 6305210484953.728, "dur": 1.519, + "args": { + "External id": 723374,"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": 6305210484954.630, "dur": 0.556, + "args": { + "External id": 723375,"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": 6305210484955.497, "dur": 2.974, + "args": { + "External id": 723376,"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": 6305210484956.728, "dur": 1.674, + "args": { + "External id": 723377,"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": 6305210484958.737, "dur": 1.246, + "args": { + "External id": 723378,"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": 6305210484959.346, "dur": 0.575, + "args": { + "External id": 723379,"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": 6305210484960.453, "dur": 2.219, + "args": { + "External id": 723380,"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": 6305210484961.969, "dur": 0.640, + "args": { + "External id": 723381,"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": 6305210484962.944, "dur": 2.540, + "args": { + "External id": 723382,"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": 6305210484964.928, "dur": 0.496, + "args": { + "External id": 723383,"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": 6305210484965.748, "dur": 1.964, + "args": { + "External id": 723384,"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": 6305210484966.988, "dur": 0.664, + "args": { + "External id": 723385,"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": 6305210484967.959, "dur": 1.561, + "args": { + "External id": 723386,"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": 6305210484968.550, "dur": 0.905, + "args": { + "External id": 723387,"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": 6305210484969.761, "dur": 2.887, + "args": { + "External id": 723388,"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": 6305210484971.941, "dur": 0.640, + "args": { + "External id": 723389,"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": 6305210484975.029, "dur": 1.743, + "args": { + "External id": 723390,"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": 6305210484975.920, "dur": 0.786, + "args": { + "External id": 723391,"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": 6305210484977.011, "dur": 3.042, + "args": { + "External id": 723392,"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": 6305210484978.070, "dur": 1.896, + "args": { + "External id": 723393,"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": 6305210484980.298, "dur": 1.739, + "args": { + "External id": 723394,"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": 6305210484981.339, "dur": 0.630, + "args": { + "External id": 723395,"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": 6305210484982.273, "dur": 1.983, + "args": { + "External id": 723396,"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": 6305210484983.487, "dur": 0.703, + "args": { + "External id": 723397,"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": 6305210484984.710, "dur": 3.371, + "args": { + "External id": 723398,"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": 6305210484987.218, "dur": 0.794, + "args": { + "External id": 723399,"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": 6305210484988.355, "dur": 1.858, + "args": { + "External id": 723400,"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": 6305210484989.501, "dur": 0.652, + "args": { + "External id": 723401,"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": 6305210484990.521, "dur": 2.100, + "args": { + "External id": 723402,"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": 6305210484991.610, "dur": 0.946, + "args": { + "External id": 723403,"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": 6305210484992.861, "dur": 2.982, + "args": { + "External id": 723404,"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": 6305210484994.977, "dur": 0.801, + "args": { + "External id": 723405,"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": 6305210484997.903, "dur": 5.507, + "args": { + "External id": 723406,"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": 6305210485002.556, "dur": 0.784, + "args": { + "External id": 723407,"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": 6305210485003.661, "dur": 2.455, + "args": { + "External id": 723408,"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": 6305210485004.443, "dur": 1.602, + "args": { + "External id": 723409,"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": 6305210485006.410, "dur": 2.054, + "args": { + "External id": 723410,"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": 6305210485007.438, "dur": 0.957, + "args": { + "External id": 723411,"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": 6305210485008.701, "dur": 1.823, + "args": { + "External id": 723412,"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": 6305210485009.528, "dur": 0.930, + "args": { + "External id": 723413,"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": 6305210485010.908, "dur": 3.827, + "args": { + "External id": 723414,"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": 6305210485013.918, "dur": 0.750, + "args": { + "External id": 723415,"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": 6305210485015.028, "dur": 1.492, + "args": { + "External id": 723416,"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": 6305210485015.695, "dur": 0.760, + "args": { + "External id": 723417,"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": 6305210485016.756, "dur": 1.887, + "args": { + "External id": 723418,"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": 6305210485017.844, "dur": 0.730, + "args": { + "External id": 723419,"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": 6305210485018.914, "dur": 2.796, + "args": { + "External id": 723420,"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": 6305210485020.846, "dur": 0.802, + "args": { + "External id": 723421,"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": 6305210485023.901, "dur": 1.497, + "args": { + "External id": 723422,"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": 6305210485024.772, "dur": 0.558, + "args": { + "External id": 723423,"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": 6305210485025.659, "dur": 2.260, + "args": { + "External id": 723424,"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": 6305210485026.466, "dur": 1.288, + "args": { + "External id": 723425,"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": 6305210485028.177, "dur": 2.160, + "args": { + "External id": 723426,"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": 6305210485029.721, "dur": 0.553, + "args": { + "External id": 723427,"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": 6305210485030.746, "dur": 1.704, + "args": { + "External id": 723428,"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": 6305210485031.635, "dur": 0.749, + "args": { + "External id": 723429,"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": 6305210485032.697, "dur": 3.391, + "args": { + "External id": 723430,"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": 6305210485035.194, "dur": 0.825, + "args": { + "External id": 723431,"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": 6305210485036.417, "dur": 1.974, + "args": { + "External id": 723432,"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": 6305210485037.439, "dur": 0.891, + "args": { + "External id": 723433,"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": 6305210485038.642, "dur": 1.975, + "args": { + "External id": 723434,"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": 6305210485039.823, "dur": 0.728, + "args": { + "External id": 723435,"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": 6305210485041.053, "dur": 2.507, + "args": { + "External id": 723436,"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": 6305210485042.764, "dur": 0.731, + "args": { + "External id": 723437,"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": 6305210485045.909, "dur": 2.106, + "args": { + "External id": 723438,"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": 6305210485047.470, "dur": 0.478, + "args": { + "External id": 723439,"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": 6305210485048.490, "dur": 2.083, + "args": { + "External id": 723440,"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": 6305210485049.228, "dur": 1.277, + "args": { + "External id": 723441,"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": 6305210485050.812, "dur": 33.230, + "args": { + "External id": 723442,"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": 6305210485052.386, "dur": 30.862, + "args": { + "External id": 723443,"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": 6305210485085.637, "dur": 2.642, + "args": { + "External id": 723444,"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": 6305210485087.325, "dur": 0.889, + "args": { + "External id": 723445,"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": 6305210485088.560, "dur": 3.731, + "args": { + "External id": 723446,"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": 6305210485091.290, "dur": 0.937, + "args": { + "External id": 723447,"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": 6305210485092.607, "dur": 1.713, + "args": { + "External id": 723448,"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": 6305210485093.664, "dur": 0.594, + "args": { + "External id": 723449,"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": 6305210485094.570, "dur": 2.052, + "args": { + "External id": 723450,"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": 6305210485095.679, "dur": 0.878, + "args": { + "External id": 723451,"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": 6305210485096.873, "dur": 2.709, + "args": { + "External id": 723452,"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": 6305210485098.789, "dur": 0.733, + "args": { + "External id": 723453,"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": 6305210485101.737, "dur": 1.791, + "args": { + "External id": 723454,"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": 6305210485102.884, "dur": 0.584, + "args": { + "External id": 723455,"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": 6305210485103.802, "dur": 21.701, + "args": { + "External id": 723456,"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": 6305210485123.549, "dur": 1.873, + "args": { + "External id": 723457,"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": 6305210485125.800, "dur": 1.637, + "args": { + "External id": 723458,"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": 6305210485126.925, "dur": 0.448, + "args": { + "External id": 723459,"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": 6305210485127.683, "dur": 1.227, + "args": { + "External id": 723460,"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": 6305210485128.279, "dur": 0.562, + "args": { + "External id": 723461,"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": 6305210485129.368, "dur": 2.954, + "args": { + "External id": 723462,"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": 6305210485131.840, "dur": 0.415, + "args": { + "External id": 723463,"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": 6305210485132.699, "dur": 1.206, + "args": { + "External id": 723464,"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": 6305210485133.395, "dur": 0.442, + "args": { + "External id": 723465,"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": 6305210485134.253, "dur": 2.437, + "args": { + "External id": 723466,"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": 6305210485135.479, "dur": 1.145, + "args": { + "External id": 723467,"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": 6305210485136.961, "dur": 2.808, + "args": { + "External id": 723468,"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": 6305210485139.150, "dur": 0.552, + "args": { + "External id": 723469,"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": 6305210485141.942, "dur": 2.296, + "args": { + "External id": 723470,"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": 6305210485143.542, "dur": 0.630, + "args": { + "External id": 723471,"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": 6305210485144.570, "dur": 2.450, + "args": { + "External id": 723472,"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": 6305210485145.295, "dur": 1.649, + "args": { + "External id": 723473,"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": 6305210485147.268, "dur": 1.657, + "args": { + "External id": 723474,"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": 6305210485148.337, "dur": 0.526, + "args": { + "External id": 723475,"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": 6305210485149.188, "dur": 1.976, + "args": { + "External id": 723476,"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": 6305210485150.512, "dur": 0.583, + "args": { + "External id": 723477,"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": 6305210485151.413, "dur": 3.393, + "args": { + "External id": 723478,"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": 6305210485154.248, "dur": 0.492, + "args": { + "External id": 723479,"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": 6305210485155.121, "dur": 1.583, + "args": { + "External id": 723480,"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": 6305210485156.010, "dur": 0.632, + "args": { + "External id": 723481,"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": 6305210485156.986, "dur": 2.180, + "args": { + "External id": 723482,"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": 6305210485158.524, "dur": 0.575, + "args": { + "External id": 723483,"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": 6305210485159.492, "dur": 2.617, + "args": { + "External id": 723484,"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": 6305210485161.502, "dur": 0.542, + "args": { + "External id": 723485,"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": 6305210485164.402, "dur": 2.473, + "args": { + "External id": 723486,"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": 6305210485165.555, "dur": 1.252, + "args": { + "External id": 723487,"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": 6305210485167.346, "dur": 2.658, + "args": { + "External id": 723488,"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": 6305210485167.986, "dur": 1.947, + "args": { + "External id": 723489,"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": 6305210485170.274, "dur": 1.620, + "args": { + "External id": 723490,"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": 6305210485171.169, "dur": 0.648, + "args": { + "External id": 723491,"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": 6305210485191.866, "dur": 129.635, + "args": { + "External id": 723492,"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": 6305210485436.057, "dur": 170.672, + "args": { + "External id": 723493,"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": 6305210485520.264, "dur": 62.119, + "args": { + "External id": 723494,"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": 6305210485541.602, "dur": 1.411, + "args": { + "External id": 723495,"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": 6305210485971.038, "dur": 933.781, + "args": { + "External id": 723496,"Sequence number": 7674854, "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": 6305210486032.324, "dur": 107.854, + "args": { + "External id": 723497,"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": 6305210486039.958, "dur": 1.772, + "args": { + "External id": 723498,"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": 6305210486043.492, "dur": 0.820, + "args": { + "External id": 723499,"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": 6305210486219.892, "dur": 358.994, + "args": { + "External id": 723500,"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": 6305210486224.662, "dur": 53.917, + "args": { + "External id": 723501,"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": 6305210486229.988, "dur": 11.410, + "args": { + "External id": 723502,"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": 6305210486234.634, "dur": 5.884, + "args": { + "External id": 723503,"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": 6305210486242.714, "dur": 34.928, + "args": { + "External id": 723504,"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": 6305210486287.607, "dur": 287.306, + "args": { + "External id": 723505,"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": 6305210486323.235, "dur": 244.437, + "args": { + "External id": 723506,"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": 6305210486336.693, "dur": 224.951, + "args": { + "External id": 723507,"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": 6305210486651.089, "dur": 217.953, + "args": { + "External id": 723508,"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": 6305210486757.611, "dur": 34.587, + "args": { + "External id": 723509,"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": 6305210486779.294, "dur": 4.337, + "args": { + "External id": 723510,"Record function id": 0, "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": 6305210486818.560, "dur": 44.528, + "args": { + "External id": 723511,"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": 6305210486821.569, "dur": 1.311, + "args": { + "External id": 723512,"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": 6305210486824.210, "dur": 0.524, + "args": { + "External id": 723513,"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": 6305210486922.523, "dur": 22.451, + "args": { + "External id": 723514,"Sequence number": 7674855, "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": 6305210486932.780, "dur": 8.990, + "args": { + "External id": 723515,"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": 6305210486935.401, "dur": 6.199, + "args": { + "External id": 723516,"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": 6305210487367.118, "dur": 39.199, + "args": { + "External id": 723517,"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": 6305210487417.332, "dur": 24.823, + "args": { + "External id": 723518,"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": 6305210487449.847, "dur": 25.396, + "args": { + "External id": 723519,"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": 6305210487488.669, "dur": 43.796, + "args": { + "External id": 723520,"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": 6305210487493.016, "dur": 0.348, + "args": { + "External id": 723521,"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": 6305210487551.541, "dur": 0.453, + "args": { + "External id": 723522,"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": 6305210487678.170, "dur": 1116.907, + "args": { + "External id": 723523,"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": 6305210488111.754, "dur": 638.827, + "args": { + "External id": 723524,"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": 6305210488847.017, "dur": 31.692, + "args": { + "External id": 723525,"Sequence number": 7674856, "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": 6305210488851.348, "dur": 26.732, + "args": { + "External id": 723526,"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": 6305210488883.818, "dur": 10655.878, + "args": { + "External id": 723527,"Sequence number": 7674856, "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": 6305210488885.738, "dur": 10653.445, + "args": { + "External id": 723528,"Sequence number": 7674856, "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": 6305210488887.621, "dur": 10649.240, + "args": { + "External id": 723529,"Sequence number": 7674856, "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": 6305210499553.210, "dur": 80.021, + "args": { + "External id": 723530,"Sequence number": 7674856, "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": 6305210499557.930, "dur": 49.263, + "args": { + "External id": 723531,"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": 6305210499569.309, "dur": 4.915, + "args": { + "External id": 723532,"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": 6305210499576.282, "dur": 30.542, + "args": { + "External id": 723533,"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": 6305210499584.601, "dur": 3.634, + "args": { + "External id": 723534,"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": 6305210499609.098, "dur": 23.177, + "args": { + "External id": 723535,"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": 6305210499636.466, "dur": 43.149, + "args": { + "External id": 723536,"Sequence number": 7674856, "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": 6305210499637.644, "dur": 41.806, + "args": { + "External id": 723537,"Sequence number": 7674856, "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": 6305210499638.956, "dur": 40.220, + "args": { + "External id": 723538,"Sequence number": 7674856, "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": 6305210499718.501, "dur": 5762.658, + "args": { + "External id": 723539,"Record function id": 0, "Ev Idx": 21655 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "Optimizer.step#AdamW.step", "pid": 2338707, "tid": 2338707, + "ts": 6305210499753.328, "dur": 5706.813, + "args": { + "External id": 723540,"Record function id": 0, "Ev Idx": 21656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_add_", "pid": 2338707, "tid": 2338707, + "ts": 6305210501081.738, "dur": 230.997, + "args": { + "External id": 723541,"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": 6305210501104.017, "dur": 1.310, + "args": { + "External id": 723542,"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": 6305210501106.439, "dur": 0.089, + "args": { + "External id": 723543,"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": 6305210501107.013, "dur": 0.275, + "args": { + "External id": 723544,"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": 6305210501107.848, "dur": 0.083, + "args": { + "External id": 723545,"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": 6305210501108.348, "dur": 0.308, + "args": { + "External id": 723546,"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": 6305210501109.223, "dur": 0.085, + "args": { + "External id": 723547,"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": 6305210501109.730, "dur": 0.265, + "args": { + "External id": 723548,"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": 6305210501110.260, "dur": 0.073, + "args": { + "External id": 723549,"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": 6305210501110.694, "dur": 0.286, + "args": { + "External id": 723550,"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": 6305210501111.242, "dur": 0.055, + "args": { + "External id": 723551,"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": 6305210501111.710, "dur": 0.070, + "args": { + "External id": 723552,"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": 6305210501112.038, "dur": 0.053, + "args": { + "External id": 723553,"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": 6305210501112.468, "dur": 0.063, + "args": { + "External id": 723554,"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": 6305210501112.795, "dur": 0.070, + "args": { + "External id": 723555,"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": 6305210501113.760, "dur": 0.060, + "args": { + "External id": 723556,"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": 6305210501114.100, "dur": 0.049, + "args": { + "External id": 723557,"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": 6305210501114.553, "dur": 0.060, + "args": { + "External id": 723558,"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": 6305210501114.873, "dur": 0.052, + "args": { + "External id": 723559,"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": 6305210501115.313, "dur": 0.065, + "args": { + "External id": 723560,"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": 6305210501115.815, "dur": 0.072, + "args": { + "External id": 723561,"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": 6305210501116.274, "dur": 0.068, + "args": { + "External id": 723562,"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": 6305210501116.604, "dur": 0.060, + "args": { + "External id": 723563,"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": 6305210501117.183, "dur": 0.067, + "args": { + "External id": 723564,"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": 6305210501117.621, "dur": 0.063, + "args": { + "External id": 723565,"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": 6305210501118.328, "dur": 0.102, + "args": { + "External id": 723566,"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": 6305210501118.807, "dur": 0.064, + "args": { + "External id": 723567,"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": 6305210501119.237, "dur": 0.293, + "args": { + "External id": 723568,"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": 6305210501119.794, "dur": 0.048, + "args": { + "External id": 723569,"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": 6305210501120.214, "dur": 0.065, + "args": { + "External id": 723570,"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": 6305210501120.574, "dur": 0.239, + "args": { + "External id": 723571,"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": 6305210501121.417, "dur": 0.313, + "args": { + "External id": 723572,"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": 6305210501121.987, "dur": 0.050, + "args": { + "External id": 723573,"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": 6305210501122.674, "dur": 0.066, + "args": { + "External id": 723574,"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": 6305210501122.998, "dur": 0.052, + "args": { + "External id": 723575,"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": 6305210501123.415, "dur": 0.065, + "args": { + "External id": 723576,"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": 6305210501123.732, "dur": 0.056, + "args": { + "External id": 723577,"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": 6305210501124.121, "dur": 0.069, + "args": { + "External id": 723578,"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": 6305210501124.444, "dur": 0.053, + "args": { + "External id": 723579,"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": 6305210501125.111, "dur": 0.064, + "args": { + "External id": 723580,"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": 6305210501125.439, "dur": 0.050, + "args": { + "External id": 723581,"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": 6305210501125.866, "dur": 0.064, + "args": { + "External id": 723582,"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": 6305210501126.191, "dur": 0.049, + "args": { + "External id": 723583,"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": 6305210501126.649, "dur": 0.055, + "args": { + "External id": 723584,"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": 6305210501126.961, "dur": 0.054, + "args": { + "External id": 723585,"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": 6305210501127.405, "dur": 0.057, + "args": { + "External id": 723586,"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": 6305210501127.723, "dur": 0.051, + "args": { + "External id": 723587,"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": 6305210501128.256, "dur": 0.051, + "args": { + "External id": 723588,"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": 6305210501128.564, "dur": 0.053, + "args": { + "External id": 723589,"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": 6305210501129.040, "dur": 0.068, + "args": { + "External id": 723590,"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": 6305210501129.364, "dur": 0.056, + "args": { + "External id": 723591,"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": 6305210501129.894, "dur": 0.088, + "args": { + "External id": 723592,"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": 6305210501130.236, "dur": 0.049, + "args": { + "External id": 723593,"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": 6305210501130.628, "dur": 0.059, + "args": { + "External id": 723594,"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": 6305210501130.948, "dur": 0.054, + "args": { + "External id": 723595,"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": 6305210501131.313, "dur": 0.055, + "args": { + "External id": 723596,"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": 6305210501131.627, "dur": 0.049, + "args": { + "External id": 723597,"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": 6305210501132.154, "dur": 0.063, + "args": { + "External id": 723598,"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": 6305210501132.479, "dur": 0.051, + "args": { + "External id": 723599,"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": 6305210501132.928, "dur": 0.063, + "args": { + "External id": 723600,"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": 6305210501133.249, "dur": 0.051, + "args": { + "External id": 723601,"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": 6305210501133.607, "dur": 0.070, + "args": { + "External id": 723602,"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": 6305210501133.934, "dur": 0.051, + "args": { + "External id": 723603,"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": 6305210501134.347, "dur": 0.064, + "args": { + "External id": 723604,"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": 6305210501134.776, "dur": 0.058, + "args": { + "External id": 723605,"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": 6305210501135.353, "dur": 0.062, + "args": { + "External id": 723606,"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": 6305210501135.782, "dur": 0.064, + "args": { + "External id": 723607,"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": 6305210501136.375, "dur": 0.056, + "args": { + "External id": 723608,"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": 6305210501136.688, "dur": 0.055, + "args": { + "External id": 723609,"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": 6305210501137.195, "dur": 0.056, + "args": { + "External id": 723610,"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": 6305210501137.507, "dur": 0.048, + "args": { + "External id": 723611,"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": 6305210501137.949, "dur": 0.051, + "args": { + "External id": 723612,"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": 6305210501138.254, "dur": 0.049, + "args": { + "External id": 723613,"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": 6305210501138.717, "dur": 0.065, + "args": { + "External id": 723614,"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": 6305210501139.044, "dur": 0.050, + "args": { + "External id": 723615,"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": 6305210501139.474, "dur": 0.068, + "args": { + "External id": 723616,"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": 6305210501139.801, "dur": 0.263, + "args": { + "External id": 723617,"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": 6305210501140.428, "dur": 0.287, + "args": { + "External id": 723618,"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": 6305210501140.967, "dur": 0.066, + "args": { + "External id": 723619,"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": 6305210501141.397, "dur": 0.296, + "args": { + "External id": 723620,"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": 6305210501141.949, "dur": 0.047, + "args": { + "External id": 723621,"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": 6305210501142.391, "dur": 0.266, + "args": { + "External id": 723622,"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": 6305210501142.917, "dur": 0.052, + "args": { + "External id": 723623,"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": 6305210501143.611, "dur": 0.056, + "args": { + "External id": 723624,"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": 6305210501143.925, "dur": 0.053, + "args": { + "External id": 723625,"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": 6305210501144.372, "dur": 0.065, + "args": { + "External id": 723626,"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": 6305210501144.700, "dur": 0.054, + "args": { + "External id": 723627,"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": 6305210501145.085, "dur": 0.053, + "args": { + "External id": 723628,"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": 6305210501145.393, "dur": 0.050, + "args": { + "External id": 723629,"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": 6305210501145.870, "dur": 0.061, + "args": { + "External id": 723630,"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": 6305210501146.187, "dur": 0.048, + "args": { + "External id": 723631,"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": 6305210501146.624, "dur": 0.064, + "args": { + "External id": 723632,"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": 6305210501146.947, "dur": 0.050, + "args": { + "External id": 723633,"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": 6305210501147.387, "dur": 0.064, + "args": { + "External id": 723634,"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": 6305210501147.707, "dur": 0.268, + "args": { + "External id": 723635,"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": 6305210501148.388, "dur": 0.301, + "args": { + "External id": 723636,"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": 6305210501148.950, "dur": 0.457, + "args": { + "External id": 723637,"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": 6305210501149.912, "dur": 0.254, + "args": { + "External id": 723638,"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": 6305210501150.422, "dur": 0.054, + "args": { + "External id": 723639,"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": 6305210501150.816, "dur": 0.265, + "args": { + "External id": 723640,"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": 6305210501151.342, "dur": 0.266, + "args": { + "External id": 723641,"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": 6305210501152.334, "dur": 0.259, + "args": { + "External id": 723642,"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": 6305210501152.851, "dur": 0.260, + "args": { + "External id": 723643,"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": 6305210501153.508, "dur": 0.103, + "args": { + "External id": 723644,"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": 6305210501153.872, "dur": 0.047, + "args": { + "External id": 723645,"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": 6305210501154.256, "dur": 0.064, + "args": { + "External id": 723646,"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": 6305210501154.580, "dur": 0.064, + "args": { + "External id": 723647,"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": 6305210501155.135, "dur": 0.052, + "args": { + "External id": 723648,"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": 6305210501155.683, "dur": 0.053, + "args": { + "External id": 723649,"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": 6305210501156.211, "dur": 0.060, + "args": { + "External id": 723650,"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": 6305210501156.574, "dur": 0.057, + "args": { + "External id": 723651,"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": 6305210501157.040, "dur": 0.067, + "args": { + "External id": 723652,"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": 6305210501157.365, "dur": 0.049, + "args": { + "External id": 723653,"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": 6305210501157.779, "dur": 0.064, + "args": { + "External id": 723654,"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": 6305210501158.104, "dur": 0.053, + "args": { + "External id": 723655,"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": 6305210501158.466, "dur": 0.063, + "args": { + "External id": 723656,"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": 6305210501158.791, "dur": 0.051, + "args": { + "External id": 723657,"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": 6305210501159.192, "dur": 0.066, + "args": { + "External id": 723658,"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": 6305210501159.519, "dur": 0.051, + "args": { + "External id": 723659,"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": 6305210501159.894, "dur": 0.068, + "args": { + "External id": 723660,"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": 6305210501160.222, "dur": 0.053, + "args": { + "External id": 723661,"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": 6305210501160.668, "dur": 0.069, + "args": { + "External id": 723662,"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": 6305210501160.997, "dur": 0.054, + "args": { + "External id": 723663,"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": 6305210501161.427, "dur": 0.067, + "args": { + "External id": 723664,"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": 6305210501161.747, "dur": 0.053, + "args": { + "External id": 723665,"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": 6305210501162.221, "dur": 0.067, + "args": { + "External id": 723666,"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": 6305210501162.548, "dur": 0.053, + "args": { + "External id": 723667,"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": 6305210501163.002, "dur": 0.070, + "args": { + "External id": 723668,"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": 6305210501163.325, "dur": 0.052, + "args": { + "External id": 723669,"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": 6305210501163.766, "dur": 0.065, + "args": { + "External id": 723670,"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": 6305210501164.087, "dur": 0.052, + "args": { + "External id": 723671,"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": 6305210501164.511, "dur": 0.069, + "args": { + "External id": 723672,"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": 6305210501164.838, "dur": 0.079, + "args": { + "External id": 723673,"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": 6305210501165.304, "dur": 0.064, + "args": { + "External id": 723674,"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": 6305210501165.629, "dur": 0.055, + "args": { + "External id": 723675,"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": 6305210501166.029, "dur": 0.070, + "args": { + "External id": 723676,"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": 6305210501166.356, "dur": 0.064, + "args": { + "External id": 723677,"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": 6305210501167.000, "dur": 0.051, + "args": { + "External id": 723678,"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": 6305210501167.312, "dur": 0.048, + "args": { + "External id": 723679,"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": 6305210501167.909, "dur": 0.066, + "args": { + "External id": 723680,"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": 6305210501168.235, "dur": 0.052, + "args": { + "External id": 723681,"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": 6305210501168.761, "dur": 0.070, + "args": { + "External id": 723682,"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": 6305210501169.094, "dur": 0.051, + "args": { + "External id": 723683,"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": 6305210501169.412, "dur": 0.072, + "args": { + "External id": 723684,"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": 6305210501169.740, "dur": 0.047, + "args": { + "External id": 723685,"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": 6305210501170.201, "dur": 0.061, + "args": { + "External id": 723686,"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": 6305210501170.516, "dur": 0.049, + "args": { + "External id": 723687,"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": 6305210501170.922, "dur": 0.055, + "args": { + "External id": 723688,"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": 6305210501171.301, "dur": 0.074, + "args": { + "External id": 723689,"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": 6305210501171.881, "dur": 0.067, + "args": { + "External id": 723690,"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": 6305210501172.314, "dur": 0.069, + "args": { + "External id": 723691,"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": 6305210501172.743, "dur": 0.067, + "args": { + "External id": 723692,"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": 6305210501173.186, "dur": 0.063, + "args": { + "External id": 723693,"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": 6305210501173.660, "dur": 0.058, + "args": { + "External id": 723694,"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": 6305210501174.081, "dur": 0.058, + "args": { + "External id": 723695,"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": 6305210501174.555, "dur": 0.056, + "args": { + "External id": 723696,"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": 6305210501174.868, "dur": 0.052, + "args": { + "External id": 723697,"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": 6305210501175.296, "dur": 0.065, + "args": { + "External id": 723698,"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": 6305210501175.641, "dur": 0.056, + "args": { + "External id": 723699,"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": 6305210501176.084, "dur": 0.069, + "args": { + "External id": 723700,"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": 6305210501176.408, "dur": 0.054, + "args": { + "External id": 723701,"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": 6305210501176.824, "dur": 0.064, + "args": { + "External id": 723702,"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": 6305210501177.147, "dur": 0.054, + "args": { + "External id": 723703,"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": 6305210501177.524, "dur": 0.068, + "args": { + "External id": 723704,"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": 6305210501177.851, "dur": 0.051, + "args": { + "External id": 723705,"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": 6305210501178.193, "dur": 0.068, + "args": { + "External id": 723706,"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": 6305210501178.519, "dur": 0.054, + "args": { + "External id": 723707,"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": 6305210501178.935, "dur": 0.068, + "args": { + "External id": 723708,"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": 6305210501179.273, "dur": 0.164, + "args": { + "External id": 723709,"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": 6305210501179.830, "dur": 0.190, + "args": { + "External id": 723710,"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": 6305210501180.292, "dur": 0.050, + "args": { + "External id": 723711,"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": 6305210501180.704, "dur": 0.159, + "args": { + "External id": 723712,"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": 6305210501181.140, "dur": 0.144, + "args": { + "External id": 723713,"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": 6305210501181.590, "dur": 0.166, + "args": { + "External id": 723714,"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": 6305210501182.032, "dur": 0.208, + "args": { + "External id": 723715,"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": 6305210501182.836, "dur": 0.205, + "args": { + "External id": 723716,"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": 6305210501183.297, "dur": 0.191, + "args": { + "External id": 723717,"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": 6305210501183.900, "dur": 0.220, + "args": { + "External id": 723718,"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": 6305210501184.374, "dur": 0.053, + "args": { + "External id": 723719,"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": 6305210501185.067, "dur": 0.067, + "args": { + "External id": 723720,"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": 6305210501185.387, "dur": 0.052, + "args": { + "External id": 723721,"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": 6305210501185.832, "dur": 0.066, + "args": { + "External id": 723722,"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": 6305210501186.155, "dur": 0.055, + "args": { + "External id": 723723,"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": 6305210501186.574, "dur": 0.066, + "args": { + "External id": 723724,"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": 6305210501186.900, "dur": 0.050, + "args": { + "External id": 723725,"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": 6305210501187.324, "dur": 0.067, + "args": { + "External id": 723726,"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": 6305210501187.648, "dur": 0.053, + "args": { + "External id": 723727,"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": 6305210501188.041, "dur": 0.066, + "args": { + "External id": 723728,"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": 6305210501188.362, "dur": 0.053, + "args": { + "External id": 723729,"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": 6305210501188.869, "dur": 0.051, + "args": { + "External id": 723730,"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": 6305210501189.182, "dur": 0.049, + "args": { + "External id": 723731,"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": 6305210501189.625, "dur": 0.069, + "args": { + "External id": 723732,"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": 6305210501189.960, "dur": 0.064, + "args": { + "External id": 723733,"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": 6305210501190.550, "dur": 0.063, + "args": { + "External id": 723734,"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": 6305210501191.022, "dur": 0.068, + "args": { + "External id": 723735,"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": 6305210501191.487, "dur": 0.065, + "args": { + "External id": 723736,"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": 6305210501191.816, "dur": 0.048, + "args": { + "External id": 723737,"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": 6305210501192.270, "dur": 0.064, + "args": { + "External id": 723738,"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": 6305210501192.594, "dur": 0.047, + "args": { + "External id": 723739,"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": 6305210501193.027, "dur": 0.069, + "args": { + "External id": 723740,"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": 6305210501193.351, "dur": 0.052, + "args": { + "External id": 723741,"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": 6305210501193.730, "dur": 0.050, + "args": { + "External id": 723742,"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": 6305210501194.038, "dur": 0.052, + "args": { + "External id": 723743,"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": 6305210501194.453, "dur": 0.064, + "args": { + "External id": 723744,"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": 6305210501194.778, "dur": 0.047, + "args": { + "External id": 723745,"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": 6305210501195.149, "dur": 0.058, + "args": { + "External id": 723746,"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": 6305210501195.466, "dur": 0.045, + "args": { + "External id": 723747,"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": 6305210501195.887, "dur": 0.060, + "args": { + "External id": 723748,"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": 6305210501196.227, "dur": 0.046, + "args": { + "External id": 723749,"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": 6305210501196.627, "dur": 0.056, + "args": { + "External id": 723750,"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": 6305210501196.946, "dur": 0.052, + "args": { + "External id": 723751,"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": 6305210501197.473, "dur": 0.065, + "args": { + "External id": 723752,"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": 6305210501197.793, "dur": 0.053, + "args": { + "External id": 723753,"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": 6305210501198.437, "dur": 0.067, + "args": { + "External id": 723754,"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": 6305210501198.851, "dur": 0.048, + "args": { + "External id": 723755,"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": 6305210501199.204, "dur": 0.065, + "args": { + "External id": 723756,"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": 6305210501199.581, "dur": 0.049, + "args": { + "External id": 723757,"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": 6305210501200.523, "dur": 0.063, + "args": { + "External id": 723758,"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": 6305210501200.874, "dur": 0.052, + "args": { + "External id": 723759,"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": 6305210501201.611, "dur": 0.064, + "args": { + "External id": 723760,"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": 6305210501202.154, "dur": 0.063, + "args": { + "External id": 723761,"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": 6305210501202.897, "dur": 0.051, + "args": { + "External id": 723762,"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": 6305210501203.218, "dur": 0.053, + "args": { + "External id": 723763,"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": 6305210501203.892, "dur": 0.052, + "args": { + "External id": 723764,"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": 6305210501204.214, "dur": 0.053, + "args": { + "External id": 723765,"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": 6305210501204.988, "dur": 0.065, + "args": { + "External id": 723766,"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": 6305210501205.367, "dur": 0.047, + "args": { + "External id": 723767,"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": 6305210501206.211, "dur": 0.053, + "args": { + "External id": 723768,"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": 6305210501206.535, "dur": 0.049, + "args": { + "External id": 723769,"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": 6305210501207.291, "dur": 0.056, + "args": { + "External id": 723770,"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": 6305210501207.614, "dur": 0.053, + "args": { + "External id": 723771,"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": 6305210501208.379, "dur": 0.067, + "args": { + "External id": 723772,"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": 6305210501208.711, "dur": 0.051, + "args": { + "External id": 723773,"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": 6305210501209.271, "dur": 0.065, + "args": { + "External id": 723774,"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": 6305210501209.713, "dur": 0.068, + "args": { + "External id": 723775,"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": 6305210501210.394, "dur": 0.061, + "args": { + "External id": 723776,"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": 6305210501210.814, "dur": 0.065, + "args": { + "External id": 723777,"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": 6305210501211.727, "dur": 0.064, + "args": { + "External id": 723778,"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": 6305210501212.062, "dur": 0.058, + "args": { + "External id": 723779,"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": 6305210501212.714, "dur": 0.067, + "args": { + "External id": 723780,"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": 6305210501213.047, "dur": 0.347, + "args": { + "External id": 723781,"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": 6305210501214.236, "dur": 0.357, + "args": { + "External id": 723782,"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": 6305210501214.853, "dur": 0.067, + "args": { + "External id": 723783,"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": 6305210501215.398, "dur": 0.274, + "args": { + "External id": 723784,"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": 6305210501216.141, "dur": 0.286, + "args": { + "External id": 723785,"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": 6305210501217.157, "dur": 0.280, + "args": { + "External id": 723786,"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": 6305210501217.688, "dur": 0.239, + "args": { + "External id": 723787,"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": 6305210501218.803, "dur": 0.261, + "args": { + "External id": 723788,"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": 6305210501219.320, "dur": 0.255, + "args": { + "External id": 723789,"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": 6305210501220.351, "dur": 0.294, + "args": { + "External id": 723790,"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": 6305210501220.900, "dur": 0.054, + "args": { + "External id": 723791,"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": 6305210501221.601, "dur": 0.055, + "args": { + "External id": 723792,"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": 6305210501221.941, "dur": 0.052, + "args": { + "External id": 723793,"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": 6305210501222.602, "dur": 0.052, + "args": { + "External id": 723794,"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": 6305210501223.102, "dur": 0.069, + "args": { + "External id": 723795,"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": 6305210501223.677, "dur": 0.070, + "args": { + "External id": 723796,"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": 6305210501224.203, "dur": 0.068, + "args": { + "External id": 723797,"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": 6305210501224.994, "dur": 0.067, + "args": { + "External id": 723798,"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": 6305210501225.326, "dur": 0.054, + "args": { + "External id": 723799,"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": 6305210501226.117, "dur": 0.064, + "args": { + "External id": 723800,"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": 6305210501226.448, "dur": 0.055, + "args": { + "External id": 723801,"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": 6305210501227.209, "dur": 0.067, + "args": { + "External id": 723802,"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": 6305210501227.539, "dur": 0.054, + "args": { + "External id": 723803,"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": 6305210501228.337, "dur": 0.067, + "args": { + "External id": 723804,"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": 6305210501228.675, "dur": 0.052, + "args": { + "External id": 723805,"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": 6305210501229.382, "dur": 0.065, + "args": { + "External id": 723806,"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": 6305210501229.713, "dur": 0.055, + "args": { + "External id": 723807,"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": 6305210501230.456, "dur": 0.071, + "args": { + "External id": 723808,"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": 6305210501230.791, "dur": 0.056, + "args": { + "External id": 723809,"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": 6305210501231.713, "dur": 0.068, + "args": { + "External id": 723810,"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": 6305210501232.049, "dur": 0.078, + "args": { + "External id": 723811,"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": 6305210501232.628, "dur": 0.072, + "args": { + "External id": 723812,"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": 6305210501233.268, "dur": 0.066, + "args": { + "External id": 723813,"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": 6305210501234.164, "dur": 0.063, + "args": { + "External id": 723814,"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": 6305210501797.696, "dur": 3571.116, + "args": { + "External id": 723815,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "1.3683465081479404e-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": 6305210504174.024, "dur": 1012.970, + "args": { + "External id": 723816,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "1.3683465081479404e-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": 6305203983448.635, "pid": 2338707, "tid": 0, + "args": { + "name": "python3.12" + } + }, + { + "name": "process_labels", "ph": "M", "ts": 6305203983448.635, "pid": 2338707, "tid": 0, + "args": { + "labels": "CPU" + } + }, + { + "name": "process_sort_index", "ph": "M", "ts": 6305203983448.635, "pid": 2338707, "tid": 0, + "args": { + "sort_index": 2338707 + } + }, + { + "name": "thread_name", "ph": "M", "ts": 6305203983448.635, "pid": 2338707, "tid": 2379456, + "args": { + "name": "thread 2379456 (pt_autograd_1)" + } + }, + { + "name": "thread_sort_index", "ph": "M", "ts": 6305203983448.635, "pid": 2338707, "tid": 2379456, + "args": { + "sort_index": 2379456 + } + }, + { + "name": "thread_name", "ph": "M", "ts": 6305203983448.635, "pid": 2338707, "tid": 2379456, + "args": { + "name": "thread 2379456 (python3.12)" + } + }, + { + "name": "thread_sort_index", "ph": "M", "ts": 6305203983448.635, "pid": 2338707, "tid": 2379456, + "args": { + "sort_index": 2379456 + } + }, + { + "name": "thread_name", "ph": "M", "ts": 6305203983448.635, "pid": 2338707, "tid": 2338707, + "args": { + "name": "thread 2338707 (python3.12)" + } + }, + { + "name": "thread_sort_index", "ph": "M", "ts": 6305203983448.635, "pid": 2338707, "tid": 2338707, + "args": { + "sort_index": 2338707 + } + }, + { + "ph": "X", "cat": "Trace", "ts": 6305203983380.092, "dur": 6529052.919, + "pid": "Spans", "tid": "PyTorch Profiler", + "name": "PyTorch Profiler (0)", + "args": { + "Op count": 0 + } + }, + { + "name": "process_sort_index", "ph": "M", "ts": 6305203983380.092, + "pid": "Spans", "tid": 0, + "args": { + "sort_index": 536870912 + } + }, + { + "name": "Iteration Start: PyTorch Profiler", "ph": "i", "s": "g", + "pid": "Traces", "tid": "Trace PyTorch Profiler", "ts": 6305203983380.092 + }, + { + "name": "Record Window End", "ph": "i", "s": "g", + "pid": "", "tid": "", "ts": 6305210606960.808 + } + ], + "traceName": "exp/mtp.code.7B.batch8.seqlen4096.context4096.warmup400.update2.steps40000.lr2e-5.cosine/profile_trace/iteration_16384/rank1_trace.json", + "displayTimeUnit": "ms", + "baseTimeNanoseconds": 1751410836000000000 +} \ No newline at end of file